OpenCloudOS-Kernel/kernel/trace/trace_branch.c

412 lines
9.0 KiB
C
Raw Normal View History

tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
/*
* unlikely profiler
*
* Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
*/
#include <linux/kallsyms.h>
#include <linux/seq_file.h>
#include <linux/spinlock.h>
#include <linux/irqflags.h>
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
#include <linux/uaccess.h>
#include <linux/module.h>
#include <linux/ftrace.h>
#include <linux/hash.h>
#include <linux/fs.h>
#include <asm/local.h>
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
#include "trace.h"
#include "trace_stat.h"
#include "trace_output.h"
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
#ifdef CONFIG_BRANCH_TRACER
static struct tracer branch_trace;
static int branch_tracing_enabled __read_mostly;
static DEFINE_MUTEX(branch_tracing_mutex);
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
static struct trace_array *branch_tracer;
static void
probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
{
tracing/filters: add run-time field descriptions to TRACE_EVENT_FORMAT events This patch adds run-time field descriptions to all the event formats exported using TRACE_EVENT_FORMAT. It also hooks up all the tracers that use them (i.e. the tracers in the 'ftrace subsystem') so they can also have their output filtered by the event-filtering mechanism. When I was testing this, there were a couple of things that fooled me into thinking the filters weren't working, when actually they were - I'll mention them here so others don't make the same mistakes (and file bug reports. ;-) One is that some of the tracers trace multiple events e.g. the sched_switch tracer uses the context_switch and wakeup events, and if you don't set filters on all of the traced events, the unfiltered output from the events without filters on them can make it look like the filtering as a whole isn't working properly, when actually it is doing what it was asked to do - it just wasn't asked to do the right thing. The other is that for the really high-volume tracers e.g. the function tracer, the volume of filtered events can be so high that it pushes the unfiltered events out of the ring buffer before they can be read so e.g. cat'ing the trace file repeatedly shows either no output, or once in awhile some output but that isn't there the next time you read the trace, which isn't what you normally expect when reading the trace file. If you read from the trace_pipe file though, you can catch them before they disappear. Changes from v1: As suggested by Frederic Weisbecker: - get rid of externs in functions - added unlikely() to filter_check_discard() Signed-off-by: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-31 13:48:49 +08:00
struct ftrace_event_call *call = &event_branch;
struct trace_array *tr = branch_tracer;
struct trace_array_cpu *data;
struct ring_buffer_event *event;
struct trace_branch *entry;
struct ring_buffer *buffer;
unsigned long flags;
int cpu, pc;
const char *p;
/*
* I would love to save just the ftrace_likely_data pointer, but
* this code can also be used by modules. Ugly things can happen
* if the module is unloaded, and then we go and read the
* pointer. This is slower, but much safer.
*/
if (unlikely(!tr))
return;
local_irq_save(flags);
cpu = raw_smp_processor_id();
data = per_cpu_ptr(tr->trace_buffer.data, cpu);
if (atomic_inc_return(&data->disabled) != 1)
goto out;
pc = preempt_count();
buffer = tr->trace_buffer.buffer;
event = trace_buffer_lock_reserve(buffer, TRACE_BRANCH,
sizeof(*entry), flags, pc);
if (!event)
goto out;
entry = ring_buffer_event_data(event);
/* Strip off the path, only save the file */
p = f->file + strlen(f->file);
while (p >= f->file && *p != '/')
p--;
p++;
strncpy(entry->func, f->func, TRACE_FUNC_SIZE);
strncpy(entry->file, p, TRACE_FILE_SIZE);
entry->func[TRACE_FUNC_SIZE] = 0;
entry->file[TRACE_FILE_SIZE] = 0;
entry->line = f->line;
entry->correct = val == expect;
tracing: Update event filters for multibuffer The trace event filters are still tied to event calls rather than event files, which means you don't get what you'd expect when using filters in the multibuffer case: Before: # echo 'bytes_alloc > 8192' > /sys/kernel/debug/tracing/events/kmem/kmalloc/filter # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter bytes_alloc > 8192 # mkdir /sys/kernel/debug/tracing/instances/test1 # echo 'bytes_alloc > 2048' > /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter bytes_alloc > 2048 # cat /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter bytes_alloc > 2048 Setting the filter in tracing/instances/test1/events shouldn't affect the same event in tracing/events as it does above. After: # echo 'bytes_alloc > 8192' > /sys/kernel/debug/tracing/events/kmem/kmalloc/filter # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter bytes_alloc > 8192 # mkdir /sys/kernel/debug/tracing/instances/test1 # echo 'bytes_alloc > 2048' > /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter bytes_alloc > 8192 # cat /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter bytes_alloc > 2048 We'd like to just move the filter directly from ftrace_event_call to ftrace_event_file, but there are a couple cases that don't yet have multibuffer support and therefore have to continue using the current event_call-based filters. For those cases, a new USE_CALL_FILTER bit is added to the event_call flags, whose main purpose is to keep the old behavior for those cases until they can be updated with multibuffer support; at that point, the USE_CALL_FILTER flag (and the new associated call_filter_check_discard() function) can go away. The multibuffer support also made filter_current_check_discard() redundant, so this change removes that function as well and replaces it with filter_check_discard() (or call_filter_check_discard() as appropriate). Link: http://lkml.kernel.org/r/f16e9ce4270c62f46b2e966119225e1c3cca7e60.1382620672.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-10-24 21:34:17 +08:00
if (!call_filter_check_discard(call, entry, buffer, event))
tracing: Cache comms only after an event occurred Whenever an event is registered, the comm of tasks are saved at every task switch instead of saving them at every event. But if an event isn't executed much, the comm cache will be filled up by tasks that did not record the event and you lose out on the comms that did. Here's an example, if you enable the following events: echo 1 > /debug/tracing/events/kvm/kvm_cr/enable echo 1 > /debug/tracing/events/net/net_dev_xmit/enable Note, there's no kvm running on this machine so the first event will never be triggered, but because it is enabled, the storing of comms will continue. If we now disable the network event: echo 0 > /debug/tracing/events/net/net_dev_xmit/enable and look at the trace: cat /debug/tracing/trace sshd-2672 [001] ..s2 375.731616: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s1 375.731617: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s2 375.859356: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s1 375.859357: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s2 375.947351: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s1 375.947352: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s2 376.035383: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s1 376.035383: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s2 377.563806: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=226 rc=0 sshd-2672 [001] ..s1 377.563807: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=226 rc=0 sshd-2672 [001] ..s2 377.563834: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6be0 len=114 rc=0 sshd-2672 [001] ..s1 377.563842: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6be0 len=114 rc=0 We see that process 2672 which triggered the events has the comm "sshd". But if we run hackbench for a bit and look again: cat /debug/tracing/trace <...>-2672 [001] ..s2 375.731616: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s1 375.731617: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s2 375.859356: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s1 375.859357: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s2 375.947351: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s1 375.947352: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s2 376.035383: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s1 376.035383: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s2 377.563806: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=226 rc=0 <...>-2672 [001] ..s1 377.563807: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=226 rc=0 <...>-2672 [001] ..s2 377.563834: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6be0 len=114 rc=0 <...>-2672 [001] ..s1 377.563842: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6be0 len=114 rc=0 The stored "sshd" comm has been flushed out and we get a useless "<...>". But by only storing comms after a trace event occurred, we can run hackbench all day and still get the same output. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-10-12 00:14:25 +08:00
__buffer_unlock_commit(buffer, event);
out:
atomic_dec(&data->disabled);
local_irq_restore(flags);
}
static inline
void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect)
{
if (!branch_tracing_enabled)
return;
probe_likely_condition(f, val, expect);
}
int enable_branch_tracing(struct trace_array *tr)
{
mutex_lock(&branch_tracing_mutex);
branch_tracer = tr;
/*
* Must be seen before enabling. The reader is a condition
* where we do not need a matching rmb()
*/
smp_wmb();
branch_tracing_enabled++;
mutex_unlock(&branch_tracing_mutex);
return 0;
}
void disable_branch_tracing(void)
{
mutex_lock(&branch_tracing_mutex);
if (!branch_tracing_enabled)
goto out_unlock;
branch_tracing_enabled--;
out_unlock:
mutex_unlock(&branch_tracing_mutex);
}
static void start_branch_trace(struct trace_array *tr)
{
enable_branch_tracing(tr);
}
static void stop_branch_trace(struct trace_array *tr)
{
disable_branch_tracing();
}
static int branch_trace_init(struct trace_array *tr)
{
start_branch_trace(tr);
return 0;
}
static void branch_trace_reset(struct trace_array *tr)
{
stop_branch_trace(tr);
}
static enum print_line_t trace_branch_print(struct trace_iterator *iter,
int flags, struct trace_event *event)
{
struct trace_branch *field;
trace_assign_type(field, iter->ent);
trace_seq_printf(&iter->seq, "[%s] %s:%s:%d\n",
field->correct ? " ok " : " MISS ",
field->func,
field->file,
field->line);
return trace_handle_return(&iter->seq);
}
static void branch_print_header(struct seq_file *s)
{
seq_puts(s, "# TASK-PID CPU# TIMESTAMP CORRECT"
" FUNC:FILE:LINE\n"
"# | | | | | "
" |\n");
}
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
static struct trace_event_functions trace_branch_funcs = {
.trace = trace_branch_print,
};
static struct trace_event trace_branch_event = {
.type = TRACE_BRANCH,
.funcs = &trace_branch_funcs,
};
static struct tracer branch_trace __read_mostly =
{
.name = "branch",
.init = branch_trace_init,
.reset = branch_trace_reset,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_branch,
#endif /* CONFIG_FTRACE_SELFTEST */
.print_header = branch_print_header,
};
__init static int init_branch_tracer(void)
{
int ret;
ret = register_ftrace_event(&trace_branch_event);
if (!ret) {
printk(KERN_WARNING "Warning: could not register "
"branch events\n");
return 1;
}
return register_tracer(&branch_trace);
}
core_initcall(init_branch_tracer);
#else
static inline
void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect)
{
}
#endif /* CONFIG_BRANCH_TRACER */
void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect)
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
{
/*
* I would love to have a trace point here instead, but the
* trace point code is so inundated with unlikely and likely
* conditions that the recursive nightmare that exists is too
* much to try to get working. At least for now.
*/
trace_likely_condition(f, val, expect);
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
/* FIXME: Make this atomic! */
if (val == expect)
f->correct++;
else
f->incorrect++;
}
EXPORT_SYMBOL(ftrace_likely_update);
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
extern unsigned long __start_annotated_branch_profile[];
extern unsigned long __stop_annotated_branch_profile[];
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
static int annotated_branch_stat_headers(struct seq_file *m)
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
{
seq_puts(m, " correct incorrect % "
" Function "
" File Line\n"
" ------- --------- - "
" -------- "
" ---- ----\n");
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
return 0;
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
}
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
static inline long get_incorrect_percent(struct ftrace_branch_data *p)
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
{
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
long percent;
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
if (p->correct) {
percent = p->incorrect * 100;
percent /= p->correct + p->incorrect;
} else
percent = p->incorrect ? 100 : -1;
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
return percent;
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
}
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
static int branch_stat_show(struct seq_file *m, void *v)
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
{
struct ftrace_branch_data *p = v;
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
const char *f;
long percent;
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
/* Only print the file, not the path */
f = p->file + strlen(p->file);
while (f >= p->file && *f != '/')
f--;
f++;
/*
* The miss is overlayed on correct, and hit on incorrect.
*/
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
percent = get_incorrect_percent(p);
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
seq_printf(m, "%8lu %8lu ", p->correct, p->incorrect);
if (percent < 0)
seq_puts(m, " X ");
else
seq_printf(m, "%3ld ", percent);
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
seq_printf(m, "%-30.30s %-20.20s %d\n", p->func, f, p->line);
return 0;
}
static void *annotated_branch_stat_start(struct tracer_stat *trace)
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
{
return __start_annotated_branch_profile;
}
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
static void *
annotated_branch_stat_next(void *v, int idx)
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
{
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
struct ftrace_branch_data *p = v;
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
++p;
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
if ((void *)p >= (void *)__stop_annotated_branch_profile)
return NULL;
return p;
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
}
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
static int annotated_branch_stat_cmp(void *p1, void *p2)
{
struct ftrace_branch_data *a = p1;
struct ftrace_branch_data *b = p2;
long percent_a, percent_b;
percent_a = get_incorrect_percent(a);
percent_b = get_incorrect_percent(b);
if (percent_a < percent_b)
return -1;
if (percent_a > percent_b)
return 1;
tracing: Add correct/incorrect to sort keys for branch annotation output The branch annotation is a bit difficult to see the worst offenders because it only sorts by percentage: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 163 100 qdisc_restart sch_generic.c 179 0 163 100 pfifo_fast_dequeue sch_generic.c 447 0 4 100 pskb_trim_rcsum skbuff.h 1689 0 4 100 llc_rcv llc_input.c 170 0 18 100 psmouse_interrupt psmouse-base.c 304 0 3 100 atkbd_interrupt atkbd.c 389 0 5 100 usb_alloc_dev usb.c 437 0 11 100 vsscanf vsprintf.c 1897 0 2 100 IS_ERR err.h 34 0 23 100 __rmqueue_fallback page_alloc.c 865 0 4 100 probe_wakeup_sched_switch trace_sched_wakeup.c 142 0 3 100 move_masked_irq migration.c 11 Adding the incorrect and correct values as sort keys makes this file a bit more informative: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 366541 100 audit_syscall_entry auditsc.c 1637 0 366538 100 audit_syscall_exit auditsc.c 1685 0 115839 100 sched_info_switch sched_stats.h 269 0 74567 100 sched_info_queued sched_stats.h 222 0 66578 100 sched_info_dequeued sched_stats.h 177 0 15113 100 trace_workqueue_insertion workqueue.h 38 0 15107 100 trace_workqueue_execution workqueue.h 45 0 3622 100 syscall_trace_leave ptrace.c 1772 0 2750 100 sched_move_task sched.c 10100 0 2750 100 sched_move_task sched.c 10110 0 1815 100 pre_schedule_rt sched_rt.c 1462 0 837 100 audit_alloc auditsc.c 879 0 814 100 tcp_mss_split_point tcp_output.c 1302 Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-01-28 00:25:54 +08:00
if (a->incorrect < b->incorrect)
return -1;
if (a->incorrect > b->incorrect)
return 1;
/*
* Since the above shows worse (incorrect) cases
* first, we continue that by showing best (correct)
* cases last.
*/
if (a->correct > b->correct)
return -1;
if (a->correct < b->correct)
return 1;
return 0;
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
}
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
static struct tracer_stat annotated_branch_stats = {
.name = "branch_annotated",
.stat_start = annotated_branch_stat_start,
.stat_next = annotated_branch_stat_next,
.stat_cmp = annotated_branch_stat_cmp,
.stat_headers = annotated_branch_stat_headers,
.stat_show = branch_stat_show
};
__init static int init_annotated_branch_stats(void)
{
int ret;
ret = register_stat_tracer(&annotated_branch_stats);
if (!ret) {
printk(KERN_WARNING "Warning: could not register "
"annotated branches stats\n");
return 1;
}
return 0;
}
fs_initcall(init_annotated_branch_stats);
#ifdef CONFIG_PROFILE_ALL_BRANCHES
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
extern unsigned long __start_branch_profile[];
extern unsigned long __stop_branch_profile[];
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
static int all_branch_stat_headers(struct seq_file *m)
{
seq_puts(m, " miss hit % "
" Function "
" File Line\n"
" ------- --------- - "
" -------- "
" ---- ----\n");
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
return 0;
}
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
static void *all_branch_stat_start(struct tracer_stat *trace)
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
{
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
return __start_branch_profile;
}
static void *
all_branch_stat_next(void *v, int idx)
{
struct ftrace_branch_data *p = v;
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
++p;
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
if ((void *)p >= (void *)__stop_branch_profile)
return NULL;
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 13:14:39 +08:00
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
return p;
}
static struct tracer_stat all_branch_stats = {
.name = "branch_all",
.stat_start = all_branch_stat_start,
.stat_next = all_branch_stat_next,
.stat_headers = all_branch_stat_headers,
.stat_show = branch_stat_show
};
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
__init static int all_annotated_branch_stats(void)
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
{
int ret;
ret = register_stat_tracer(&all_branch_stats);
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
if (!ret) {
printk(KERN_WARNING "Warning: could not register "
"all branches stats\n");
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
return 1;
}
return 0;
tracing/branch-tracer: adapt to the stat tracing API Impact: refactor the branch tracer This patch adapts the branch tracer to the tracing API. This is a proof of concept because the branch tracer implements two "stat tracing" that were split in two files. So I added an option to the branch tracer: stat_all_branch. If it is set, then trace_stat will output all of the branches entries stats. Otherwise, it will print the annotated branches. Its is a kind of quick trick, waiting for a better solution. By default, the annotated branches stat are sorted by incorrect branch prediction percentage. Ie: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 1 100 native_smp_prepare_cpus smpboot.c 1228 0 1 100 hpet_rtc_timer_reinit hpet.c 1057 0 18032 100 sched_info_queued sched_stats.h 223 0 684 100 yield_task_fair sched_fair.c 984 0 282 100 pre_schedule_rt sched_rt.c 1263 0 13414 100 sched_info_dequeued sched_stats.h 178 0 21724 100 sched_info_switch sched_stats.h 270 0 1 100 get_signal_to_deliver signal.c 1820 0 8 100 __cancel_work_timer workqueue.c 560 0 212 100 verify_export_symbols module.c 1509 0 17 100 __rmqueue_fallback page_alloc.c 793 0 43 100 clear_page_mlock internal.h 129 0 124 100 try_to_unmap_anon rmap.c 1021 0 53 100 try_to_unmap_anon rmap.c 1013 0 6 100 vma_address rmap.c 232 0 3301 100 try_to_unmap_file rmap.c 1082 0 466 100 try_to_unmap_file rmap.c 1077 0 1 100 mem_cgroup_create memcontrol.c 1090 0 3 100 inotify_find_update_watch inotify.c 726 2 30163 99 perf_counter_task_sched_out perf_counter.c 385 1 2935 99 percpu_free allocpercpu.c 138 1544 297672 99 dentry_lru_del_init dcache.c 153 8 1074 99 input_pass_event input.c 86 1390 76781 98 mapping_unevictable pagemap.h 50 280 6665 95 pick_next_task_rt sched_rt.c 889 750 4826 86 next_pidmap pid.c 194 2 8 80 blocking_notifier_chain_regist notifier.c 220 36 130 78 ioremap_pte_range ioremap.c 22 1093 3247 74 IS_ERR err.h 34 1023 2908 73 sched_slice sched_fair.c 445 22 60 73 disk_put_part genhd.h 206 [...] It enables a developer to quickly address the source of incorrect branch predictions. Note that this sorting would be better with a second sort on the number of incorrect predictions. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-28 06:25:38 +08:00
}
fs_initcall(all_annotated_branch_stats);
#endif /* CONFIG_PROFILE_ALL_BRANCHES */