linux-sg2042/tools/perf/builtin.h

44 lines
2.2 KiB
C
Raw Normal View History

#ifndef BUILTIN_H
#define BUILTIN_H
#include "util/util.h"
#include "util/strbuf.h"
extern const char perf_usage_string[];
extern const char perf_more_info_string[];
extern void list_common_cmds_help(void);
extern const char *help_unknown_cmd(const char *cmd);
extern void prune_packed_objects(int);
extern int read_line_with_nul(char *buf, int size, FILE *file);
extern int check_pager_config(const char *cmd);
extern int cmd_annotate(int argc, const char **argv, const char *prefix);
extern int cmd_bench(int argc, const char **argv, const char *prefix);
extern int cmd_buildid_cache(int argc, const char **argv, const char *prefix);
extern int cmd_buildid_list(int argc, const char **argv, const char *prefix);
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
extern int cmd_diff(int argc, const char **argv, const char *prefix);
extern int cmd_evlist(int argc, const char **argv, const char *prefix);
extern int cmd_help(int argc, const char **argv, const char *prefix);
extern int cmd_sched(int argc, const char **argv, const char *prefix);
extern int cmd_list(int argc, const char **argv, const char *prefix);
extern int cmd_record(int argc, const char **argv, const char *prefix);
extern int cmd_report(int argc, const char **argv, const char *prefix);
extern int cmd_stat(int argc, const char **argv, const char *prefix);
extern int cmd_timechart(int argc, const char **argv, const char *prefix);
extern int cmd_top(int argc, const char **argv, const char *prefix);
extern int cmd_script(int argc, const char **argv, const char *prefix);
extern int cmd_version(int argc, const char **argv, const char *prefix);
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
extern int cmd_probe(int argc, const char **argv, const char *prefix);
perf: Add 'perf kmem' tool This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-20 15:53:25 +08:00
extern int cmd_kmem(int argc, const char **argv, const char *prefix);
extern int cmd_lock(int argc, const char **argv, const char *prefix);
extern int cmd_kvm(int argc, const char **argv, const char *prefix);
perf test: Initial regression testing command First an example with the first internal test: [acme@doppio linux-2.6-tip]$ perf test 1: vmlinux symtab matches kallsyms: Ok So it run just one test, that is "vmlinux symtab matches kallsyms", and it was successful. If we run it in verbose mode, we'll see details about errors and extra warnings for non-fatal problems: [acme@doppio linux-2.6-tip]$ perf test -v 1: vmlinux symtab matches kallsyms: --- start --- Looking at the vmlinux_path (5 entries long) No build_id in vmlinux, ignoring it No build_id in /boot/vmlinux, ignoring it No build_id in /boot/vmlinux-2.6.34-rc4-tip+, ignoring it Using /lib/modules/2.6.34-rc4-tip+/build/vmlinux for symbols Maps only in vmlinux: ffffffff81cb81b1-ffffffff81e1149b 0 [kernel].init.text ffffffff81e1149c-ffffffff9fffffff 0 [kernel].exit.text ffffffffff600000-ffffffffff6000ff 0 [kernel].vsyscall_0 ffffffffff600100-ffffffffff6003ff 0 [kernel].vsyscall_fn ffffffffff600400-ffffffffff6007ff 0 [kernel].vsyscall_1 ffffffffff600800-ffffffffffffffff 0 [kernel].vsyscall_2 Maps in vmlinux with a different name in kallsyms: ffffffffff600000-ffffffffff6000ff 0 [kernel].vsyscall_0 in kallsyms as [kernel].0 ffffffffff600100-ffffffffff6003ff 0 [kernel].vsyscall_fn in kallsyms as: *ffffffffff600100-ffffffffff60012f 0 [kernel].2 ffffffffff600400-ffffffffff6007ff 0 [kernel].vsyscall_1 in kallsyms as [kernel].6 ffffffffff600800-ffffffffffffffff 0 [kernel].vsyscall_2 in kallsyms as [kernel].8 Maps only in kallsyms: ffffffffff600130-ffffffffff6003ff 0 [kernel].4 ---- end ---- vmlinux symtab matches kallsyms: Ok [acme@doppio linux-2.6-tip]$ In the above case we only know the name of the non contiguous kernel ranges in the address space when reading the symbol information from the ELF symtab in vmlinux. The /proc/kallsyms file lack this, we only notice they are separate because there are modules after the kernel and after that more kernel functions, so we need to have a module rbtree backed by the module .ko path to get symtabs in the vmlinux case. The tool uses it to match by address to emit appropriate warning, but don't considers this fatal. The .init.text and .exit.text ines, of course, aren't in kallsyms, so I left these cases just as extra info in verbose mode. The end of the sections also aren't in kallsyms, so we the symbols layer does another pass and sets the end addresses as the next map start minus one, which sometimes pads, causing harmless mismatches. But at least the symbols match, tested it by copying /proc/kallsyms to /tmp/kallsyms and doing changes to see if they were detected. This first test also should serve as a first stab at documenting the symbol library by providing a self contained example that exercises it together with comments about what is being done. More tests to check if actions done on a monitored app, like doing mmaps, etc, makes the kernel generate the expected events should be added next. Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-04-30 05:58:32 +08:00
extern int cmd_test(int argc, const char **argv, const char *prefix);
perf trace: New tool Initially should look loosely like the venerable 'strace' tool, but using the infrastructure in the perf tools to allow tracing extra targets: [acme@sandy linux]$ perf trace --hell Error: unknown option `hell' usage: perf trace <PID> -p, --pid <pid> trace events on existing process id --tid <tid> trace events on existing thread id --all-cpus system-wide collection from all CPUs --cpu <cpu> list of cpus to monitor --no-inherit child tasks do not inherit counters --mmap-pages <n> number of mmap data pages --uid <user> user to profile [acme@sandy linux]$ Those should have the same semantics as when using with 'perf record'. It gets stuck sometimes, but hey, it works sometimes too! In time it should support perf.data based workloads, i.e. it should have a: -o filename Command line option that will produce a perf.data file that can then be used with 'perf trace' or any of the other perf tools (script, report, etc). It will also eventually have the set of functionalities described in the previous 'trace' prototype by Thomas Gleixner: "Announcing a new utility: 'trace'" http://lwn.net/Articles/415728/ Also planned is to have some of the features suggested in the comments of that LWN article. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/n/tip-v9x3q9rv4caxtox7wtjpchq5@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-27 07:05:56 +08:00
extern int cmd_trace(int argc, const char **argv, const char *prefix);
perf: add perf-inject builtin Currently, perf 'live mode' writes build-ids at the end of the session, which isn't actually useful for processing live mode events. What would be better would be to have the build-ids sent before any of the samples that reference them, which can be done by processing the event stream and retrieving the build-ids on the first hit. Doing that in perf-record itself, however, is off-limits. This patch introduces perf-inject, which does the same job while leaving perf-record untouched. Normal mode perf still records the build-ids at the end of the session as it should, but for live mode, perf-inject can be injected in between the record and report steps e.g.: perf record -o - ./hackbench 10 | perf inject -v -b | perf report -v -i - perf-inject reads a perf-record event stream and repipes it to stdout. At any point the processing code can inject other events into the event stream - in this case build-ids (-b option) are read and injected as needed into the event stream. Build-ids are just the first user of perf-inject - potentially anything that needs userspace processing to augment the trace stream with additional information could make use of this facility. Cc: Ingo Molnar <mingo@elte.hu> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frédéric Weisbecker <fweisbec@gmail.com> LKML-Reference: <1272696080-16435-3-git-send-email-tzanussi@gmail.com> Signed-off-by: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-05-01 14:41:20 +08:00
extern int cmd_inject(int argc, const char **argv, const char *prefix);
extern int cmd_mem(int argc, const char **argv, const char *prefix);
extern int cmd_data(int argc, const char **argv, const char *prefix);
extern int find_scripts(char **scripts_array, char **scripts_path_array);
#endif