linux/tools/perf/builtin-report.c

978 lines
27 KiB
C
Raw Normal View History

/*
* builtin-report.c
*
* Builtin report command: Analyze the perf.data input file,
* look up and read DSOs and symbol information and display
* a histogram of results, along various sorting keys.
*/
#include "builtin.h"
#include "util/util.h"
#include "util/cache.h"
#include "util/annotate.h"
#include "util/color.h"
#include <linux/list.h>
#include <linux/rbtree.h>
#include "util/symbol.h"
#include "util/callchain.h"
#include "util/strlist.h"
#include "util/values.h"
#include "perf.h"
#include "util/debug.h"
#include "util/evlist.h"
#include "util/evsel.h"
#include "util/header.h"
#include "util/session.h"
#include "util/tool.h"
#include "util/parse-options.h"
#include "util/parse-events.h"
#include "util/thread.h"
#include "util/sort.h"
#include "util/hist.h"
#include "util/data.h"
#include "arch/common.h"
#include <dlfcn.h>
#include <linux/bitmap.h>
struct report {
struct perf_tool tool;
struct perf_session *session;
bool force, use_tui, use_gtk, use_stdio;
bool hide_unresolved;
bool dont_use_callchains;
bool show_full_info;
bool show_threads;
bool inverted_callchain;
bool mem_mode;
bool header;
bool header_only;
perf report: Add --max-stack option to limit callchain stack scan When callgraph data was included in the perf data file, it may take a long time to scan all those data and merge them together especially if the stored callchains are long and the perf data file itself is large, like a Gbyte or so. The callchain stack is currently limited to PERF_MAX_STACK_DEPTH (127). This is a large value. Usually the callgraph data that developers are most interested in are the first few levels, the rests are usually not looked at. This patch adds a new --max-stack option to perf-report to limit the depth of callchain stack data to look at to reduce the time it takes for perf-report to finish its processing. It trades the presence of trailing stack information with faster speed. The following table shows the elapsed time of doing perf-report on a perf.data file of size 985,531,828 bytes. --max_stack Elapsed Time Output data size ----------- ------------ ---------------- not set 88.0s 124,422,651 64 87.5s 116,303,213 32 87.2s 112,023,804 16 86.6s 94,326,380 8 59.9s 33,697,248 4 40.7s 10,116,637 -g none 27.1s 2,555,810 Signed-off-by: Waiman Long <Waiman.Long@hp.com> Acked-by: David Ahern <dsahern@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Aswin Chandramouleeswaran <aswin@hp.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Scott J Norton <scott.norton@hp.com> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1382107129-2010-4-git-send-email-Waiman.Long@hp.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-18 14:38:48 +00:00
int max_stack;
struct perf_read_values show_threads_values;
const char *pretty_printing_style;
const char *cpu_list;
const char *symbol_filter_str;
float min_percent;
DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
};
static int report__config(const char *var, const char *value, void *cb)
{
if (!strcmp(var, "report.group")) {
symbol_conf.event_group = perf_config_bool(var, value);
return 0;
}
if (!strcmp(var, "report.percent-limit")) {
struct report *rep = cb;
rep->min_percent = strtof(value, NULL);
return 0;
}
return perf_default_config(var, value, cb);
}
static int report__resolve_callchain(struct report *rep, struct symbol **parent,
struct perf_evsel *evsel, struct addr_location *al,
struct perf_sample *sample)
{
if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
return machine__resolve_callchain(al->machine, evsel, al->thread, sample,
parent, al, rep->max_stack);
}
return 0;
}
static int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample)
{
if (!symbol_conf.use_callchain)
return 0;
return callchain_append(he->callchain, &callchain_cursor, sample->period);
}
static int report__add_mem_hist_entry(struct perf_tool *tool, struct addr_location *al,
struct perf_sample *sample, struct perf_evsel *evsel,
union perf_event *event)
{
struct report *rep = container_of(tool, struct report, tool);
struct symbol *parent = NULL;
u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
struct hist_entry *he;
struct mem_info *mi, *mx;
uint64_t cost;
int err = report__resolve_callchain(rep, &parent, evsel, al, sample);
if (err)
return err;
mi = machine__resolve_mem(al->machine, al->thread, sample, cpumode);
if (!mi)
return -ENOMEM;
if (rep->hide_unresolved && !al->sym)
return 0;
cost = sample->weight;
if (!cost)
cost = 1;
/*
* must pass period=weight in order to get the correct
* sorting from hists__collapse_resort() which is solely
* based on periods. We want sorting be done on nr_events * weight
* and this is indirectly achieved by passing period=weight here
* and the he_stat__add_period() function.
*/
he = __hists__add_entry(&evsel->hists, al, parent, NULL, mi,
cost, cost, 0);
if (!he)
return -ENOMEM;
err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
if (err)
goto out;
mx = he->mem_info;
err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx);
if (err)
goto out;
evsel->hists.stats.total_period += cost;
hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
err = hist_entry__append_callchain(he, sample);
out:
return err;
}
static int report__add_branch_hist_entry(struct perf_tool *tool, struct addr_location *al,
struct perf_sample *sample, struct perf_evsel *evsel)
perf report: Add support for taken branch sampling This patch adds support for taken branch sampling, i.e, the PERF_SAMPLE_BRANCH_STACK feature to perf report. In other words, to display histograms based on taken branches rather than executed instructions addresses. The new option is called -b and it takes no argument. To generate meaningful output, the perf.data must have been obtained using perf record -b xxx ... where xxx is a branch filter option. The output shows symbols, modules, sorted by 'who branches where' the most often. The percentages reported in the first column refer to the total number of branches captured and not the usual number of samples. Here is a quick example. Here branchy is simple test program which looks as follows: void f2(void) {} void f3(void) {} void f1(unsigned long n) { if (n & 1UL) f2(); else f3(); } int main(void) { unsigned long i; for (i=0; i < N; i++) f1(i); return 0; } Here is the output captured on Nehalem, if we are only interested in user level function calls. $ perf record -b any_call,u -e cycles:u branchy $ perf report -b --sort=symbol 52.34% [.] main [.] f1 24.04% [.] f1 [.] f3 23.60% [.] f1 [.] f2 0.01% [k] _IO_new_file_xsputn [k] _IO_file_overflow 0.01% [k] _IO_vfprintf_internal [k] _IO_new_file_xsputn 0.01% [k] _IO_vfprintf_internal [k] strchrnul 0.01% [k] __printf [k] _IO_vfprintf_internal 0.01% [k] main [k] __printf About half (52%) of the call branches captured are from main() -> f1(). The second half (24%+23%) is split in two equal shares between f1() -> f2(), f1() ->f3(). The output is as expected given the code. It should be noted, that using -b in perf record does not eliminate information in the perf.data file. Consequently, a typical profile can also be obtained by perf report by simply not using its -b option. It is possible to sort on branch related columns: - dso_from, symbol_from - dso_to, symbol_to - mispredict Signed-off-by: Roberto Agostino Vitillo <ravitillo@lbl.gov> Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-14-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-09 22:21:03 +00:00
{
struct report *rep = container_of(tool, struct report, tool);
perf report: Add support for taken branch sampling This patch adds support for taken branch sampling, i.e, the PERF_SAMPLE_BRANCH_STACK feature to perf report. In other words, to display histograms based on taken branches rather than executed instructions addresses. The new option is called -b and it takes no argument. To generate meaningful output, the perf.data must have been obtained using perf record -b xxx ... where xxx is a branch filter option. The output shows symbols, modules, sorted by 'who branches where' the most often. The percentages reported in the first column refer to the total number of branches captured and not the usual number of samples. Here is a quick example. Here branchy is simple test program which looks as follows: void f2(void) {} void f3(void) {} void f1(unsigned long n) { if (n & 1UL) f2(); else f3(); } int main(void) { unsigned long i; for (i=0; i < N; i++) f1(i); return 0; } Here is the output captured on Nehalem, if we are only interested in user level function calls. $ perf record -b any_call,u -e cycles:u branchy $ perf report -b --sort=symbol 52.34% [.] main [.] f1 24.04% [.] f1 [.] f3 23.60% [.] f1 [.] f2 0.01% [k] _IO_new_file_xsputn [k] _IO_file_overflow 0.01% [k] _IO_vfprintf_internal [k] _IO_new_file_xsputn 0.01% [k] _IO_vfprintf_internal [k] strchrnul 0.01% [k] __printf [k] _IO_vfprintf_internal 0.01% [k] main [k] __printf About half (52%) of the call branches captured are from main() -> f1(). The second half (24%+23%) is split in two equal shares between f1() -> f2(), f1() ->f3(). The output is as expected given the code. It should be noted, that using -b in perf record does not eliminate information in the perf.data file. Consequently, a typical profile can also be obtained by perf report by simply not using its -b option. It is possible to sort on branch related columns: - dso_from, symbol_from - dso_to, symbol_to - mispredict Signed-off-by: Roberto Agostino Vitillo <ravitillo@lbl.gov> Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-14-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-09 22:21:03 +00:00
struct symbol *parent = NULL;
unsigned i;
struct hist_entry *he;
struct branch_info *bi, *bx;
int err = report__resolve_callchain(rep, &parent, evsel, al, sample);
perf report: Add support for taken branch sampling This patch adds support for taken branch sampling, i.e, the PERF_SAMPLE_BRANCH_STACK feature to perf report. In other words, to display histograms based on taken branches rather than executed instructions addresses. The new option is called -b and it takes no argument. To generate meaningful output, the perf.data must have been obtained using perf record -b xxx ... where xxx is a branch filter option. The output shows symbols, modules, sorted by 'who branches where' the most often. The percentages reported in the first column refer to the total number of branches captured and not the usual number of samples. Here is a quick example. Here branchy is simple test program which looks as follows: void f2(void) {} void f3(void) {} void f1(unsigned long n) { if (n & 1UL) f2(); else f3(); } int main(void) { unsigned long i; for (i=0; i < N; i++) f1(i); return 0; } Here is the output captured on Nehalem, if we are only interested in user level function calls. $ perf record -b any_call,u -e cycles:u branchy $ perf report -b --sort=symbol 52.34% [.] main [.] f1 24.04% [.] f1 [.] f3 23.60% [.] f1 [.] f2 0.01% [k] _IO_new_file_xsputn [k] _IO_file_overflow 0.01% [k] _IO_vfprintf_internal [k] _IO_new_file_xsputn 0.01% [k] _IO_vfprintf_internal [k] strchrnul 0.01% [k] __printf [k] _IO_vfprintf_internal 0.01% [k] main [k] __printf About half (52%) of the call branches captured are from main() -> f1(). The second half (24%+23%) is split in two equal shares between f1() -> f2(), f1() ->f3(). The output is as expected given the code. It should be noted, that using -b in perf record does not eliminate information in the perf.data file. Consequently, a typical profile can also be obtained by perf report by simply not using its -b option. It is possible to sort on branch related columns: - dso_from, symbol_from - dso_to, symbol_to - mispredict Signed-off-by: Roberto Agostino Vitillo <ravitillo@lbl.gov> Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-14-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-09 22:21:03 +00:00
if (err)
return err;
perf report: Add support for taken branch sampling This patch adds support for taken branch sampling, i.e, the PERF_SAMPLE_BRANCH_STACK feature to perf report. In other words, to display histograms based on taken branches rather than executed instructions addresses. The new option is called -b and it takes no argument. To generate meaningful output, the perf.data must have been obtained using perf record -b xxx ... where xxx is a branch filter option. The output shows symbols, modules, sorted by 'who branches where' the most often. The percentages reported in the first column refer to the total number of branches captured and not the usual number of samples. Here is a quick example. Here branchy is simple test program which looks as follows: void f2(void) {} void f3(void) {} void f1(unsigned long n) { if (n & 1UL) f2(); else f3(); } int main(void) { unsigned long i; for (i=0; i < N; i++) f1(i); return 0; } Here is the output captured on Nehalem, if we are only interested in user level function calls. $ perf record -b any_call,u -e cycles:u branchy $ perf report -b --sort=symbol 52.34% [.] main [.] f1 24.04% [.] f1 [.] f3 23.60% [.] f1 [.] f2 0.01% [k] _IO_new_file_xsputn [k] _IO_file_overflow 0.01% [k] _IO_vfprintf_internal [k] _IO_new_file_xsputn 0.01% [k] _IO_vfprintf_internal [k] strchrnul 0.01% [k] __printf [k] _IO_vfprintf_internal 0.01% [k] main [k] __printf About half (52%) of the call branches captured are from main() -> f1(). The second half (24%+23%) is split in two equal shares between f1() -> f2(), f1() ->f3(). The output is as expected given the code. It should be noted, that using -b in perf record does not eliminate information in the perf.data file. Consequently, a typical profile can also be obtained by perf report by simply not using its -b option. It is possible to sort on branch related columns: - dso_from, symbol_from - dso_to, symbol_to - mispredict Signed-off-by: Roberto Agostino Vitillo <ravitillo@lbl.gov> Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-14-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-09 22:21:03 +00:00
bi = machine__resolve_bstack(al->machine, al->thread,
perf report: Add support for taken branch sampling This patch adds support for taken branch sampling, i.e, the PERF_SAMPLE_BRANCH_STACK feature to perf report. In other words, to display histograms based on taken branches rather than executed instructions addresses. The new option is called -b and it takes no argument. To generate meaningful output, the perf.data must have been obtained using perf record -b xxx ... where xxx is a branch filter option. The output shows symbols, modules, sorted by 'who branches where' the most often. The percentages reported in the first column refer to the total number of branches captured and not the usual number of samples. Here is a quick example. Here branchy is simple test program which looks as follows: void f2(void) {} void f3(void) {} void f1(unsigned long n) { if (n & 1UL) f2(); else f3(); } int main(void) { unsigned long i; for (i=0; i < N; i++) f1(i); return 0; } Here is the output captured on Nehalem, if we are only interested in user level function calls. $ perf record -b any_call,u -e cycles:u branchy $ perf report -b --sort=symbol 52.34% [.] main [.] f1 24.04% [.] f1 [.] f3 23.60% [.] f1 [.] f2 0.01% [k] _IO_new_file_xsputn [k] _IO_file_overflow 0.01% [k] _IO_vfprintf_internal [k] _IO_new_file_xsputn 0.01% [k] _IO_vfprintf_internal [k] strchrnul 0.01% [k] __printf [k] _IO_vfprintf_internal 0.01% [k] main [k] __printf About half (52%) of the call branches captured are from main() -> f1(). The second half (24%+23%) is split in two equal shares between f1() -> f2(), f1() ->f3(). The output is as expected given the code. It should be noted, that using -b in perf record does not eliminate information in the perf.data file. Consequently, a typical profile can also be obtained by perf report by simply not using its -b option. It is possible to sort on branch related columns: - dso_from, symbol_from - dso_to, symbol_to - mispredict Signed-off-by: Roberto Agostino Vitillo <ravitillo@lbl.gov> Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-14-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-09 22:21:03 +00:00
sample->branch_stack);
if (!bi)
return -ENOMEM;
for (i = 0; i < sample->branch_stack->nr; i++) {
if (rep->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym))
continue;
err = -ENOMEM;
/* overwrite the 'al' to branch-to info */
al->map = bi[i].to.map;
al->sym = bi[i].to.sym;
al->addr = bi[i].to.addr;
perf report: Add support for taken branch sampling This patch adds support for taken branch sampling, i.e, the PERF_SAMPLE_BRANCH_STACK feature to perf report. In other words, to display histograms based on taken branches rather than executed instructions addresses. The new option is called -b and it takes no argument. To generate meaningful output, the perf.data must have been obtained using perf record -b xxx ... where xxx is a branch filter option. The output shows symbols, modules, sorted by 'who branches where' the most often. The percentages reported in the first column refer to the total number of branches captured and not the usual number of samples. Here is a quick example. Here branchy is simple test program which looks as follows: void f2(void) {} void f3(void) {} void f1(unsigned long n) { if (n & 1UL) f2(); else f3(); } int main(void) { unsigned long i; for (i=0; i < N; i++) f1(i); return 0; } Here is the output captured on Nehalem, if we are only interested in user level function calls. $ perf record -b any_call,u -e cycles:u branchy $ perf report -b --sort=symbol 52.34% [.] main [.] f1 24.04% [.] f1 [.] f3 23.60% [.] f1 [.] f2 0.01% [k] _IO_new_file_xsputn [k] _IO_file_overflow 0.01% [k] _IO_vfprintf_internal [k] _IO_new_file_xsputn 0.01% [k] _IO_vfprintf_internal [k] strchrnul 0.01% [k] __printf [k] _IO_vfprintf_internal 0.01% [k] main [k] __printf About half (52%) of the call branches captured are from main() -> f1(). The second half (24%+23%) is split in two equal shares between f1() -> f2(), f1() ->f3(). The output is as expected given the code. It should be noted, that using -b in perf record does not eliminate information in the perf.data file. Consequently, a typical profile can also be obtained by perf report by simply not using its -b option. It is possible to sort on branch related columns: - dso_from, symbol_from - dso_to, symbol_to - mispredict Signed-off-by: Roberto Agostino Vitillo <ravitillo@lbl.gov> Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-14-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-09 22:21:03 +00:00
/*
* The report shows the percentage of total branches captured
* and not events sampled. Thus we use a pseudo period of 1.
*/
he = __hists__add_entry(&evsel->hists, al, parent, &bi[i], NULL,
1, 1, 0);
perf report: Add support for taken branch sampling This patch adds support for taken branch sampling, i.e, the PERF_SAMPLE_BRANCH_STACK feature to perf report. In other words, to display histograms based on taken branches rather than executed instructions addresses. The new option is called -b and it takes no argument. To generate meaningful output, the perf.data must have been obtained using perf record -b xxx ... where xxx is a branch filter option. The output shows symbols, modules, sorted by 'who branches where' the most often. The percentages reported in the first column refer to the total number of branches captured and not the usual number of samples. Here is a quick example. Here branchy is simple test program which looks as follows: void f2(void) {} void f3(void) {} void f1(unsigned long n) { if (n & 1UL) f2(); else f3(); } int main(void) { unsigned long i; for (i=0; i < N; i++) f1(i); return 0; } Here is the output captured on Nehalem, if we are only interested in user level function calls. $ perf record -b any_call,u -e cycles:u branchy $ perf report -b --sort=symbol 52.34% [.] main [.] f1 24.04% [.] f1 [.] f3 23.60% [.] f1 [.] f2 0.01% [k] _IO_new_file_xsputn [k] _IO_file_overflow 0.01% [k] _IO_vfprintf_internal [k] _IO_new_file_xsputn 0.01% [k] _IO_vfprintf_internal [k] strchrnul 0.01% [k] __printf [k] _IO_vfprintf_internal 0.01% [k] main [k] __printf About half (52%) of the call branches captured are from main() -> f1(). The second half (24%+23%) is split in two equal shares between f1() -> f2(), f1() ->f3(). The output is as expected given the code. It should be noted, that using -b in perf record does not eliminate information in the perf.data file. Consequently, a typical profile can also be obtained by perf report by simply not using its -b option. It is possible to sort on branch related columns: - dso_from, symbol_from - dso_to, symbol_to - mispredict Signed-off-by: Roberto Agostino Vitillo <ravitillo@lbl.gov> Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-14-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-09 22:21:03 +00:00
if (he) {
bx = he->branch_info;
err = addr_map_symbol__inc_samples(&bx->from, evsel->idx);
if (err)
goto out;
err = addr_map_symbol__inc_samples(&bx->to, evsel->idx);
if (err)
goto out;
perf report: Add support for taken branch sampling This patch adds support for taken branch sampling, i.e, the PERF_SAMPLE_BRANCH_STACK feature to perf report. In other words, to display histograms based on taken branches rather than executed instructions addresses. The new option is called -b and it takes no argument. To generate meaningful output, the perf.data must have been obtained using perf record -b xxx ... where xxx is a branch filter option. The output shows symbols, modules, sorted by 'who branches where' the most often. The percentages reported in the first column refer to the total number of branches captured and not the usual number of samples. Here is a quick example. Here branchy is simple test program which looks as follows: void f2(void) {} void f3(void) {} void f1(unsigned long n) { if (n & 1UL) f2(); else f3(); } int main(void) { unsigned long i; for (i=0; i < N; i++) f1(i); return 0; } Here is the output captured on Nehalem, if we are only interested in user level function calls. $ perf record -b any_call,u -e cycles:u branchy $ perf report -b --sort=symbol 52.34% [.] main [.] f1 24.04% [.] f1 [.] f3 23.60% [.] f1 [.] f2 0.01% [k] _IO_new_file_xsputn [k] _IO_file_overflow 0.01% [k] _IO_vfprintf_internal [k] _IO_new_file_xsputn 0.01% [k] _IO_vfprintf_internal [k] strchrnul 0.01% [k] __printf [k] _IO_vfprintf_internal 0.01% [k] main [k] __printf About half (52%) of the call branches captured are from main() -> f1(). The second half (24%+23%) is split in two equal shares between f1() -> f2(), f1() ->f3(). The output is as expected given the code. It should be noted, that using -b in perf record does not eliminate information in the perf.data file. Consequently, a typical profile can also be obtained by perf report by simply not using its -b option. It is possible to sort on branch related columns: - dso_from, symbol_from - dso_to, symbol_to - mispredict Signed-off-by: Roberto Agostino Vitillo <ravitillo@lbl.gov> Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-14-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-09 22:21:03 +00:00
evsel->hists.stats.total_period += 1;
hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
} else
goto out;
perf report: Add support for taken branch sampling This patch adds support for taken branch sampling, i.e, the PERF_SAMPLE_BRANCH_STACK feature to perf report. In other words, to display histograms based on taken branches rather than executed instructions addresses. The new option is called -b and it takes no argument. To generate meaningful output, the perf.data must have been obtained using perf record -b xxx ... where xxx is a branch filter option. The output shows symbols, modules, sorted by 'who branches where' the most often. The percentages reported in the first column refer to the total number of branches captured and not the usual number of samples. Here is a quick example. Here branchy is simple test program which looks as follows: void f2(void) {} void f3(void) {} void f1(unsigned long n) { if (n & 1UL) f2(); else f3(); } int main(void) { unsigned long i; for (i=0; i < N; i++) f1(i); return 0; } Here is the output captured on Nehalem, if we are only interested in user level function calls. $ perf record -b any_call,u -e cycles:u branchy $ perf report -b --sort=symbol 52.34% [.] main [.] f1 24.04% [.] f1 [.] f3 23.60% [.] f1 [.] f2 0.01% [k] _IO_new_file_xsputn [k] _IO_file_overflow 0.01% [k] _IO_vfprintf_internal [k] _IO_new_file_xsputn 0.01% [k] _IO_vfprintf_internal [k] strchrnul 0.01% [k] __printf [k] _IO_vfprintf_internal 0.01% [k] main [k] __printf About half (52%) of the call branches captured are from main() -> f1(). The second half (24%+23%) is split in two equal shares between f1() -> f2(), f1() ->f3(). The output is as expected given the code. It should be noted, that using -b in perf record does not eliminate information in the perf.data file. Consequently, a typical profile can also be obtained by perf report by simply not using its -b option. It is possible to sort on branch related columns: - dso_from, symbol_from - dso_to, symbol_to - mispredict Signed-off-by: Roberto Agostino Vitillo <ravitillo@lbl.gov> Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-14-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-09 22:21:03 +00:00
}
err = 0;
out:
free(bi);
perf report: Add support for taken branch sampling This patch adds support for taken branch sampling, i.e, the PERF_SAMPLE_BRANCH_STACK feature to perf report. In other words, to display histograms based on taken branches rather than executed instructions addresses. The new option is called -b and it takes no argument. To generate meaningful output, the perf.data must have been obtained using perf record -b xxx ... where xxx is a branch filter option. The output shows symbols, modules, sorted by 'who branches where' the most often. The percentages reported in the first column refer to the total number of branches captured and not the usual number of samples. Here is a quick example. Here branchy is simple test program which looks as follows: void f2(void) {} void f3(void) {} void f1(unsigned long n) { if (n & 1UL) f2(); else f3(); } int main(void) { unsigned long i; for (i=0; i < N; i++) f1(i); return 0; } Here is the output captured on Nehalem, if we are only interested in user level function calls. $ perf record -b any_call,u -e cycles:u branchy $ perf report -b --sort=symbol 52.34% [.] main [.] f1 24.04% [.] f1 [.] f3 23.60% [.] f1 [.] f2 0.01% [k] _IO_new_file_xsputn [k] _IO_file_overflow 0.01% [k] _IO_vfprintf_internal [k] _IO_new_file_xsputn 0.01% [k] _IO_vfprintf_internal [k] strchrnul 0.01% [k] __printf [k] _IO_vfprintf_internal 0.01% [k] main [k] __printf About half (52%) of the call branches captured are from main() -> f1(). The second half (24%+23%) is split in two equal shares between f1() -> f2(), f1() ->f3(). The output is as expected given the code. It should be noted, that using -b in perf record does not eliminate information in the perf.data file. Consequently, a typical profile can also be obtained by perf report by simply not using its -b option. It is possible to sort on branch related columns: - dso_from, symbol_from - dso_to, symbol_to - mispredict Signed-off-by: Roberto Agostino Vitillo <ravitillo@lbl.gov> Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-14-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-09 22:21:03 +00:00
return err;
}
static int report__add_hist_entry(struct perf_tool *tool, struct perf_evsel *evsel,
struct addr_location *al, struct perf_sample *sample)
{
struct report *rep = container_of(tool, struct report, tool);
struct symbol *parent = NULL;
struct hist_entry *he;
int err = report__resolve_callchain(rep, &parent, evsel, al, sample);
if (err)
return err;
he = __hists__add_entry(&evsel->hists, al, parent, NULL, NULL,
sample->period, sample->weight,
sample->transaction);
if (he == NULL)
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 03:51:58 +00:00
return -ENOMEM;
err = hist_entry__append_callchain(he, sample);
if (err)
goto out;
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 03:51:58 +00:00
err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
evsel->hists.stats.total_period += sample->period;
hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
out:
return err;
}
static int process_sample_event(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct perf_evsel *evsel,
struct machine *machine)
{
struct report *rep = container_of(tool, struct report, tool);
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-27 18:29:23 +00:00
struct addr_location al;
int ret;
if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
pr_debug("problem processing %d event, skipping it.\n",
event->header.type);
return -1;
}
if (al.filtered || (rep->hide_unresolved && al.sym == NULL))
return 0;
if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
return 0;
if (sort__mode == SORT_MODE__BRANCH) {
ret = report__add_branch_hist_entry(tool, &al, sample, evsel);
if (ret < 0)
perf report: Add support for taken branch sampling This patch adds support for taken branch sampling, i.e, the PERF_SAMPLE_BRANCH_STACK feature to perf report. In other words, to display histograms based on taken branches rather than executed instructions addresses. The new option is called -b and it takes no argument. To generate meaningful output, the perf.data must have been obtained using perf record -b xxx ... where xxx is a branch filter option. The output shows symbols, modules, sorted by 'who branches where' the most often. The percentages reported in the first column refer to the total number of branches captured and not the usual number of samples. Here is a quick example. Here branchy is simple test program which looks as follows: void f2(void) {} void f3(void) {} void f1(unsigned long n) { if (n & 1UL) f2(); else f3(); } int main(void) { unsigned long i; for (i=0; i < N; i++) f1(i); return 0; } Here is the output captured on Nehalem, if we are only interested in user level function calls. $ perf record -b any_call,u -e cycles:u branchy $ perf report -b --sort=symbol 52.34% [.] main [.] f1 24.04% [.] f1 [.] f3 23.60% [.] f1 [.] f2 0.01% [k] _IO_new_file_xsputn [k] _IO_file_overflow 0.01% [k] _IO_vfprintf_internal [k] _IO_new_file_xsputn 0.01% [k] _IO_vfprintf_internal [k] strchrnul 0.01% [k] __printf [k] _IO_vfprintf_internal 0.01% [k] main [k] __printf About half (52%) of the call branches captured are from main() -> f1(). The second half (24%+23%) is split in two equal shares between f1() -> f2(), f1() ->f3(). The output is as expected given the code. It should be noted, that using -b in perf record does not eliminate information in the perf.data file. Consequently, a typical profile can also be obtained by perf report by simply not using its -b option. It is possible to sort on branch related columns: - dso_from, symbol_from - dso_to, symbol_to - mispredict Signed-off-by: Roberto Agostino Vitillo <ravitillo@lbl.gov> Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-14-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-09 22:21:03 +00:00
pr_debug("problem adding lbr entry, skipping event\n");
} else if (rep->mem_mode == 1) {
ret = report__add_mem_hist_entry(tool, &al, sample, evsel, event);
if (ret < 0)
pr_debug("problem adding mem entry, skipping event\n");
perf report: Add support for taken branch sampling This patch adds support for taken branch sampling, i.e, the PERF_SAMPLE_BRANCH_STACK feature to perf report. In other words, to display histograms based on taken branches rather than executed instructions addresses. The new option is called -b and it takes no argument. To generate meaningful output, the perf.data must have been obtained using perf record -b xxx ... where xxx is a branch filter option. The output shows symbols, modules, sorted by 'who branches where' the most often. The percentages reported in the first column refer to the total number of branches captured and not the usual number of samples. Here is a quick example. Here branchy is simple test program which looks as follows: void f2(void) {} void f3(void) {} void f1(unsigned long n) { if (n & 1UL) f2(); else f3(); } int main(void) { unsigned long i; for (i=0; i < N; i++) f1(i); return 0; } Here is the output captured on Nehalem, if we are only interested in user level function calls. $ perf record -b any_call,u -e cycles:u branchy $ perf report -b --sort=symbol 52.34% [.] main [.] f1 24.04% [.] f1 [.] f3 23.60% [.] f1 [.] f2 0.01% [k] _IO_new_file_xsputn [k] _IO_file_overflow 0.01% [k] _IO_vfprintf_internal [k] _IO_new_file_xsputn 0.01% [k] _IO_vfprintf_internal [k] strchrnul 0.01% [k] __printf [k] _IO_vfprintf_internal 0.01% [k] main [k] __printf About half (52%) of the call branches captured are from main() -> f1(). The second half (24%+23%) is split in two equal shares between f1() -> f2(), f1() ->f3(). The output is as expected given the code. It should be noted, that using -b in perf record does not eliminate information in the perf.data file. Consequently, a typical profile can also be obtained by perf report by simply not using its -b option. It is possible to sort on branch related columns: - dso_from, symbol_from - dso_to, symbol_to - mispredict Signed-off-by: Roberto Agostino Vitillo <ravitillo@lbl.gov> Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-14-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-09 22:21:03 +00:00
} else {
if (al.map != NULL)
al.map->dso->hit = 1;
perf symbols: Handle /proc/sys/kernel/kptr_restrict Perf uses /proc/modules to figure out where kernel modules are loaded. With the advent of kptr_restrict, non root users get zeroes for all module start addresses. So check if kptr_restrict is non zero and don't generate the syntethic PERF_RECORD_MMAP events for them. Warn the user about it in perf record and in perf report. In perf report the reference relocation symbol being zero means that kptr_restrict was set, thus /proc/kallsyms has only zeroed addresses, so don't use it to fixup symbol addresses when using a valid kallsyms (in the buildid cache) or vmlinux (in the vmlinux path) build-id located automatically or specified by the user. Provide an explanation about it in 'perf report' if kernel samples were taken, checking if a suitable vmlinux or kallsyms was found/specified. Restricted /proc/kallsyms don't go to the buildid cache anymore. Example: [acme@emilia ~]$ perf record -F 100000 sleep 1 WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted, check /proc/sys/kernel/kptr_restrict. Samples in kernel functions may not be resolved if a suitable vmlinux file is not found in the buildid cache or in the vmlinux path. Samples in kernel modules won't be resolved at all. If some relocation was applied (e.g. kexec) symbols may be misresolved even with a suitable vmlinux or kallsyms file. [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.005 MB perf.data (~231 samples) ] [acme@emilia ~]$ [acme@emilia ~]$ perf report --stdio Kernel address maps (/proc/{kallsyms,modules}) were restricted, check /proc/sys/kernel/kptr_restrict before running 'perf record'. If some relocation was applied (e.g. kexec) symbols may be misresolved. Samples in kernel modules can't be resolved as well. # Events: 13 cycles # # Overhead Command Shared Object Symbol # ........ ....... ................. ..................... # 20.24% sleep [kernel.kallsyms] [k] page_fault 20.04% sleep [kernel.kallsyms] [k] filemap_fault 19.78% sleep [kernel.kallsyms] [k] __lru_cache_add 19.69% sleep ld-2.12.so [.] memcpy 14.71% sleep [kernel.kallsyms] [k] dput 4.70% sleep [kernel.kallsyms] [k] flush_signal_handlers 0.73% sleep [kernel.kallsyms] [k] perf_event_comm 0.11% sleep [kernel.kallsyms] [k] native_write_msr_safe # # (For a higher level overview, try: perf report --sort comm,dso) # [acme@emilia ~]$ This is because it found a suitable vmlinux (build-id checked) in /lib/modules/2.6.39-rc7+/build/vmlinux (use -v in perf report to see the long file name). If we remove that file from the vmlinux path: [root@emilia ~]# mv /lib/modules/2.6.39-rc7+/build/vmlinux \ /lib/modules/2.6.39-rc7+/build/vmlinux.OFF [acme@emilia ~]$ perf report --stdio [kernel.kallsyms] with build id 57298cdbe0131f6871667ec0eaab4804dcf6f562 not found, continuing without symbols Kernel address maps (/proc/{kallsyms,modules}) were restricted, check /proc/sys/kernel/kptr_restrict before running 'perf record'. As no suitable kallsyms nor vmlinux was found, kernel samples can't be resolved. Samples in kernel modules can't be resolved as well. # Events: 13 cycles # # Overhead Command Shared Object Symbol # ........ ....... ................. ...... # 80.31% sleep [kernel.kallsyms] [k] 0xffffffff8103425a 19.69% sleep ld-2.12.so [.] memcpy # # (For a higher level overview, try: perf report --sort comm,dso) # [acme@emilia ~]$ Reported-by: Stephane Eranian <eranian@google.com> Suggested-by: David Miller <davem@davemloft.net> Cc: Dave Jones <davej@redhat.com> Cc: David Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Kees Cook <kees.cook@canonical.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> Link: http://lkml.kernel.org/n/tip-mt512joaxxbhhp1odop04yit@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-05-26 12:53:51 +00:00
ret = report__add_hist_entry(tool, evsel, &al, sample);
if (ret < 0)
perf report: Add support for taken branch sampling This patch adds support for taken branch sampling, i.e, the PERF_SAMPLE_BRANCH_STACK feature to perf report. In other words, to display histograms based on taken branches rather than executed instructions addresses. The new option is called -b and it takes no argument. To generate meaningful output, the perf.data must have been obtained using perf record -b xxx ... where xxx is a branch filter option. The output shows symbols, modules, sorted by 'who branches where' the most often. The percentages reported in the first column refer to the total number of branches captured and not the usual number of samples. Here is a quick example. Here branchy is simple test program which looks as follows: void f2(void) {} void f3(void) {} void f1(unsigned long n) { if (n & 1UL) f2(); else f3(); } int main(void) { unsigned long i; for (i=0; i < N; i++) f1(i); return 0; } Here is the output captured on Nehalem, if we are only interested in user level function calls. $ perf record -b any_call,u -e cycles:u branchy $ perf report -b --sort=symbol 52.34% [.] main [.] f1 24.04% [.] f1 [.] f3 23.60% [.] f1 [.] f2 0.01% [k] _IO_new_file_xsputn [k] _IO_file_overflow 0.01% [k] _IO_vfprintf_internal [k] _IO_new_file_xsputn 0.01% [k] _IO_vfprintf_internal [k] strchrnul 0.01% [k] __printf [k] _IO_vfprintf_internal 0.01% [k] main [k] __printf About half (52%) of the call branches captured are from main() -> f1(). The second half (24%+23%) is split in two equal shares between f1() -> f2(), f1() ->f3(). The output is as expected given the code. It should be noted, that using -b in perf record does not eliminate information in the perf.data file. Consequently, a typical profile can also be obtained by perf report by simply not using its -b option. It is possible to sort on branch related columns: - dso_from, symbol_from - dso_to, symbol_to - mispredict Signed-off-by: Roberto Agostino Vitillo <ravitillo@lbl.gov> Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-14-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-09 22:21:03 +00:00
pr_debug("problem incrementing symbol period, skipping event\n");
}
return ret;
}
static int process_read_event(struct perf_tool *tool,
union perf_event *event,
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-10 22:15:03 +00:00
struct perf_sample *sample __maybe_unused,
struct perf_evsel *evsel,
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-10 22:15:03 +00:00
struct machine *machine __maybe_unused)
{
struct report *rep = container_of(tool, struct report, tool);
if (rep->show_threads) {
const char *name = evsel ? perf_evsel__name(evsel) : "unknown";
perf_read_values_add_value(&rep->show_threads_values,
event->read.pid, event->read.tid,
event->read.id,
name,
event->read.value);
}
dump_printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
evsel ? perf_evsel__name(evsel) : "FAIL",
event->read.value);
return 0;
}
/* For pipe mode, sample_type is not currently set */
static int report__setup_sample_type(struct report *rep)
{
struct perf_session *session = rep->session;
u64 sample_type = perf_evlist__combined_sample_type(session->evlist);
bool is_pipe = perf_data_file__is_pipe(session->file);
if (!is_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) {
if (sort__has_parent) {
ui__error("Selected --sort parent, but no "
"callchain data. Did you call "
"'perf record' without -g?\n");
return -EINVAL;
}
if (symbol_conf.use_callchain) {
ui__error("Selected -g but no callchain data. Did "
"you call 'perf record' without -g?\n");
return -1;
}
} else if (!rep->dont_use_callchains &&
callchain_param.mode != CHAIN_NONE &&
!symbol_conf.use_callchain) {
symbol_conf.use_callchain = true;
if (callchain_register_param(&callchain_param) < 0) {
ui__error("Can't register callchain params.\n");
return -EINVAL;
}
}
if (sort__mode == SORT_MODE__BRANCH) {
if (!is_pipe &&
!(sample_type & PERF_SAMPLE_BRANCH_STACK)) {
ui__error("Selected -b but no branch data. "
"Did you call perf record without -b?\n");
perf report: Add support for taken branch sampling This patch adds support for taken branch sampling, i.e, the PERF_SAMPLE_BRANCH_STACK feature to perf report. In other words, to display histograms based on taken branches rather than executed instructions addresses. The new option is called -b and it takes no argument. To generate meaningful output, the perf.data must have been obtained using perf record -b xxx ... where xxx is a branch filter option. The output shows symbols, modules, sorted by 'who branches where' the most often. The percentages reported in the first column refer to the total number of branches captured and not the usual number of samples. Here is a quick example. Here branchy is simple test program which looks as follows: void f2(void) {} void f3(void) {} void f1(unsigned long n) { if (n & 1UL) f2(); else f3(); } int main(void) { unsigned long i; for (i=0; i < N; i++) f1(i); return 0; } Here is the output captured on Nehalem, if we are only interested in user level function calls. $ perf record -b any_call,u -e cycles:u branchy $ perf report -b --sort=symbol 52.34% [.] main [.] f1 24.04% [.] f1 [.] f3 23.60% [.] f1 [.] f2 0.01% [k] _IO_new_file_xsputn [k] _IO_file_overflow 0.01% [k] _IO_vfprintf_internal [k] _IO_new_file_xsputn 0.01% [k] _IO_vfprintf_internal [k] strchrnul 0.01% [k] __printf [k] _IO_vfprintf_internal 0.01% [k] main [k] __printf About half (52%) of the call branches captured are from main() -> f1(). The second half (24%+23%) is split in two equal shares between f1() -> f2(), f1() ->f3(). The output is as expected given the code. It should be noted, that using -b in perf record does not eliminate information in the perf.data file. Consequently, a typical profile can also be obtained by perf report by simply not using its -b option. It is possible to sort on branch related columns: - dso_from, symbol_from - dso_to, symbol_to - mispredict Signed-off-by: Roberto Agostino Vitillo <ravitillo@lbl.gov> Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-14-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-09 22:21:03 +00:00
return -1;
}
}
return 0;
}
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-10 22:15:03 +00:00
static void sig_handler(int sig __maybe_unused)
{
session_done = 1;
}
static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report *rep,
const char *evname, FILE *fp)
{
size_t ret;
char unit;
unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
u64 nr_events = hists->stats.total_period;
struct perf_evsel *evsel = hists_to_evsel(hists);
char buf[512];
size_t size = sizeof(buf);
if (perf_evsel__is_group_event(evsel)) {
struct perf_evsel *pos;
perf_evsel__group_desc(evsel, buf, size);
evname = buf;
for_each_group_member(pos, evsel) {
nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
nr_events += pos->hists.stats.total_period;
}
}
nr_samples = convert_unit(nr_samples, &unit);
ret = fprintf(fp, "# Samples: %lu%c", nr_samples, unit);
if (evname != NULL)
ret += fprintf(fp, " of event '%s'", evname);
if (rep->mem_mode) {
ret += fprintf(fp, "\n# Total weight : %" PRIu64, nr_events);
ret += fprintf(fp, "\n# Sort order : %s", sort_order);
} else
ret += fprintf(fp, "\n# Event count (approx.): %" PRIu64, nr_events);
return ret + fprintf(fp, "\n#\n");
}
static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
struct report *rep,
const char *help)
{
struct perf_evsel *pos;
list_for_each_entry(pos, &evlist->entries, node) {
struct hists *hists = &pos->hists;
const char *evname = perf_evsel__name(pos);
if (symbol_conf.event_group &&
!perf_evsel__is_group_leader(pos))
continue;
hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
hists__fprintf(hists, true, 0, 0, rep->min_percent, stdout);
fprintf(stdout, "\n\n");
}
if (sort_order == default_sort_order &&
parent_pattern == default_parent_pattern) {
fprintf(stdout, "#\n# (%s)\n#\n", help);
if (rep->show_threads) {
bool style = !strcmp(rep->pretty_printing_style, "raw");
perf_read_values_display(stdout, &rep->show_threads_values,
style);
perf_read_values_destroy(&rep->show_threads_values);
}
}
return 0;
}
static void report__warn_kptr_restrict(const struct report *rep)
{
struct map *kernel_map = rep->session->machines.host.vmlinux_maps[MAP__FUNCTION];
struct kmap *kernel_kmap = map__kmap(kernel_map);
if (kernel_map == NULL ||
(kernel_map->dso->hit &&
(kernel_kmap->ref_reloc_sym == NULL ||
kernel_kmap->ref_reloc_sym->addr == 0))) {
const char *desc =
"As no suitable kallsyms nor vmlinux was found, kernel samples\n"
"can't be resolved.";
if (kernel_map) {
const struct dso *kdso = kernel_map->dso;
if (!RB_EMPTY_ROOT(&kdso->symbols[MAP__FUNCTION])) {
desc = "If some relocation was applied (e.g. "
"kexec) symbols may be misresolved.";
}
}
ui__warning(
"Kernel address maps (/proc/{kallsyms,modules}) were restricted.\n\n"
"Check /proc/sys/kernel/kptr_restrict before running 'perf record'.\n\n%s\n\n"
"Samples in kernel modules can't be resolved as well.\n\n",
desc);
}
}
static int report__gtk_browse_hists(struct report *rep, const char *help)
{
int (*hist_browser)(struct perf_evlist *evlist, const char *help,
struct hist_browser_timer *timer, float min_pcnt);
hist_browser = dlsym(perf_gtk_handle, "perf_evlist__gtk_browse_hists");
if (hist_browser == NULL) {
ui__error("GTK browser not found!\n");
return -1;
}
return hist_browser(rep->session->evlist, help, NULL, rep->min_percent);
}
static int report__browse_hists(struct report *rep)
{
int ret;
struct perf_session *session = rep->session;
struct perf_evlist *evlist = session->evlist;
const char *help = "For a higher level overview, try: perf report --sort comm,dso";
switch (use_browser) {
case 1:
ret = perf_evlist__tui_browse_hists(evlist, help, NULL,
rep->min_percent,
&session->header.env);
/*
* Usually "ret" is the last pressed key, and we only
* care if the key notifies us to switch data file.
*/
if (ret != K_SWITCH_INPUT_DATA)
ret = 0;
break;
case 2:
ret = report__gtk_browse_hists(rep, help);
break;
default:
ret = perf_evlist__tty_browse_hists(evlist, rep, help);
break;
}
return ret;
}
static int __cmd_report(struct report *rep)
{
int ret = -EINVAL;
u64 nr_samples;
struct perf_session *session = rep->session;
struct perf_evsel *pos;
struct ui_progress prog;
struct perf_data_file *file = session->file;
signal(SIGINT, sig_handler);
if (rep->cpu_list) {
ret = perf_session__cpu_bitmap(session, rep->cpu_list,
rep->cpu_bitmap);
if (ret)
return ret;
}
if (rep->show_threads)
perf_read_values_init(&rep->show_threads_values);
ret = report__setup_sample_type(rep);
if (ret)
return ret;
ret = perf_session__process_events(session, &rep->tool);
if (ret)
return ret;
report__warn_kptr_restrict(rep);
perf symbols: Handle /proc/sys/kernel/kptr_restrict Perf uses /proc/modules to figure out where kernel modules are loaded. With the advent of kptr_restrict, non root users get zeroes for all module start addresses. So check if kptr_restrict is non zero and don't generate the syntethic PERF_RECORD_MMAP events for them. Warn the user about it in perf record and in perf report. In perf report the reference relocation symbol being zero means that kptr_restrict was set, thus /proc/kallsyms has only zeroed addresses, so don't use it to fixup symbol addresses when using a valid kallsyms (in the buildid cache) or vmlinux (in the vmlinux path) build-id located automatically or specified by the user. Provide an explanation about it in 'perf report' if kernel samples were taken, checking if a suitable vmlinux or kallsyms was found/specified. Restricted /proc/kallsyms don't go to the buildid cache anymore. Example: [acme@emilia ~]$ perf record -F 100000 sleep 1 WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted, check /proc/sys/kernel/kptr_restrict. Samples in kernel functions may not be resolved if a suitable vmlinux file is not found in the buildid cache or in the vmlinux path. Samples in kernel modules won't be resolved at all. If some relocation was applied (e.g. kexec) symbols may be misresolved even with a suitable vmlinux or kallsyms file. [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.005 MB perf.data (~231 samples) ] [acme@emilia ~]$ [acme@emilia ~]$ perf report --stdio Kernel address maps (/proc/{kallsyms,modules}) were restricted, check /proc/sys/kernel/kptr_restrict before running 'perf record'. If some relocation was applied (e.g. kexec) symbols may be misresolved. Samples in kernel modules can't be resolved as well. # Events: 13 cycles # # Overhead Command Shared Object Symbol # ........ ....... ................. ..................... # 20.24% sleep [kernel.kallsyms] [k] page_fault 20.04% sleep [kernel.kallsyms] [k] filemap_fault 19.78% sleep [kernel.kallsyms] [k] __lru_cache_add 19.69% sleep ld-2.12.so [.] memcpy 14.71% sleep [kernel.kallsyms] [k] dput 4.70% sleep [kernel.kallsyms] [k] flush_signal_handlers 0.73% sleep [kernel.kallsyms] [k] perf_event_comm 0.11% sleep [kernel.kallsyms] [k] native_write_msr_safe # # (For a higher level overview, try: perf report --sort comm,dso) # [acme@emilia ~]$ This is because it found a suitable vmlinux (build-id checked) in /lib/modules/2.6.39-rc7+/build/vmlinux (use -v in perf report to see the long file name). If we remove that file from the vmlinux path: [root@emilia ~]# mv /lib/modules/2.6.39-rc7+/build/vmlinux \ /lib/modules/2.6.39-rc7+/build/vmlinux.OFF [acme@emilia ~]$ perf report --stdio [kernel.kallsyms] with build id 57298cdbe0131f6871667ec0eaab4804dcf6f562 not found, continuing without symbols Kernel address maps (/proc/{kallsyms,modules}) were restricted, check /proc/sys/kernel/kptr_restrict before running 'perf record'. As no suitable kallsyms nor vmlinux was found, kernel samples can't be resolved. Samples in kernel modules can't be resolved as well. # Events: 13 cycles # # Overhead Command Shared Object Symbol # ........ ....... ................. ...... # 80.31% sleep [kernel.kallsyms] [k] 0xffffffff8103425a 19.69% sleep ld-2.12.so [.] memcpy # # (For a higher level overview, try: perf report --sort comm,dso) # [acme@emilia ~]$ Reported-by: Stephane Eranian <eranian@google.com> Suggested-by: David Miller <davem@davemloft.net> Cc: Dave Jones <davej@redhat.com> Cc: David Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Kees Cook <kees.cook@canonical.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> Link: http://lkml.kernel.org/n/tip-mt512joaxxbhhp1odop04yit@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-05-26 12:53:51 +00:00
if (use_browser == 0) {
if (verbose > 3)
perf_session__fprintf(session, stdout);
if (verbose > 2)
perf_session__fprintf_dsos(session, stdout);
if (dump_trace) {
perf_session__fprintf_nr_events(session, stdout);
return 0;
}
perf tools: Support for DWARF CFI unwinding on post processing This brings the support for DWARF cfi unwinding on perf post processing. Call frame informations are retrieved and then passed to libunwind that requests memory and register content from the applications. Adding unwind object to handle the user stack backtrace based on the user register values and user stack dump. The unwind object access the libunwind via remote interface and provides to it all the necessary data to unwind the stack. The unwind interface provides following function: unwind__get_entries And callback (specified in above function) to retrieve the backtrace entries: typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg); Signed-off-by: Jiri Olsa <jolsa@redhat.com> Original-patch-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: "Frank Ch. Eigler" <fche@redhat.com> Cc: Arun Sharma <asharma@fb.com> Cc: Benjamin Redelings <benjamin.redelings@nescent.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Frank Ch. Eigler <fche@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Ulrich Drepper <drepper@gmail.com> Link: http://lkml.kernel.org/r/1344345647-11536-12-git-send-email-jolsa@redhat.com [ Replaced use of perf_session by usage of perf_evsel ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-08-07 13:20:46 +00:00
}
nr_samples = 0;
list_for_each_entry(pos, &session->evlist->entries, node)
nr_samples += pos->hists.nr_entries;
ui_progress__init(&prog, nr_samples, "Merging related events...");
nr_samples = 0;
list_for_each_entry(pos, &session->evlist->entries, node) {
struct hists *hists = &pos->hists;
if (pos->idx == 0)
hists->symbol_filter_str = rep->symbol_filter_str;
hists__collapse_resort(hists, &prog);
nr_samples += hists->stats.nr_events[PERF_RECORD_SAMPLE];
/* Non-group events are considered as leader */
if (symbol_conf.event_group &&
!perf_evsel__is_group_leader(pos)) {
struct hists *leader_hists = &pos->leader->hists;
hists__match(leader_hists, hists);
hists__link(leader_hists, hists);
}
}
ui_progress__finish();
if (session_done())
return 0;
if (nr_samples == 0) {
ui__error("The %s file has no samples!\n", file->path);
return 0;
}
list_for_each_entry(pos, &session->evlist->entries, node)
hists__output_resort(&pos->hists);
return report__browse_hists(rep);
}
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
static int
parse_callchain_opt(const struct option *opt, const char *arg, int unset)
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
{
struct report *rep = (struct report *)opt->value;
char *tok, *tok2;
2009-07-02 18:14:33 +00:00
char *endptr;
/*
* --no-call-graph
*/
if (unset) {
rep->dont_use_callchains = true;
return 0;
}
symbol_conf.use_callchain = true;
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
if (!arg)
return 0;
2009-07-02 18:14:33 +00:00
tok = strtok((char *)arg, ",");
if (!tok)
return -1;
/* get the output mode */
if (!strncmp(tok, "graph", strlen(arg)))
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
callchain_param.mode = CHAIN_GRAPH_ABS;
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
2009-07-02 18:14:33 +00:00
else if (!strncmp(tok, "flat", strlen(arg)))
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
callchain_param.mode = CHAIN_FLAT;
else if (!strncmp(tok, "fractal", strlen(arg)))
callchain_param.mode = CHAIN_GRAPH_REL;
else if (!strncmp(tok, "none", strlen(arg))) {
callchain_param.mode = CHAIN_NONE;
symbol_conf.use_callchain = false;
return 0;
}
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
else
return -1;
2009-07-02 18:14:33 +00:00
/* get the min percentage */
tok = strtok(NULL, ",");
if (!tok)
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
goto setup;
2009-07-02 18:14:33 +00:00
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
callchain_param.min_percent = strtod(tok, &endptr);
2009-07-02 18:14:33 +00:00
if (tok == endptr)
return -1;
/* get the print limit */
tok2 = strtok(NULL, ",");
if (!tok2)
goto setup;
if (tok2[0] != 'c') {
callchain_param.print_limit = strtoul(tok2, &endptr, 0);
tok2 = strtok(NULL, ",");
if (!tok2)
goto setup;
}
/* get the call chain order */
if (!strncmp(tok2, "caller", strlen("caller")))
callchain_param.order = ORDER_CALLER;
else if (!strncmp(tok2, "callee", strlen("callee")))
callchain_param.order = ORDER_CALLEE;
else
return -1;
/* Get the sort key */
tok2 = strtok(NULL, ",");
if (!tok2)
goto setup;
if (!strncmp(tok2, "function", strlen("function")))
callchain_param.key = CCKEY_FUNCTION;
else if (!strncmp(tok2, "address", strlen("address")))
callchain_param.key = CCKEY_ADDRESS;
else
return -1;
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
setup:
if (callchain_register_param(&callchain_param) < 0) {
pr_err("Can't register callchain params\n");
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
return -1;
}
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
return 0;
}
perf report/top: Add option to collapse undesired parts of call graph For example, in an application with an expensive function implemented with deeply nested recursive calls, the default call-graph presentation is dominated by the different callchains within that function. By ignoring these callees, we can collect the callchains leading into the function and compactly identify what to blame for expensive calls. For example, in this report the callers of garbage_collect() are scattered across the tree: $ perf report -d ruby 2>- | grep -m10 ^[^#]*[a-z] 22.03% ruby [.] gc_mark --- gc_mark |--59.40%-- mark_keyvalue | st_foreach | gc_mark_children | |--99.75%-- rb_gc_mark | | rb_vm_mark | | gc_mark_children | | gc_marks | | |--99.00%-- garbage_collect If we ignore the callees of garbage_collect(), its callers are coalesced: $ perf report --ignore-callees garbage_collect -d ruby 2>- | grep -m10 ^[^#]*[a-z] 72.92% ruby [.] garbage_collect --- garbage_collect vm_xmalloc |--47.08%-- ruby_xmalloc | st_insert2 | rb_hash_aset | |--98.45%-- features_index_add | | rb_provide_feature | | rb_require_safe | | vm_call_method Signed-off-by: Greg Price <price@mit.edu> Tested-by: Jiri Olsa <jolsa@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130623031720.GW22203@biohazard-cafe.mit.edu Link: http://lkml.kernel.org/r/20130708115746.GO22203@biohazard-cafe.mit.edu Cc: Fengguang Wu <fengguang.wu@intel.com> [ remove spaces at beginning of line, reported by Fengguang Wu ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-12-07 05:48:05 +00:00
int
report_parse_ignore_callees_opt(const struct option *opt __maybe_unused,
const char *arg, int unset __maybe_unused)
{
if (arg) {
int err = regcomp(&ignore_callees_regex, arg, REG_EXTENDED);
if (err) {
char buf[BUFSIZ];
regerror(err, &ignore_callees_regex, buf, sizeof(buf));
pr_err("Invalid --ignore-callees regex: %s\n%s", arg, buf);
return -1;
}
have_ignore_callees = 1;
}
return 0;
}
static int
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-10 22:15:03 +00:00
parse_branch_mode(const struct option *opt __maybe_unused,
const char *str __maybe_unused, int unset)
{
int *branch_mode = opt->value;
*branch_mode = !unset;
return 0;
}
static int
parse_percent_limit(const struct option *opt, const char *str,
int unset __maybe_unused)
{
struct report *rep = opt->value;
rep->min_percent = strtof(str, NULL);
return 0;
}
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-10 22:15:03 +00:00
int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
{
struct perf_session *session;
struct stat st;
bool has_br_stack = false;
int branch_mode = -1;
int ret = -1;
char callchain_default_opt[] = "fractal,0.5,callee";
const char * const report_usage[] = {
"perf report [<options>]",
NULL
};
struct report report = {
.tool = {
.sample = process_sample_event,
.mmap = perf_event__process_mmap,
.mmap2 = perf_event__process_mmap2,
.comm = perf_event__process_comm,
.exit = perf_event__process_exit,
.fork = perf_event__process_fork,
.lost = perf_event__process_lost,
.read = process_read_event,
.attr = perf_event__process_attr,
.tracing_data = perf_event__process_tracing_data,
.build_id = perf_event__process_build_id,
.ordered_samples = true,
.ordering_requires_timestamps = true,
},
perf report: Add --max-stack option to limit callchain stack scan When callgraph data was included in the perf data file, it may take a long time to scan all those data and merge them together especially if the stored callchains are long and the perf data file itself is large, like a Gbyte or so. The callchain stack is currently limited to PERF_MAX_STACK_DEPTH (127). This is a large value. Usually the callgraph data that developers are most interested in are the first few levels, the rests are usually not looked at. This patch adds a new --max-stack option to perf-report to limit the depth of callchain stack data to look at to reduce the time it takes for perf-report to finish its processing. It trades the presence of trailing stack information with faster speed. The following table shows the elapsed time of doing perf-report on a perf.data file of size 985,531,828 bytes. --max_stack Elapsed Time Output data size ----------- ------------ ---------------- not set 88.0s 124,422,651 64 87.5s 116,303,213 32 87.2s 112,023,804 16 86.6s 94,326,380 8 59.9s 33,697,248 4 40.7s 10,116,637 -g none 27.1s 2,555,810 Signed-off-by: Waiman Long <Waiman.Long@hp.com> Acked-by: David Ahern <dsahern@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Aswin Chandramouleeswaran <aswin@hp.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Scott J Norton <scott.norton@hp.com> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1382107129-2010-4-git-send-email-Waiman.Long@hp.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-18 14:38:48 +00:00
.max_stack = PERF_MAX_STACK_DEPTH,
.pretty_printing_style = "normal",
};
const struct option options[] = {
OPT_STRING('i', "input", &input_name, "file",
"input file name"),
perf: Fix endianness argument compatibility with OPT_BOOLEAN() and introduce OPT_INCR() Parsing an option from the command line with OPT_BOOLEAN on a bool data type would not work on a big-endian machine due to the manner in which the boolean was being cast into an int and incremented. For example, running 'perf probe --list' on a PowerPC machine would fail to properly set the list_events bool and would therefore print out the usage information and terminate. This patch makes OPT_BOOLEAN work as expected with a bool datatype. For cases where the original OPT_BOOLEAN was intentionally being used to increment an int each time it was passed in on the command line, this patch introduces OPT_INCR with the old behaviour of OPT_BOOLEAN (the verbose variable is currently the only such example of this). I have reviewed every use of OPT_BOOLEAN to verify that a true C99 bool was passed. Where integers were used, I verified that they were only being used for boolean logic and changed them to bools to ensure that they would not be mistakenly used as ints. The major exception was the verbose variable which now uses OPT_INCR instead of OPT_BOOLEAN. Signed-off-by: Ian Munsie <imunsie@au.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Cc: <stable@kernel.org> # NOTE: wont apply to .3[34].x cleanly, please backport Cc: Git development list <git@vger.kernel.org> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric B Munson <ebmunson@us.ibm.com> Cc: Valdis.Kletnieks@vt.edu Cc: WANG Cong <amwang@redhat.com> Cc: Thiago Farina <tfransosi@gmail.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Cc: Jaswinder Singh Rajput <jaswinderrajput@gmail.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Mike Galbraith <efault@gmx.de> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Anton Blanchard <anton@samba.org> Cc: John Kacur <jkacur@redhat.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1271147857-11604-1-git-send-email-imunsie@au.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-04-13 08:37:33 +00:00
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show symbol address, etc)"),
OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
"dump raw trace in ASCII"),
OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
"file", "vmlinux pathname"),
OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name,
"file", "kallsyms pathname"),
OPT_BOOLEAN('f', "force", &report.force, "don't complain, do it"),
OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules,
"load module symbols - WARNING: use only with -k and LIVE kernel"),
OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
"Show a column with the number of samples"),
OPT_BOOLEAN('T', "threads", &report.show_threads,
"Show per-thread event counters"),
OPT_STRING(0, "pretty", &report.pretty_printing_style, "key",
"pretty printing style key: normal raw"),
OPT_BOOLEAN(0, "tui", &report.use_tui, "Use the TUI interface"),
OPT_BOOLEAN(0, "gtk", &report.use_gtk, "Use the GTK2 interface"),
OPT_BOOLEAN(0, "stdio", &report.use_stdio,
"Use the stdio interface"),
OPT_BOOLEAN(0, "header", &report.header, "Show data header."),
OPT_BOOLEAN(0, "header-only", &report.header_only,
"Show only data header."),
OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
"sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline,"
" dso_to, dso_from, symbol_to, symbol_from, mispredict,"
" weight, local_weight, mem, symbol_daddr, dso_daddr, tlb, "
"snoop, locked, abort, in_tx, transaction"),
OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
"Show sample percentage for different cpu modes"),
OPT_STRING('p', "parent", &parent_pattern, "regex",
"regex filter to identify parent, see: '--sort parent'"),
OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other,
"Only display entries with parent-match"),
OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order",
"Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address). "
"Default: fractal,0.5,callee,function", &parse_callchain_opt, callchain_default_opt),
perf report: Add --max-stack option to limit callchain stack scan When callgraph data was included in the perf data file, it may take a long time to scan all those data and merge them together especially if the stored callchains are long and the perf data file itself is large, like a Gbyte or so. The callchain stack is currently limited to PERF_MAX_STACK_DEPTH (127). This is a large value. Usually the callgraph data that developers are most interested in are the first few levels, the rests are usually not looked at. This patch adds a new --max-stack option to perf-report to limit the depth of callchain stack data to look at to reduce the time it takes for perf-report to finish its processing. It trades the presence of trailing stack information with faster speed. The following table shows the elapsed time of doing perf-report on a perf.data file of size 985,531,828 bytes. --max_stack Elapsed Time Output data size ----------- ------------ ---------------- not set 88.0s 124,422,651 64 87.5s 116,303,213 32 87.2s 112,023,804 16 86.6s 94,326,380 8 59.9s 33,697,248 4 40.7s 10,116,637 -g none 27.1s 2,555,810 Signed-off-by: Waiman Long <Waiman.Long@hp.com> Acked-by: David Ahern <dsahern@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Aswin Chandramouleeswaran <aswin@hp.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Scott J Norton <scott.norton@hp.com> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1382107129-2010-4-git-send-email-Waiman.Long@hp.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-18 14:38:48 +00:00
OPT_INTEGER(0, "max-stack", &report.max_stack,
"Set the maximum stack depth when parsing the callchain, "
"anything beyond the specified depth will be ignored. "
"Default: " __stringify(PERF_MAX_STACK_DEPTH)),
OPT_BOOLEAN('G', "inverted", &report.inverted_callchain,
"alias for inverted call graph"),
perf report/top: Add option to collapse undesired parts of call graph For example, in an application with an expensive function implemented with deeply nested recursive calls, the default call-graph presentation is dominated by the different callchains within that function. By ignoring these callees, we can collect the callchains leading into the function and compactly identify what to blame for expensive calls. For example, in this report the callers of garbage_collect() are scattered across the tree: $ perf report -d ruby 2>- | grep -m10 ^[^#]*[a-z] 22.03% ruby [.] gc_mark --- gc_mark |--59.40%-- mark_keyvalue | st_foreach | gc_mark_children | |--99.75%-- rb_gc_mark | | rb_vm_mark | | gc_mark_children | | gc_marks | | |--99.00%-- garbage_collect If we ignore the callees of garbage_collect(), its callers are coalesced: $ perf report --ignore-callees garbage_collect -d ruby 2>- | grep -m10 ^[^#]*[a-z] 72.92% ruby [.] garbage_collect --- garbage_collect vm_xmalloc |--47.08%-- ruby_xmalloc | st_insert2 | rb_hash_aset | |--98.45%-- features_index_add | | rb_provide_feature | | rb_require_safe | | vm_call_method Signed-off-by: Greg Price <price@mit.edu> Tested-by: Jiri Olsa <jolsa@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130623031720.GW22203@biohazard-cafe.mit.edu Link: http://lkml.kernel.org/r/20130708115746.GO22203@biohazard-cafe.mit.edu Cc: Fengguang Wu <fengguang.wu@intel.com> [ remove spaces at beginning of line, reported by Fengguang Wu ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-12-07 05:48:05 +00:00
OPT_CALLBACK(0, "ignore-callees", NULL, "regex",
"ignore callees of these functions in call graphs",
report_parse_ignore_callees_opt),
OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
"only consider symbols in these dsos"),
OPT_STRING('c', "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
"only consider symbols in these comms"),
OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
"only consider these symbols"),
OPT_STRING(0, "symbol-filter", &report.symbol_filter_str, "filter",
"only show symbols that (partially) match with this filter"),
OPT_STRING('w', "column-widths", &symbol_conf.col_width_list_str,
perf report: Adjust column width to the values sampled Auto-adjust column width of perf report output to the longest occuring string length. Example: [acme@doppio pahole]$ perf report --sort comm,dso,symbol | head -13 12.79% pahole /usr/lib64/libdw-0.141.so [.] __libdw_find_attr 8.90% pahole /lib64/libc-2.10.1.so [.] _int_malloc 8.68% pahole /usr/lib64/libdw-0.141.so [.] __libdw_form_val_len 8.15% pahole /lib64/libc-2.10.1.so [.] __GI_strcmp 6.80% pahole /lib64/libc-2.10.1.so [.] __tsearch 5.54% pahole ./build/libdwarves.so.1.0.0 [.] tag__recode_dwarf_type [acme@doppio pahole]$ [acme@doppio pahole]$ perf report --sort comm,dso,symbol -d /lib64/libc-2.10.1.so | head -10 21.92% pahole /lib64/libc-2.10.1.so [.] _int_malloc 20.08% pahole /lib64/libc-2.10.1.so [.] __GI_strcmp 16.75% pahole /lib64/libc-2.10.1.so [.] __tsearch [acme@doppio pahole]$ Also add these extra options to control the new behaviour: -w, --field-width Force each column width to the provided list, for large terminal readability. -t, --field-separator: Use a special separator character and don't pad with spaces, replacing all occurances of this separator in symbol names (and other output) with a '.' character, that thus it's the only non valid separator. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <20090711014728.GH3452@ghostprotocols.net> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-11 01:47:28 +00:00
"width[,width...]",
"don't try to adjust column width, use these fixed values"),
OPT_STRING('t', "field-separator", &symbol_conf.field_sep, "separator",
perf report: Adjust column width to the values sampled Auto-adjust column width of perf report output to the longest occuring string length. Example: [acme@doppio pahole]$ perf report --sort comm,dso,symbol | head -13 12.79% pahole /usr/lib64/libdw-0.141.so [.] __libdw_find_attr 8.90% pahole /lib64/libc-2.10.1.so [.] _int_malloc 8.68% pahole /usr/lib64/libdw-0.141.so [.] __libdw_form_val_len 8.15% pahole /lib64/libc-2.10.1.so [.] __GI_strcmp 6.80% pahole /lib64/libc-2.10.1.so [.] __tsearch 5.54% pahole ./build/libdwarves.so.1.0.0 [.] tag__recode_dwarf_type [acme@doppio pahole]$ [acme@doppio pahole]$ perf report --sort comm,dso,symbol -d /lib64/libc-2.10.1.so | head -10 21.92% pahole /lib64/libc-2.10.1.so [.] _int_malloc 20.08% pahole /lib64/libc-2.10.1.so [.] __GI_strcmp 16.75% pahole /lib64/libc-2.10.1.so [.] __tsearch [acme@doppio pahole]$ Also add these extra options to control the new behaviour: -w, --field-width Force each column width to the provided list, for large terminal readability. -t, --field-separator: Use a special separator character and don't pad with spaces, replacing all occurances of this separator in symbol names (and other output) with a '.' character, that thus it's the only non valid separator. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <20090711014728.GH3452@ghostprotocols.net> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-11 01:47:28 +00:00
"separator for columns, no spaces will be added between "
"columns '.' is reserved."),
OPT_BOOLEAN('U', "hide-unresolved", &report.hide_unresolved,
"Only display entries resolved to a symbol"),
OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
"Look for files with symbols relative to this directory"),
OPT_STRING('C', "cpu", &report.cpu_list, "cpu",
"list of cpus to profile"),
OPT_BOOLEAN('I', "show-info", &report.show_full_info,
perf tools: Make perf.data more self-descriptive (v8) The goal of this patch is to include more information about the host environment into the perf.data so it is more self-descriptive. Overtime, profiles are captured on various machines and it becomes hard to track what was recorded, on what machine and when. This patch provides a way to solve this by extending the perf.data file with basic information about the host machine. To add those extensions, we leverage the feature bits capabilities of the perf.data format. The change is backward compatible with existing perf.data files. We define the following useful new extensions: - HEADER_HOSTNAME: the hostname - HEADER_OSRELEASE: the kernel release number - HEADER_ARCH: the hw architecture - HEADER_CPUDESC: generic CPU description - HEADER_NRCPUS: number of online/avail cpus - HEADER_CMDLINE: perf command line - HEADER_VERSION: perf version - HEADER_TOPOLOGY: cpu topology - HEADER_EVENT_DESC: full event description (attrs) - HEADER_CPUID: easy-to-parse low level CPU identication The small granularity for the entries is to make it easier to extend without breaking backward compatiblity. Many entries are provided as ASCII strings. Perf report/script have been modified to print the basic information as easy-to-parse ASCII strings. Extended information about CPU and NUMA topology may be requested with the -I option. Thanks to David Ahern for reviewing and testing the many versions of this patch. $ perf report --stdio # ======== # captured on : Mon Sep 26 15:22:14 2011 # hostname : quad # os release : 3.1.0-rc4-tip # perf version : 3.1.0-rc4 # arch : x86_64 # nrcpus online : 4 # nrcpus avail : 4 # cpudesc : Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz # cpuid : GenuineIntel,6,15,11 # total memory : 8105360 kB # cmdline : /home/eranian/perfmon/official/tip/build/tools/perf/perf record date # event : name = cycles, type = 0, config = 0x0, config1 = 0x0, config2 = 0x0, excl_usr = 0, excl_kern = 0, id = { 29, 30, 31, # HEADER_CPU_TOPOLOGY info available, use -I to display # HEADER_NUMA_TOPOLOGY info available, use -I to display # ======== # ... $ perf report --stdio -I # ======== # captured on : Mon Sep 26 15:22:14 2011 # hostname : quad # os release : 3.1.0-rc4-tip # perf version : 3.1.0-rc4 # arch : x86_64 # nrcpus online : 4 # nrcpus avail : 4 # cpudesc : Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz # cpuid : GenuineIntel,6,15,11 # total memory : 8105360 kB # cmdline : /home/eranian/perfmon/official/tip/build/tools/perf/perf record date # event : name = cycles, type = 0, config = 0x0, config1 = 0x0, config2 = 0x0, excl_usr = 0, excl_kern = 0, id = { 29, 30, 31, # sibling cores : 0-3 # sibling threads : 0 # sibling threads : 1 # sibling threads : 2 # sibling threads : 3 # node0 meminfo : total = 8320608 kB, free = 7571024 kB # node0 cpu list : 0-3 # ======== # ... Reviewed-by: David Ahern <dsahern@gmail.com> Tested-by: David Ahern <dsahern@gmail.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> Cc: Andi Kleen <ak@linux.intel.com> Link: http://lkml.kernel.org/r/20110930134040.GA5575@quad Signed-off-by: Stephane Eranian <eranian@google.com> [ committer notes: Use --show-info in the tools as was in the docs, rename perf_header_fprintf_info to perf_file_section__fprintf_info, fixup conflict with f69b64f7 "perf: Support setting the disassembler style" ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-09-30 13:40:40 +00:00
"Display extended information about perf.data file"),
OPT_BOOLEAN(0, "source", &symbol_conf.annotate_src,
"Interleave source code with assembly code (default)"),
OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw,
"Display raw encoding of assembly instructions (default)"),
OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
"Specify disassembler style (e.g. -M intel for intel syntax)"),
OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
"Show a column with the sum of periods"),
2013-01-22 09:09:45 +00:00
OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
"Show event group information together"),
OPT_CALLBACK_NOOPT('b', "branch-stack", &branch_mode, "",
"use branch records for histogram filling", parse_branch_mode),
OPT_STRING(0, "objdump", &objdump_path, "path",
"objdump binary to use for disassembly and annotations"),
OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
"Disable symbol demangling"),
OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"),
OPT_CALLBACK(0, "percent-limit", &report, "percent",
"Don't show entries under that percent", parse_percent_limit),
OPT_END()
};
struct perf_data_file file = {
.mode = PERF_DATA_MODE_READ,
};
perf_config(report__config, &report);
argc = parse_options(argc, argv, options, report_usage, 0);
if (report.use_stdio)
use_browser = 0;
else if (report.use_tui)
use_browser = 1;
else if (report.use_gtk)
use_browser = 2;
if (report.inverted_callchain)
callchain_param.order = ORDER_CALLER;
if (!input_name || !strlen(input_name)) {
if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode))
input_name = "-";
else
input_name = "perf.data";
}
file.path = input_name;
file.force = report.force;
repeat:
session = perf_session__new(&file, false, &report.tool);
if (session == NULL)
return -ENOMEM;
report.session = session;
has_br_stack = perf_header__has_feat(&session->header,
HEADER_BRANCH_STACK);
if (branch_mode == -1 && has_br_stack)
sort__mode = SORT_MODE__BRANCH;
/* sort__mode could be NORMAL if --no-branch-stack */
if (sort__mode == SORT_MODE__BRANCH) {
perf report: Add support for taken branch sampling This patch adds support for taken branch sampling, i.e, the PERF_SAMPLE_BRANCH_STACK feature to perf report. In other words, to display histograms based on taken branches rather than executed instructions addresses. The new option is called -b and it takes no argument. To generate meaningful output, the perf.data must have been obtained using perf record -b xxx ... where xxx is a branch filter option. The output shows symbols, modules, sorted by 'who branches where' the most often. The percentages reported in the first column refer to the total number of branches captured and not the usual number of samples. Here is a quick example. Here branchy is simple test program which looks as follows: void f2(void) {} void f3(void) {} void f1(unsigned long n) { if (n & 1UL) f2(); else f3(); } int main(void) { unsigned long i; for (i=0; i < N; i++) f1(i); return 0; } Here is the output captured on Nehalem, if we are only interested in user level function calls. $ perf record -b any_call,u -e cycles:u branchy $ perf report -b --sort=symbol 52.34% [.] main [.] f1 24.04% [.] f1 [.] f3 23.60% [.] f1 [.] f2 0.01% [k] _IO_new_file_xsputn [k] _IO_file_overflow 0.01% [k] _IO_vfprintf_internal [k] _IO_new_file_xsputn 0.01% [k] _IO_vfprintf_internal [k] strchrnul 0.01% [k] __printf [k] _IO_vfprintf_internal 0.01% [k] main [k] __printf About half (52%) of the call branches captured are from main() -> f1(). The second half (24%+23%) is split in two equal shares between f1() -> f2(), f1() ->f3(). The output is as expected given the code. It should be noted, that using -b in perf record does not eliminate information in the perf.data file. Consequently, a typical profile can also be obtained by perf report by simply not using its -b option. It is possible to sort on branch related columns: - dso_from, symbol_from - dso_to, symbol_to - mispredict Signed-off-by: Roberto Agostino Vitillo <ravitillo@lbl.gov> Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-14-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-09 22:21:03 +00:00
/*
* if no sort_order is provided, then specify
* branch-mode specific order
perf report: Add support for taken branch sampling This patch adds support for taken branch sampling, i.e, the PERF_SAMPLE_BRANCH_STACK feature to perf report. In other words, to display histograms based on taken branches rather than executed instructions addresses. The new option is called -b and it takes no argument. To generate meaningful output, the perf.data must have been obtained using perf record -b xxx ... where xxx is a branch filter option. The output shows symbols, modules, sorted by 'who branches where' the most often. The percentages reported in the first column refer to the total number of branches captured and not the usual number of samples. Here is a quick example. Here branchy is simple test program which looks as follows: void f2(void) {} void f3(void) {} void f1(unsigned long n) { if (n & 1UL) f2(); else f3(); } int main(void) { unsigned long i; for (i=0; i < N; i++) f1(i); return 0; } Here is the output captured on Nehalem, if we are only interested in user level function calls. $ perf record -b any_call,u -e cycles:u branchy $ perf report -b --sort=symbol 52.34% [.] main [.] f1 24.04% [.] f1 [.] f3 23.60% [.] f1 [.] f2 0.01% [k] _IO_new_file_xsputn [k] _IO_file_overflow 0.01% [k] _IO_vfprintf_internal [k] _IO_new_file_xsputn 0.01% [k] _IO_vfprintf_internal [k] strchrnul 0.01% [k] __printf [k] _IO_vfprintf_internal 0.01% [k] main [k] __printf About half (52%) of the call branches captured are from main() -> f1(). The second half (24%+23%) is split in two equal shares between f1() -> f2(), f1() ->f3(). The output is as expected given the code. It should be noted, that using -b in perf record does not eliminate information in the perf.data file. Consequently, a typical profile can also be obtained by perf report by simply not using its -b option. It is possible to sort on branch related columns: - dso_from, symbol_from - dso_to, symbol_to - mispredict Signed-off-by: Roberto Agostino Vitillo <ravitillo@lbl.gov> Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-14-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-09 22:21:03 +00:00
*/
if (sort_order == default_sort_order)
sort_order = "comm,dso_from,symbol_from,"
"dso_to,symbol_to";
}
if (report.mem_mode) {
if (sort__mode == SORT_MODE__BRANCH) {
pr_err("branch and mem mode incompatible\n");
goto error;
}
sort__mode = SORT_MODE__MEMORY;
/*
* if no sort_order is provided, then specify
* branch-mode specific order
*/
if (sort_order == default_sort_order)
sort_order = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked";
}
if (setup_sorting() < 0) {
parse_options_usage(report_usage, options, "s", 1);
goto error;
}
if (parent_pattern != default_parent_pattern) {
if (sort_dimension__add("parent") < 0)
goto error;
}
/* Force tty output for header output. */
if (report.header || report.header_only)
use_browser = 0;
if (strcmp(input_name, "-") != 0)
setup_browser(true);
else {
use_browser = 0;
perf_hpp__init();
}
if (report.header || report.header_only) {
perf_session__fprintf_info(session, stdout,
report.show_full_info);
if (report.header_only)
return 0;
} else if (use_browser == 0) {
fputs("# To display the perf.data header info, please use --header/--header-only options.\n#\n",
stdout);
}
/*
* Only in the TUI browser we are doing integrated annotation,
* so don't allocate extra space that won't be used in the stdio
* implementation.
*/
if (use_browser == 1 && sort__has_sym) {
symbol_conf.priv_size = sizeof(struct annotation);
machines__set_symbol_filter(&session->machines,
symbol__annotate_init);
/*
* For searching by name on the "Browse map details".
* providing it only in verbose mode not to bloat too
* much struct symbol.
*/
if (verbose) {
/*
* XXX: Need to provide a less kludgy way to ask for
* more space per symbol, the u32 is for the index on
* the ui browser.
* See symbol__browser_index.
*/
symbol_conf.priv_size += sizeof(u32);
symbol_conf.sort_by_name = true;
}
}
if (symbol__init() < 0)
goto error;
if (argc) {
/*
* Special case: if there's an argument left then assume that
* it's a symbol filter:
*/
if (argc > 1)
usage_with_options(report_usage, options);
report.symbol_filter_str = argv[0];
}
sort__setup_elide(stdout);
ret = __cmd_report(&report);
if (ret == K_SWITCH_INPUT_DATA) {
perf_session__delete(session);
goto repeat;
} else
ret = 0;
error:
perf_session__delete(session);
return ret;
}