perf tools: Record total sampling time
Namhyung Kim
maintainerPATCH v2 1/3 perf tools: Record total sampling time
From: Namhyung Kim <[email protected]>
It's sometimes useful to see total sampling or elapsed time with normal performance result. To do that, record first and last sample time for each evsel and to display it in the header (--stdio only for now).
$ perf record -a sleep 1
$ perf report --stdio
...
# Samples: 4K of event 'cycles'
# Event count (approx.): 4087481688
# Total sampling time : 1.001260 (sec)
#
# Overhead Command Shared Object Symbol
# ........ ............ .......................... .......................
#
89.06% nautilus libgobject-2.0.so.0.3701.0 [.] 0x0000000000020bf0
1.79% kworker/1:0 [kernel.kallsyms] [k] generic_exec_single
1.75% swapper [kernel.kallsyms] [k] intel_idle
1.14% nautilus [unknown] [.] 0x0000003153f2ff61
0.69% kworker/0:1 [kernel.kallsyms] [k] generic_exec_single
0.67% nautilus ld-2.17.so [.] do_lookup_x--- tools/perf/builtin-report.c | 15 ++++++++++++++- tools/perf/util/evsel.h | 2 ++ tools/perf/util/hist.h | 1 + tools/perf/util/session.c | 7 +++++++ 4 files changed, 24 insertions(+), 1 deletion(-)
tools/perf/builtin-report.c +14 -1
@@ -456,6 +456,14 @@ static size_t hists__fprintf_nr_sample_events(struct perf_report *rep, ret +=fprintf (fp,"\n# Sort order : %s" , sort_order); }else ret +=fprintf (fp,"\n# Event count (approx.): %" PRIu64, nr_events); +if (rep->tool.ordered_samples) { +u64 total_time = hists->stats.total_time; +u64 sec = total_time /NSEC_PER_SEC ; +u64 usec = (total_time - sec *NSEC_PER_SEC ) /NSEC_PER_USEC ; + + ret +=fprintf (fp,"\n# Total sampling time : " +"%" PRIu64".%06" PRIu64" (sec)" , sec, usec); + }return ret +fprintf (fp,"\n#\n" ); }
@@ -565,8 +573,13 @@ static int __cmd_report(struct perf_report *rep) } nr_samples =0 ; -list_for_each_entry (pos, &session->evlist->entries, node) +list_for_each_entry (pos, &session->evlist->entries, node) { nr_samples += pos->hists.nr_entries; +if (rep->tool.ordered_samples) { + pos->hists.stats.total_time = pos->last_timestamp - + pos->first_timestamp; + } + }ui_progress__init (&prog, nr_samples,"Merging related events..." );
tools/perf/util/evsel.h +2 -0
@@ -67,6 +67,8 @@ struct perf_evsel {int idx;u32 ids;struct hists hists; +u64 first_timestamp; +u64 last_timestamp;char *name;double scale;const char *unit;
tools/perf/util/hist.h +1 -0
@@ -28,6 +28,7 @@ struct symbol;*/ struct events_stats {u64 total_period; +u64 total_time;u64 total_lost;u64 total_invalid_chains;u32 nr_events[PERF_RECORD_HEADER_MAX ];
tools/perf/util/session.c +7 -0
@@ -925,6 +925,13 @@ perf_session__deliver_sample(struct perf_session *session,u64 sample_type = evsel->attr.sample_type;u64 read_format = evsel->attr.read_format; +if (tool->ordered_samples) { +if (evsel->first_timestamp ==0 ) + evsel->first_timestamp = sample->time; + + evsel->last_timestamp = sample->time; + } +/* Standard sample delievery. */ if (!(sample_type &PERF_SAMPLE_READ ))return tool->sample (tool, event, sample, evsel, machine);
Signature · 1 line
1.7.11.7
Namhyung Kim
maintainerPATCH v2 2/3 perf tools: Record sampling time for each entry
From: Namhyung Kim <[email protected]>
Sometimes users might want see a relation between value and time of a sample. And the time itself is a very important information to have. As the sample->period value is a diff of counter values between samples it might make sense to add time-diff between samples into a hist entry.
To do that, calculate elapsed time for each sample and record it. The elapsed time is the diff between current sample->time and previous sample->time which was saved for each evsel.
Maybe we can use PERF_SAMPLE_READ for the precise result.
--- tools/perf/builtin-annotate.c | 2 +- tools/perf/builtin-diff.c | 2 +- tools/perf/builtin-report.c | 9 +++++---- tools/perf/builtin-top.c | 2 +- tools/perf/tests/hists_link.c | 4 ++-- tools/perf/util/evsel.h | 1 + tools/perf/util/hist.c | 10 ++++++++-- tools/perf/util/hist.h | 2 +- tools/perf/util/session.c | 42 ++++++++++++++++++++++++++++++++++++++++++ tools/perf/util/sort.h | 1 + 10 files changed, 63 insertions(+), 12 deletions(-)
tools/perf/builtin-annotate.c +1 -1
@@ -65,7 +65,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,return 0 ; } - he =__hists__add_entry (&evsel->hists, al,NULL ,NULL ,NULL ,1 ,1 ,0 ); + he =__hists__add_entry (&evsel->hists, al,NULL ,NULL ,NULL ,1 ,0 ,1 ,0 );if (he ==NULL )return -ENOMEM ;
tools/perf/builtin-diff.c +1 -1
@@ -307,7 +307,7 @@ static int hists__add_entry(struct hists *hists, struct addr_location *al, u64 period, u64 weight, u64 transaction) { - if (__hists__add_entry(hists, al, NULL, NULL, NULL, period, weight, + if (__hists__add_entry(hists, al, NULL, NULL, NULL, period, 0, weight, transaction) != NULL) return 0; return -ENOMEM;
tools/perf/builtin-report.c +5 -4
@@ -116,7 +116,7 @@ static int perf_report__add_mem_hist_entry(struct perf_tool *tool,* and the he_stat__add_period() function. */ he =__hists__add_entry (&evsel->hists, al, parent,NULL , mi, - cost, cost,0 ); + cost,0 , cost,0 );if (!he)return -ENOMEM ;
@@ -210,7 +210,7 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool,* 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 ); +1 ,0 ,1 ,0 );if (he) {struct annotation *notes; bx = he->branch_info;
@@ -272,8 +272,9 @@ static int perf_evsel__add_hist_entry(struct perf_tool *tool, } he =__hists__add_entry (&evsel->hists, al, parent,NULL ,NULL , - sample->period, sample->weight, - sample->transaction); + sample->period, + tool->ordered_samples ? sample->read.time_enabled :0 , + sample->weight, sample->transaction);if (he ==NULL )return -ENOMEM ;
tools/perf/builtin-top.c +1 -1
@@ -247,7 +247,7 @@ static struct hist_entry *perf_evsel__add_hist_entry(struct perf_evsel *evsel,pthread_mutex_lock (&evsel->hists.lock); he =__hists__add_entry (&evsel->hists, al,NULL ,NULL ,NULL , - sample->period, sample->weight, + sample->period,0 , sample->weight, sample->transaction);pthread_mutex_unlock (&evsel->hists.lock);if (he ==NULL )
tools/perf/tests/hists_link.c +2 -2
@@ -223,7 +223,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) goto out; he =__hists__add_entry (&evsel->hists, &al,NULL , -NULL ,NULL ,1 ,1 ,0 ); +NULL ,NULL ,1 ,0 ,1 ,0 );if (he ==NULL ) goto out;
@@ -246,7 +246,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) goto out; he =__hists__add_entry (&evsel->hists, &al,NULL , -NULL ,NULL ,1 ,1 ,0 ); +NULL ,NULL ,1 ,0 ,1 ,0 );if (he ==NULL ) goto out;
tools/perf/util/evsel.h +1 -0
@@ -69,6 +69,7 @@ struct perf_evsel {struct hists hists;u64 first_timestamp;u64 last_timestamp; +u64 *prev_timestamps;char *name;double scale;const char *unit;
tools/perf/util/hist.c +8 -2
@@ -204,11 +204,12 @@ static void hist_entry__add_cpumode_period(struct hist_entry *he, }static void he_stat__add_period (struct he_stat *he_stat,u64 period, -u64 weight) +u64 sample_time,u64 weight) { he_stat->period += period; he_stat->weight += weight; + he_stat->time += sample_time; he_stat->nr_events +=1 ; }
@@ -221,10 +222,12 @@ static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src) dest->period_guest_us += src->period_guest_us; dest->nr_events += src->nr_events; dest->weight += src->weight; + dest->time += src->time; }static void hist_entry__decay (struct hist_entry *he) { + he->stat.time = (he->stat.time *7 ) /8 ; he->stat.period = (he->stat.period *7 ) /8 ; he->stat.nr_events = (he->stat.nr_events *7 ) /8 ;/* XXX need decay for weight too? */
@@ -366,6 +369,7 @@ static struct hist_entry *add_hist_entry(struct hists *hists,if (!cmp) {he_stat__add_period (&he->stat, entry->stat.period, + entry->stat.time, entry->stat.weight);/*
@@ -411,7 +415,8 @@ struct hist_entry *__hists__add_entry(struct hists *hists, struct symbol *sym_parent, struct branch_info *bi, struct mem_info *mi, - u64 period, u64 weight, u64 transaction) + u64 period, u64 sample_time, + u64 weight, u64 transaction) { struct hist_entry entry = { .thread = al->thread,
@@ -427,6 +432,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists, .nr_events = 1, .period = period, .weight = weight, + .time = sample_time, }, .parent = sym_parent, .filtered = symbol__parent_filter(sym_parent),
tools/perf/util/hist.h +1 -1
@@ -89,7 +89,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,struct addr_location *al, struct symbol *parent, struct branch_info *bi, - struct mem_info *mi, u64 period, + struct mem_info *mi, u64 period, u64 time, u64 weight, u64 transaction);int64_t hist_entry__cmp (struct hist_entry *left,struct hist_entry *right);int64_t hist_entry__collapse (struct hist_entry *left,struct hist_entry *right);
tools/perf/util/session.c +42 -0
48 lines not on this page · raw message
tools/perf/util/sort.h +1 -0
@@ -51,6 +51,7 @@ struct he_stat {u64 period_guest_sys;u64 period_guest_us;u64 weight; +u64 time;u32 nr_events; };
Signature · 1 line
1.7.11.7
Re: [PATCH v2 2/3] perf tools: Record sampling time for each entry
tools/perf/util/evsel.h struct perf_evsel { · line 72
Quoted 9 lines · Namhyung Kim
tools/perf/util/evsel.h +1
-0@@ -69,6 +69,7 @@ struct perf_evsel {struct hists hists;u64 first_timestamp;u64 last_timestamp; +u64 *prev_timestamps;
Why plural and why dynamically allocated? The allocation only does a single u64, not an array.
David
Namhyung Kim
maintainerRe: [PATCH v2 2/3] perf tools: Record sampling time for each entry
Hi David,
Quoted 14 lines · David Ahern
tools/perf/util/evsel.h struct perf_evsel { · line 72
Quoted 9 lines · Namhyung Kim
tools/perf/util/evsel.h +1
-0@@ -69,6 +69,7 @@ struct perf_evsel {struct hists hists;u64 first_timestamp;u64 last_timestamp; +u64 *prev_timestamps;Why plural and why dynamically allocated? The allocation only does a single u64, not an array.
Nope, it'll be an array if the session was a system-wide one, so plural.
But, I think the current code won't work well if there're multiple unrelated processes recorded - e.g. perf record -u id -u - since it'll intermix all timestamps between the samples regardless of process.
Hmm.. I think there's not much thing we can do for this without help from kernel side (PERF_SAMPLE_READ?). So I'll just drop this unless I can come up with a better idea. But the patch 1/3 still makes some sense and worth to merge by itself IMHO.
What do you think?
Thanks,
Namhyung
Namhyung Kim
maintainerPATCH v2 3/3 perf report: Add --event-time option
In reply to Namhyung KimFrom: Namhyung Kim <[email protected]>
The --event-time option is for displaying elapsed sampling time information for each entry.
$ perf record -- perf bench sched messaging
$ perf report --stdio --event-time
...
# Samples: 10K of event 'cycles'
# Event count (approx.): 5118793536
# Total sampling time : 0.184277 (sec)
#
# Overhead Time Command Shared Object Symbol
# ........ .......... ............... ................. ...........................
#
7.26% 0.007413 sched-messaging [unknown] [.] 0x0000003153e7a6e7
4.79% 0.006088 sched-messaging [kernel.kallsyms] [k] avc_has_perm_flags
4.38% 0.004809 sched-messaging [kernel.kallsyms] [k] copy_user_generic_string
3.81% 0.005457 sched-messaging [kernel.kallsyms] [k] _raw_spin_lock
2.92% 0.002745 sched-messaging [kernel.kallsyms] [k] _raw_spin_lock_irqsave
2.72% 0.002896 sched-messaging [kernel.kallsyms] [k] unix_stream_recvmsg
2.55% 0.003745 sched-messaging [kernel.kallsyms] [k] __slab_free
2.45% 0.002807 sched-messaging [kernel.kallsyms] [k] page_fault
2.08% 0.002258 sched-messaging [kernel.kallsyms] [k] sock_has_perm--- tools/perf/Documentation/perf-report.txt | 6 +++ tools/perf/builtin-report.c | 2 + tools/perf/ui/hist.c | 68 ++++++++++++++++++++++++++------ tools/perf/util/hist.h | 1 + tools/perf/util/symbol.h | 3 +- 5 files changed, 68 insertions(+), 12 deletions(-)
tools/perf/Documentation/perf-report.txt +6 -0
@@ -237,6 +237,12 @@ OPTIONS Do not show entries which have an overhead under that percent. (Default: 0). +--event-time:: + Show a column with elapsed sample times. It could be useful when you + want to see a relation between time and period of samples. The elapsed + time is a sum of time-diff between two adjacent samples of a event as + sample period is a diff of counter values between the two samples. + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-annotate[1]
tools/perf/builtin-report.c +2 -0
@@ -898,6 +898,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)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_BOOLEAN (0 ,"event-time" , &symbol_conf.show_event_time, +"Show a column with the elapsed time" ),OPT_END () }; struct perf_data_file file = {
tools/perf/ui/hist.c +57 -11
152 lines not on this page · raw message
tools/perf/util/hist.h +1 -0
@@ -162,6 +162,7 @@ enum {PERF_HPP__OVERHEAD_GUEST_US ,PERF_HPP__SAMPLES ,PERF_HPP__PERIOD , +PERF_HPP__TIME , PERF_HPP__MAX_INDEX };
tools/perf/util/symbol.h +2 -1
@@ -99,7 +99,8 @@ struct symbol_conf { annotate_asm_raw, annotate_src, event_group, - demangle; + demangle, + show_event_time;const char *vmlinux_name, *kallsyms_name, *source_prefix,
Signature · 1 line
1.7.11.7