linux-sg2042/tools/perf/builtin-kmem.c

1485 lines
34 KiB
C
Raw Normal View History

perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
#include "builtin.h"
#include "perf.h"
#include "util/evlist.h"
#include "util/evsel.h"
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
#include "util/util.h"
#include "util/cache.h"
#include "util/symbol.h"
#include "util/thread.h"
#include "util/header.h"
#include "util/session.h"
#include "util/tool.h"
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
#include "util/callchain.h"
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
#include "util/parse-options.h"
#include "util/trace-event.h"
#include "util/data.h"
#include "util/cpumap.h"
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
#include "util/debug.h"
#include <linux/rbtree.h>
#include <linux/string.h>
#include <locale.h>
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
#include <regex.h>
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
static int kmem_slab;
static int kmem_page;
static long kmem_page_size;
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
struct alloc_stat;
typedef int (*sort_fn_t)(struct alloc_stat *, struct alloc_stat *);
static int alloc_flag;
static int caller_flag;
static int alloc_lines = -1;
static int caller_lines = -1;
static bool raw_ip;
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
struct alloc_stat {
perf kmem: Measure kmalloc/kfree CPU ping-pong call-sites Show statistics for allocations and frees on different cpus: ------------------------------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag ------------------------------------------------------------------------------------------------------ perf_event_alloc.clone.0+0 | 7504/682 | 7128/648 | 11 | 0 | 5.011% alloc_buffer_head+16 | 288/57 | 280/56 | 5 | 0 | 2.778% radix_tree_preload+51 | 296/296 | 288/288 | 1 | 0 | 2.703% tracepoint_add_probe+32e | 157/31 | 154/30 | 5 | 0 | 1.911% do_maps_open+0 | 796/12 | 792/12 | 66 | 0 | 0.503% sock_alloc_send_pskb+16e | 23780/495 | 23744/494 | 48 | 38 | 0.151% anon_vma_prepare+9a | 3744/44 | 3740/44 | 85 | 0 | 0.107% d_alloc+21 | 64948/164 | 64944/164 | 396 | 0 | 0.006% proc_alloc_inode+23 | 262292/676 | 262288/676 | 388 | 0 | 0.002% create_object+28 | 459600/200 | 459600/200 | 2298 | 71 | 0.000% journal_start+67 | 14440/40 | 14440/40 | 361 | 0 | 0.000% get_empty_filp+df | 53504/256 | 53504/256 | 209 | 0 | 0.000% getname+2a | 823296/4096 | 823296/4096 | 201 | 0 | 0.000% seq_read+2b0 | 544768/4096 | 544768/4096 | 133 | 0 | 0.000% seq_open+6d | 17024/128 | 17024/128 | 133 | 0 | 0.000% mmap_region+2e6 | 11704/88 | 11704/88 | 133 | 0 | 0.000% single_open+0 | 1072/16 | 1072/16 | 67 | 0 | 0.000% __alloc_skb+2e | 12544/256 | 12544/256 | 49 | 38 | 0.000% __sigqueue_alloc+4a | 1296/144 | 1296/144 | 9 | 8 | 0.000% tracepoint_add_probe+6f | 80/16 | 80/16 | 5 | 0 | 0.000% ------------------------------------------------------------------------------------------------------ ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B0B6E9F.6020309@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-24 13:26:55 +08:00
u64 call_site;
u64 ptr;
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
u64 bytes_req;
u64 bytes_alloc;
u32 hit;
perf kmem: Measure kmalloc/kfree CPU ping-pong call-sites Show statistics for allocations and frees on different cpus: ------------------------------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag ------------------------------------------------------------------------------------------------------ perf_event_alloc.clone.0+0 | 7504/682 | 7128/648 | 11 | 0 | 5.011% alloc_buffer_head+16 | 288/57 | 280/56 | 5 | 0 | 2.778% radix_tree_preload+51 | 296/296 | 288/288 | 1 | 0 | 2.703% tracepoint_add_probe+32e | 157/31 | 154/30 | 5 | 0 | 1.911% do_maps_open+0 | 796/12 | 792/12 | 66 | 0 | 0.503% sock_alloc_send_pskb+16e | 23780/495 | 23744/494 | 48 | 38 | 0.151% anon_vma_prepare+9a | 3744/44 | 3740/44 | 85 | 0 | 0.107% d_alloc+21 | 64948/164 | 64944/164 | 396 | 0 | 0.006% proc_alloc_inode+23 | 262292/676 | 262288/676 | 388 | 0 | 0.002% create_object+28 | 459600/200 | 459600/200 | 2298 | 71 | 0.000% journal_start+67 | 14440/40 | 14440/40 | 361 | 0 | 0.000% get_empty_filp+df | 53504/256 | 53504/256 | 209 | 0 | 0.000% getname+2a | 823296/4096 | 823296/4096 | 201 | 0 | 0.000% seq_read+2b0 | 544768/4096 | 544768/4096 | 133 | 0 | 0.000% seq_open+6d | 17024/128 | 17024/128 | 133 | 0 | 0.000% mmap_region+2e6 | 11704/88 | 11704/88 | 133 | 0 | 0.000% single_open+0 | 1072/16 | 1072/16 | 67 | 0 | 0.000% __alloc_skb+2e | 12544/256 | 12544/256 | 49 | 38 | 0.000% __sigqueue_alloc+4a | 1296/144 | 1296/144 | 9 | 8 | 0.000% tracepoint_add_probe+6f | 80/16 | 80/16 | 5 | 0 | 0.000% ------------------------------------------------------------------------------------------------------ ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B0B6E9F.6020309@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-24 13:26:55 +08:00
u32 pingpong;
short alloc_cpu;
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
struct rb_node node;
};
static struct rb_root root_alloc_stat;
static struct rb_root root_alloc_sorted;
static struct rb_root root_caller_stat;
static struct rb_root root_caller_sorted;
static unsigned long total_requested, total_allocated;
static unsigned long nr_allocs, nr_cross_allocs;
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
static int insert_alloc_stat(unsigned long call_site, unsigned long ptr,
int bytes_req, int bytes_alloc, int cpu)
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
{
struct rb_node **node = &root_alloc_stat.rb_node;
struct rb_node *parent = NULL;
struct alloc_stat *data = NULL;
while (*node) {
parent = *node;
data = rb_entry(*node, struct alloc_stat, node);
if (ptr > data->ptr)
node = &(*node)->rb_right;
else if (ptr < data->ptr)
node = &(*node)->rb_left;
else
break;
}
if (data && data->ptr == ptr) {
data->hit++;
data->bytes_req += bytes_req;
data->bytes_alloc += bytes_alloc;
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
} else {
data = malloc(sizeof(*data));
if (!data) {
pr_err("%s: malloc failed\n", __func__);
return -1;
}
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
data->ptr = ptr;
perf kmem: Measure kmalloc/kfree CPU ping-pong call-sites Show statistics for allocations and frees on different cpus: ------------------------------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag ------------------------------------------------------------------------------------------------------ perf_event_alloc.clone.0+0 | 7504/682 | 7128/648 | 11 | 0 | 5.011% alloc_buffer_head+16 | 288/57 | 280/56 | 5 | 0 | 2.778% radix_tree_preload+51 | 296/296 | 288/288 | 1 | 0 | 2.703% tracepoint_add_probe+32e | 157/31 | 154/30 | 5 | 0 | 1.911% do_maps_open+0 | 796/12 | 792/12 | 66 | 0 | 0.503% sock_alloc_send_pskb+16e | 23780/495 | 23744/494 | 48 | 38 | 0.151% anon_vma_prepare+9a | 3744/44 | 3740/44 | 85 | 0 | 0.107% d_alloc+21 | 64948/164 | 64944/164 | 396 | 0 | 0.006% proc_alloc_inode+23 | 262292/676 | 262288/676 | 388 | 0 | 0.002% create_object+28 | 459600/200 | 459600/200 | 2298 | 71 | 0.000% journal_start+67 | 14440/40 | 14440/40 | 361 | 0 | 0.000% get_empty_filp+df | 53504/256 | 53504/256 | 209 | 0 | 0.000% getname+2a | 823296/4096 | 823296/4096 | 201 | 0 | 0.000% seq_read+2b0 | 544768/4096 | 544768/4096 | 133 | 0 | 0.000% seq_open+6d | 17024/128 | 17024/128 | 133 | 0 | 0.000% mmap_region+2e6 | 11704/88 | 11704/88 | 133 | 0 | 0.000% single_open+0 | 1072/16 | 1072/16 | 67 | 0 | 0.000% __alloc_skb+2e | 12544/256 | 12544/256 | 49 | 38 | 0.000% __sigqueue_alloc+4a | 1296/144 | 1296/144 | 9 | 8 | 0.000% tracepoint_add_probe+6f | 80/16 | 80/16 | 5 | 0 | 0.000% ------------------------------------------------------------------------------------------------------ ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B0B6E9F.6020309@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-24 13:26:55 +08:00
data->pingpong = 0;
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
data->hit = 1;
data->bytes_req = bytes_req;
data->bytes_alloc = bytes_alloc;
rb_link_node(&data->node, parent, node);
rb_insert_color(&data->node, &root_alloc_stat);
}
perf kmem: Measure kmalloc/kfree CPU ping-pong call-sites Show statistics for allocations and frees on different cpus: ------------------------------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag ------------------------------------------------------------------------------------------------------ perf_event_alloc.clone.0+0 | 7504/682 | 7128/648 | 11 | 0 | 5.011% alloc_buffer_head+16 | 288/57 | 280/56 | 5 | 0 | 2.778% radix_tree_preload+51 | 296/296 | 288/288 | 1 | 0 | 2.703% tracepoint_add_probe+32e | 157/31 | 154/30 | 5 | 0 | 1.911% do_maps_open+0 | 796/12 | 792/12 | 66 | 0 | 0.503% sock_alloc_send_pskb+16e | 23780/495 | 23744/494 | 48 | 38 | 0.151% anon_vma_prepare+9a | 3744/44 | 3740/44 | 85 | 0 | 0.107% d_alloc+21 | 64948/164 | 64944/164 | 396 | 0 | 0.006% proc_alloc_inode+23 | 262292/676 | 262288/676 | 388 | 0 | 0.002% create_object+28 | 459600/200 | 459600/200 | 2298 | 71 | 0.000% journal_start+67 | 14440/40 | 14440/40 | 361 | 0 | 0.000% get_empty_filp+df | 53504/256 | 53504/256 | 209 | 0 | 0.000% getname+2a | 823296/4096 | 823296/4096 | 201 | 0 | 0.000% seq_read+2b0 | 544768/4096 | 544768/4096 | 133 | 0 | 0.000% seq_open+6d | 17024/128 | 17024/128 | 133 | 0 | 0.000% mmap_region+2e6 | 11704/88 | 11704/88 | 133 | 0 | 0.000% single_open+0 | 1072/16 | 1072/16 | 67 | 0 | 0.000% __alloc_skb+2e | 12544/256 | 12544/256 | 49 | 38 | 0.000% __sigqueue_alloc+4a | 1296/144 | 1296/144 | 9 | 8 | 0.000% tracepoint_add_probe+6f | 80/16 | 80/16 | 5 | 0 | 0.000% ------------------------------------------------------------------------------------------------------ ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B0B6E9F.6020309@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-24 13:26:55 +08:00
data->call_site = call_site;
data->alloc_cpu = cpu;
return 0;
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
}
static int insert_caller_stat(unsigned long call_site,
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
int bytes_req, int bytes_alloc)
{
struct rb_node **node = &root_caller_stat.rb_node;
struct rb_node *parent = NULL;
struct alloc_stat *data = NULL;
while (*node) {
parent = *node;
data = rb_entry(*node, struct alloc_stat, node);
if (call_site > data->call_site)
node = &(*node)->rb_right;
else if (call_site < data->call_site)
node = &(*node)->rb_left;
else
break;
}
if (data && data->call_site == call_site) {
data->hit++;
data->bytes_req += bytes_req;
data->bytes_alloc += bytes_alloc;
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
} else {
data = malloc(sizeof(*data));
if (!data) {
pr_err("%s: malloc failed\n", __func__);
return -1;
}
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
data->call_site = call_site;
perf kmem: Measure kmalloc/kfree CPU ping-pong call-sites Show statistics for allocations and frees on different cpus: ------------------------------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag ------------------------------------------------------------------------------------------------------ perf_event_alloc.clone.0+0 | 7504/682 | 7128/648 | 11 | 0 | 5.011% alloc_buffer_head+16 | 288/57 | 280/56 | 5 | 0 | 2.778% radix_tree_preload+51 | 296/296 | 288/288 | 1 | 0 | 2.703% tracepoint_add_probe+32e | 157/31 | 154/30 | 5 | 0 | 1.911% do_maps_open+0 | 796/12 | 792/12 | 66 | 0 | 0.503% sock_alloc_send_pskb+16e | 23780/495 | 23744/494 | 48 | 38 | 0.151% anon_vma_prepare+9a | 3744/44 | 3740/44 | 85 | 0 | 0.107% d_alloc+21 | 64948/164 | 64944/164 | 396 | 0 | 0.006% proc_alloc_inode+23 | 262292/676 | 262288/676 | 388 | 0 | 0.002% create_object+28 | 459600/200 | 459600/200 | 2298 | 71 | 0.000% journal_start+67 | 14440/40 | 14440/40 | 361 | 0 | 0.000% get_empty_filp+df | 53504/256 | 53504/256 | 209 | 0 | 0.000% getname+2a | 823296/4096 | 823296/4096 | 201 | 0 | 0.000% seq_read+2b0 | 544768/4096 | 544768/4096 | 133 | 0 | 0.000% seq_open+6d | 17024/128 | 17024/128 | 133 | 0 | 0.000% mmap_region+2e6 | 11704/88 | 11704/88 | 133 | 0 | 0.000% single_open+0 | 1072/16 | 1072/16 | 67 | 0 | 0.000% __alloc_skb+2e | 12544/256 | 12544/256 | 49 | 38 | 0.000% __sigqueue_alloc+4a | 1296/144 | 1296/144 | 9 | 8 | 0.000% tracepoint_add_probe+6f | 80/16 | 80/16 | 5 | 0 | 0.000% ------------------------------------------------------------------------------------------------------ ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B0B6E9F.6020309@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-24 13:26:55 +08:00
data->pingpong = 0;
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
data->hit = 1;
data->bytes_req = bytes_req;
data->bytes_alloc = bytes_alloc;
rb_link_node(&data->node, parent, node);
rb_insert_color(&data->node, &root_caller_stat);
}
return 0;
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
}
static int perf_evsel__process_alloc_event(struct perf_evsel *evsel,
struct perf_sample *sample)
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
{
unsigned long ptr = perf_evsel__intval(evsel, sample, "ptr"),
call_site = perf_evsel__intval(evsel, sample, "call_site");
int bytes_req = perf_evsel__intval(evsel, sample, "bytes_req"),
bytes_alloc = perf_evsel__intval(evsel, sample, "bytes_alloc");
if (insert_alloc_stat(call_site, ptr, bytes_req, bytes_alloc, sample->cpu) ||
insert_caller_stat(call_site, bytes_req, bytes_alloc))
return -1;
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
total_requested += bytes_req;
total_allocated += bytes_alloc;
nr_allocs++;
return 0;
}
static int perf_evsel__process_alloc_node_event(struct perf_evsel *evsel,
struct perf_sample *sample)
{
int ret = perf_evsel__process_alloc_event(evsel, sample);
if (!ret) {
int node1 = cpu__get_node(sample->cpu),
node2 = perf_evsel__intval(evsel, sample, "node");
if (node1 != node2)
nr_cross_allocs++;
}
return ret;
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
}
perf kmem: Measure kmalloc/kfree CPU ping-pong call-sites Show statistics for allocations and frees on different cpus: ------------------------------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag ------------------------------------------------------------------------------------------------------ perf_event_alloc.clone.0+0 | 7504/682 | 7128/648 | 11 | 0 | 5.011% alloc_buffer_head+16 | 288/57 | 280/56 | 5 | 0 | 2.778% radix_tree_preload+51 | 296/296 | 288/288 | 1 | 0 | 2.703% tracepoint_add_probe+32e | 157/31 | 154/30 | 5 | 0 | 1.911% do_maps_open+0 | 796/12 | 792/12 | 66 | 0 | 0.503% sock_alloc_send_pskb+16e | 23780/495 | 23744/494 | 48 | 38 | 0.151% anon_vma_prepare+9a | 3744/44 | 3740/44 | 85 | 0 | 0.107% d_alloc+21 | 64948/164 | 64944/164 | 396 | 0 | 0.006% proc_alloc_inode+23 | 262292/676 | 262288/676 | 388 | 0 | 0.002% create_object+28 | 459600/200 | 459600/200 | 2298 | 71 | 0.000% journal_start+67 | 14440/40 | 14440/40 | 361 | 0 | 0.000% get_empty_filp+df | 53504/256 | 53504/256 | 209 | 0 | 0.000% getname+2a | 823296/4096 | 823296/4096 | 201 | 0 | 0.000% seq_read+2b0 | 544768/4096 | 544768/4096 | 133 | 0 | 0.000% seq_open+6d | 17024/128 | 17024/128 | 133 | 0 | 0.000% mmap_region+2e6 | 11704/88 | 11704/88 | 133 | 0 | 0.000% single_open+0 | 1072/16 | 1072/16 | 67 | 0 | 0.000% __alloc_skb+2e | 12544/256 | 12544/256 | 49 | 38 | 0.000% __sigqueue_alloc+4a | 1296/144 | 1296/144 | 9 | 8 | 0.000% tracepoint_add_probe+6f | 80/16 | 80/16 | 5 | 0 | 0.000% ------------------------------------------------------------------------------------------------------ ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B0B6E9F.6020309@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-24 13:26:55 +08:00
static int ptr_cmp(struct alloc_stat *, struct alloc_stat *);
static int callsite_cmp(struct alloc_stat *, struct alloc_stat *);
static struct alloc_stat *search_alloc_stat(unsigned long ptr,
unsigned long call_site,
struct rb_root *root,
sort_fn_t sort_fn)
{
struct rb_node *node = root->rb_node;
struct alloc_stat key = { .ptr = ptr, .call_site = call_site };
while (node) {
struct alloc_stat *data;
int cmp;
data = rb_entry(node, struct alloc_stat, node);
cmp = sort_fn(&key, data);
if (cmp < 0)
node = node->rb_left;
else if (cmp > 0)
node = node->rb_right;
else
return data;
}
return NULL;
}
static int perf_evsel__process_free_event(struct perf_evsel *evsel,
struct perf_sample *sample)
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
{
unsigned long ptr = perf_evsel__intval(evsel, sample, "ptr");
perf kmem: Measure kmalloc/kfree CPU ping-pong call-sites Show statistics for allocations and frees on different cpus: ------------------------------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag ------------------------------------------------------------------------------------------------------ perf_event_alloc.clone.0+0 | 7504/682 | 7128/648 | 11 | 0 | 5.011% alloc_buffer_head+16 | 288/57 | 280/56 | 5 | 0 | 2.778% radix_tree_preload+51 | 296/296 | 288/288 | 1 | 0 | 2.703% tracepoint_add_probe+32e | 157/31 | 154/30 | 5 | 0 | 1.911% do_maps_open+0 | 796/12 | 792/12 | 66 | 0 | 0.503% sock_alloc_send_pskb+16e | 23780/495 | 23744/494 | 48 | 38 | 0.151% anon_vma_prepare+9a | 3744/44 | 3740/44 | 85 | 0 | 0.107% d_alloc+21 | 64948/164 | 64944/164 | 396 | 0 | 0.006% proc_alloc_inode+23 | 262292/676 | 262288/676 | 388 | 0 | 0.002% create_object+28 | 459600/200 | 459600/200 | 2298 | 71 | 0.000% journal_start+67 | 14440/40 | 14440/40 | 361 | 0 | 0.000% get_empty_filp+df | 53504/256 | 53504/256 | 209 | 0 | 0.000% getname+2a | 823296/4096 | 823296/4096 | 201 | 0 | 0.000% seq_read+2b0 | 544768/4096 | 544768/4096 | 133 | 0 | 0.000% seq_open+6d | 17024/128 | 17024/128 | 133 | 0 | 0.000% mmap_region+2e6 | 11704/88 | 11704/88 | 133 | 0 | 0.000% single_open+0 | 1072/16 | 1072/16 | 67 | 0 | 0.000% __alloc_skb+2e | 12544/256 | 12544/256 | 49 | 38 | 0.000% __sigqueue_alloc+4a | 1296/144 | 1296/144 | 9 | 8 | 0.000% tracepoint_add_probe+6f | 80/16 | 80/16 | 5 | 0 | 0.000% ------------------------------------------------------------------------------------------------------ ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B0B6E9F.6020309@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-24 13:26:55 +08:00
struct alloc_stat *s_alloc, *s_caller;
s_alloc = search_alloc_stat(ptr, 0, &root_alloc_stat, ptr_cmp);
if (!s_alloc)
return 0;
perf kmem: Measure kmalloc/kfree CPU ping-pong call-sites Show statistics for allocations and frees on different cpus: ------------------------------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag ------------------------------------------------------------------------------------------------------ perf_event_alloc.clone.0+0 | 7504/682 | 7128/648 | 11 | 0 | 5.011% alloc_buffer_head+16 | 288/57 | 280/56 | 5 | 0 | 2.778% radix_tree_preload+51 | 296/296 | 288/288 | 1 | 0 | 2.703% tracepoint_add_probe+32e | 157/31 | 154/30 | 5 | 0 | 1.911% do_maps_open+0 | 796/12 | 792/12 | 66 | 0 | 0.503% sock_alloc_send_pskb+16e | 23780/495 | 23744/494 | 48 | 38 | 0.151% anon_vma_prepare+9a | 3744/44 | 3740/44 | 85 | 0 | 0.107% d_alloc+21 | 64948/164 | 64944/164 | 396 | 0 | 0.006% proc_alloc_inode+23 | 262292/676 | 262288/676 | 388 | 0 | 0.002% create_object+28 | 459600/200 | 459600/200 | 2298 | 71 | 0.000% journal_start+67 | 14440/40 | 14440/40 | 361 | 0 | 0.000% get_empty_filp+df | 53504/256 | 53504/256 | 209 | 0 | 0.000% getname+2a | 823296/4096 | 823296/4096 | 201 | 0 | 0.000% seq_read+2b0 | 544768/4096 | 544768/4096 | 133 | 0 | 0.000% seq_open+6d | 17024/128 | 17024/128 | 133 | 0 | 0.000% mmap_region+2e6 | 11704/88 | 11704/88 | 133 | 0 | 0.000% single_open+0 | 1072/16 | 1072/16 | 67 | 0 | 0.000% __alloc_skb+2e | 12544/256 | 12544/256 | 49 | 38 | 0.000% __sigqueue_alloc+4a | 1296/144 | 1296/144 | 9 | 8 | 0.000% tracepoint_add_probe+6f | 80/16 | 80/16 | 5 | 0 | 0.000% ------------------------------------------------------------------------------------------------------ ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B0B6E9F.6020309@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-24 13:26:55 +08:00
if ((short)sample->cpu != s_alloc->alloc_cpu) {
perf kmem: Measure kmalloc/kfree CPU ping-pong call-sites Show statistics for allocations and frees on different cpus: ------------------------------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag ------------------------------------------------------------------------------------------------------ perf_event_alloc.clone.0+0 | 7504/682 | 7128/648 | 11 | 0 | 5.011% alloc_buffer_head+16 | 288/57 | 280/56 | 5 | 0 | 2.778% radix_tree_preload+51 | 296/296 | 288/288 | 1 | 0 | 2.703% tracepoint_add_probe+32e | 157/31 | 154/30 | 5 | 0 | 1.911% do_maps_open+0 | 796/12 | 792/12 | 66 | 0 | 0.503% sock_alloc_send_pskb+16e | 23780/495 | 23744/494 | 48 | 38 | 0.151% anon_vma_prepare+9a | 3744/44 | 3740/44 | 85 | 0 | 0.107% d_alloc+21 | 64948/164 | 64944/164 | 396 | 0 | 0.006% proc_alloc_inode+23 | 262292/676 | 262288/676 | 388 | 0 | 0.002% create_object+28 | 459600/200 | 459600/200 | 2298 | 71 | 0.000% journal_start+67 | 14440/40 | 14440/40 | 361 | 0 | 0.000% get_empty_filp+df | 53504/256 | 53504/256 | 209 | 0 | 0.000% getname+2a | 823296/4096 | 823296/4096 | 201 | 0 | 0.000% seq_read+2b0 | 544768/4096 | 544768/4096 | 133 | 0 | 0.000% seq_open+6d | 17024/128 | 17024/128 | 133 | 0 | 0.000% mmap_region+2e6 | 11704/88 | 11704/88 | 133 | 0 | 0.000% single_open+0 | 1072/16 | 1072/16 | 67 | 0 | 0.000% __alloc_skb+2e | 12544/256 | 12544/256 | 49 | 38 | 0.000% __sigqueue_alloc+4a | 1296/144 | 1296/144 | 9 | 8 | 0.000% tracepoint_add_probe+6f | 80/16 | 80/16 | 5 | 0 | 0.000% ------------------------------------------------------------------------------------------------------ ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B0B6E9F.6020309@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-24 13:26:55 +08:00
s_alloc->pingpong++;
s_caller = search_alloc_stat(0, s_alloc->call_site,
&root_caller_stat, callsite_cmp);
if (!s_caller)
return -1;
perf kmem: Measure kmalloc/kfree CPU ping-pong call-sites Show statistics for allocations and frees on different cpus: ------------------------------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag ------------------------------------------------------------------------------------------------------ perf_event_alloc.clone.0+0 | 7504/682 | 7128/648 | 11 | 0 | 5.011% alloc_buffer_head+16 | 288/57 | 280/56 | 5 | 0 | 2.778% radix_tree_preload+51 | 296/296 | 288/288 | 1 | 0 | 2.703% tracepoint_add_probe+32e | 157/31 | 154/30 | 5 | 0 | 1.911% do_maps_open+0 | 796/12 | 792/12 | 66 | 0 | 0.503% sock_alloc_send_pskb+16e | 23780/495 | 23744/494 | 48 | 38 | 0.151% anon_vma_prepare+9a | 3744/44 | 3740/44 | 85 | 0 | 0.107% d_alloc+21 | 64948/164 | 64944/164 | 396 | 0 | 0.006% proc_alloc_inode+23 | 262292/676 | 262288/676 | 388 | 0 | 0.002% create_object+28 | 459600/200 | 459600/200 | 2298 | 71 | 0.000% journal_start+67 | 14440/40 | 14440/40 | 361 | 0 | 0.000% get_empty_filp+df | 53504/256 | 53504/256 | 209 | 0 | 0.000% getname+2a | 823296/4096 | 823296/4096 | 201 | 0 | 0.000% seq_read+2b0 | 544768/4096 | 544768/4096 | 133 | 0 | 0.000% seq_open+6d | 17024/128 | 17024/128 | 133 | 0 | 0.000% mmap_region+2e6 | 11704/88 | 11704/88 | 133 | 0 | 0.000% single_open+0 | 1072/16 | 1072/16 | 67 | 0 | 0.000% __alloc_skb+2e | 12544/256 | 12544/256 | 49 | 38 | 0.000% __sigqueue_alloc+4a | 1296/144 | 1296/144 | 9 | 8 | 0.000% tracepoint_add_probe+6f | 80/16 | 80/16 | 5 | 0 | 0.000% ------------------------------------------------------------------------------------------------------ ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B0B6E9F.6020309@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-24 13:26:55 +08:00
s_caller->pingpong++;
}
s_alloc->alloc_cpu = -1;
return 0;
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
}
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
static u64 total_page_alloc_bytes;
static u64 total_page_free_bytes;
static u64 total_page_nomatch_bytes;
static u64 total_page_fail_bytes;
static unsigned long nr_page_allocs;
static unsigned long nr_page_frees;
static unsigned long nr_page_fails;
static unsigned long nr_page_nomatch;
static bool use_pfn;
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
static struct perf_session *kmem_session;
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
#define MAX_MIGRATE_TYPES 6
#define MAX_PAGE_ORDER 11
static int order_stats[MAX_PAGE_ORDER][MAX_MIGRATE_TYPES];
struct page_stat {
struct rb_node node;
u64 page;
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
u64 callsite;
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
int order;
unsigned gfp_flags;
unsigned migrate_type;
u64 alloc_bytes;
u64 free_bytes;
int nr_alloc;
int nr_free;
};
static struct rb_root page_tree;
static struct rb_root page_alloc_tree;
static struct rb_root page_alloc_sorted;
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
static struct rb_root page_caller_tree;
static struct rb_root page_caller_sorted;
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
struct alloc_func {
u64 start;
u64 end;
char *name;
};
static int nr_alloc_funcs;
static struct alloc_func *alloc_func_list;
static int funcmp(const void *a, const void *b)
{
const struct alloc_func *fa = a;
const struct alloc_func *fb = b;
if (fa->start > fb->start)
return 1;
else
return -1;
}
static int callcmp(const void *a, const void *b)
{
const struct alloc_func *fa = a;
const struct alloc_func *fb = b;
if (fb->start <= fa->start && fa->end < fb->end)
return 0;
if (fa->start > fb->start)
return 1;
else
return -1;
}
static int build_alloc_func_list(void)
{
int ret;
struct map *kernel_map;
struct symbol *sym;
struct rb_node *node;
struct alloc_func *func;
struct machine *machine = &kmem_session->machines.host;
regex_t alloc_func_regex;
const char pattern[] = "^_?_?(alloc|get_free|get_zeroed)_pages?";
ret = regcomp(&alloc_func_regex, pattern, REG_EXTENDED);
if (ret) {
char err[BUFSIZ];
regerror(ret, &alloc_func_regex, err, sizeof(err));
pr_err("Invalid regex: %s\n%s", pattern, err);
return -EINVAL;
}
kernel_map = machine->vmlinux_maps[MAP__FUNCTION];
if (map__load(kernel_map, NULL) < 0) {
pr_err("cannot load kernel map\n");
return -ENOENT;
}
map__for_each_symbol(kernel_map, sym, node) {
if (regexec(&alloc_func_regex, sym->name, 0, NULL, 0))
continue;
func = realloc(alloc_func_list,
(nr_alloc_funcs + 1) * sizeof(*func));
if (func == NULL)
return -ENOMEM;
pr_debug("alloc func: %s\n", sym->name);
func[nr_alloc_funcs].start = sym->start;
func[nr_alloc_funcs].end = sym->end;
func[nr_alloc_funcs].name = sym->name;
alloc_func_list = func;
nr_alloc_funcs++;
}
qsort(alloc_func_list, nr_alloc_funcs, sizeof(*func), funcmp);
regfree(&alloc_func_regex);
return 0;
}
/*
* Find first non-memory allocation function from callchain.
* The allocation functions are in the 'alloc_func_list'.
*/
static u64 find_callsite(struct perf_evsel *evsel, struct perf_sample *sample)
{
struct addr_location al;
struct machine *machine = &kmem_session->machines.host;
struct callchain_cursor_node *node;
if (alloc_func_list == NULL) {
if (build_alloc_func_list() < 0)
goto out;
}
al.thread = machine__findnew_thread(machine, sample->pid, sample->tid);
sample__resolve_callchain(sample, NULL, evsel, &al, 16);
callchain_cursor_commit(&callchain_cursor);
while (true) {
struct alloc_func key, *caller;
u64 addr;
node = callchain_cursor_current(&callchain_cursor);
if (node == NULL)
break;
key.start = key.end = node->ip;
caller = bsearch(&key, alloc_func_list, nr_alloc_funcs,
sizeof(key), callcmp);
if (!caller) {
/* found */
if (node->map)
addr = map__unmap_ip(node->map, node->ip);
else
addr = node->ip;
return addr;
} else
pr_debug3("skipping alloc function: %s\n", caller->name);
callchain_cursor_advance(&callchain_cursor);
}
out:
pr_debug2("unknown callsite: %"PRIx64 "\n", sample->ip);
return sample->ip;
}
static struct page_stat *
__page_stat__findnew_page(u64 page, bool create)
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
{
struct rb_node **node = &page_tree.rb_node;
struct rb_node *parent = NULL;
struct page_stat *data;
while (*node) {
s64 cmp;
parent = *node;
data = rb_entry(*node, struct page_stat, node);
cmp = data->page - page;
if (cmp < 0)
node = &parent->rb_left;
else if (cmp > 0)
node = &parent->rb_right;
else
return data;
}
if (!create)
return NULL;
data = zalloc(sizeof(*data));
if (data != NULL) {
data->page = page;
rb_link_node(&data->node, parent, node);
rb_insert_color(&data->node, &page_tree);
}
return data;
}
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
static struct page_stat *page_stat__find_page(u64 page)
{
return __page_stat__findnew_page(page, false);
}
static struct page_stat *page_stat__findnew_page(u64 page)
{
return __page_stat__findnew_page(page, true);
}
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
static int page_stat_cmp(struct page_stat *a, struct page_stat *b)
{
if (a->page > b->page)
return -1;
if (a->page < b->page)
return 1;
if (a->order > b->order)
return -1;
if (a->order < b->order)
return 1;
if (a->migrate_type > b->migrate_type)
return -1;
if (a->migrate_type < b->migrate_type)
return 1;
if (a->gfp_flags > b->gfp_flags)
return -1;
if (a->gfp_flags < b->gfp_flags)
return 1;
return 0;
}
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
static struct page_stat *
__page_stat__findnew_alloc(struct page_stat *pstat, bool create)
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
{
struct rb_node **node = &page_alloc_tree.rb_node;
struct rb_node *parent = NULL;
struct page_stat *data;
while (*node) {
s64 cmp;
parent = *node;
data = rb_entry(*node, struct page_stat, node);
cmp = page_stat_cmp(data, pstat);
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
if (cmp < 0)
node = &parent->rb_left;
else if (cmp > 0)
node = &parent->rb_right;
else
return data;
}
if (!create)
return NULL;
data = zalloc(sizeof(*data));
if (data != NULL) {
data->page = pstat->page;
data->order = pstat->order;
data->gfp_flags = pstat->gfp_flags;
data->migrate_type = pstat->migrate_type;
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
rb_link_node(&data->node, parent, node);
rb_insert_color(&data->node, &page_alloc_tree);
}
return data;
}
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
static struct page_stat *page_stat__find_alloc(struct page_stat *pstat)
{
return __page_stat__findnew_alloc(pstat, false);
}
static struct page_stat *page_stat__findnew_alloc(struct page_stat *pstat)
{
return __page_stat__findnew_alloc(pstat, true);
}
static struct page_stat *
__page_stat__findnew_caller(u64 callsite, bool create)
{
struct rb_node **node = &page_caller_tree.rb_node;
struct rb_node *parent = NULL;
struct page_stat *data;
while (*node) {
s64 cmp;
parent = *node;
data = rb_entry(*node, struct page_stat, node);
cmp = data->callsite - callsite;
if (cmp < 0)
node = &parent->rb_left;
else if (cmp > 0)
node = &parent->rb_right;
else
return data;
}
if (!create)
return NULL;
data = zalloc(sizeof(*data));
if (data != NULL) {
data->callsite = callsite;
rb_link_node(&data->node, parent, node);
rb_insert_color(&data->node, &page_caller_tree);
}
return data;
}
static struct page_stat *page_stat__find_caller(u64 callsite)
{
return __page_stat__findnew_caller(callsite, false);
}
static struct page_stat *page_stat__findnew_caller(u64 callsite)
{
return __page_stat__findnew_caller(callsite, true);
}
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
static bool valid_page(u64 pfn_or_page)
{
if (use_pfn && pfn_or_page == -1UL)
return false;
if (!use_pfn && pfn_or_page == 0)
return false;
return true;
}
static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
struct perf_sample *sample)
{
u64 page;
unsigned int order = perf_evsel__intval(evsel, sample, "order");
unsigned int gfp_flags = perf_evsel__intval(evsel, sample, "gfp_flags");
unsigned int migrate_type = perf_evsel__intval(evsel, sample,
"migratetype");
u64 bytes = kmem_page_size << order;
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
u64 callsite;
struct page_stat *pstat;
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
struct page_stat this = {
.order = order,
.gfp_flags = gfp_flags,
.migrate_type = migrate_type,
};
if (use_pfn)
page = perf_evsel__intval(evsel, sample, "pfn");
else
page = perf_evsel__intval(evsel, sample, "page");
nr_page_allocs++;
total_page_alloc_bytes += bytes;
if (!valid_page(page)) {
nr_page_fails++;
total_page_fail_bytes += bytes;
return 0;
}
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
callsite = find_callsite(evsel, sample);
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
/*
* This is to find the current page (with correct gfp flags and
* migrate type) at free event.
*/
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
pstat = page_stat__findnew_page(page);
if (pstat == NULL)
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
return -ENOMEM;
pstat->order = order;
pstat->gfp_flags = gfp_flags;
pstat->migrate_type = migrate_type;
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
pstat->callsite = callsite;
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
this.page = page;
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
pstat = page_stat__findnew_alloc(&this);
if (pstat == NULL)
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
return -ENOMEM;
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
pstat->nr_alloc++;
pstat->alloc_bytes += bytes;
pstat->callsite = callsite;
pstat = page_stat__findnew_caller(callsite);
if (pstat == NULL)
return -ENOMEM;
pstat->order = order;
pstat->gfp_flags = gfp_flags;
pstat->migrate_type = migrate_type;
pstat->nr_alloc++;
pstat->alloc_bytes += bytes;
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
order_stats[order][migrate_type]++;
return 0;
}
static int perf_evsel__process_page_free_event(struct perf_evsel *evsel,
struct perf_sample *sample)
{
u64 page;
unsigned int order = perf_evsel__intval(evsel, sample, "order");
u64 bytes = kmem_page_size << order;
struct page_stat *pstat;
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
struct page_stat this = {
.order = order,
};
if (use_pfn)
page = perf_evsel__intval(evsel, sample, "pfn");
else
page = perf_evsel__intval(evsel, sample, "page");
nr_page_frees++;
total_page_free_bytes += bytes;
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
pstat = page_stat__find_page(page);
if (pstat == NULL) {
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
pr_debug2("missing free at page %"PRIx64" (order: %d)\n",
page, order);
nr_page_nomatch++;
total_page_nomatch_bytes += bytes;
return 0;
}
this.page = page;
this.gfp_flags = pstat->gfp_flags;
this.migrate_type = pstat->migrate_type;
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
this.callsite = pstat->callsite;
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
rb_erase(&pstat->node, &page_tree);
free(pstat);
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
pstat = page_stat__find_alloc(&this);
if (pstat == NULL)
return -ENOENT;
pstat->nr_free++;
pstat->free_bytes += bytes;
pstat = page_stat__find_caller(this.callsite);
if (pstat == NULL)
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
return -ENOENT;
pstat->nr_free++;
pstat->free_bytes += bytes;
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
return 0;
}
typedef int (*tracepoint_handler)(struct perf_evsel *evsel,
struct perf_sample *sample);
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 06:15:03 +08:00
static int process_sample_event(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample,
struct perf_evsel *evsel,
struct machine *machine)
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
{
struct thread *thread = machine__findnew_thread(machine, sample->pid,
sample->tid);
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
if (thread == NULL) {
pr_debug("problem processing %d event, skipping it.\n",
event->header.type);
return -1;
}
dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
if (evsel->handler != NULL) {
tracepoint_handler f = evsel->handler;
return f(evsel, sample);
}
return 0;
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
}
static struct perf_tool perf_kmem = {
.sample = process_sample_event,
.comm = perf_event__process_comm,
.mmap = perf_event__process_mmap,
.mmap2 = perf_event__process_mmap2,
.ordered_events = true,
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
};
static double fragmentation(unsigned long n_req, unsigned long n_alloc)
{
if (n_alloc == 0)
return 0.0;
else
return 100.0 - (100.0 * n_req / n_alloc);
}
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
static void __print_slab_result(struct rb_root *root,
struct perf_session *session,
int n_lines, int is_caller)
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
{
struct rb_node *next;
struct machine *machine = &session->machines.host;
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
perf kmem: Fix alignment of slab result table Its table was a bit misaligned. Fix it. Before: # perf kmem stat --caller -l 10 ------------------------------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag ------------------------------------------------------------------------------------------------------ radeon_cs_parser_init.part.1+11a | 2080/260 | 1504/188 | 8 | 0 | 27.692% radeon_cs_parser_init.part.1+e1 | 384/96 | 288/72 | 4 | 0 | 25.000% radeon_cs_parser_init.part.1+93 | 128/32 | 96/24 | 4 | 0 | 25.000% load_elf_binary+a39 | 512/512 | 392/392 | 1 | 0 | 23.438% __alloc_skb+89 | 6144/877 | 4800/685 | 7 | 6 | 21.875% radeon_fence_emit+5c | 1152/192 | 912/152 | 6 | 0 | 20.833% radeon_cs_parser_relocs+ad | 8192/2048 | 6624/1656 | 4 | 0 | 19.141% radeon_sa_bo_new+78 | 1280/64 | 1120/56 | 20 | 0 | 12.500% load_elf_binary+2c4 | 32/32 | 28/28 | 1 | 0 | 12.500% anon_vma_prepare+101 | 576/72 | 512/64 | 8 | 0 | 11.111% ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------------------------------ After: --------------------------------------------------------------------------------------------------------- Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag --------------------------------------------------------------------------------------------------------- radeon_cs_parser_init.part.1+11a | 2080/260 | 1504/188 | 8 | 0 | 27.692% radeon_cs_parser_init.part.1+e1 | 384/96 | 288/72 | 4 | 0 | 25.000% radeon_cs_parser_init.part.1+93 | 128/32 | 96/24 | 4 | 0 | 25.000% load_elf_binary+a39 | 512/512 | 392/392 | 1 | 0 | 23.438% __alloc_skb+89 | 6144/877 | 4800/685 | 7 | 6 | 21.875% radeon_fence_emit+5c | 1152/192 | 912/152 | 6 | 0 | 20.833% radeon_cs_parser_relocs+ad | 8192/2048 | 6624/1656 | 4 | 0 | 19.141% radeon_sa_bo_new+78 | 1280/64 | 1120/56 | 20 | 0 | 12.500% load_elf_binary+2c4 | 32/32 | 28/28 | 1 | 0 | 12.500% anon_vma_prepare+101 | 576/72 | 512/64 | 8 | 0 | 11.111% ... | ... | ... | ... | ... | ... --------------------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1426145571-3065-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-03-12 15:32:48 +08:00
printf("%.105s\n", graph_dotted_line);
perf kmem: Measure kmalloc/kfree CPU ping-pong call-sites Show statistics for allocations and frees on different cpus: ------------------------------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag ------------------------------------------------------------------------------------------------------ perf_event_alloc.clone.0+0 | 7504/682 | 7128/648 | 11 | 0 | 5.011% alloc_buffer_head+16 | 288/57 | 280/56 | 5 | 0 | 2.778% radix_tree_preload+51 | 296/296 | 288/288 | 1 | 0 | 2.703% tracepoint_add_probe+32e | 157/31 | 154/30 | 5 | 0 | 1.911% do_maps_open+0 | 796/12 | 792/12 | 66 | 0 | 0.503% sock_alloc_send_pskb+16e | 23780/495 | 23744/494 | 48 | 38 | 0.151% anon_vma_prepare+9a | 3744/44 | 3740/44 | 85 | 0 | 0.107% d_alloc+21 | 64948/164 | 64944/164 | 396 | 0 | 0.006% proc_alloc_inode+23 | 262292/676 | 262288/676 | 388 | 0 | 0.002% create_object+28 | 459600/200 | 459600/200 | 2298 | 71 | 0.000% journal_start+67 | 14440/40 | 14440/40 | 361 | 0 | 0.000% get_empty_filp+df | 53504/256 | 53504/256 | 209 | 0 | 0.000% getname+2a | 823296/4096 | 823296/4096 | 201 | 0 | 0.000% seq_read+2b0 | 544768/4096 | 544768/4096 | 133 | 0 | 0.000% seq_open+6d | 17024/128 | 17024/128 | 133 | 0 | 0.000% mmap_region+2e6 | 11704/88 | 11704/88 | 133 | 0 | 0.000% single_open+0 | 1072/16 | 1072/16 | 67 | 0 | 0.000% __alloc_skb+2e | 12544/256 | 12544/256 | 49 | 38 | 0.000% __sigqueue_alloc+4a | 1296/144 | 1296/144 | 9 | 8 | 0.000% tracepoint_add_probe+6f | 80/16 | 80/16 | 5 | 0 | 0.000% ------------------------------------------------------------------------------------------------------ ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B0B6E9F.6020309@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-24 13:26:55 +08:00
printf(" %-34s |", is_caller ? "Callsite": "Alloc Ptr");
printf(" Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag\n");
perf kmem: Fix alignment of slab result table Its table was a bit misaligned. Fix it. Before: # perf kmem stat --caller -l 10 ------------------------------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag ------------------------------------------------------------------------------------------------------ radeon_cs_parser_init.part.1+11a | 2080/260 | 1504/188 | 8 | 0 | 27.692% radeon_cs_parser_init.part.1+e1 | 384/96 | 288/72 | 4 | 0 | 25.000% radeon_cs_parser_init.part.1+93 | 128/32 | 96/24 | 4 | 0 | 25.000% load_elf_binary+a39 | 512/512 | 392/392 | 1 | 0 | 23.438% __alloc_skb+89 | 6144/877 | 4800/685 | 7 | 6 | 21.875% radeon_fence_emit+5c | 1152/192 | 912/152 | 6 | 0 | 20.833% radeon_cs_parser_relocs+ad | 8192/2048 | 6624/1656 | 4 | 0 | 19.141% radeon_sa_bo_new+78 | 1280/64 | 1120/56 | 20 | 0 | 12.500% load_elf_binary+2c4 | 32/32 | 28/28 | 1 | 0 | 12.500% anon_vma_prepare+101 | 576/72 | 512/64 | 8 | 0 | 11.111% ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------------------------------ After: --------------------------------------------------------------------------------------------------------- Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag --------------------------------------------------------------------------------------------------------- radeon_cs_parser_init.part.1+11a | 2080/260 | 1504/188 | 8 | 0 | 27.692% radeon_cs_parser_init.part.1+e1 | 384/96 | 288/72 | 4 | 0 | 25.000% radeon_cs_parser_init.part.1+93 | 128/32 | 96/24 | 4 | 0 | 25.000% load_elf_binary+a39 | 512/512 | 392/392 | 1 | 0 | 23.438% __alloc_skb+89 | 6144/877 | 4800/685 | 7 | 6 | 21.875% radeon_fence_emit+5c | 1152/192 | 912/152 | 6 | 0 | 20.833% radeon_cs_parser_relocs+ad | 8192/2048 | 6624/1656 | 4 | 0 | 19.141% radeon_sa_bo_new+78 | 1280/64 | 1120/56 | 20 | 0 | 12.500% load_elf_binary+2c4 | 32/32 | 28/28 | 1 | 0 | 12.500% anon_vma_prepare+101 | 576/72 | 512/64 | 8 | 0 | 11.111% ... | ... | ... | ... | ... | ... --------------------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1426145571-3065-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-03-12 15:32:48 +08:00
printf("%.105s\n", graph_dotted_line);
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
next = rb_first(root);
while (next && n_lines--) {
struct alloc_stat *data = rb_entry(next, struct alloc_stat,
node);
struct symbol *sym = NULL;
struct map *map;
perf kmem: Measure kmalloc/kfree CPU ping-pong call-sites Show statistics for allocations and frees on different cpus: ------------------------------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag ------------------------------------------------------------------------------------------------------ perf_event_alloc.clone.0+0 | 7504/682 | 7128/648 | 11 | 0 | 5.011% alloc_buffer_head+16 | 288/57 | 280/56 | 5 | 0 | 2.778% radix_tree_preload+51 | 296/296 | 288/288 | 1 | 0 | 2.703% tracepoint_add_probe+32e | 157/31 | 154/30 | 5 | 0 | 1.911% do_maps_open+0 | 796/12 | 792/12 | 66 | 0 | 0.503% sock_alloc_send_pskb+16e | 23780/495 | 23744/494 | 48 | 38 | 0.151% anon_vma_prepare+9a | 3744/44 | 3740/44 | 85 | 0 | 0.107% d_alloc+21 | 64948/164 | 64944/164 | 396 | 0 | 0.006% proc_alloc_inode+23 | 262292/676 | 262288/676 | 388 | 0 | 0.002% create_object+28 | 459600/200 | 459600/200 | 2298 | 71 | 0.000% journal_start+67 | 14440/40 | 14440/40 | 361 | 0 | 0.000% get_empty_filp+df | 53504/256 | 53504/256 | 209 | 0 | 0.000% getname+2a | 823296/4096 | 823296/4096 | 201 | 0 | 0.000% seq_read+2b0 | 544768/4096 | 544768/4096 | 133 | 0 | 0.000% seq_open+6d | 17024/128 | 17024/128 | 133 | 0 | 0.000% mmap_region+2e6 | 11704/88 | 11704/88 | 133 | 0 | 0.000% single_open+0 | 1072/16 | 1072/16 | 67 | 0 | 0.000% __alloc_skb+2e | 12544/256 | 12544/256 | 49 | 38 | 0.000% __sigqueue_alloc+4a | 1296/144 | 1296/144 | 9 | 8 | 0.000% tracepoint_add_probe+6f | 80/16 | 80/16 | 5 | 0 | 0.000% ------------------------------------------------------------------------------------------------------ ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B0B6E9F.6020309@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-24 13:26:55 +08:00
char buf[BUFSIZ];
u64 addr;
if (is_caller) {
addr = data->call_site;
if (!raw_ip)
sym = machine__find_kernel_function(machine, addr, &map, NULL);
} else
addr = data->ptr;
if (sym != NULL)
snprintf(buf, sizeof(buf), "%s+%" PRIx64 "", sym->name,
addr - map->unmap_ip(map, sym->start));
else
snprintf(buf, sizeof(buf), "%#" PRIx64 "", addr);
perf kmem: Measure kmalloc/kfree CPU ping-pong call-sites Show statistics for allocations and frees on different cpus: ------------------------------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag ------------------------------------------------------------------------------------------------------ perf_event_alloc.clone.0+0 | 7504/682 | 7128/648 | 11 | 0 | 5.011% alloc_buffer_head+16 | 288/57 | 280/56 | 5 | 0 | 2.778% radix_tree_preload+51 | 296/296 | 288/288 | 1 | 0 | 2.703% tracepoint_add_probe+32e | 157/31 | 154/30 | 5 | 0 | 1.911% do_maps_open+0 | 796/12 | 792/12 | 66 | 0 | 0.503% sock_alloc_send_pskb+16e | 23780/495 | 23744/494 | 48 | 38 | 0.151% anon_vma_prepare+9a | 3744/44 | 3740/44 | 85 | 0 | 0.107% d_alloc+21 | 64948/164 | 64944/164 | 396 | 0 | 0.006% proc_alloc_inode+23 | 262292/676 | 262288/676 | 388 | 0 | 0.002% create_object+28 | 459600/200 | 459600/200 | 2298 | 71 | 0.000% journal_start+67 | 14440/40 | 14440/40 | 361 | 0 | 0.000% get_empty_filp+df | 53504/256 | 53504/256 | 209 | 0 | 0.000% getname+2a | 823296/4096 | 823296/4096 | 201 | 0 | 0.000% seq_read+2b0 | 544768/4096 | 544768/4096 | 133 | 0 | 0.000% seq_open+6d | 17024/128 | 17024/128 | 133 | 0 | 0.000% mmap_region+2e6 | 11704/88 | 11704/88 | 133 | 0 | 0.000% single_open+0 | 1072/16 | 1072/16 | 67 | 0 | 0.000% __alloc_skb+2e | 12544/256 | 12544/256 | 49 | 38 | 0.000% __sigqueue_alloc+4a | 1296/144 | 1296/144 | 9 | 8 | 0.000% tracepoint_add_probe+6f | 80/16 | 80/16 | 5 | 0 | 0.000% ------------------------------------------------------------------------------------------------------ ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B0B6E9F.6020309@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-24 13:26:55 +08:00
printf(" %-34s |", buf);
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
perf kmem: Fix alignment of slab result table Its table was a bit misaligned. Fix it. Before: # perf kmem stat --caller -l 10 ------------------------------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag ------------------------------------------------------------------------------------------------------ radeon_cs_parser_init.part.1+11a | 2080/260 | 1504/188 | 8 | 0 | 27.692% radeon_cs_parser_init.part.1+e1 | 384/96 | 288/72 | 4 | 0 | 25.000% radeon_cs_parser_init.part.1+93 | 128/32 | 96/24 | 4 | 0 | 25.000% load_elf_binary+a39 | 512/512 | 392/392 | 1 | 0 | 23.438% __alloc_skb+89 | 6144/877 | 4800/685 | 7 | 6 | 21.875% radeon_fence_emit+5c | 1152/192 | 912/152 | 6 | 0 | 20.833% radeon_cs_parser_relocs+ad | 8192/2048 | 6624/1656 | 4 | 0 | 19.141% radeon_sa_bo_new+78 | 1280/64 | 1120/56 | 20 | 0 | 12.500% load_elf_binary+2c4 | 32/32 | 28/28 | 1 | 0 | 12.500% anon_vma_prepare+101 | 576/72 | 512/64 | 8 | 0 | 11.111% ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------------------------------ After: --------------------------------------------------------------------------------------------------------- Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag --------------------------------------------------------------------------------------------------------- radeon_cs_parser_init.part.1+11a | 2080/260 | 1504/188 | 8 | 0 | 27.692% radeon_cs_parser_init.part.1+e1 | 384/96 | 288/72 | 4 | 0 | 25.000% radeon_cs_parser_init.part.1+93 | 128/32 | 96/24 | 4 | 0 | 25.000% load_elf_binary+a39 | 512/512 | 392/392 | 1 | 0 | 23.438% __alloc_skb+89 | 6144/877 | 4800/685 | 7 | 6 | 21.875% radeon_fence_emit+5c | 1152/192 | 912/152 | 6 | 0 | 20.833% radeon_cs_parser_relocs+ad | 8192/2048 | 6624/1656 | 4 | 0 | 19.141% radeon_sa_bo_new+78 | 1280/64 | 1120/56 | 20 | 0 | 12.500% load_elf_binary+2c4 | 32/32 | 28/28 | 1 | 0 | 12.500% anon_vma_prepare+101 | 576/72 | 512/64 | 8 | 0 | 11.111% ... | ... | ... | ... | ... | ... --------------------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1426145571-3065-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-03-12 15:32:48 +08:00
printf(" %9llu/%-5lu | %9llu/%-5lu | %8lu | %9lu | %6.3f%%\n",
perf kmem: Measure kmalloc/kfree CPU ping-pong call-sites Show statistics for allocations and frees on different cpus: ------------------------------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag ------------------------------------------------------------------------------------------------------ perf_event_alloc.clone.0+0 | 7504/682 | 7128/648 | 11 | 0 | 5.011% alloc_buffer_head+16 | 288/57 | 280/56 | 5 | 0 | 2.778% radix_tree_preload+51 | 296/296 | 288/288 | 1 | 0 | 2.703% tracepoint_add_probe+32e | 157/31 | 154/30 | 5 | 0 | 1.911% do_maps_open+0 | 796/12 | 792/12 | 66 | 0 | 0.503% sock_alloc_send_pskb+16e | 23780/495 | 23744/494 | 48 | 38 | 0.151% anon_vma_prepare+9a | 3744/44 | 3740/44 | 85 | 0 | 0.107% d_alloc+21 | 64948/164 | 64944/164 | 396 | 0 | 0.006% proc_alloc_inode+23 | 262292/676 | 262288/676 | 388 | 0 | 0.002% create_object+28 | 459600/200 | 459600/200 | 2298 | 71 | 0.000% journal_start+67 | 14440/40 | 14440/40 | 361 | 0 | 0.000% get_empty_filp+df | 53504/256 | 53504/256 | 209 | 0 | 0.000% getname+2a | 823296/4096 | 823296/4096 | 201 | 0 | 0.000% seq_read+2b0 | 544768/4096 | 544768/4096 | 133 | 0 | 0.000% seq_open+6d | 17024/128 | 17024/128 | 133 | 0 | 0.000% mmap_region+2e6 | 11704/88 | 11704/88 | 133 | 0 | 0.000% single_open+0 | 1072/16 | 1072/16 | 67 | 0 | 0.000% __alloc_skb+2e | 12544/256 | 12544/256 | 49 | 38 | 0.000% __sigqueue_alloc+4a | 1296/144 | 1296/144 | 9 | 8 | 0.000% tracepoint_add_probe+6f | 80/16 | 80/16 | 5 | 0 | 0.000% ------------------------------------------------------------------------------------------------------ ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B0B6E9F.6020309@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-24 13:26:55 +08:00
(unsigned long long)data->bytes_alloc,
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
(unsigned long)data->bytes_alloc / data->hit,
(unsigned long long)data->bytes_req,
(unsigned long)data->bytes_req / data->hit,
(unsigned long)data->hit,
perf kmem: Measure kmalloc/kfree CPU ping-pong call-sites Show statistics for allocations and frees on different cpus: ------------------------------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag ------------------------------------------------------------------------------------------------------ perf_event_alloc.clone.0+0 | 7504/682 | 7128/648 | 11 | 0 | 5.011% alloc_buffer_head+16 | 288/57 | 280/56 | 5 | 0 | 2.778% radix_tree_preload+51 | 296/296 | 288/288 | 1 | 0 | 2.703% tracepoint_add_probe+32e | 157/31 | 154/30 | 5 | 0 | 1.911% do_maps_open+0 | 796/12 | 792/12 | 66 | 0 | 0.503% sock_alloc_send_pskb+16e | 23780/495 | 23744/494 | 48 | 38 | 0.151% anon_vma_prepare+9a | 3744/44 | 3740/44 | 85 | 0 | 0.107% d_alloc+21 | 64948/164 | 64944/164 | 396 | 0 | 0.006% proc_alloc_inode+23 | 262292/676 | 262288/676 | 388 | 0 | 0.002% create_object+28 | 459600/200 | 459600/200 | 2298 | 71 | 0.000% journal_start+67 | 14440/40 | 14440/40 | 361 | 0 | 0.000% get_empty_filp+df | 53504/256 | 53504/256 | 209 | 0 | 0.000% getname+2a | 823296/4096 | 823296/4096 | 201 | 0 | 0.000% seq_read+2b0 | 544768/4096 | 544768/4096 | 133 | 0 | 0.000% seq_open+6d | 17024/128 | 17024/128 | 133 | 0 | 0.000% mmap_region+2e6 | 11704/88 | 11704/88 | 133 | 0 | 0.000% single_open+0 | 1072/16 | 1072/16 | 67 | 0 | 0.000% __alloc_skb+2e | 12544/256 | 12544/256 | 49 | 38 | 0.000% __sigqueue_alloc+4a | 1296/144 | 1296/144 | 9 | 8 | 0.000% tracepoint_add_probe+6f | 80/16 | 80/16 | 5 | 0 | 0.000% ------------------------------------------------------------------------------------------------------ ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B0B6E9F.6020309@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-24 13:26:55 +08:00
(unsigned long)data->pingpong,
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
fragmentation(data->bytes_req, data->bytes_alloc));
next = rb_next(next);
}
if (n_lines == -1)
perf kmem: Fix alignment of slab result table Its table was a bit misaligned. Fix it. Before: # perf kmem stat --caller -l 10 ------------------------------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag ------------------------------------------------------------------------------------------------------ radeon_cs_parser_init.part.1+11a | 2080/260 | 1504/188 | 8 | 0 | 27.692% radeon_cs_parser_init.part.1+e1 | 384/96 | 288/72 | 4 | 0 | 25.000% radeon_cs_parser_init.part.1+93 | 128/32 | 96/24 | 4 | 0 | 25.000% load_elf_binary+a39 | 512/512 | 392/392 | 1 | 0 | 23.438% __alloc_skb+89 | 6144/877 | 4800/685 | 7 | 6 | 21.875% radeon_fence_emit+5c | 1152/192 | 912/152 | 6 | 0 | 20.833% radeon_cs_parser_relocs+ad | 8192/2048 | 6624/1656 | 4 | 0 | 19.141% radeon_sa_bo_new+78 | 1280/64 | 1120/56 | 20 | 0 | 12.500% load_elf_binary+2c4 | 32/32 | 28/28 | 1 | 0 | 12.500% anon_vma_prepare+101 | 576/72 | 512/64 | 8 | 0 | 11.111% ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------------------------------ After: --------------------------------------------------------------------------------------------------------- Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag --------------------------------------------------------------------------------------------------------- radeon_cs_parser_init.part.1+11a | 2080/260 | 1504/188 | 8 | 0 | 27.692% radeon_cs_parser_init.part.1+e1 | 384/96 | 288/72 | 4 | 0 | 25.000% radeon_cs_parser_init.part.1+93 | 128/32 | 96/24 | 4 | 0 | 25.000% load_elf_binary+a39 | 512/512 | 392/392 | 1 | 0 | 23.438% __alloc_skb+89 | 6144/877 | 4800/685 | 7 | 6 | 21.875% radeon_fence_emit+5c | 1152/192 | 912/152 | 6 | 0 | 20.833% radeon_cs_parser_relocs+ad | 8192/2048 | 6624/1656 | 4 | 0 | 19.141% radeon_sa_bo_new+78 | 1280/64 | 1120/56 | 20 | 0 | 12.500% load_elf_binary+2c4 | 32/32 | 28/28 | 1 | 0 | 12.500% anon_vma_prepare+101 | 576/72 | 512/64 | 8 | 0 | 11.111% ... | ... | ... | ... | ... | ... --------------------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1426145571-3065-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-03-12 15:32:48 +08:00
printf(" ... | ... | ... | ... | ... | ... \n");
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
perf kmem: Fix alignment of slab result table Its table was a bit misaligned. Fix it. Before: # perf kmem stat --caller -l 10 ------------------------------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag ------------------------------------------------------------------------------------------------------ radeon_cs_parser_init.part.1+11a | 2080/260 | 1504/188 | 8 | 0 | 27.692% radeon_cs_parser_init.part.1+e1 | 384/96 | 288/72 | 4 | 0 | 25.000% radeon_cs_parser_init.part.1+93 | 128/32 | 96/24 | 4 | 0 | 25.000% load_elf_binary+a39 | 512/512 | 392/392 | 1 | 0 | 23.438% __alloc_skb+89 | 6144/877 | 4800/685 | 7 | 6 | 21.875% radeon_fence_emit+5c | 1152/192 | 912/152 | 6 | 0 | 20.833% radeon_cs_parser_relocs+ad | 8192/2048 | 6624/1656 | 4 | 0 | 19.141% radeon_sa_bo_new+78 | 1280/64 | 1120/56 | 20 | 0 | 12.500% load_elf_binary+2c4 | 32/32 | 28/28 | 1 | 0 | 12.500% anon_vma_prepare+101 | 576/72 | 512/64 | 8 | 0 | 11.111% ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------------------------------ After: --------------------------------------------------------------------------------------------------------- Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag --------------------------------------------------------------------------------------------------------- radeon_cs_parser_init.part.1+11a | 2080/260 | 1504/188 | 8 | 0 | 27.692% radeon_cs_parser_init.part.1+e1 | 384/96 | 288/72 | 4 | 0 | 25.000% radeon_cs_parser_init.part.1+93 | 128/32 | 96/24 | 4 | 0 | 25.000% load_elf_binary+a39 | 512/512 | 392/392 | 1 | 0 | 23.438% __alloc_skb+89 | 6144/877 | 4800/685 | 7 | 6 | 21.875% radeon_fence_emit+5c | 1152/192 | 912/152 | 6 | 0 | 20.833% radeon_cs_parser_relocs+ad | 8192/2048 | 6624/1656 | 4 | 0 | 19.141% radeon_sa_bo_new+78 | 1280/64 | 1120/56 | 20 | 0 | 12.500% load_elf_binary+2c4 | 32/32 | 28/28 | 1 | 0 | 12.500% anon_vma_prepare+101 | 576/72 | 512/64 | 8 | 0 | 11.111% ... | ... | ... | ... | ... | ... --------------------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1426145571-3065-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-03-12 15:32:48 +08:00
printf("%.105s\n", graph_dotted_line);
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
}
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
static const char * const migrate_type_str[] = {
"UNMOVABL",
"RECLAIM",
"MOVABLE",
"RESERVED",
"CMA/ISLT",
"UNKNOWN",
};
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
static void __print_page_alloc_result(struct perf_session *session, int n_lines)
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
{
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
struct rb_node *next = rb_first(&page_alloc_sorted);
struct machine *machine = &session->machines.host;
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
const char *format;
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
printf("\n%.105s\n", graph_dotted_line);
printf(" %-16s | Total alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite\n",
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
use_pfn ? "PFN" : "Page");
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
printf("%.105s\n", graph_dotted_line);
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
if (use_pfn)
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
format = " %16llu | %'16llu | %'9d | %5d | %8s | %08lx | %s\n";
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
else
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
format = " %016llx | %'16llu | %'9d | %5d | %8s | %08lx | %s\n";
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
while (next && n_lines--) {
struct page_stat *data;
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
struct symbol *sym;
struct map *map;
char buf[32];
char *caller = buf;
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
data = rb_entry(next, struct page_stat, node);
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
sym = machine__find_kernel_function(machine, data->callsite,
&map, NULL);
if (sym && sym->name)
caller = sym->name;
else
scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
printf(format, (unsigned long long)data->page,
(unsigned long long)data->alloc_bytes / 1024,
data->nr_alloc, data->order,
migrate_type_str[data->migrate_type],
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
(unsigned long)data->gfp_flags, caller);
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
next = rb_next(next);
}
if (n_lines == -1)
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
printf(" ... | ... | ... | ... | ... | ... | ...\n");
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
printf("%.105s\n", graph_dotted_line);
}
static void __print_page_caller_result(struct perf_session *session, int n_lines)
{
struct rb_node *next = rb_first(&page_caller_sorted);
struct machine *machine = &session->machines.host;
printf("\n%.105s\n", graph_dotted_line);
printf(" Total alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite\n");
printf("%.105s\n", graph_dotted_line);
while (next && n_lines--) {
struct page_stat *data;
struct symbol *sym;
struct map *map;
char buf[32];
char *caller = buf;
data = rb_entry(next, struct page_stat, node);
sym = machine__find_kernel_function(machine, data->callsite,
&map, NULL);
if (sym && sym->name)
caller = sym->name;
else
scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
printf(" %'16llu | %'9d | %5d | %8s | %08lx | %s\n",
(unsigned long long)data->alloc_bytes / 1024,
data->nr_alloc, data->order,
migrate_type_str[data->migrate_type],
(unsigned long)data->gfp_flags, caller);
next = rb_next(next);
}
if (n_lines == -1)
printf(" ... | ... | ... | ... | ... | ...\n");
printf("%.105s\n", graph_dotted_line);
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
}
static void print_slab_summary(void)
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
{
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
printf("\nSUMMARY (SLAB allocator)");
printf("\n========================\n");
printf("Total bytes requested: %'lu\n", total_requested);
printf("Total bytes allocated: %'lu\n", total_allocated);
printf("Total bytes wasted on internal fragmentation: %'lu\n",
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
total_allocated - total_requested);
printf("Internal fragmentation: %f%%\n",
fragmentation(total_requested, total_allocated));
printf("Cross CPU allocations: %'lu/%'lu\n", nr_cross_allocs, nr_allocs);
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
}
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
static void print_page_summary(void)
{
int o, m;
u64 nr_alloc_freed = nr_page_frees - nr_page_nomatch;
u64 total_alloc_freed_bytes = total_page_free_bytes - total_page_nomatch_bytes;
printf("\nSUMMARY (page allocator)");
printf("\n========================\n");
printf("%-30s: %'16lu [ %'16"PRIu64" KB ]\n", "Total allocation requests",
nr_page_allocs, total_page_alloc_bytes / 1024);
printf("%-30s: %'16lu [ %'16"PRIu64" KB ]\n", "Total free requests",
nr_page_frees, total_page_free_bytes / 1024);
printf("\n");
printf("%-30s: %'16lu [ %'16"PRIu64" KB ]\n", "Total alloc+freed requests",
nr_alloc_freed, (total_alloc_freed_bytes) / 1024);
printf("%-30s: %'16lu [ %'16"PRIu64" KB ]\n", "Total alloc-only requests",
nr_page_allocs - nr_alloc_freed,
(total_page_alloc_bytes - total_alloc_freed_bytes) / 1024);
printf("%-30s: %'16lu [ %'16"PRIu64" KB ]\n", "Total free-only requests",
nr_page_nomatch, total_page_nomatch_bytes / 1024);
printf("\n");
printf("%-30s: %'16lu [ %'16"PRIu64" KB ]\n", "Total allocation failures",
nr_page_fails, total_page_fail_bytes / 1024);
printf("\n");
printf("%5s %12s %12s %12s %12s %12s\n", "Order", "Unmovable",
"Reclaimable", "Movable", "Reserved", "CMA/Isolated");
printf("%.5s %.12s %.12s %.12s %.12s %.12s\n", graph_dotted_line,
graph_dotted_line, graph_dotted_line, graph_dotted_line,
graph_dotted_line, graph_dotted_line);
for (o = 0; o < MAX_PAGE_ORDER; o++) {
printf("%5d", o);
for (m = 0; m < MAX_MIGRATE_TYPES - 1; m++) {
if (order_stats[o][m])
printf(" %'12d", order_stats[o][m]);
else
printf(" %12c", '.');
}
printf("\n");
}
}
static void print_slab_result(struct perf_session *session)
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
{
if (caller_flag)
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
__print_slab_result(&root_caller_sorted, session, caller_lines, 1);
if (alloc_flag)
__print_slab_result(&root_alloc_sorted, session, alloc_lines, 0);
print_slab_summary();
}
static void print_page_result(struct perf_session *session)
{
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
if (caller_flag)
__print_page_caller_result(session, caller_lines);
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
if (alloc_flag)
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
__print_page_alloc_result(session, alloc_lines);
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
print_page_summary();
}
static void print_result(struct perf_session *session)
{
if (kmem_slab)
print_slab_result(session);
if (kmem_page)
print_page_result(session);
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
}
struct sort_dimension {
const char name[20];
sort_fn_t cmp;
struct list_head list;
};
static LIST_HEAD(caller_sort);
static LIST_HEAD(alloc_sort);
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
static void sort_slab_insert(struct rb_root *root, struct alloc_stat *data,
struct list_head *sort_list)
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
{
struct rb_node **new = &(root->rb_node);
struct rb_node *parent = NULL;
struct sort_dimension *sort;
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
while (*new) {
struct alloc_stat *this;
int cmp = 0;
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
this = rb_entry(*new, struct alloc_stat, node);
parent = *new;
list_for_each_entry(sort, sort_list, list) {
cmp = sort->cmp(data, this);
if (cmp)
break;
}
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
if (cmp > 0)
new = &((*new)->rb_left);
else
new = &((*new)->rb_right);
}
rb_link_node(&data->node, parent, new);
rb_insert_color(&data->node, root);
}
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
static void __sort_slab_result(struct rb_root *root, struct rb_root *root_sorted,
struct list_head *sort_list)
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
{
struct rb_node *node;
struct alloc_stat *data;
for (;;) {
node = rb_first(root);
if (!node)
break;
rb_erase(node, root);
data = rb_entry(node, struct alloc_stat, node);
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
sort_slab_insert(root_sorted, data, sort_list);
}
}
static void sort_page_insert(struct rb_root *root, struct page_stat *data)
{
struct rb_node **new = &root->rb_node;
struct rb_node *parent = NULL;
while (*new) {
struct page_stat *this;
int cmp = 0;
this = rb_entry(*new, struct page_stat, node);
parent = *new;
/* TODO: support more sort key */
cmp = data->alloc_bytes - this->alloc_bytes;
if (cmp > 0)
new = &parent->rb_left;
else
new = &parent->rb_right;
}
rb_link_node(&data->node, parent, new);
rb_insert_color(&data->node, root);
}
static void __sort_page_result(struct rb_root *root, struct rb_root *root_sorted)
{
struct rb_node *node;
struct page_stat *data;
for (;;) {
node = rb_first(root);
if (!node)
break;
rb_erase(node, root);
data = rb_entry(node, struct page_stat, node);
sort_page_insert(root_sorted, data);
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
}
}
static void sort_result(void)
{
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
if (kmem_slab) {
__sort_slab_result(&root_alloc_stat, &root_alloc_sorted,
&alloc_sort);
__sort_slab_result(&root_caller_stat, &root_caller_sorted,
&caller_sort);
}
if (kmem_page) {
__sort_page_result(&page_alloc_tree, &page_alloc_sorted);
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
__sort_page_result(&page_caller_tree, &page_caller_sorted);
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
}
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
}
static int __cmd_kmem(struct perf_session *session)
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
{
int err = -EINVAL;
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
struct perf_evsel *evsel;
const struct perf_evsel_str_handler kmem_tracepoints[] = {
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
/* slab allocator */
{ "kmem:kmalloc", perf_evsel__process_alloc_event, },
{ "kmem:kmem_cache_alloc", perf_evsel__process_alloc_event, },
{ "kmem:kmalloc_node", perf_evsel__process_alloc_node_event, },
{ "kmem:kmem_cache_alloc_node", perf_evsel__process_alloc_node_event, },
{ "kmem:kfree", perf_evsel__process_free_event, },
{ "kmem:kmem_cache_free", perf_evsel__process_free_event, },
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
/* page allocator */
{ "kmem:mm_page_alloc", perf_evsel__process_page_alloc_event, },
{ "kmem:mm_page_free", perf_evsel__process_page_free_event, },
};
if (!perf_session__has_traces(session, "kmem record"))
goto out;
if (perf_session__set_tracepoints_handlers(session, kmem_tracepoints)) {
pr_err("Initializing perf session tracepoint handlers failed\n");
goto out;
}
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
evlist__for_each(session->evlist, evsel) {
if (!strcmp(perf_evsel__name(evsel), "kmem:mm_page_alloc") &&
perf_evsel__field(evsel, "pfn")) {
use_pfn = true;
break;
}
}
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
setup_pager();
err = perf_session__process_events(session);
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
if (err != 0) {
pr_err("error during process events: %d\n", err);
goto out;
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
}
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
sort_result();
print_result(session);
out:
return err;
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
}
static int ptr_cmp(struct alloc_stat *l, struct alloc_stat *r)
{
if (l->ptr < r->ptr)
return -1;
else if (l->ptr > r->ptr)
return 1;
return 0;
}
static struct sort_dimension ptr_sort_dimension = {
.name = "ptr",
.cmp = ptr_cmp,
};
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
static int callsite_cmp(struct alloc_stat *l, struct alloc_stat *r)
{
if (l->call_site < r->call_site)
return -1;
else if (l->call_site > r->call_site)
return 1;
return 0;
}
static struct sort_dimension callsite_sort_dimension = {
.name = "callsite",
.cmp = callsite_cmp,
};
static int hit_cmp(struct alloc_stat *l, struct alloc_stat *r)
{
if (l->hit < r->hit)
return -1;
else if (l->hit > r->hit)
return 1;
return 0;
}
static struct sort_dimension hit_sort_dimension = {
.name = "hit",
.cmp = hit_cmp,
};
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
static int bytes_cmp(struct alloc_stat *l, struct alloc_stat *r)
{
if (l->bytes_alloc < r->bytes_alloc)
return -1;
else if (l->bytes_alloc > r->bytes_alloc)
return 1;
return 0;
}
static struct sort_dimension bytes_sort_dimension = {
.name = "bytes",
.cmp = bytes_cmp,
};
static int frag_cmp(struct alloc_stat *l, struct alloc_stat *r)
{
double x, y;
x = fragmentation(l->bytes_req, l->bytes_alloc);
y = fragmentation(r->bytes_req, r->bytes_alloc);
if (x < y)
return -1;
else if (x > y)
return 1;
return 0;
}
static struct sort_dimension frag_sort_dimension = {
.name = "frag",
.cmp = frag_cmp,
};
perf kmem: Measure kmalloc/kfree CPU ping-pong call-sites Show statistics for allocations and frees on different cpus: ------------------------------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag ------------------------------------------------------------------------------------------------------ perf_event_alloc.clone.0+0 | 7504/682 | 7128/648 | 11 | 0 | 5.011% alloc_buffer_head+16 | 288/57 | 280/56 | 5 | 0 | 2.778% radix_tree_preload+51 | 296/296 | 288/288 | 1 | 0 | 2.703% tracepoint_add_probe+32e | 157/31 | 154/30 | 5 | 0 | 1.911% do_maps_open+0 | 796/12 | 792/12 | 66 | 0 | 0.503% sock_alloc_send_pskb+16e | 23780/495 | 23744/494 | 48 | 38 | 0.151% anon_vma_prepare+9a | 3744/44 | 3740/44 | 85 | 0 | 0.107% d_alloc+21 | 64948/164 | 64944/164 | 396 | 0 | 0.006% proc_alloc_inode+23 | 262292/676 | 262288/676 | 388 | 0 | 0.002% create_object+28 | 459600/200 | 459600/200 | 2298 | 71 | 0.000% journal_start+67 | 14440/40 | 14440/40 | 361 | 0 | 0.000% get_empty_filp+df | 53504/256 | 53504/256 | 209 | 0 | 0.000% getname+2a | 823296/4096 | 823296/4096 | 201 | 0 | 0.000% seq_read+2b0 | 544768/4096 | 544768/4096 | 133 | 0 | 0.000% seq_open+6d | 17024/128 | 17024/128 | 133 | 0 | 0.000% mmap_region+2e6 | 11704/88 | 11704/88 | 133 | 0 | 0.000% single_open+0 | 1072/16 | 1072/16 | 67 | 0 | 0.000% __alloc_skb+2e | 12544/256 | 12544/256 | 49 | 38 | 0.000% __sigqueue_alloc+4a | 1296/144 | 1296/144 | 9 | 8 | 0.000% tracepoint_add_probe+6f | 80/16 | 80/16 | 5 | 0 | 0.000% ------------------------------------------------------------------------------------------------------ ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B0B6E9F.6020309@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-24 13:26:55 +08:00
static int pingpong_cmp(struct alloc_stat *l, struct alloc_stat *r)
{
if (l->pingpong < r->pingpong)
return -1;
else if (l->pingpong > r->pingpong)
return 1;
return 0;
}
static struct sort_dimension pingpong_sort_dimension = {
.name = "pingpong",
.cmp = pingpong_cmp,
};
static struct sort_dimension *avail_sorts[] = {
&ptr_sort_dimension,
&callsite_sort_dimension,
&hit_sort_dimension,
&bytes_sort_dimension,
&frag_sort_dimension,
perf kmem: Measure kmalloc/kfree CPU ping-pong call-sites Show statistics for allocations and frees on different cpus: ------------------------------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag ------------------------------------------------------------------------------------------------------ perf_event_alloc.clone.0+0 | 7504/682 | 7128/648 | 11 | 0 | 5.011% alloc_buffer_head+16 | 288/57 | 280/56 | 5 | 0 | 2.778% radix_tree_preload+51 | 296/296 | 288/288 | 1 | 0 | 2.703% tracepoint_add_probe+32e | 157/31 | 154/30 | 5 | 0 | 1.911% do_maps_open+0 | 796/12 | 792/12 | 66 | 0 | 0.503% sock_alloc_send_pskb+16e | 23780/495 | 23744/494 | 48 | 38 | 0.151% anon_vma_prepare+9a | 3744/44 | 3740/44 | 85 | 0 | 0.107% d_alloc+21 | 64948/164 | 64944/164 | 396 | 0 | 0.006% proc_alloc_inode+23 | 262292/676 | 262288/676 | 388 | 0 | 0.002% create_object+28 | 459600/200 | 459600/200 | 2298 | 71 | 0.000% journal_start+67 | 14440/40 | 14440/40 | 361 | 0 | 0.000% get_empty_filp+df | 53504/256 | 53504/256 | 209 | 0 | 0.000% getname+2a | 823296/4096 | 823296/4096 | 201 | 0 | 0.000% seq_read+2b0 | 544768/4096 | 544768/4096 | 133 | 0 | 0.000% seq_open+6d | 17024/128 | 17024/128 | 133 | 0 | 0.000% mmap_region+2e6 | 11704/88 | 11704/88 | 133 | 0 | 0.000% single_open+0 | 1072/16 | 1072/16 | 67 | 0 | 0.000% __alloc_skb+2e | 12544/256 | 12544/256 | 49 | 38 | 0.000% __sigqueue_alloc+4a | 1296/144 | 1296/144 | 9 | 8 | 0.000% tracepoint_add_probe+6f | 80/16 | 80/16 | 5 | 0 | 0.000% ------------------------------------------------------------------------------------------------------ ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B0B6E9F.6020309@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-24 13:26:55 +08:00
&pingpong_sort_dimension,
};
#define NUM_AVAIL_SORTS ((int)ARRAY_SIZE(avail_sorts))
static int sort_dimension__add(const char *tok, struct list_head *list)
{
struct sort_dimension *sort;
int i;
for (i = 0; i < NUM_AVAIL_SORTS; i++) {
if (!strcmp(avail_sorts[i]->name, tok)) {
sort = memdup(avail_sorts[i], sizeof(*avail_sorts[i]));
if (!sort) {
pr_err("%s: memdup failed\n", __func__);
return -1;
}
list_add_tail(&sort->list, list);
return 0;
}
}
return -1;
}
static int setup_sorting(struct list_head *sort_list, const char *arg)
{
char *tok;
char *str = strdup(arg);
char *pos = str;
if (!str) {
pr_err("%s: strdup failed\n", __func__);
return -1;
}
while (true) {
tok = strsep(&pos, ",");
if (!tok)
break;
if (sort_dimension__add(tok, sort_list) < 0) {
error("Unknown --sort key: '%s'", tok);
free(str);
return -1;
}
}
free(str);
return 0;
}
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 06:15:03 +08:00
static int parse_sort_opt(const struct option *opt __maybe_unused,
const char *arg, int unset __maybe_unused)
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
{
if (!arg)
return -1;
if (caller_flag > alloc_flag)
return setup_sorting(&caller_sort, arg);
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
else
return setup_sorting(&alloc_sort, arg);
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
return 0;
}
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 06:15:03 +08:00
static int parse_caller_opt(const struct option *opt __maybe_unused,
const char *arg __maybe_unused,
int unset __maybe_unused)
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
{
caller_flag = (alloc_flag + 1);
return 0;
}
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 06:15:03 +08:00
static int parse_alloc_opt(const struct option *opt __maybe_unused,
const char *arg __maybe_unused,
int unset __maybe_unused)
{
alloc_flag = (caller_flag + 1);
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
return 0;
}
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
static int parse_slab_opt(const struct option *opt __maybe_unused,
const char *arg __maybe_unused,
int unset __maybe_unused)
{
kmem_slab = (kmem_page + 1);
return 0;
}
static int parse_page_opt(const struct option *opt __maybe_unused,
const char *arg __maybe_unused,
int unset __maybe_unused)
{
kmem_page = (kmem_slab + 1);
return 0;
}
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 06:15:03 +08:00
static int parse_line_opt(const struct option *opt __maybe_unused,
const char *arg, int unset __maybe_unused)
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
{
int lines;
if (!arg)
return -1;
lines = strtoul(arg, NULL, 10);
if (caller_flag > alloc_flag)
caller_lines = lines;
else
alloc_lines = lines;
return 0;
}
static int __cmd_record(int argc, const char **argv)
{
const char * const record_args[] = {
"record", "-a", "-R", "-c", "1",
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
};
const char * const slab_events[] = {
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
"-e", "kmem:kmalloc",
"-e", "kmem:kmalloc_node",
"-e", "kmem:kfree",
"-e", "kmem:kmem_cache_alloc",
"-e", "kmem:kmem_cache_alloc_node",
"-e", "kmem:kmem_cache_free",
};
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
const char * const page_events[] = {
"-e", "kmem:mm_page_alloc",
"-e", "kmem:mm_page_free",
};
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
unsigned int rec_argc, i, j;
const char **rec_argv;
rec_argc = ARRAY_SIZE(record_args) + argc - 1;
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
if (kmem_slab)
rec_argc += ARRAY_SIZE(slab_events);
if (kmem_page)
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
rec_argc += ARRAY_SIZE(page_events) + 1; /* for -g */
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
rec_argv = calloc(rec_argc + 1, sizeof(char *));
if (rec_argv == NULL)
return -ENOMEM;
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
for (i = 0; i < ARRAY_SIZE(record_args); i++)
rec_argv[i] = strdup(record_args[i]);
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
if (kmem_slab) {
for (j = 0; j < ARRAY_SIZE(slab_events); j++, i++)
rec_argv[i] = strdup(slab_events[j]);
}
if (kmem_page) {
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
rec_argv[i++] = strdup("-g");
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
for (j = 0; j < ARRAY_SIZE(page_events); j++, i++)
rec_argv[i] = strdup(page_events[j]);
}
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
for (j = 1; j < (unsigned int)argc; j++, i++)
rec_argv[i] = argv[j];
return cmd_record(i, rec_argv, NULL);
}
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 06:15:03 +08:00
int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
{
const char * const default_sort_order = "frag,hit,bytes";
perf kmem: Support using -f to override perf.data file ownership Enable perf kmem to use perf.data when it is not owned by current user or root. Example: # perf kmem record ls # chown Yunlong.Song:Yunlong.Song perf.data # ls -al perf.data -rw------- 1 Yunlong.Song Yunlong.Song 5315665 Apr 2 10:54 perf.data # id uid=0(root) gid=0(root) groups=0(root),64(pkcs11) Before this patch: # perf kmem stat File perf.data not owned by current user or root (use -f to override) # perf kmem stat -f Error: unknown switch `f' usage: perf kmem [<options>] {record|stat} -i, --input <file> input file name -v, --verbose be more verbose (show symbol address, etc) --caller show per-callsite statistics --alloc show per-allocation statistics -s, --sort <key[,key2...]> sort by keys: ptr, call_site, bytes, hit, pingpong, frag -l, --line <num> show n lines --raw-ip show raw ip instead of symbol As shown above, the -f option does not work at all. After this patch: # perf kmem stat File perf.data not owned by current user or root (use -f to override) # perf kmem stat -f SUMMARY ======= Total bytes requested: 437599 Total bytes allocated: 615472 Total bytes wasted on internal fragmentation: 177873 Internal fragmentation: 28.900259% Cross CPU allocations: 6/1192 As shown above, the -f option really works now. Signed-off-by: Yunlong Song <yunlong.song@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1427982439-27388-4-git-send-email-yunlong.song@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-02 21:47:12 +08:00
struct perf_data_file file = {
.mode = PERF_DATA_MODE_READ,
};
const struct option kmem_options[] = {
OPT_STRING('i', "input", &input_name, "file", "input file name"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show symbol address, etc)"),
OPT_CALLBACK_NOOPT(0, "caller", NULL, NULL,
"show per-callsite statistics", parse_caller_opt),
OPT_CALLBACK_NOOPT(0, "alloc", NULL, NULL,
"show per-allocation statistics", parse_alloc_opt),
OPT_CALLBACK('s', "sort", NULL, "key[,key2...]",
"sort by keys: ptr, call_site, bytes, hit, pingpong, frag",
parse_sort_opt),
OPT_CALLBACK('l', "line", NULL, "num", "show n lines", parse_line_opt),
OPT_BOOLEAN(0, "raw-ip", &raw_ip, "show raw ip instead of symbol"),
perf kmem: Support using -f to override perf.data file ownership Enable perf kmem to use perf.data when it is not owned by current user or root. Example: # perf kmem record ls # chown Yunlong.Song:Yunlong.Song perf.data # ls -al perf.data -rw------- 1 Yunlong.Song Yunlong.Song 5315665 Apr 2 10:54 perf.data # id uid=0(root) gid=0(root) groups=0(root),64(pkcs11) Before this patch: # perf kmem stat File perf.data not owned by current user or root (use -f to override) # perf kmem stat -f Error: unknown switch `f' usage: perf kmem [<options>] {record|stat} -i, --input <file> input file name -v, --verbose be more verbose (show symbol address, etc) --caller show per-callsite statistics --alloc show per-allocation statistics -s, --sort <key[,key2...]> sort by keys: ptr, call_site, bytes, hit, pingpong, frag -l, --line <num> show n lines --raw-ip show raw ip instead of symbol As shown above, the -f option does not work at all. After this patch: # perf kmem stat File perf.data not owned by current user or root (use -f to override) # perf kmem stat -f SUMMARY ======= Total bytes requested: 437599 Total bytes allocated: 615472 Total bytes wasted on internal fragmentation: 177873 Internal fragmentation: 28.900259% Cross CPU allocations: 6/1192 As shown above, the -f option really works now. Signed-off-by: Yunlong Song <yunlong.song@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1427982439-27388-4-git-send-email-yunlong.song@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-02 21:47:12 +08:00
OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
OPT_CALLBACK_NOOPT(0, "slab", NULL, NULL, "Analyze slab allocator",
parse_slab_opt),
OPT_CALLBACK_NOOPT(0, "page", NULL, NULL, "Analyze page allocator",
parse_page_opt),
OPT_END()
};
const char *const kmem_subcommands[] = { "record", "stat", NULL };
const char *kmem_usage[] = {
NULL,
NULL
};
struct perf_session *session;
int ret = -1;
argc = parse_options_subcommand(argc, argv, kmem_options,
kmem_subcommands, kmem_usage, 0);
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
if (!argc)
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
usage_with_options(kmem_usage, kmem_options);
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
if (kmem_slab == 0 && kmem_page == 0)
kmem_slab = 1; /* for backward compatibility */
if (!strncmp(argv[0], "rec", 3)) {
perf tools: Check recorded kernel version when finding vmlinux Currently vmlinux_path__init() only tries to find vmlinux file from current directory, /boot and some canonical directories with version number of the running kernel. This can be a problem when reporting old data recorded on a kernel version not running currently. We can use --symfs option for this but it's annoying for user to do it always. As we already have the info in the perf.data file, it can be changed to use it for the search automatically. Before: $ perf report ... # Samples: 4K of event 'cpu-clock' # Event count (approx.): 1067250000 # # Overhead Command Shared Object Symbol # ........ .......... ................. .............................. 71.87% swapper [kernel.kallsyms] [k] recover_probed_instruction After: # Overhead Command Shared Object Symbol # ........ .......... ................. .................... 71.87% swapper [kernel.kallsyms] [k] native_safe_halt This requires to change signature of symbol__init() to receive struct perf_session_env *. Reported-by: Minchan Kim <minchan@kernel.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1407825645-24586-14-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-08-12 14:40:45 +08:00
symbol__init(NULL);
return __cmd_record(argc, argv);
}
file.path = input_name;
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
kmem_session = session = perf_session__new(&file, false, &perf_kmem);
if (session == NULL)
return -1;
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
if (kmem_page) {
struct perf_evsel *evsel = perf_evlist__first(session->evlist);
if (evsel == NULL || evsel->tp_format == NULL) {
pr_err("invalid event found.. aborting\n");
return -1;
}
kmem_page_size = pevent_get_page_size(evsel->tp_format->pevent);
perf kmem: Implement stat --page --caller It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1429592107-1807-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-21 12:55:02 +08:00
symbol_conf.use_callchain = true;
perf kmem: Analyze page allocator events also The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events. It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does. The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only. If none of these --slab nor --page is specified, --slab is implied. First run 'perf kmem record' to generate a suitable perf.data file: # perf kmem record --page sleep 5 Then run 'perf kmem stat' to postprocess the perf.data file: # perf kmem stat --page --alloc --line 10 ------------------------------------------------------------------------------- PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags ------------------------------------------------------------------------------- 4045014 | 16 | 1 | 2 | RECLAIM | 00285250 4143980 | 16 | 1 | 2 | RECLAIM | 00285250 3938658 | 16 | 1 | 2 | RECLAIM | 00285250 4045400 | 16 | 1 | 2 | RECLAIM | 00285250 3568708 | 16 | 1 | 2 | RECLAIM | 00285250 3729824 | 16 | 1 | 2 | RECLAIM | 00285250 3657210 | 16 | 1 | 2 | RECLAIM | 00285250 4120750 | 16 | 1 | 2 | RECLAIM | 00285250 3678850 | 16 | 1 | 2 | RECLAIM | 00285250 3693874 | 16 | 1 | 2 | RECLAIM | 00285250 ... | ... | ... | ... | ... | ... ------------------------------------------------------------------------------- SUMMARY (page allocator) ======================== Total allocation requests : 44,260 [ 177,256 KB ] Total free requests : 117 [ 468 KB ] Total alloc+freed requests : 49 [ 196 KB ] Total alloc-only requests : 44,211 [ 177,060 KB ] Total free-only requests : 68 [ 272 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 32 . 44,210 . . 1 . . . . . 2 . 18 . . . 3 . . . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1428298576-9785-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 13:36:10 +08:00
}
perf tools: Check recorded kernel version when finding vmlinux Currently vmlinux_path__init() only tries to find vmlinux file from current directory, /boot and some canonical directories with version number of the running kernel. This can be a problem when reporting old data recorded on a kernel version not running currently. We can use --symfs option for this but it's annoying for user to do it always. As we already have the info in the perf.data file, it can be changed to use it for the search automatically. Before: $ perf report ... # Samples: 4K of event 'cpu-clock' # Event count (approx.): 1067250000 # # Overhead Command Shared Object Symbol # ........ .......... ................. .............................. 71.87% swapper [kernel.kallsyms] [k] recover_probed_instruction After: # Overhead Command Shared Object Symbol # ........ .......... ................. .................... 71.87% swapper [kernel.kallsyms] [k] native_safe_halt This requires to change signature of symbol__init() to receive struct perf_session_env *. Reported-by: Minchan Kim <minchan@kernel.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1407825645-24586-14-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-08-12 14:40:45 +08:00
symbol__init(&session->header.env);
if (!strcmp(argv[0], "stat")) {
setlocale(LC_ALL, "");
if (cpu__setup_cpunode_map())
goto out_delete;
if (list_empty(&caller_sort))
setup_sorting(&caller_sort, default_sort_order);
if (list_empty(&alloc_sort))
setup_sorting(&alloc_sort, default_sort_order);
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
ret = __cmd_kmem(session);
} else
usage_with_options(kmem_usage, kmem_options);
out_delete:
perf_session__delete(session);
return ret;
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
}