Skip to contentSkip to conversation

perf report/script: Support percent and multiple range in --time option

PATCH Superseded Jin Yao 3 participants 13 messages Oct 3, 2017 – Oct 19, 2017 perf events

v4 of 7 Superseded Latest is v7 →

lore
Share & tools
lore

Jin Yao

author
#0 lore raw

v4 cover perf report/script: Support percent and multiple range in --time option

v4:
---
1. Use perf script time style for timestamp printing. Also add with the printing of sample duration. For example:

   perf report --header

time of first sample : 5276531.323099
time of last sample : 5276555.345625
sample duration : 24022.526 ms

2. Fix an invalid time string issue. For example,

   perf script --time 10%/10x12321xsdfdasfdsafdsafdsa

Now in code, it uses strtol to replace atoi.

3. Remove perf_time__skip_sample, only uses perf_time__ranges_skip_sample in perf report/perf script.

v3:
---
1. Move the definitions of first_sample_time/last_sample_time from perf_session and struct record to perf_evlist and update the related code.

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                        |   5 +
 tools/perf/builtin-report.c                        |  28 ++-
 tools/perf/builtin-script.c                        |  25 ++-
 tools/perf/util/evlist.h                           |   2 +
 tools/perf/util/header.c                           |  60 ++++++
 tools/perf/util/header.h                           |   1 +
 tools/perf/util/time-utils.c                       | 233 +++++++++++++++++++--
 tools/perf/util/time-utils.h                       |   6 +
 11 files changed, 375 insertions(+), 21 deletions(-)
Signature · 1 line
2.7.4
author
#1 lore raw

PATCH v4 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.

Change log:
-----------
v4: Use perf script time style for timestamp printing. Also add with
the printing of sample duration.

v3: Remove the definitions of first_sample_time/last_sample_time from
perf_session. Just define them in perf_evlist

---
 tools/perf/Documentation/perf.data-file-format.txt |  4 ++
 tools/perf/util/evlist.h                           |  2 +
 tools/perf/util/header.c                           | 60 ++++++++++++++++++++++
 tools/perf/util/header.h                           |  1 +
 4 files changed, 67 insertions(+)
tools/perf/Documentation/perf.data-file-format.txt +4 -0
index e90c59c..d5e3043 100644
@@ -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
index b1c14f1..9ccc2fb 100644
@@ -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 +60 -0

96 lines not on this page · raw message

tools/perf/util/header.h +1 -0
index f7a16ee..1911831 100644
@@ -33,6 +33,7 @@ enum {
 	HEADER_AUXTRACE,
 	HEADER_STAT,
 	HEADER_CACHE,
+	HEADER_SAMPLE_TIME,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
Signature · 1 line
2.7.4
#2 lore raw

Re: [PATCH v4 1/6] perf header: Record first sample time and last sample time in perf file header

Em Tue, Oct 03, 2017 at 10:22:33PM +0800, Jin Yao escreveu:

Quoted 4 lines

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.

Quoted 8 lines

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/...

So _who_ will walk all the samples, its not clear from this specific message (1/6) who will do this...

- Arnaldo

Quoted 171 lines

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.

Change log:
-----------
v4: Use perf script time style for timestamp printing. Also add with
the printing of sample duration.

v3: Remove the definitions of first_sample_time/last_sample_time from
perf_session. Just define them in perf_evlist

---
 tools/perf/Documentation/perf.data-file-format.txt |  4 ++
 tools/perf/util/evlist.h                           |  2 +
 tools/perf/util/header.c                           | 60 ++++++++++++++++++++++
 tools/perf/util/header.h                           |  1 +
 4 files changed, 67 insertions(+)
tools/perf/Documentation/perf.data-file-format.txt +4 -0
index e90c59c..d5e3043 100644
@@ -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
index b1c14f1..9ccc2fb 100644
@@ -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 +60 -0
index 605bbd5..61b28d89 100644
@@ -17,6 +17,7 @@
 #include <sys/types.h>
 #include <sys/utsname.h>
 #include <unistd.h>
+#include <linux/time64.h>
 
 #include "evlist.h"
 #include "evsel.h"
@@ -36,6 +37,7 @@
 #include <api/fs/fs.h>
 #include "asm/bug.h"
 #include "tool.h"
+#include "time-utils.h"
 
 #include "sane_ctype.h"
 
@@ -1181,6 +1183,20 @@ static int write_stat(struct feat_fd *ff __maybe_unused,
 	return 0;
 }
 
+static int write_sample_time(struct feat_fd *ff,
+			     struct perf_evlist *evlist)
+{
+	int ret;
+
+	ret = do_write(ff, &evlist->first_sample_time,
+		       sizeof(evlist->first_sample_time));
+	if (ret < 0)
+		return ret;
+
+	return do_write(ff, &evlist->last_sample_time,
+			sizeof(evlist->last_sample_time));
+}
+
 static void print_hostname(struct feat_fd *ff, FILE *fp)
 {
 	fprintf(fp, "# hostname : %s\n", ff->ph->env.hostname);
@@ -1506,6 +1522,28 @@ static void print_group_desc(struct feat_fd *ff, FILE *fp)
 	}
 }
 
+static void print_sample_time(struct feat_fd *ff, FILE *fp)
+{
+	struct perf_session *session;
+	char time_buf[32];
+	double d;
+
+	session = container_of(ff->ph, struct perf_session, header);
+
+	timestamp__scnprintf_usec(session->evlist->first_sample_time,
+				  time_buf, sizeof(time_buf));
+	fprintf(fp, "# time of first sample : %s\n", time_buf);
+
+	timestamp__scnprintf_usec(session->evlist->last_sample_time,
+				  time_buf, sizeof(time_buf));
+	fprintf(fp, "# time of last sample : %s\n", time_buf);
+
+	d = (double)(session->evlist->last_sample_time -
+		session->evlist->first_sample_time) / NSEC_PER_MSEC;
+
+	fprintf(fp, "# sample duration : %10.3f ms\n", d);
+}
+
 static int __event_process_build_id(struct build_id_event *bev,
 				    char *filename,
 				    struct perf_session *session)
@@ -2147,6 +2185,27 @@ static int process_cache(struct feat_fd *ff, void *data __maybe_unused)
 	return -1;
 }
 
+static int process_sample_time(struct feat_fd *ff, void *data __maybe_unused)
+{
+	struct perf_session *session;
+	u64 first_sample_time, last_sample_time;
+	int ret;
+
+	session = container_of(ff->ph, struct perf_session, header);
+
+	ret = do_read_u64(ff, &first_sample_time);
+	if (ret)
+		return -1;
+
+	ret = do_read_u64(ff, &last_sample_time);
+	if (ret)
+		return -1;
+
+	session->evlist->first_sample_time = first_sample_time;
+	session->evlist->last_sample_time = last_sample_time;
+	return 0;
+}
+
 struct feature_ops {
 	int (*write)(struct feat_fd *ff, struct perf_evlist *evlist);
 	void (*print)(struct feat_fd *ff, FILE *fp);
@@ -2204,6 +2263,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPN(AUXTRACE,	auxtrace,	false),
 	FEAT_OPN(STAT,		stat,		false),
 	FEAT_OPN(CACHE,		cache,		true),
+	FEAT_OPR(SAMPLE_TIME,	sample_time,	false),
 };
 
 struct header_print_data {
tools/perf/util/header.h +1 -0
index f7a16ee..1911831 100644
@@ -33,6 +33,7 @@ enum {
 	HEADER_AUXTRACE,
 	HEADER_STAT,
 	HEADER_CACHE,
+	HEADER_SAMPLE_TIME,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
Signature · 1 line
2.7.4
author
#3 lore raw

PATCH v4 2/6 perf record: Get the first sample time and last sample time

In reply to 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.

Change log:
-----------
v3: Remove the definitions of first_sample_time and last_sample_time
from struct record and directly save them in perf_evlist.

---
 tools/perf/builtin-record.c | 5 +++++
 1 file changed, 5 insertions(+)
tools/perf/builtin-record.c +5 -0
index 9b379f3..d5b78449 100644
@@ -488,6 +488,11 @@ static int process_sample_event(struct perf_tool *tool,
 
 	rec->samples++;
 
+	if (rec->evlist->first_sample_time == 0)
+		rec->evlist->first_sample_time = sample->time;
+
+	rec->evlist->last_sample_time = sample->time;
+
 	return build_id__mark_dso_hit(tool, event, sample, evsel, machine);
 }
 
Signature · 1 line
2.7.4
#4 lore raw

Re: [PATCH v4 2/6] perf record: Get the first sample time and last sample time

Em Tue, Oct 03, 2017 at 10:22:34PM +0800, Jin Yao escreveu:

Quoted 1 line

In perf record, it's walked on all samples yet. So it's very easy to get

You're saying that perf record walks all samples always? That only happens when we generate the build-id table, right? And people disable that to speed up the process, knowing that some limitations will come from that, for doing analysis right after running it is mostly OK to disable the build-id processing.

- Arnaldo

Quoted 33 lines

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.

Change log:
-----------
v3: Remove the definitions of first_sample_time and last_sample_time
from struct record and directly save them in perf_evlist.

---
 tools/perf/builtin-record.c | 5 +++++
 1 file changed, 5 insertions(+)
tools/perf/builtin-record.c +5 -0
index 9b379f3..d5b78449 100644
@@ -488,6 +488,11 @@ static int process_sample_event(struct perf_tool *tool,
 
 	rec->samples++;
 
+	if (rec->evlist->first_sample_time == 0)
+		rec->evlist->first_sample_time = sample->time;
+
+	rec->evlist->last_sample_time = sample->time;
+
 	return build_id__mark_dso_hit(tool, event, sample, evsel, machine);
 }
 
Signature · 1 line
2.7.4
#5 lore raw

Re: [PATCH v4 2/6] perf record: Get the first sample time and last sample time

Em Thu, Oct 19, 2017 at 05:21:27PM -0300, Arnaldo Carvalho de Melo escreveu:

Quoted 8 lines

Em Tue, Oct 03, 2017 at 10:22:34PM +0800, Jin Yao escreveu:

Quoted 1 line

In perf record, it's walked on all samples yet. So it's very easy to get

You're saying that perf record walks all samples always? That only happens when we generate the build-id table, right? And people disable that to speed up the process, knowing that some limitations will come from that, for doing analysis right after running it is mostly OK to disable the build-id processing.

So either you add a new option that processes all events without doing build-id processing (and all the locking, struct thread, map, etc processing it entails) and just looks at the sample->time, and when build id processing is enabled, just do as you're doing in this patch, then, at perf report --time you should look to see if those start/end times were filled in and if not tell that to the user, i.e. that either --record-time-boundaries (or a better name :-) ) has to be used, or, that build-id process, with a short explanation that --record-time-boundaries is a bit cheaper.

- Arnaldo

Quoted 35 lines

- Arnaldo

Quoted 33 lines

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.

Change log:
-----------
v3: Remove the definitions of first_sample_time and last_sample_time
from struct record and directly save them in perf_evlist.

---
 tools/perf/builtin-record.c | 5 +++++
 1 file changed, 5 insertions(+)
tools/perf/builtin-record.c +5 -0
index 9b379f3..d5b78449 100644
@@ -488,6 +488,11 @@ static int process_sample_event(struct perf_tool *tool,
 
 	rec->samples++;
 
+	if (rec->evlist->first_sample_time == 0)
+		rec->evlist->first_sample_time = sample->time;
+
+	rec->evlist->last_sample_time = sample->time;
+
 	return build_id__mark_dso_hit(tool, event, sample, evsel, machine);
 }
 
Signature · 1 line
2.7.4
author
#6 lore raw

Re: [PATCH v4 2/6] perf record: Get the first sample time and last sample time

Quoted 20 lines · Arnaldo Carvalho de Melo

Em Thu, Oct 19, 2017 at 05:21:27PM -0300, Arnaldo Carvalho de Melo escreveu:

Quoted 8 lines

Em Tue, Oct 03, 2017 at 10:22:34PM +0800, Jin Yao escreveu:

Quoted 1 line

In perf record, it's walked on all samples yet. So it's very easy to get

You're saying that perf record walks all samples always? That only happens when we generate the build-id table, right? And people disable that to speed up the process, knowing that some limitations will come from that, for doing analysis right after running it is mostly OK to disable the build-id processing.

So either you add a new option that processes all events without doing build-id processing (and all the locking, struct thread, map, etc processing it entails) and just looks at the sample->time, and when build id processing is enabled, just do as you're doing in this patch, then, at perf report --time you should look to see if those start/end times were filled in and if not tell that to the user, i.e. that either --record-time-boundaries (or a better name :-) ) has to be used, or, that build-id process, with a short explanation that --record-time-boundaries is a bit cheaper.

Quoted 2 lines

- Arnaldo

Hi Arnaldo,

Thanks so much for reminding me that the walking only happens when build-id processing is enabled. Yes, the step is same as what you said so there will be an issue when the build-id processing is disabled.

According to your suggestion, I will provide a new option "--record-time-boundaries" in perf record. If user disables the build-id processing, the perf record will ask user to set the "--record-time-boundaries". If user enables the build-id processing, the perf record will not ask user to set the "--record-time-boundaries".

Also in perf report, if it doesn't see start/end time filled in the perf file header, it will show some information to let user know he should set "--record-time-boundaries" or enable the build-id processing in perf record.

I will provide v5 patch series, maybe some days later.

Thanks
Jin Yao

author
#7 lore raw

PATCH v4 3/6 perf util: Create function to parse time percent

In reply to Jin Yao

Current 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%

Change log:
-----------
v4: An issue is found. Following passes.
perf script --time 10%/10x12321xsdfdasfdsafdsafdsa

Now it uses strtol to replace atoi.

---
 tools/perf/util/time-utils.c | 205 ++++++++++++++++++++++++++++++++++++++++---
 tools/perf/util/time-utils.h |   3 +
 2 files changed, 196 insertions(+), 12 deletions(-)
tools/perf/util/time-utils.c +193 -12
index 5b5d021..79e4281 100644
@@ -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 +113,177 @@ 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, *end_str;
+	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 = (int)strtol(p, &end_str, 10);
+	if (*end_str)
+		return -1;
+
+	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
index 8656be0..fd018e2 100644
@@ -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
author
#8 lore raw

PATCH v4 4/6 perf util: Create function to perform multiple time range checking

In reply to Jin Yao

Previous 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.

Change log:
-----------
v4: Let perf_time__ranges_skip_sample be compatible with
perf_time__skip_sample when only one time range.

---
 tools/perf/util/time-utils.c | 28 ++++++++++++++++++++++++++++
 tools/perf/util/time-utils.h |  3 +++
 2 files changed, 31 insertions(+)
tools/perf/util/time-utils.c +28 -0
index 79e4281..b380356 100644
@@ -299,6 +299,34 @@ 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;
+
+	if (num == 1)
+		return perf_time__skip_sample(&ptime_buf[0], timestamp);
+
+	/*
+	 * start/end of multiple time ranges must be valid.
+	 */
+	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
index fd018e2..de279ea 100644
@@ -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
author
#9 lore raw

PATCH v4 5/6 perf report: support time percent and multiple time ranges

In reply to Jin Yao

perf 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%

Change log:
-----------
v4: Remove perf_time__skip_sample, only uses perf_time__ranges_skip_sample

v3: Since the definitions of first_sample_time/last_sample_time
are moved from perf_session to perf_evlist so change the related code.

---
 tools/perf/Documentation/perf-report.txt | 16 ++++++++++++++++
 tools/perf/builtin-report.c              | 28 ++++++++++++++++++++++++----
 2 files changed, 40 insertions(+), 4 deletions(-)
tools/perf/Documentation/perf-report.txt +16 -0
index 383a98d..3a0975c 100644
@@ -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 +24 -4
index f9dff65..ab7ab25 100644
@@ -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;
@@ -68,7 +70,8 @@ struct report {
 	const char		*cpu_list;
 	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 +188,10 @@ static int process_sample_event(struct perf_tool *tool,
 	};
 	int ret = 0;
 
-	if (perf_time__skip_sample(&rep->ptime, sample->time))
+	if (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",
@@ -1073,8 +1078,23 @@ int cmd_report(int argc, const char **argv)
 	if (symbol__init(&session->header.env) < 0)
 		goto error;
 
-	if (perf_time__parse_str(&report.ptime, report.time_str) != 0) {
-		pr_err("Invalid time string\n");
+	if (perf_time__parse_str(report.ptime_range, report.time_str) != 0) {
+		report.range_num = perf_time__percent_parse_str(
+					report.ptime_range, PTIME_RANGE_MAX,
+					report.time_str,
+					session->evlist->first_sample_time,
+					session->evlist->last_sample_time);
+
+		if (report.range_num < 0) {
+			pr_err("Invalid time string\n");
+			return -EINVAL;
+		}
+	} else {
+		report.range_num = 1;
+	}
+
+	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
author
#10 lore raw

PATCH v4 6/6 perf script: support time percent and multiple time ranges

In reply to Jin Yao

perf 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%

Change log:
-----------
v4: Remove perf_time__skip_sample, only uses perf_time__ranges_skip_sample

v3: Since the definitions of first_sample_time/last_sample_time
are moved from perf_session to perf_evlist so change the related code.

---
 tools/perf/Documentation/perf-script.txt | 16 ++++++++++++++++
 tools/perf/builtin-script.c              | 25 ++++++++++++++++++++-----
 2 files changed, 36 insertions(+), 5 deletions(-)
tools/perf/Documentation/perf-script.txt +16 -0
index bcc1ba3..2c1f2b9 100644
@@ -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 +20 -5
index 9092de0..a8d5f02 100644
@@ -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;
@@ -1369,7 +1371,8 @@ struct perf_script {
 	struct thread_map	*threads;
 	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 +1568,10 @@ 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__ranges_skip_sample(scr->ptime_range, scr->range_num,
+					  sample->time)) {
 		return 0;
+	}
 
 	if (debug_mode) {
 		if (sample->time < last_timestamp) {
@@ -3103,9 +3108,19 @@ int cmd_script(int argc, const char **argv)
 		goto out_delete;
 
 	/* 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;
+	if (perf_time__parse_str(script.ptime_range, script.time_str) != 0) {
+		script.range_num = perf_time__percent_parse_str(
+					script.ptime_range, PTIME_RANGE_MAX,
+					script.time_str,
+					session->evlist->first_sample_time,
+					session->evlist->last_sample_time);
+
+		if (script.range_num < 0) {
+			pr_err("Invalid time string\n");
+			return -EINVAL;
+		}
+	} else {
+		script.range_num = 1;
 	}
 
 	err = __cmd_script(&script);
Signature · 1 line
2.7.4
Acked-by on the v4 series
#11 lore raw
In reply to Jin Yao
Quoted 11 lines · Jin Yao

v4:
---
1. Use perf script time style for timestamp printing. Also add with the printing of sample duration. For example:

   perf report --header
   time of first sample : 5276531.323099
   time of last sample : 5276555.345625
   sample duration :  24022.526 ms
Quoted 5 lines

2. Fix an invalid time string issue. For example,

   perf script --time 10%/10x12321xsdfdasfdsafdsafdsa

Now in code, it uses strtol to replace atoi.

for the patchset:

thanks,
jirka

author
#12 lore raw
Quoted 16 lines · Jiri Olsa
Quoted 15 lines · Jin Yao

v4:
---
1. Use perf script time style for timestamp printing. Also add with

    the printing of sample duration. For example:

    perf report --header

    time of first sample : 5276531.323099
    time of last sample : 5276555.345625
    sample duration :  24022.526 ms

2. Fix an invalid time string issue. For example,

    perf script --time 10%/10x12321xsdfdasfdsafdsafdsa
Quoted 9 lines
Quoted 1 line

Now in code, it uses strtol to replace atoi.

for the patchset:

thanks,
jirka

Thanks Jiri!

Hi Arnaldo,

Could this patchset be merged?

Thanks
Jin Yao