perf report/script: Support percent and multiple range in --time option
v2 cover perf report/script: Support percent and multiple range in --time option
v2:
---
1. This patch creates a new header feature type HEADER_SAMPLE_TIME and related ops. Save the first sample time and the last sample time to the feature section in perf file header.
2. Add checking for last element in time range.
For example, select the first and second 10% time slices. perf report --time 10%/1,10%/2
Note that now it includes the last element in [10%, 20%] but it doesn't include the last element in [0, 10%). It's to avoid the overlap.
Following patches are changed:
perf header: Record first sample time and last sample time in perf file header perf record: Get the first sample time and last sample time
perf util: Create function to perform multiple time range checking
v1: initial post
----------------
Current perf report/script/... have a --time option to limit the time range of output. But it only supports the absolute time.
The patch series extend this option to let it support percent of time and support the multiple time ranges.
For example:
1. Select the second 10% time slice
perf report --time 10%/2
2. Select from 0% to 10% time slice
perf report --time 0%-10%
It also support the multiple time ranges.
3. Select the first and second 10% time slices
perf report --time 10%/1,10%/2
4. Select from 0% to 10% and 30% to 40% slices
perf report --time 0%-10%,30%-40%
Jin Yao (6):
perf header: Record first sample time and last sample time in perf
file header
perf record: Get the first sample time and last sample time perf util: Create function to parse time percent
perf util: Create function to perform multiple time range checking perf report: support time percent and multiple time ranges perf script: support time percent and multiple time ranges
tools/perf/Documentation/perf-report.txt | 16 ++ tools/perf/Documentation/perf-script.txt | 16 ++ tools/perf/Documentation/perf.data-file-format.txt | 4 + tools/perf/builtin-record.c | 17 ++ tools/perf/builtin-report.c | 24 ++- tools/perf/builtin-script.c | 21 +- tools/perf/util/evlist.h | 2 + tools/perf/util/header.c | 49 +++++ tools/perf/util/header.h | 1 + tools/perf/util/session.h | 2 + tools/perf/util/time-utils.c | 225 +++++++++++++++++++-- tools/perf/util/time-utils.h | 6 + 12 files changed, 366 insertions(+), 17 deletions(-)
Signature · 1 line
2.7.4
PATCH v2 1/6 perf header: Record first sample time and last sample time in perf file header
perf report/script/... have a --time option to limit the time range of output. That's very useful to slice large traces, e.g. when processing the output of perf script for some analysis.
But right now --time only supports absolute time. Also there is no fast way to get the start/end times of a given trace except for looking at it. This makes it hard to e.g. only decode the first half of the trace, which is useful for parallelization of scripts
Another problem is that perf records are variable size and there is no synchronization mechanism. So the only way to find the last sample reliably would be to walk all samples. But we want to avoid that in perf report/... because it is already quite expensive. That is why storing the first sample time and last sample time in perf record is better.
This patch creates a new header feature type HEADER_SAMPLE_TIME and related ops. Save the first sample time and the last sample time to the feature section in perf file header.
--- tools/perf/Documentation/perf.data-file-format.txt | 4 ++ tools/perf/util/evlist.h | 2 + tools/perf/util/header.c | 49 ++++++++++++++++++++++ tools/perf/util/header.h | 1 + tools/perf/util/session.h | 2 + 5 files changed, 58 insertions(+)
tools/perf/Documentation/perf.data-file-format.txt +4 -0
@@ -238,6 +238,10 @@ struct auxtrace_index { struct auxtrace_index_entry entries[PERF_AUXTRACE_INDEX_ENTRY_COUNT]; }; + HEADER_SAMPLE_TIME = 21, + +Two uint64_t for the time of first sample and the time of last sample. + other bits are reserved and should ignored for now HEADER_FEAT_BITS = 256,
tools/perf/util/evlist.h +2 -0
@@ -99,6 +99,8 @@ struct perf_evlist {struct perf_evsel *selected;struct events_stats stats;struct perf_env *env; +u64 first_sample_time; +u64 last_sample_time; };struct perf_evsel_str_handler {
tools/perf/util/header.c +49 -0
73 lines not on this page · raw message
tools/perf/util/header.h +1 -0
@@ -33,6 +33,7 @@ enum {HEADER_AUXTRACE ,HEADER_STAT ,HEADER_CACHE , +HEADER_SAMPLE_TIME ,HEADER_LAST_FEATURE , HEADER_FEAT_BITS = 256, };
tools/perf/util/session.h +2 -0
@@ -34,6 +34,8 @@ struct perf_session {struct ordered_events ordered_events;struct perf_data_file *file;struct perf_tool *tool; +u64 first_sample_time; +u64 last_sample_time; };struct perf_tool ;
Signature · 1 line
2.7.4
PATCH v2 2/6 perf record: Get the first sample time and last sample time
In reply to Jin YaoIn perf record, it's walked on all samples yet. So it's very easy to get the first/last samples and save the time to perf file header via the function write_sample_time().
In later, perf report/script will fetch the time from perf file header.
--- tools/perf/builtin-record.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+)
tools/perf/builtin-record.c +17 -0
@@ -80,6 +80,8 @@ struct record {bool timestamp_filename;struct switch_output switch_output;unsigned long long samples; +u64 first_sample_time; +u64 last_sample_time; };static volatile int auxtrace_record__snapshot_started;
@@ -488,6 +490,11 @@ static int process_sample_event(struct perf_tool *tool, rec->samples++; +if (rec->first_sample_time ==0 ) + rec->first_sample_time = sample->time; + + rec->last_sample_time = sample->time; +return build_id__mark_dso_hit (tool, event, sample, evsel, machine); }
@@ -637,6 +644,14 @@ static void record__init_features(struct record *rec)perf_header__clear_feat (&session->header,HEADER_STAT ); } +static void update_sample_time (struct record *rec) +{ +struct perf_evlist *evlist = rec->evlist; + + evlist->first_sample_time = rec->first_sample_time; + evlist->last_sample_time = rec->last_sample_time; +} +static void record__finish_output (struct record *rec) {
@@ -655,6 +670,8 @@ record__finish_output(struct record *rec)if (rec->buildid_all)dsos__hit_all (rec->session); } + +update_sample_time (rec);perf_session__write_header (rec->session, rec->evlist, fd, true);return ;
Signature · 1 line
2.7.4
Re: [PATCH v2 2/6] perf record: Get the first sample time and last sample time
Quoted 16 lines · Jin Yao
In perf record, it's walked on all samples yet. So it's very easy to get the first/last samples and save the time to perf file header via the function
write_sample_time().In later, perf report/script will fetch the time from perf file header.
Signed-off-by Jin Yao <[email protected]>--- tools/perf/builtin-record.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+)tools/perf/builtin-record.c +0
-0
tools/perf/builtin-record.c struct record { · line 84
Quoted 5 lines
tools/perf/builtin-record.c +2
-0@@ -80,6 +80,8 @@ struct record {bool timestamp_filename;struct switch_output switch_output;unsigned long long samples; +u64 first_sample_time; +u64 last_sample_time;
so we have those 2 u64 already in 3 structs: evlist, session and now record
can't we do that with just in one? I'd think all of them should be available and reachable everywhere
jirka
Re: [PATCH v2 2/6] perf record: Get the first sample time and last sample time
Quoted 25 lines · Jiri Olsa
Quoted 16 lines · Jin Yao
In perf record, it's walked on all samples yet. So it's very easy to get the first/last samples and save the time to perf file header via the function
write_sample_time().In later, perf report/script will fetch the time from perf file header.
Signed-off-by Jin Yao <[email protected]>--- tools/perf/builtin-record.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+)tools/perf/builtin-record.c +0
-0tools/perf/builtin-record.c struct record { · line 84
Quoted 5 lines
tools/perf/builtin-record.c +2
-0@@ -80,6 +80,8 @@ struct record {bool timestamp_filename;struct switch_output switch_output;unsigned long long samples; +u64 first_sample_time; +u64 last_sample_time;so we have those 2 u64 already in 3 structs: evlist, session and now record
Quoted 5 lines
can't we do that with just in one? I'd think all of them should be available and reachable everywhere
jirka
Thanks!
Yes, you are right. It looks we only need to define them in evlist.
If no other comments, I will prepare v3 to fix this.
Thanks
Jin Yao
PATCH v2 3/6 perf util: Create function to parse time percent
In reply to Jin YaoCurrent perf report/script/... have a --time option to limit the time range of output. But right now it only supports absolute time.
For easy using, now it can support a percent of time usage.
For example:
1. Select the second 10% time slice
perf report --time 10%/2
2. Select from 0% to 10% time slice
perf report --time 0%-10%
It also support the multiple time ranges.
3. Select the first and second 10% time slices
perf report --time 10%/1,10%/2
4. Select from 0% to 10% and 30% to 40% slices
perf report --time 0%-10%,30%-40%
--- tools/perf/util/time-utils.c | 203 ++++++++++++++++++++++++++++++++++++++++--- tools/perf/util/time-utils.h | 3 + 2 files changed, 194 insertions(+), 12 deletions(-)
tools/perf/util/time-utils.c +191 -12
@@ -5,6 +5,7 @@#include <time.h> #include <errno.h> #include <inttypes.h> +#include <math.h> #include "perf.h" #include "debug.h"
@@ -59,11 +60,10 @@ static int parse_timestr_sec_nsec(struct perf_time_interval *ptime,return 0 ; } -int perf_time__parse_str (struct perf_time_interval *ptime,const char *ostr) +static int split_start_end (char **start,char **end,const char *ostr,char ch) {char *start_str, *end_str;char *d, *str; -int rc =0 ;if (ostr ==NULL || *ostr =='\0' )return 0 ;
@@ -73,25 +73,35 @@ int perf_time__parse_str(struct perf_time_interval *ptime, const char *ostr)if (str ==NULL )return -ENOMEM ; - ptime->start =0 ; - ptime->end =0 ; - -/* str has the format: <start>,<stop> -* variations: <start>, -* ,<stop> -* , -*/ start_str = str; - d =strchr (start_str,',' ); + d =strchr (start_str, ch);if (d) { *d ='\0' ; ++d; } end_str = d; + *start = start_str; + *end = end_str; + +return 0 ; +} + +int perf_time__parse_str (struct perf_time_interval *ptime,const char *ostr) +{ +char *start_str =NULL , *end_str; +int rc; + + rc =split_start_end (&start_str, &end_str, ostr,',' ); +if (rc || !start_str) +return rc; + + ptime->start =0 ; + ptime->end =0 ; + rc =parse_timestr_sec_nsec (ptime, start_str, end_str); -free (str); +free (start_str);/* make sure end time is after start time if it was given */ if (rc ==0 && ptime->end && ptime->end < ptime->start)
@@ -103,6 +113,175 @@ int perf_time__parse_str(struct perf_time_interval *ptime, const char *ostr)return rc; } +static int parse_percent (double *pcnt,char *str) +{ +char *c; + + c =strchr (str,'%' ); +if (c) + *c ='\0' ; +else +return -1 ; + + *pcnt =atof (str) /100.0 ; + +return 0 ; +} + +static int percent_slash_split (char *str,struct perf_time_interval *ptime, +u64 start,u64 end) +{ +char *p; +double pcnt, start_pcnt, end_pcnt; +u64 total = end - start; +int i; + +/* +* Example: +* 10%/2: select the second 10% slice and the third 10% slice +*/ + +/* We can modify this string since the original one is copied */ + p =strchr (str,'/' ); +if (!p) +return -1 ; + + *p ='\0' ; +if (parse_percent (&pcnt, str) <0 ) +return -1 ; + + p++; + i =atoi (p); + +if (pcnt <=0.0 ) +return -1 ; + + start_pcnt = pcnt * (i -1 ); + end_pcnt = pcnt * i; + +if (start_pcnt <0.0 || start_pcnt >1.0 || + end_pcnt <0.0 || end_pcnt >1.0 ) { +return -1 ; + } + + ptime->start = start +round (start_pcnt * total); + ptime->end = start +round (end_pcnt * total); + +return 0 ; +} + +static int percent_dash_split (char *str,struct perf_time_interval *ptime, +u64 start,u64 end) +{ +char *start_str =NULL , *end_str; +double start_pcnt, end_pcnt; +u64 total = end - start; +int ret; + +/* +* Example: 0%-10% +*/ + + ret =split_start_end (&start_str, &end_str, str,'-' ); +if (ret || !start_str) +return ret; + +if ((parse_percent (&start_pcnt, start_str) !=0 ) || + (parse_percent (&end_pcnt, end_str) !=0 )) { +free (start_str); +return -1 ; + } + +free (start_str); + +if (start_pcnt <0.0 || start_pcnt >1.0 || + end_pcnt <0.0 || end_pcnt >1.0 || + start_pcnt > end_pcnt) { +return -1 ; + } + + ptime->start = start +round (start_pcnt * total); + ptime->end = start +round (end_pcnt * total); + +return 0 ; +} + +typedef int (*time_pecent_split )(char *,struct perf_time_interval *, +u64 start,u64 end); + +static int percent_comma_split (struct perf_time_interval *ptime_buf,int num, +const char *ostr,u64 start,u64 end, +time_pecent_split func) +{ +char *str, *p1, *p2; +int len, ret, i =0 ; + + str =strdup (ostr); +if (str ==NULL ) +return -ENOMEM ; + + len =strlen (str); + p1 = str; + +while (p1 < str + len) { +if (i >= num) { +free (str); +return -1 ; + } + + p2 =strchr (p1,',' ); +if (p2) + *p2 ='\0' ; + + ret = (func)(p1, &ptime_buf[i], start, end); +if (ret <0 ) { +free (str); +return -1 ; + } + +pr_debug ("start time %d: %" PRIu64", " , i, ptime_buf[i].start); +pr_debug ("end time %d: %" PRIu64"\n" , i, ptime_buf[i].end); + + i++; + +if (p2) + p1 = p2 +1 ; +else +break ; + } + +free (str); +return i; +} + +int perf_time__percent_parse_str (struct perf_time_interval *ptime_buf,int num, +const char *ostr,u64 start,u64 end) +{ +char *c; + +/* +* ostr example: +* 10%/2,10%/3: select the second 10% slice and the third 10% slice +* 0%-10%,30%-40%: multiple time range +*/ + +memset (ptime_buf,0 ,sizeof (*ptime_buf) * num); + + c =strchr (ostr,'/' ); +if (c) { +return percent_comma_split (ptime_buf, num, ostr, start, + end, percent_slash_split); + } + + c =strchr (ostr,'-' ); +if (c) { +return percent_comma_split (ptime_buf, num, ostr, start, + end, percent_dash_split); + } + +return -1 ; +} +bool perf_time__skip_sample (struct perf_time_interval *ptime,u64 timestamp) {/* if time is not set don't drop sample */
tools/perf/util/time-utils.h +3 -0
@@ -12,6 +12,9 @@ int parse_nsec_time(const char *str, u64 *ptime);int perf_time__parse_str (struct perf_time_interval *ptime,const char *ostr); +int perf_time__percent_parse_str (struct perf_time_interval *ptime_buf,int num, +const char *ostr,u64 start,u64 end); +bool perf_time__skip_sample (struct perf_time_interval *ptime,u64 timestamp);int timestamp__scnprintf_usec (u64 timestamp,char *buf,size_t sz);
Signature · 1 line
2.7.4
Re: [PATCH v2 3/6] perf util: Create function to parse time percent
On Tue, Sep 26, 2017 at 06:57:59PM +0800, Jin Yao wrote:
SNIP
Quoted 4 lines
tools/perf/util/time-utils.c +4
-0+ +if (p2) + p1 = p2 +1 ; +else
tools/perf/util/time-utils.c int perf_time__parse_str(struct perf_time_interval *ptime, const char *ostr) · line 259
Quoted 10 lines
tools/perf/util/time-utils.c +10
-0+break ; + } + +free (str); +return i; +} + +int perf_time__percent_parse_str (struct perf_time_interval *ptime_buf,int num, +const char *ostr,u64 start,u64 end) +{
this function is perfect for automated test ;-)
jirka
PATCH v2 4/6 perf util: Create function to perform multiple time range checking
In reply to Jin YaoPrevious patch supports the multiple time range.
For example, select the first and second 10% time slices. perf report --time 10%/1,10%/2
We need a function to check if a timestamp is in the ranges of [0, 10%) and [10%, 20%].
Note that it includes the last element in [10%, 20%] but it doesn't include the last element in [0, 10%). It's to avoid the overlap.
This patch implments a new function perf_time__ranges_skip_sample for this checking.
--- tools/perf/util/time-utils.c | 22 ++++++++++++++++++++++ tools/perf/util/time-utils.h | 3 +++ 2 files changed, 25 insertions(+)
tools/perf/util/time-utils.c +22 -0
@@ -297,6 +297,28 @@ bool perf_time__skip_sample(struct perf_time_interval *ptime, u64 timestamp)return false; } +bool perf_time__ranges_skip_sample (struct perf_time_interval *ptime_buf, +int num,u64 timestamp) +{ +struct perf_time_interval *ptime; +int i; + +if ((timestamp ==0 ) || (num ==0 )) +return false; + +for (i =0 ; i < num; i++) { + ptime = &ptime_buf[i]; + +if (timestamp >= ptime->start && + ((timestamp < ptime->end && i < num -1 ) || + (timestamp <= ptime->end && i == num -1 ))) { +break ; + } + } + +return (i == num) ? true : false; +} +int timestamp__scnprintf_usec (u64 timestamp,char *buf,size_t sz) {u64 sec = timestamp /NSEC_PER_SEC ;
tools/perf/util/time-utils.h +3 -0
@@ -17,6 +17,9 @@ int perf_time__percent_parse_str(struct perf_time_interval *ptime_buf, int num,bool perf_time__skip_sample (struct perf_time_interval *ptime,u64 timestamp); +bool perf_time__ranges_skip_sample (struct perf_time_interval *ptime_buf, +int num,u64 timestamp); +int timestamp__scnprintf_usec (u64 timestamp,char *buf,size_t sz);int fetch_current_timestamp (char *buf,size_t sz);
Signature · 1 line
2.7.4
PATCH v2 5/6 perf report: support time percent and multiple time ranges
In reply to Jin Yaoperf report has a --time option to limit the time range of output. It only supports absolute time.
Now this option is extended to support multiple time ranges and support the percent of time.
For example:
1. Select the first and second 10% time slices
perf report --time 10%/1,10%/2
2. Select from 0% to 10% and 30% to 40% slices
perf report --time 0%-10%,30%-40%
--- tools/perf/Documentation/perf-report.txt | 16 ++++++++++++++++ tools/perf/builtin-report.c | 24 ++++++++++++++++++++++-- 2 files changed, 38 insertions(+), 2 deletions(-)
tools/perf/Documentation/perf-report.txt +16 -0
@@ -402,6 +402,22 @@ OPTIONS stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. + Also support time percent with multipe time range. Time string is + 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. The maximum number of slices is 10. + + For example: + Select the second 10% time slice + perf report --time 10%/2 + + Select from 0% to 10% time slice + perf report --time 0%-10% + + Select the first and second 10% time slices + perf report --time 10%/1,10%/2 + + Select from 0% to 10% and 30% to 40% slices + perf report --time 0%-10%,30%-40% + --itrace:: Options for decoding instruction tracing data. The options are:
tools/perf/builtin-report.c +22 -2
@@ -51,6 +51,8 @@#include <sys/stat.h> #include <unistd.h> +#define PTIME_RANGE_MAX 10 +struct report {struct perf_tool tool;struct perf_session *session;
@@ -69,6 +71,8 @@ struct report {const char *symbol_filter_str;const char *time_str;struct perf_time_interval ptime; +struct perf_time_interval ptime_range[PTIME_RANGE_MAX ]; +int range_num;float min_percent;u64 nr_entries;u64 queue_size;
@@ -185,8 +189,11 @@ static int process_sample_event(struct perf_tool *tool, };int ret =0 ; -if (perf_time__skip_sample (&rep->ptime, sample->time)) +if (perf_time__skip_sample (&rep->ptime, sample->time) || +perf_time__ranges_skip_sample (rep->ptime_range, rep->range_num, + sample->time)) {return 0 ; + }if (machine__resolve (machine, &al, sample) <0 ) { pr_debug("problem processing %d event, skipping it.\n",
@@ -1074,7 +1081,20 @@ int cmd_report(int argc, const char **argv) goto error;if (perf_time__parse_str (&report.ptime, report.time_str) !=0 ) { -pr_err ("Invalid time string\n" ); + report.range_num =perf_time__percent_parse_str ( + report.ptime_range,PTIME_RANGE_MAX , + report.time_str, + session->first_sample_time, + session->last_sample_time); + +if (report.range_num <0 ) { +pr_err ("Invalid time string\n" ); +return -EINVAL ; + } + } + +if (report.range_num >0 &&perf_data_file__is_pipe (session->file)) { +pr_err ("Time percent range is not supported in pipe\n" );return -EINVAL ; }
Signature · 1 line
2.7.4
PATCH v2 6/6 perf script: support time percent and multiple time ranges
In reply to Jin Yaoperf script has a --time option to limit the time range of output. It only supports absolute time.
Now this option is extended to support multiple time ranges and support the percent of time.
For example:
1. Select the first and second 10% time slices
perf script --time 10%/1,10%/2
2. Select from 0% to 10% and 30% to 40% slices
perf script --time 0%-10%,30%-40%
--- tools/perf/Documentation/perf-script.txt | 16 ++++++++++++++++ tools/perf/builtin-script.c | 21 ++++++++++++++++++--- 2 files changed, 34 insertions(+), 3 deletions(-)
tools/perf/Documentation/perf-script.txt +16 -0
@@ -321,6 +321,22 @@ include::itrace.txt[] stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. + Also support time percent with multipe time range. Time string is + 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. The maximum number of slices is 10. + + For example: + Select the second 10% time slice + perf script --time 10%/2 + + Select from 0% to 10% time slice + perf script --time 0%-10% + + Select the first and second 10% time slices + perf script --time 10%/1,10%/2 + + Select from 0% to 10% and 30% to 40% slices + perf script --time 0%-10%,30%-40% + --max-blocks:: Set the maximum number of program blocks to print with brstackasm for each sample.
tools/perf/builtin-script.c +18 -3
@@ -1357,6 +1357,8 @@ static void print_sample_synth(struct perf_sample *sample, } } +#define PTIME_RANGE_MAX 10 +struct perf_script {struct perf_tool tool;struct perf_session *session;
@@ -1370,6 +1372,8 @@ struct perf_script {int name_width;const char *time_str;struct perf_time_interval ptime; +struct perf_time_interval ptime_range[PTIME_RANGE_MAX ]; +int range_num; };static int perf_evlist__max_name_len (struct perf_evlist *evlist)
@@ -1565,8 +1569,11 @@ static int process_sample_event(struct perf_tool *tool, struct perf_script *scr = container_of(tool, struct perf_script, tool);struct addr_location al; -if (perf_time__skip_sample (&scr->ptime, sample->time)) +if (perf_time__skip_sample (&scr->ptime, sample->time) || +perf_time__ranges_skip_sample (scr->ptime_range, scr->range_num, + sample->time)) {return 0 ; + }if (debug_mode) {if (sample->time < last_timestamp) {
@@ -3104,8 +3111,16 @@ int cmd_script(int argc, const char **argv)/* needs to be parsed after looking up reference time */ if (perf_time__parse_str (&script.ptime, script.time_str) !=0 ) { -pr_err ("Invalid time string\n" ); -return -EINVAL ; + script.range_num =perf_time__percent_parse_str ( + script.ptime_range,PTIME_RANGE_MAX , + script.time_str, + session->first_sample_time, + session->last_sample_time); + +if (script.range_num <0 ) { +pr_err ("Invalid time string\n" ); +return -EINVAL ; + } } err =__cmd_script (&script);
Signature · 1 line
2.7.4