* [PATCH] perf stat: Support --all-kernel/--all-user @ 2019-10-11 5:05 Jin Yao 2019-10-14 14:42 ` Jiri Olsa 2019-10-21 23:19 ` [tip: perf/core] " tip-bot2 for Jin Yao 0 siblings, 2 replies; 7+ messages in thread From: Jin Yao @ 2019-10-11 5:05 UTC (permalink / raw) To: acme, jolsa, peterz, mingo, alexander.shishkin Cc: Linux-kernel, ak, kan.liang, yao.jin, Jin Yao perf record has supported --all-kernel / --all-user to configure all used events to run in kernel space or run in user space. But perf stat doesn't support these options. It would be useful to support these options in perf-stat too to keep the same semantics. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> --- tools/perf/Documentation/perf-stat.txt | 6 ++++++ tools/perf/builtin-stat.c | 6 ++++++ tools/perf/util/stat.c | 10 ++++++++++ tools/perf/util/stat.h | 2 ++ 4 files changed, 24 insertions(+) diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 930c51c01201..a9af4e440e80 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -323,6 +323,12 @@ The output is SMI cycles%, equals to (aperf - unhalted core cycles) / aperf Users who wants to get the actual value can apply --no-metric-only. +--all-kernel:: +Configure all used events to run in kernel space. + +--all-user:: +Configure all used events to run in user space. + EXAMPLES -------- diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 468fc49420ce..c88d4e118409 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -803,6 +803,12 @@ static struct option stat_options[] = { OPT_CALLBACK('M', "metrics", &evsel_list, "metric/metric group list", "monitor specified metrics or metric groups (separated by ,)", parse_metric_groups), + OPT_BOOLEAN_FLAG(0, "all-kernel", &stat_config.all_kernel, + "Configure all used events to run in kernel space.", + PARSE_OPT_EXCLUSIVE), + OPT_BOOLEAN_FLAG(0, "all-user", &stat_config.all_user, + "Configure all used events to run in user space.", + PARSE_OPT_EXCLUSIVE), OPT_END() }; diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index ebdd130557fb..6822e4ffe224 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -490,6 +490,16 @@ int create_perf_stat_counter(struct evsel *evsel, if (config->identifier) attr->sample_type = PERF_SAMPLE_IDENTIFIER; + if (config->all_user) { + attr->exclude_kernel = 1; + attr->exclude_user = 0; + } + + if (config->all_kernel) { + attr->exclude_kernel = 0; + attr->exclude_user = 1; + } + /* * Disabling all counters initially, they will be enabled * either manually by us or by kernel via enable_on_exec diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index edbeb2f63e8d..081c4a5113c6 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -106,6 +106,8 @@ struct perf_stat_config { bool big_num; bool no_merge; bool walltime_run_table; + bool all_kernel; + bool all_user; FILE *output; unsigned int interval; unsigned int timeout; -- 2.17.1 ^ permalink raw reply related [flat|nested] 7+ messages in thread
* Re: [PATCH] perf stat: Support --all-kernel/--all-user 2019-10-11 5:05 [PATCH] perf stat: Support --all-kernel/--all-user Jin Yao @ 2019-10-14 14:42 ` Jiri Olsa 2019-10-14 16:23 ` Arnaldo Carvalho de Melo 2019-10-21 23:19 ` [tip: perf/core] " tip-bot2 for Jin Yao 1 sibling, 1 reply; 7+ messages in thread From: Jiri Olsa @ 2019-10-14 14:42 UTC (permalink / raw) To: Jin Yao Cc: acme, jolsa, peterz, mingo, alexander.shishkin, Linux-kernel, ak, kan.liang, yao.jin On Fri, Oct 11, 2019 at 01:05:45PM +0800, Jin Yao wrote: > perf record has supported --all-kernel / --all-user to configure all > used events to run in kernel space or run in user space. But perf > stat doesn't support these options. > > It would be useful to support these options in perf-stat too to keep > the same semantics. > > Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> thanks, jirka > --- > tools/perf/Documentation/perf-stat.txt | 6 ++++++ > tools/perf/builtin-stat.c | 6 ++++++ > tools/perf/util/stat.c | 10 ++++++++++ > tools/perf/util/stat.h | 2 ++ > 4 files changed, 24 insertions(+) > > diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt > index 930c51c01201..a9af4e440e80 100644 > --- a/tools/perf/Documentation/perf-stat.txt > +++ b/tools/perf/Documentation/perf-stat.txt > @@ -323,6 +323,12 @@ The output is SMI cycles%, equals to (aperf - unhalted core cycles) / aperf > > Users who wants to get the actual value can apply --no-metric-only. > > +--all-kernel:: > +Configure all used events to run in kernel space. > + > +--all-user:: > +Configure all used events to run in user space. > + > EXAMPLES > -------- > > diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c > index 468fc49420ce..c88d4e118409 100644 > --- a/tools/perf/builtin-stat.c > +++ b/tools/perf/builtin-stat.c > @@ -803,6 +803,12 @@ static struct option stat_options[] = { > OPT_CALLBACK('M', "metrics", &evsel_list, "metric/metric group list", > "monitor specified metrics or metric groups (separated by ,)", > parse_metric_groups), > + OPT_BOOLEAN_FLAG(0, "all-kernel", &stat_config.all_kernel, > + "Configure all used events to run in kernel space.", > + PARSE_OPT_EXCLUSIVE), > + OPT_BOOLEAN_FLAG(0, "all-user", &stat_config.all_user, > + "Configure all used events to run in user space.", > + PARSE_OPT_EXCLUSIVE), > OPT_END() > }; > > diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c > index ebdd130557fb..6822e4ffe224 100644 > --- a/tools/perf/util/stat.c > +++ b/tools/perf/util/stat.c > @@ -490,6 +490,16 @@ int create_perf_stat_counter(struct evsel *evsel, > if (config->identifier) > attr->sample_type = PERF_SAMPLE_IDENTIFIER; > > + if (config->all_user) { > + attr->exclude_kernel = 1; > + attr->exclude_user = 0; > + } > + > + if (config->all_kernel) { > + attr->exclude_kernel = 0; > + attr->exclude_user = 1; > + } > + > /* > * Disabling all counters initially, they will be enabled > * either manually by us or by kernel via enable_on_exec > diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h > index edbeb2f63e8d..081c4a5113c6 100644 > --- a/tools/perf/util/stat.h > +++ b/tools/perf/util/stat.h > @@ -106,6 +106,8 @@ struct perf_stat_config { > bool big_num; > bool no_merge; > bool walltime_run_table; > + bool all_kernel; > + bool all_user; > FILE *output; > unsigned int interval; > unsigned int timeout; > -- > 2.17.1 > ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH] perf stat: Support --all-kernel/--all-user 2019-10-14 14:42 ` Jiri Olsa @ 2019-10-14 16:23 ` Arnaldo Carvalho de Melo 2019-10-15 1:57 ` Jin, Yao 0 siblings, 1 reply; 7+ messages in thread From: Arnaldo Carvalho de Melo @ 2019-10-14 16:23 UTC (permalink / raw) To: Jiri Olsa Cc: Jin Yao, jolsa, peterz, mingo, alexander.shishkin, Linux-kernel, ak, kan.liang, yao.jin Em Mon, Oct 14, 2019 at 04:42:08PM +0200, Jiri Olsa escreveu: > On Fri, Oct 11, 2019 at 01:05:45PM +0800, Jin Yao wrote: > > perf record has supported --all-kernel / --all-user to configure all > > used events to run in kernel space or run in user space. But perf > > stat doesn't support these options. > > > > It would be useful to support these options in perf-stat too to keep > > the same semantics. > > > > Signed-off-by: Jin Yao <yao.jin@linux.intel.com> > > Acked-by: Jiri Olsa <jolsa@kernel.org> What happens if one asks for both? From the patch only the --all-kernel will stick, right? Is that the behaviour for 'perf record'? Lemme see, as I recall having this discussion at that time... Yeah, same thing, and looking at that I wonder why we dong use perf_evsel__config() in 'perf stat'... Ok, I'm going to apply it. > thanks, > jirka > > > --- > > tools/perf/Documentation/perf-stat.txt | 6 ++++++ > > tools/perf/builtin-stat.c | 6 ++++++ > > tools/perf/util/stat.c | 10 ++++++++++ > > tools/perf/util/stat.h | 2 ++ > > 4 files changed, 24 insertions(+) > > > > diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt > > index 930c51c01201..a9af4e440e80 100644 > > --- a/tools/perf/Documentation/perf-stat.txt > > +++ b/tools/perf/Documentation/perf-stat.txt > > @@ -323,6 +323,12 @@ The output is SMI cycles%, equals to (aperf - unhalted core cycles) / aperf > > > > Users who wants to get the actual value can apply --no-metric-only. > > > > +--all-kernel:: > > +Configure all used events to run in kernel space. > > + > > +--all-user:: > > +Configure all used events to run in user space. > > + > > EXAMPLES > > -------- > > > > diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c > > index 468fc49420ce..c88d4e118409 100644 > > --- a/tools/perf/builtin-stat.c > > +++ b/tools/perf/builtin-stat.c > > @@ -803,6 +803,12 @@ static struct option stat_options[] = { > > OPT_CALLBACK('M', "metrics", &evsel_list, "metric/metric group list", > > "monitor specified metrics or metric groups (separated by ,)", > > parse_metric_groups), > > + OPT_BOOLEAN_FLAG(0, "all-kernel", &stat_config.all_kernel, > > + "Configure all used events to run in kernel space.", > > + PARSE_OPT_EXCLUSIVE), > > + OPT_BOOLEAN_FLAG(0, "all-user", &stat_config.all_user, > > + "Configure all used events to run in user space.", > > + PARSE_OPT_EXCLUSIVE), > > OPT_END() > > }; > > > > diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c > > index ebdd130557fb..6822e4ffe224 100644 > > --- a/tools/perf/util/stat.c > > +++ b/tools/perf/util/stat.c > > @@ -490,6 +490,16 @@ int create_perf_stat_counter(struct evsel *evsel, > > if (config->identifier) > > attr->sample_type = PERF_SAMPLE_IDENTIFIER; > > > > + if (config->all_user) { > > + attr->exclude_kernel = 1; > > + attr->exclude_user = 0; > > + } > > + > > + if (config->all_kernel) { > > + attr->exclude_kernel = 0; > > + attr->exclude_user = 1; > > + } > > + > > /* > > * Disabling all counters initially, they will be enabled > > * either manually by us or by kernel via enable_on_exec > > diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h > > index edbeb2f63e8d..081c4a5113c6 100644 > > --- a/tools/perf/util/stat.h > > +++ b/tools/perf/util/stat.h > > @@ -106,6 +106,8 @@ struct perf_stat_config { > > bool big_num; > > bool no_merge; > > bool walltime_run_table; > > + bool all_kernel; > > + bool all_user; > > FILE *output; > > unsigned int interval; > > unsigned int timeout; > > -- > > 2.17.1 > > -- - Arnaldo ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH] perf stat: Support --all-kernel/--all-user 2019-10-14 16:23 ` Arnaldo Carvalho de Melo @ 2019-10-15 1:57 ` Jin, Yao 2019-10-15 15:11 ` Arnaldo Carvalho de Melo 0 siblings, 1 reply; 7+ messages in thread From: Jin, Yao @ 2019-10-15 1:57 UTC (permalink / raw) To: Arnaldo Carvalho de Melo, Jiri Olsa Cc: jolsa, peterz, mingo, alexander.shishkin, Linux-kernel, ak, kan.liang, yao.jin On 10/15/2019 12:23 AM, Arnaldo Carvalho de Melo wrote: > Em Mon, Oct 14, 2019 at 04:42:08PM +0200, Jiri Olsa escreveu: >> On Fri, Oct 11, 2019 at 01:05:45PM +0800, Jin Yao wrote: >>> perf record has supported --all-kernel / --all-user to configure all >>> used events to run in kernel space or run in user space. But perf >>> stat doesn't support these options. >>> >>> It would be useful to support these options in perf-stat too to keep >>> the same semantics. >>> >>> Signed-off-by: Jin Yao <yao.jin@linux.intel.com> >> >> Acked-by: Jiri Olsa <jolsa@kernel.org> > > What happens if one asks for both? From the patch only the --all-kernel > will stick, right? Is that the behaviour for 'perf record'? Lemme see, > as I recall having this discussion at that time... > > Yeah, same thing, and looking at that I wonder why we dong use > perf_evsel__config() in 'perf stat'... > > Ok, I'm going to apply it. > Hi Arnaldo, If we specify both, we will see the error. root@kbl:~# perf stat --all-kernel --all-user -a -- sleep 1 Error: option `all-user' cannot be used with all-kernel root@kbl:~# perf record --all-kernel --all-user -a -- sleep 1 Error: option `all-user' cannot be used with all-kernel For why I don't set them in perf_evsel__config, because perf_evsel__config is called in record but not called in stat. Thanks for reviewing and applying this patch. Thanks Jin Yao >> thanks, >> jirka >> >>> --- >>> tools/perf/Documentation/perf-stat.txt | 6 ++++++ >>> tools/perf/builtin-stat.c | 6 ++++++ >>> tools/perf/util/stat.c | 10 ++++++++++ >>> tools/perf/util/stat.h | 2 ++ >>> 4 files changed, 24 insertions(+) >>> >>> diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt >>> index 930c51c01201..a9af4e440e80 100644 >>> --- a/tools/perf/Documentation/perf-stat.txt >>> +++ b/tools/perf/Documentation/perf-stat.txt >>> @@ -323,6 +323,12 @@ The output is SMI cycles%, equals to (aperf - unhalted core cycles) / aperf >>> >>> Users who wants to get the actual value can apply --no-metric-only. >>> >>> +--all-kernel:: >>> +Configure all used events to run in kernel space. >>> + >>> +--all-user:: >>> +Configure all used events to run in user space. >>> + >>> EXAMPLES >>> -------- >>> >>> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c >>> index 468fc49420ce..c88d4e118409 100644 >>> --- a/tools/perf/builtin-stat.c >>> +++ b/tools/perf/builtin-stat.c >>> @@ -803,6 +803,12 @@ static struct option stat_options[] = { >>> OPT_CALLBACK('M', "metrics", &evsel_list, "metric/metric group list", >>> "monitor specified metrics or metric groups (separated by ,)", >>> parse_metric_groups), >>> + OPT_BOOLEAN_FLAG(0, "all-kernel", &stat_config.all_kernel, >>> + "Configure all used events to run in kernel space.", >>> + PARSE_OPT_EXCLUSIVE), >>> + OPT_BOOLEAN_FLAG(0, "all-user", &stat_config.all_user, >>> + "Configure all used events to run in user space.", >>> + PARSE_OPT_EXCLUSIVE), >>> OPT_END() >>> }; >>> >>> diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c >>> index ebdd130557fb..6822e4ffe224 100644 >>> --- a/tools/perf/util/stat.c >>> +++ b/tools/perf/util/stat.c >>> @@ -490,6 +490,16 @@ int create_perf_stat_counter(struct evsel *evsel, >>> if (config->identifier) >>> attr->sample_type = PERF_SAMPLE_IDENTIFIER; >>> >>> + if (config->all_user) { >>> + attr->exclude_kernel = 1; >>> + attr->exclude_user = 0; >>> + } >>> + >>> + if (config->all_kernel) { >>> + attr->exclude_kernel = 0; >>> + attr->exclude_user = 1; >>> + } >>> + >>> /* >>> * Disabling all counters initially, they will be enabled >>> * either manually by us or by kernel via enable_on_exec >>> diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h >>> index edbeb2f63e8d..081c4a5113c6 100644 >>> --- a/tools/perf/util/stat.h >>> +++ b/tools/perf/util/stat.h >>> @@ -106,6 +106,8 @@ struct perf_stat_config { >>> bool big_num; >>> bool no_merge; >>> bool walltime_run_table; >>> + bool all_kernel; >>> + bool all_user; >>> FILE *output; >>> unsigned int interval; >>> unsigned int timeout; >>> -- >>> 2.17.1 >>> > ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH] perf stat: Support --all-kernel/--all-user 2019-10-15 1:57 ` Jin, Yao @ 2019-10-15 15:11 ` Arnaldo Carvalho de Melo 2019-10-16 0:43 ` Jin, Yao 0 siblings, 1 reply; 7+ messages in thread From: Arnaldo Carvalho de Melo @ 2019-10-15 15:11 UTC (permalink / raw) To: Jin, Yao Cc: Arnaldo Carvalho de Melo, Jiri Olsa, jolsa, peterz, mingo, alexander.shishkin, Linux-kernel, ak, kan.liang, yao.jin Em Tue, Oct 15, 2019 at 09:57:33AM +0800, Jin, Yao escreveu: > > > On 10/15/2019 12:23 AM, Arnaldo Carvalho de Melo wrote: > > Em Mon, Oct 14, 2019 at 04:42:08PM +0200, Jiri Olsa escreveu: > > > On Fri, Oct 11, 2019 at 01:05:45PM +0800, Jin Yao wrote: > > > > perf record has supported --all-kernel / --all-user to configure all > > > > used events to run in kernel space or run in user space. But perf > > > > stat doesn't support these options. > > > > > > > > It would be useful to support these options in perf-stat too to keep > > > > the same semantics. > > > > > > > > Signed-off-by: Jin Yao <yao.jin@linux.intel.com> > > > > > > Acked-by: Jiri Olsa <jolsa@kernel.org> > > > > What happens if one asks for both? From the patch only the --all-kernel > > will stick, right? Is that the behaviour for 'perf record'? Lemme see, > > as I recall having this discussion at that time... > > > > Yeah, same thing, and looking at that I wonder why we dong use > > perf_evsel__config() in 'perf stat'... > > > > Ok, I'm going to apply it. > > > > Hi Arnaldo, > > If we specify both, we will see the error. Cool, I looked for this code and couldn't quickly spot it nor tried running with both to see what happened, my bad, thanks for replying and making sure that that is the behaviour. > root@kbl:~# perf stat --all-kernel --all-user -a -- sleep 1 > Error: option `all-user' cannot be used with all-kernel > > root@kbl:~# perf record --all-kernel --all-user -a -- sleep 1 > Error: option `all-user' cannot be used with all-kernel > > For why I don't set them in perf_evsel__config, because perf_evsel__config > is called in record but not called in stat. Ok, at some point we should try and check if we could make 'perf stat' use perf_evsel__config(), even if we have to separate what is shared into some __perf_evsel__config() that then gets called by 'perf stat' while the preexisting perf_evsel__config() calls it and does things that don't make sense for 'perf stat'. > Thanks for reviewing and applying this patch. You're welcome! - Arnaldo > Thanks > Jin Yao > > > > thanks, > > > jirka > > > > > > > --- > > > > tools/perf/Documentation/perf-stat.txt | 6 ++++++ > > > > tools/perf/builtin-stat.c | 6 ++++++ > > > > tools/perf/util/stat.c | 10 ++++++++++ > > > > tools/perf/util/stat.h | 2 ++ > > > > 4 files changed, 24 insertions(+) > > > > > > > > diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt > > > > index 930c51c01201..a9af4e440e80 100644 > > > > --- a/tools/perf/Documentation/perf-stat.txt > > > > +++ b/tools/perf/Documentation/perf-stat.txt > > > > @@ -323,6 +323,12 @@ The output is SMI cycles%, equals to (aperf - unhalted core cycles) / aperf > > > > Users who wants to get the actual value can apply --no-metric-only. > > > > +--all-kernel:: > > > > +Configure all used events to run in kernel space. > > > > + > > > > +--all-user:: > > > > +Configure all used events to run in user space. > > > > + > > > > EXAMPLES > > > > -------- > > > > diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c > > > > index 468fc49420ce..c88d4e118409 100644 > > > > --- a/tools/perf/builtin-stat.c > > > > +++ b/tools/perf/builtin-stat.c > > > > @@ -803,6 +803,12 @@ static struct option stat_options[] = { > > > > OPT_CALLBACK('M', "metrics", &evsel_list, "metric/metric group list", > > > > "monitor specified metrics or metric groups (separated by ,)", > > > > parse_metric_groups), > > > > + OPT_BOOLEAN_FLAG(0, "all-kernel", &stat_config.all_kernel, > > > > + "Configure all used events to run in kernel space.", > > > > + PARSE_OPT_EXCLUSIVE), > > > > + OPT_BOOLEAN_FLAG(0, "all-user", &stat_config.all_user, > > > > + "Configure all used events to run in user space.", > > > > + PARSE_OPT_EXCLUSIVE), > > > > OPT_END() > > > > }; > > > > diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c > > > > index ebdd130557fb..6822e4ffe224 100644 > > > > --- a/tools/perf/util/stat.c > > > > +++ b/tools/perf/util/stat.c > > > > @@ -490,6 +490,16 @@ int create_perf_stat_counter(struct evsel *evsel, > > > > if (config->identifier) > > > > attr->sample_type = PERF_SAMPLE_IDENTIFIER; > > > > + if (config->all_user) { > > > > + attr->exclude_kernel = 1; > > > > + attr->exclude_user = 0; > > > > + } > > > > + > > > > + if (config->all_kernel) { > > > > + attr->exclude_kernel = 0; > > > > + attr->exclude_user = 1; > > > > + } > > > > + > > > > /* > > > > * Disabling all counters initially, they will be enabled > > > > * either manually by us or by kernel via enable_on_exec > > > > diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h > > > > index edbeb2f63e8d..081c4a5113c6 100644 > > > > --- a/tools/perf/util/stat.h > > > > +++ b/tools/perf/util/stat.h > > > > @@ -106,6 +106,8 @@ struct perf_stat_config { > > > > bool big_num; > > > > bool no_merge; > > > > bool walltime_run_table; > > > > + bool all_kernel; > > > > + bool all_user; > > > > FILE *output; > > > > unsigned int interval; > > > > unsigned int timeout; > > > > -- > > > > 2.17.1 > > > > > > -- - Arnaldo ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH] perf stat: Support --all-kernel/--all-user 2019-10-15 15:11 ` Arnaldo Carvalho de Melo @ 2019-10-16 0:43 ` Jin, Yao 0 siblings, 0 replies; 7+ messages in thread From: Jin, Yao @ 2019-10-16 0:43 UTC (permalink / raw) To: Arnaldo Carvalho de Melo Cc: Jiri Olsa, jolsa, peterz, mingo, alexander.shishkin, Linux-kernel, ak, kan.liang, yao.jin On 10/15/2019 11:11 PM, Arnaldo Carvalho de Melo wrote: > Em Tue, Oct 15, 2019 at 09:57:33AM +0800, Jin, Yao escreveu: >> >> >> On 10/15/2019 12:23 AM, Arnaldo Carvalho de Melo wrote: >>> Em Mon, Oct 14, 2019 at 04:42:08PM +0200, Jiri Olsa escreveu: >>>> On Fri, Oct 11, 2019 at 01:05:45PM +0800, Jin Yao wrote: >>>>> perf record has supported --all-kernel / --all-user to configure all >>>>> used events to run in kernel space or run in user space. But perf >>>>> stat doesn't support these options. >>>>> >>>>> It would be useful to support these options in perf-stat too to keep >>>>> the same semantics. >>>>> >>>>> Signed-off-by: Jin Yao <yao.jin@linux.intel.com> >>>> >>>> Acked-by: Jiri Olsa <jolsa@kernel.org> >>> >>> What happens if one asks for both? From the patch only the --all-kernel >>> will stick, right? Is that the behaviour for 'perf record'? Lemme see, >>> as I recall having this discussion at that time... >>> >>> Yeah, same thing, and looking at that I wonder why we dong use >>> perf_evsel__config() in 'perf stat'... >>> >>> Ok, I'm going to apply it. >>> >> >> Hi Arnaldo, >> >> If we specify both, we will see the error. > > Cool, I looked for this code and couldn't quickly spot it nor tried > running with both to see what happened, my bad, thanks for replying and > making sure that that is the behaviour. > >> root@kbl:~# perf stat --all-kernel --all-user -a -- sleep 1 >> Error: option `all-user' cannot be used with all-kernel >> >> root@kbl:~# perf record --all-kernel --all-user -a -- sleep 1 >> Error: option `all-user' cannot be used with all-kernel >> >> For why I don't set them in perf_evsel__config, because perf_evsel__config >> is called in record but not called in stat. > > Ok, at some point we should try and check if we could make 'perf stat' > use perf_evsel__config(), even if we have to separate what is shared > into some __perf_evsel__config() that then gets called by 'perf stat' > while the preexisting perf_evsel__config() calls it and does things > that don't make sense for 'perf stat'. > Yes, fully agree, that should be better. If we reconstruct the perf_evsel__config() and make it be shared by perf stat, perf record and others, that would be nice. :) Thanks Jin Yao >> Thanks for reviewing and applying this patch. > > You're welcome! > > - Arnaldo > >> Thanks >> Jin Yao >> >>>> thanks, >>>> jirka >>>> >>>>> --- >>>>> tools/perf/Documentation/perf-stat.txt | 6 ++++++ >>>>> tools/perf/builtin-stat.c | 6 ++++++ >>>>> tools/perf/util/stat.c | 10 ++++++++++ >>>>> tools/perf/util/stat.h | 2 ++ >>>>> 4 files changed, 24 insertions(+) >>>>> >>>>> diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt >>>>> index 930c51c01201..a9af4e440e80 100644 >>>>> --- a/tools/perf/Documentation/perf-stat.txt >>>>> +++ b/tools/perf/Documentation/perf-stat.txt >>>>> @@ -323,6 +323,12 @@ The output is SMI cycles%, equals to (aperf - unhalted core cycles) / aperf >>>>> Users who wants to get the actual value can apply --no-metric-only. >>>>> +--all-kernel:: >>>>> +Configure all used events to run in kernel space. >>>>> + >>>>> +--all-user:: >>>>> +Configure all used events to run in user space. >>>>> + >>>>> EXAMPLES >>>>> -------- >>>>> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c >>>>> index 468fc49420ce..c88d4e118409 100644 >>>>> --- a/tools/perf/builtin-stat.c >>>>> +++ b/tools/perf/builtin-stat.c >>>>> @@ -803,6 +803,12 @@ static struct option stat_options[] = { >>>>> OPT_CALLBACK('M', "metrics", &evsel_list, "metric/metric group list", >>>>> "monitor specified metrics or metric groups (separated by ,)", >>>>> parse_metric_groups), >>>>> + OPT_BOOLEAN_FLAG(0, "all-kernel", &stat_config.all_kernel, >>>>> + "Configure all used events to run in kernel space.", >>>>> + PARSE_OPT_EXCLUSIVE), >>>>> + OPT_BOOLEAN_FLAG(0, "all-user", &stat_config.all_user, >>>>> + "Configure all used events to run in user space.", >>>>> + PARSE_OPT_EXCLUSIVE), >>>>> OPT_END() >>>>> }; >>>>> diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c >>>>> index ebdd130557fb..6822e4ffe224 100644 >>>>> --- a/tools/perf/util/stat.c >>>>> +++ b/tools/perf/util/stat.c >>>>> @@ -490,6 +490,16 @@ int create_perf_stat_counter(struct evsel *evsel, >>>>> if (config->identifier) >>>>> attr->sample_type = PERF_SAMPLE_IDENTIFIER; >>>>> + if (config->all_user) { >>>>> + attr->exclude_kernel = 1; >>>>> + attr->exclude_user = 0; >>>>> + } >>>>> + >>>>> + if (config->all_kernel) { >>>>> + attr->exclude_kernel = 0; >>>>> + attr->exclude_user = 1; >>>>> + } >>>>> + >>>>> /* >>>>> * Disabling all counters initially, they will be enabled >>>>> * either manually by us or by kernel via enable_on_exec >>>>> diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h >>>>> index edbeb2f63e8d..081c4a5113c6 100644 >>>>> --- a/tools/perf/util/stat.h >>>>> +++ b/tools/perf/util/stat.h >>>>> @@ -106,6 +106,8 @@ struct perf_stat_config { >>>>> bool big_num; >>>>> bool no_merge; >>>>> bool walltime_run_table; >>>>> + bool all_kernel; >>>>> + bool all_user; >>>>> FILE *output; >>>>> unsigned int interval; >>>>> unsigned int timeout; >>>>> -- >>>>> 2.17.1 >>>>> >>> > ^ permalink raw reply [flat|nested] 7+ messages in thread
* [tip: perf/core] perf stat: Support --all-kernel/--all-user 2019-10-11 5:05 [PATCH] perf stat: Support --all-kernel/--all-user Jin Yao 2019-10-14 14:42 ` Jiri Olsa @ 2019-10-21 23:19 ` tip-bot2 for Jin Yao 1 sibling, 0 replies; 7+ messages in thread From: tip-bot2 for Jin Yao @ 2019-10-21 23:19 UTC (permalink / raw) To: linux-tip-commits Cc: Jin Yao, Jiri Olsa, Alexander Shishkin, Andi Kleen, Kan Liang, Peter Zijlstra, Arnaldo Carvalho de Melo, Ingo Molnar, Borislav Petkov, linux-kernel The following commit has been merged into the perf/core branch of tip: Commit-ID: dd071024bf52156eed31deaf511c6e7a82a6f57b Gitweb: https://git.kernel.org/tip/dd071024bf52156eed31deaf511c6e7a82a6f57b Author: Jin Yao <yao.jin@linux.intel.com> AuthorDate: Fri, 11 Oct 2019 13:05:45 +08:00 Committer: Arnaldo Carvalho de Melo <acme@redhat.com> CommitterDate: Tue, 15 Oct 2019 08:39:42 -03:00 perf stat: Support --all-kernel/--all-user 'perf record' has supported --all-kernel / --all-user to configure all used events to run in kernel space or run in user space. But 'perf stat' doesn't support these options. It would be useful to support these options in 'perf stat' too to keep the same semantics available in both tools. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20191011050545.3899-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> --- tools/perf/Documentation/perf-stat.txt | 6 ++++++ tools/perf/builtin-stat.c | 6 ++++++ tools/perf/util/stat.c | 10 ++++++++++ tools/perf/util/stat.h | 2 ++ 4 files changed, 24 insertions(+) diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 930c51c..a9af4e4 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -323,6 +323,12 @@ The output is SMI cycles%, equals to (aperf - unhalted core cycles) / aperf Users who wants to get the actual value can apply --no-metric-only. +--all-kernel:: +Configure all used events to run in kernel space. + +--all-user:: +Configure all used events to run in user space. + EXAMPLES -------- diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 468fc49..c88d4e1 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -803,6 +803,12 @@ static struct option stat_options[] = { OPT_CALLBACK('M', "metrics", &evsel_list, "metric/metric group list", "monitor specified metrics or metric groups (separated by ,)", parse_metric_groups), + OPT_BOOLEAN_FLAG(0, "all-kernel", &stat_config.all_kernel, + "Configure all used events to run in kernel space.", + PARSE_OPT_EXCLUSIVE), + OPT_BOOLEAN_FLAG(0, "all-user", &stat_config.all_user, + "Configure all used events to run in user space.", + PARSE_OPT_EXCLUSIVE), OPT_END() }; diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index ebdd130..6822e4f 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -490,6 +490,16 @@ int create_perf_stat_counter(struct evsel *evsel, if (config->identifier) attr->sample_type = PERF_SAMPLE_IDENTIFIER; + if (config->all_user) { + attr->exclude_kernel = 1; + attr->exclude_user = 0; + } + + if (config->all_kernel) { + attr->exclude_kernel = 0; + attr->exclude_user = 1; + } + /* * Disabling all counters initially, they will be enabled * either manually by us or by kernel via enable_on_exec diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index edbeb2f..081c4a5 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -106,6 +106,8 @@ struct perf_stat_config { bool big_num; bool no_merge; bool walltime_run_table; + bool all_kernel; + bool all_user; FILE *output; unsigned int interval; unsigned int timeout; ^ permalink raw reply related [flat|nested] 7+ messages in thread
end of thread, other threads:[~2019-10-22 0:06 UTC | newest] Thread overview: 7+ messages (download: mbox.gz follow: Atom feed -- links below jump to the message on this page -- 2019-10-11 5:05 [PATCH] perf stat: Support --all-kernel/--all-user Jin Yao 2019-10-14 14:42 ` Jiri Olsa 2019-10-14 16:23 ` Arnaldo Carvalho de Melo 2019-10-15 1:57 ` Jin, Yao 2019-10-15 15:11 ` Arnaldo Carvalho de Melo 2019-10-16 0:43 ` Jin, Yao 2019-10-21 23:19 ` [tip: perf/core] " tip-bot2 for Jin Yao
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for NNTP newsgroup(s).