[PATCH 19/19] perf stat: Remove unused perf_counts.aggr field

Namhyung Kim posted 19 patches 3 years, 6 months ago
[PATCH 19/19] perf stat: Remove unused perf_counts.aggr field
Posted by Namhyung Kim 3 years, 6 months ago
The aggr field in the struct perf_counts is to keep the aggregated value
in the AGGR_GLOBAL for the old code.  But it's not used anymore.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/counts.c |  1 -
 tools/perf/util/counts.h |  1 -
 tools/perf/util/stat.c   | 35 ++---------------------------------
 3 files changed, 2 insertions(+), 35 deletions(-)

diff --git a/tools/perf/util/counts.c b/tools/perf/util/counts.c
index 7a447d918458..11cd85b278a6 100644
--- a/tools/perf/util/counts.c
+++ b/tools/perf/util/counts.c
@@ -48,7 +48,6 @@ void perf_counts__reset(struct perf_counts *counts)
 {
 	xyarray__reset(counts->loaded);
 	xyarray__reset(counts->values);
-	memset(&counts->aggr, 0, sizeof(struct perf_counts_values));
 }
 
 void evsel__reset_counts(struct evsel *evsel)
diff --git a/tools/perf/util/counts.h b/tools/perf/util/counts.h
index 5de275194f2b..42760242e0df 100644
--- a/tools/perf/util/counts.h
+++ b/tools/perf/util/counts.h
@@ -11,7 +11,6 @@ struct evsel;
 
 struct perf_counts {
 	s8			  scaled;
-	struct perf_counts_values aggr;
 	struct xyarray		  *values;
 	struct xyarray		  *loaded;
 };
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 1652586a4925..0dccfa273fa7 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -307,8 +307,6 @@ static void evsel__copy_prev_raw_counts(struct evsel *evsel)
 				*perf_counts(evsel->prev_raw_counts, idx, thread);
 		}
 	}
-
-	evsel->counts->aggr = evsel->prev_raw_counts->aggr;
 }
 
 void evlist__copy_prev_raw_counts(struct evlist *evlist)
@@ -319,26 +317,6 @@ void evlist__copy_prev_raw_counts(struct evlist *evlist)
 		evsel__copy_prev_raw_counts(evsel);
 }
 
-void evlist__save_aggr_prev_raw_counts(struct evlist *evlist)
-{
-	struct evsel *evsel;
-
-	/*
-	 * To collect the overall statistics for interval mode,
-	 * we copy the counts from evsel->prev_raw_counts to
-	 * evsel->counts. The perf_stat_process_counter creates
-	 * aggr values from per cpu values, but the per cpu values
-	 * are 0 for AGGR_GLOBAL. So we use a trick that saves the
-	 * previous aggr value to the first member of perf_counts,
-	 * then aggr calculation in process_counter_values can work
-	 * correctly.
-	 */
-	evlist__for_each_entry(evlist, evsel) {
-		*perf_counts(evsel->prev_raw_counts, 0, 0) =
-			evsel->prev_raw_counts->aggr;
-	}
-}
-
 static size_t pkg_id_hash(const void *__key, void *ctx __maybe_unused)
 {
 	uint64_t *key = (uint64_t *) __key;
@@ -422,7 +400,6 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
 		       int cpu_map_idx, int thread,
 		       struct perf_counts_values *count)
 {
-	struct perf_counts_values *aggr = &evsel->counts->aggr;
 	struct perf_stat_evsel *ps = evsel->stats;
 	static struct perf_counts_values zero;
 	bool skip = false;
@@ -491,12 +468,6 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
 		}
 	}
 
-	if (config->aggr_mode == AGGR_GLOBAL) {
-		aggr->val += count->val;
-		aggr->ena += count->ena;
-		aggr->run += count->run;
-	}
-
 	return 0;
 }
 
@@ -521,13 +492,10 @@ static int process_counter_maps(struct perf_stat_config *config,
 int perf_stat_process_counter(struct perf_stat_config *config,
 			      struct evsel *counter)
 {
-	struct perf_counts_values *aggr = &counter->counts->aggr;
 	struct perf_stat_evsel *ps = counter->stats;
-	u64 *count = counter->counts->aggr.values;
+	u64 *count;
 	int ret;
 
-	aggr->val = aggr->ena = aggr->run = 0;
-
 	if (counter->per_pkg)
 		evsel__zero_per_pkg(counter);
 
@@ -538,6 +506,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 	if (config->aggr_mode != AGGR_GLOBAL)
 		return 0;
 
+	count = ps->aggr[0].counts.values;
 	update_stats(&ps->res_stats, *count);
 
 	if (verbose > 0) {
-- 
2.38.0.rc1.362.ged0d419d3c-goog
Re: [PATCH 19/19] perf stat: Remove unused perf_counts.aggr field
Posted by Jiri Olsa 3 years, 5 months ago
On Sun, Oct 09, 2022 at 10:36:00PM -0700, Namhyung Kim wrote:
> The aggr field in the struct perf_counts is to keep the aggregated value
> in the AGGR_GLOBAL for the old code.  But it's not used anymore.
> 
> Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> ---
>  tools/perf/util/counts.c |  1 -
>  tools/perf/util/counts.h |  1 -
>  tools/perf/util/stat.c   | 35 ++---------------------------------
>  3 files changed, 2 insertions(+), 35 deletions(-)
> 
> diff --git a/tools/perf/util/counts.c b/tools/perf/util/counts.c
> index 7a447d918458..11cd85b278a6 100644
> --- a/tools/perf/util/counts.c
> +++ b/tools/perf/util/counts.c
> @@ -48,7 +48,6 @@ void perf_counts__reset(struct perf_counts *counts)
>  {
>  	xyarray__reset(counts->loaded);
>  	xyarray__reset(counts->values);
> -	memset(&counts->aggr, 0, sizeof(struct perf_counts_values));
>  }
>  
>  void evsel__reset_counts(struct evsel *evsel)
> diff --git a/tools/perf/util/counts.h b/tools/perf/util/counts.h
> index 5de275194f2b..42760242e0df 100644
> --- a/tools/perf/util/counts.h
> +++ b/tools/perf/util/counts.h
> @@ -11,7 +11,6 @@ struct evsel;
>  
>  struct perf_counts {
>  	s8			  scaled;
> -	struct perf_counts_values aggr;
>  	struct xyarray		  *values;
>  	struct xyarray		  *loaded;
>  };
> diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
> index 1652586a4925..0dccfa273fa7 100644
> --- a/tools/perf/util/stat.c
> +++ b/tools/perf/util/stat.c
> @@ -307,8 +307,6 @@ static void evsel__copy_prev_raw_counts(struct evsel *evsel)
>  				*perf_counts(evsel->prev_raw_counts, idx, thread);
>  		}
>  	}
> -
> -	evsel->counts->aggr = evsel->prev_raw_counts->aggr;
>  }
>  
>  void evlist__copy_prev_raw_counts(struct evlist *evlist)
> @@ -319,26 +317,6 @@ void evlist__copy_prev_raw_counts(struct evlist *evlist)
>  		evsel__copy_prev_raw_counts(evsel);
>  }
>  
> -void evlist__save_aggr_prev_raw_counts(struct evlist *evlist)
> -{
> -	struct evsel *evsel;
> -
> -	/*
> -	 * To collect the overall statistics for interval mode,
> -	 * we copy the counts from evsel->prev_raw_counts to
> -	 * evsel->counts. The perf_stat_process_counter creates
> -	 * aggr values from per cpu values, but the per cpu values
> -	 * are 0 for AGGR_GLOBAL. So we use a trick that saves the
> -	 * previous aggr value to the first member of perf_counts,
> -	 * then aggr calculation in process_counter_values can work
> -	 * correctly.
> -	 */
> -	evlist__for_each_entry(evlist, evsel) {
> -		*perf_counts(evsel->prev_raw_counts, 0, 0) =
> -			evsel->prev_raw_counts->aggr;
> -	}
> -}
> -
>  static size_t pkg_id_hash(const void *__key, void *ctx __maybe_unused)
>  {
>  	uint64_t *key = (uint64_t *) __key;
> @@ -422,7 +400,6 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
>  		       int cpu_map_idx, int thread,
>  		       struct perf_counts_values *count)
>  {
> -	struct perf_counts_values *aggr = &evsel->counts->aggr;
>  	struct perf_stat_evsel *ps = evsel->stats;
>  	static struct perf_counts_values zero;
>  	bool skip = false;
> @@ -491,12 +468,6 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
>  		}
>  	}
>  
> -	if (config->aggr_mode == AGGR_GLOBAL) {
> -		aggr->val += count->val;
> -		aggr->ena += count->ena;
> -		aggr->run += count->run;
> -	}
> -
>  	return 0;
>  }
>  
> @@ -521,13 +492,10 @@ static int process_counter_maps(struct perf_stat_config *config,
>  int perf_stat_process_counter(struct perf_stat_config *config,
>  			      struct evsel *counter)
>  {
> -	struct perf_counts_values *aggr = &counter->counts->aggr;
>  	struct perf_stat_evsel *ps = counter->stats;
> -	u64 *count = counter->counts->aggr.values;
> +	u64 *count;
>  	int ret;
>  
> -	aggr->val = aggr->ena = aggr->run = 0;
> -
>  	if (counter->per_pkg)
>  		evsel__zero_per_pkg(counter);
>  
> @@ -538,6 +506,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
>  	if (config->aggr_mode != AGGR_GLOBAL)
>  		return 0;
>  
> +	count = ps->aggr[0].counts.values;
>  	update_stats(&ps->res_stats, *count);

hi,
for some reason 'count' could be NULL, I'm getting crash in here:

	$ ./perf stat record -o krava.data true 
	...

	$ gdb ./perf

	(gdb) r stat report -i krava.data
	Starting program: /home/jolsa/kernel/linux-perf/tools/perf/perf stat report -i krava.data
	[Thread debugging using libthread_db enabled]
	Using host libthread_db library "/lib64/libthread_db.so.1".

	Program received signal SIGSEGV, Segmentation fault.
	0x00000000005ae90b in perf_stat_process_counter (config=0xe18d60 <stat_config>, counter=0xecfd00) at util/stat.c:510
	510             update_stats(&ps->res_stats, *count);
	Missing separate debuginfos, use: dnf debuginfo-install bzip2-libs-1.0.8-11.fc36.x86_64 cyrus-sasl-lib-2.1.27-18.fc36.x86_64 elfutils-debuginfod-client-0.187-4.fc36.x86_64 elfutils-libelf-0.187-4.fc36.x86_64 elfutils-libs-0.187-4.fc36.x86_64 glibc-2.35-15.fc36.x86_64 glibc-2.35-17.fc36.x86_64 keyutils-libs-1.6.1-4.fc36.x86_64 krb5-libs-1.19.2-11.fc36.x86_64 libbrotli-1.0.9-7.fc36.x86_64 libcap-2.48-4.fc36.x86_64 libcom_err-1.46.5-2.fc36.x86_64 libcurl-7.82.0-8.fc36.x86_64 libevent-2.1.12-6.fc36.x86_64 libgcc-12.2.1-2.fc36.x86_64 libidn2-2.3.3-1.fc36.x86_64 libnghttp2-1.46.0-2.fc36.x86_64 libpsl-0.21.1-5.fc36.x86_64 libselinux-3.3-4.fc36.x86_64 libssh-0.9.6-4.fc36.x86_64 libunistring-1.0-1.fc36.x86_64 libunwind-1.6.2-2.fc36.x86_64 libxcrypt-4.4.28-1.fc36.x86_64 libzstd-1.5.2-2.fc36.x86_64 numactl-libs-2.0.14-5.fc36.x86_64 openldap-2.6.3-1.fc36.x86_64 openssl-libs-3.0.5-1.fc36.x86_64 perl-libs-5.34.1-486.fc36.x86_64 python3-libs-3.10.7-1.fc36.x86_64 slang-2.3.2-11.fc36.x86_64 xz-libs-5.2.5-9.fc36.x86_64 zlib-1.2.11-33.fc36.x86_64
	(gdb) bt
	#0  0x00000000005ae90b in perf_stat_process_counter (config=0xe18d60 <stat_config>, counter=0xecfd00) at util/stat.c:510
	#1  0x000000000043b716 in process_counters () at builtin-stat.c:485
	#2  0x000000000043f2bf in process_stat_round_event (session=0xec84f0, event=0x7ffff7ffaba8) at builtin-stat.c:2099
	#3  0x000000000056c7b6 in perf_session__process_user_event (session=0xec84f0, event=0x7ffff7ffaba8, file_offset=2984, file_path=0xecf220 "krava.data")
	    at util/session.c:1714
	#4  0x000000000056cea5 in perf_session__process_event (session=0xec84f0, event=0x7ffff7ffaba8, file_offset=2984, file_path=0xecf220 "krava.data")
	    at util/session.c:1857
	#5  0x000000000056e4fa in process_simple (session=0xec84f0, event=0x7ffff7ffaba8, file_offset=2984, file_path=0xecf220 "krava.data") at util/session.c:2432
	#6  0x000000000056e1b9 in reader__read_event (rd=0x7fffffffb6c0, session=0xec84f0, prog=0x7fffffffb690) at util/session.c:2361
	#7  0x000000000056e3ae in reader__process_events (rd=0x7fffffffb6c0, session=0xec84f0, prog=0x7fffffffb690) at util/session.c:2410
	#8  0x000000000056e652 in __perf_session__process_events (session=0xec84f0) at util/session.c:2457
	#9  0x000000000056eff8 in perf_session__process_events (session=0xec84f0) at util/session.c:2623
	#10 0x000000000043fa53 in __cmd_report (argc=0, argv=0x7fffffffdf70) at builtin-stat.c:2265
	#11 0x000000000043fd94 in cmd_stat (argc=3, argv=0x7fffffffdf70) at builtin-stat.c:2346
	#12 0x00000000004ef495 in run_builtin (p=0xe2f930 <commands+336>, argc=4, argv=0x7fffffffdf70) at perf.c:322
	#13 0x00000000004ef709 in handle_internal_command (argc=4, argv=0x7fffffffdf70) at perf.c:376
	#14 0x00000000004ef858 in run_argv (argcp=0x7fffffffdd9c, argv=0x7fffffffdd90) at perf.c:420
	#15 0x00000000004efc1f in main (argc=4, argv=0x7fffffffdf70) at perf.c:550
	(gdb) p count
	$1 = (u64 *) 0x0

jirka

>  
>  	if (verbose > 0) {
> -- 
> 2.38.0.rc1.362.ged0d419d3c-goog
> 
Re: [PATCH 19/19] perf stat: Remove unused perf_counts.aggr field
Posted by Namhyung Kim 3 years, 5 months ago
Hi Jiri,

On Wed, Oct 12, 2022 at 1:41 AM Jiri Olsa <olsajiri@gmail.com> wrote:
>
> On Sun, Oct 09, 2022 at 10:36:00PM -0700, Namhyung Kim wrote:
> > The aggr field in the struct perf_counts is to keep the aggregated value
> > in the AGGR_GLOBAL for the old code.  But it's not used anymore.
> >
> > Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> > ---
> >  tools/perf/util/counts.c |  1 -
> >  tools/perf/util/counts.h |  1 -
> >  tools/perf/util/stat.c   | 35 ++---------------------------------
> >  3 files changed, 2 insertions(+), 35 deletions(-)
> >
> > diff --git a/tools/perf/util/counts.c b/tools/perf/util/counts.c
> > index 7a447d918458..11cd85b278a6 100644
> > --- a/tools/perf/util/counts.c
> > +++ b/tools/perf/util/counts.c
> > @@ -48,7 +48,6 @@ void perf_counts__reset(struct perf_counts *counts)
> >  {
> >       xyarray__reset(counts->loaded);
> >       xyarray__reset(counts->values);
> > -     memset(&counts->aggr, 0, sizeof(struct perf_counts_values));
> >  }
> >
> >  void evsel__reset_counts(struct evsel *evsel)
> > diff --git a/tools/perf/util/counts.h b/tools/perf/util/counts.h
> > index 5de275194f2b..42760242e0df 100644
> > --- a/tools/perf/util/counts.h
> > +++ b/tools/perf/util/counts.h
> > @@ -11,7 +11,6 @@ struct evsel;
> >
> >  struct perf_counts {
> >       s8                        scaled;
> > -     struct perf_counts_values aggr;
> >       struct xyarray            *values;
> >       struct xyarray            *loaded;
> >  };
> > diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
> > index 1652586a4925..0dccfa273fa7 100644
> > --- a/tools/perf/util/stat.c
> > +++ b/tools/perf/util/stat.c
> > @@ -307,8 +307,6 @@ static void evsel__copy_prev_raw_counts(struct evsel *evsel)
> >                               *perf_counts(evsel->prev_raw_counts, idx, thread);
> >               }
> >       }
> > -
> > -     evsel->counts->aggr = evsel->prev_raw_counts->aggr;
> >  }
> >
> >  void evlist__copy_prev_raw_counts(struct evlist *evlist)
> > @@ -319,26 +317,6 @@ void evlist__copy_prev_raw_counts(struct evlist *evlist)
> >               evsel__copy_prev_raw_counts(evsel);
> >  }
> >
> > -void evlist__save_aggr_prev_raw_counts(struct evlist *evlist)
> > -{
> > -     struct evsel *evsel;
> > -
> > -     /*
> > -      * To collect the overall statistics for interval mode,
> > -      * we copy the counts from evsel->prev_raw_counts to
> > -      * evsel->counts. The perf_stat_process_counter creates
> > -      * aggr values from per cpu values, but the per cpu values
> > -      * are 0 for AGGR_GLOBAL. So we use a trick that saves the
> > -      * previous aggr value to the first member of perf_counts,
> > -      * then aggr calculation in process_counter_values can work
> > -      * correctly.
> > -      */
> > -     evlist__for_each_entry(evlist, evsel) {
> > -             *perf_counts(evsel->prev_raw_counts, 0, 0) =
> > -                     evsel->prev_raw_counts->aggr;
> > -     }
> > -}
> > -
> >  static size_t pkg_id_hash(const void *__key, void *ctx __maybe_unused)
> >  {
> >       uint64_t *key = (uint64_t *) __key;
> > @@ -422,7 +400,6 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
> >                      int cpu_map_idx, int thread,
> >                      struct perf_counts_values *count)
> >  {
> > -     struct perf_counts_values *aggr = &evsel->counts->aggr;
> >       struct perf_stat_evsel *ps = evsel->stats;
> >       static struct perf_counts_values zero;
> >       bool skip = false;
> > @@ -491,12 +468,6 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
> >               }
> >       }
> >
> > -     if (config->aggr_mode == AGGR_GLOBAL) {
> > -             aggr->val += count->val;
> > -             aggr->ena += count->ena;
> > -             aggr->run += count->run;
> > -     }
> > -
> >       return 0;
> >  }
> >
> > @@ -521,13 +492,10 @@ static int process_counter_maps(struct perf_stat_config *config,
> >  int perf_stat_process_counter(struct perf_stat_config *config,
> >                             struct evsel *counter)
> >  {
> > -     struct perf_counts_values *aggr = &counter->counts->aggr;
> >       struct perf_stat_evsel *ps = counter->stats;
> > -     u64 *count = counter->counts->aggr.values;
> > +     u64 *count;
> >       int ret;
> >
> > -     aggr->val = aggr->ena = aggr->run = 0;
> > -
> >       if (counter->per_pkg)
> >               evsel__zero_per_pkg(counter);
> >
> > @@ -538,6 +506,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
> >       if (config->aggr_mode != AGGR_GLOBAL)
> >               return 0;
> >
> > +     count = ps->aggr[0].counts.values;
> >       update_stats(&ps->res_stats, *count);
>
> hi,
> for some reason 'count' could be NULL, I'm getting crash in here:

Ouch, will check.  Thanks for the test!

Thanks,
Namhyung


>
>         $ ./perf stat record -o krava.data true
>         ...
>
>         $ gdb ./perf
>
>         (gdb) r stat report -i krava.data
>         Starting program: /home/jolsa/kernel/linux-perf/tools/perf/perf stat report -i krava.data
>         [Thread debugging using libthread_db enabled]
>         Using host libthread_db library "/lib64/libthread_db.so.1".
>
>         Program received signal SIGSEGV, Segmentation fault.
>         0x00000000005ae90b in perf_stat_process_counter (config=0xe18d60 <stat_config>, counter=0xecfd00) at util/stat.c:510
>         510             update_stats(&ps->res_stats, *count);
>         Missing separate debuginfos, use: dnf debuginfo-install bzip2-libs-1.0.8-11.fc36.x86_64 cyrus-sasl-lib-2.1.27-18.fc36.x86_64 elfutils-debuginfod-client-0.187-4.fc36.x86_64 elfutils-libelf-0.187-4.fc36.x86_64 elfutils-libs-0.187-4.fc36.x86_64 glibc-2.35-15.fc36.x86_64 glibc-2.35-17.fc36.x86_64 keyutils-libs-1.6.1-4.fc36.x86_64 krb5-libs-1.19.2-11.fc36.x86_64 libbrotli-1.0.9-7.fc36.x86_64 libcap-2.48-4.fc36.x86_64 libcom_err-1.46.5-2.fc36.x86_64 libcurl-7.82.0-8.fc36.x86_64 libevent-2.1.12-6.fc36.x86_64 libgcc-12.2.1-2.fc36.x86_64 libidn2-2.3.3-1.fc36.x86_64 libnghttp2-1.46.0-2.fc36.x86_64 libpsl-0.21.1-5.fc36.x86_64 libselinux-3.3-4.fc36.x86_64 libssh-0.9.6-4.fc36.x86_64 libunistring-1.0-1.fc36.x86_64 libunwind-1.6.2-2.fc36.x86_64 libxcrypt-4.4.28-1.fc36.x86_64 libzstd-1.5.2-2.fc36.x86_64 numactl-libs-2.0.14-5.fc36.x86_64 openldap-2.6.3-1.fc36.x86_64 openssl-libs-3.0.5-1.fc36.x86_64 perl-libs-5.34.1-486.fc36.x86_64 python3-libs-3.10.7-1.fc36.x86_64 slang-2.3.2-11.fc36.x86_64 xz-libs-5.2.5-9.fc36.x86_64 zlib-1.2.11-33.fc36.x86_64
>         (gdb) bt
>         #0  0x00000000005ae90b in perf_stat_process_counter (config=0xe18d60 <stat_config>, counter=0xecfd00) at util/stat.c:510
>         #1  0x000000000043b716 in process_counters () at builtin-stat.c:485
>         #2  0x000000000043f2bf in process_stat_round_event (session=0xec84f0, event=0x7ffff7ffaba8) at builtin-stat.c:2099
>         #3  0x000000000056c7b6 in perf_session__process_user_event (session=0xec84f0, event=0x7ffff7ffaba8, file_offset=2984, file_path=0xecf220 "krava.data")
>             at util/session.c:1714
>         #4  0x000000000056cea5 in perf_session__process_event (session=0xec84f0, event=0x7ffff7ffaba8, file_offset=2984, file_path=0xecf220 "krava.data")
>             at util/session.c:1857
>         #5  0x000000000056e4fa in process_simple (session=0xec84f0, event=0x7ffff7ffaba8, file_offset=2984, file_path=0xecf220 "krava.data") at util/session.c:2432
>         #6  0x000000000056e1b9 in reader__read_event (rd=0x7fffffffb6c0, session=0xec84f0, prog=0x7fffffffb690) at util/session.c:2361
>         #7  0x000000000056e3ae in reader__process_events (rd=0x7fffffffb6c0, session=0xec84f0, prog=0x7fffffffb690) at util/session.c:2410
>         #8  0x000000000056e652 in __perf_session__process_events (session=0xec84f0) at util/session.c:2457
>         #9  0x000000000056eff8 in perf_session__process_events (session=0xec84f0) at util/session.c:2623
>         #10 0x000000000043fa53 in __cmd_report (argc=0, argv=0x7fffffffdf70) at builtin-stat.c:2265
>         #11 0x000000000043fd94 in cmd_stat (argc=3, argv=0x7fffffffdf70) at builtin-stat.c:2346
>         #12 0x00000000004ef495 in run_builtin (p=0xe2f930 <commands+336>, argc=4, argv=0x7fffffffdf70) at perf.c:322
>         #13 0x00000000004ef709 in handle_internal_command (argc=4, argv=0x7fffffffdf70) at perf.c:376
>         #14 0x00000000004ef858 in run_argv (argcp=0x7fffffffdd9c, argv=0x7fffffffdd90) at perf.c:420
>         #15 0x00000000004efc1f in main (argc=4, argv=0x7fffffffdf70) at perf.c:550
>         (gdb) p count
>         $1 = (u64 *) 0x0
>
> jirka
>
> >
> >       if (verbose > 0) {
> > --
> > 2.38.0.rc1.362.ged0d419d3c-goog
> >
[PATCH] perf stat: Init aggr_map when reporting per-process stat
Posted by Namhyung Kim 3 years, 5 months ago
I'll merge this into the problematic commit.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/builtin-stat.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 4cb3ceeb7ba4..9d35a3338976 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1355,7 +1355,11 @@ static struct aggr_cpu_id perf_stat__get_cpu(struct perf_stat_config *config __m
 static struct aggr_cpu_id perf_stat__get_aggr(struct perf_stat_config *config,
 					      aggr_get_id_t get_id, struct perf_cpu cpu)
 {
-	struct aggr_cpu_id id = aggr_cpu_id__empty();
+	struct aggr_cpu_id id;
+
+	/* per-process mode - should use global aggr mode */
+	if (cpu.cpu == -1)
+		return get_id(config, cpu);
 
 	if (aggr_cpu_id__is_empty(&config->cpus_aggr_map->map[cpu.cpu]))
 		config->cpus_aggr_map->map[cpu.cpu] = get_id(config, cpu);
@@ -2120,11 +2124,9 @@ int process_stat_config_event(struct perf_session *session,
 	if (perf_cpu_map__empty(st->cpus)) {
 		if (st->aggr_mode != AGGR_UNSET)
 			pr_warning("warning: processing task data, aggregation mode not set\n");
-		return 0;
-	}
-
-	if (st->aggr_mode != AGGR_UNSET)
+	} else if (st->aggr_mode != AGGR_UNSET) {
 		stat_config.aggr_mode = st->aggr_mode;
+	}
 
 	if (perf_stat.data.is_pipe)
 		perf_stat_init_aggr_mode();
-- 
2.38.0.413.g74048e4d9e-goog
Re: [PATCH 19/19] perf stat: Remove unused perf_counts.aggr field
Posted by Ian Rogers 3 years, 6 months ago
On Sun, Oct 9, 2022 at 10:36 PM Namhyung Kim <namhyung@kernel.org> wrote:
>
> The aggr field in the struct perf_counts is to keep the aggregated value
> in the AGGR_GLOBAL for the old code.  But it's not used anymore.
>
> Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> ---
>  tools/perf/util/counts.c |  1 -
>  tools/perf/util/counts.h |  1 -
>  tools/perf/util/stat.c   | 35 ++---------------------------------
>  3 files changed, 2 insertions(+), 35 deletions(-)

Very nice!

Acked-by: Ian Rogers <irogers@google.com>

Thanks,
Ian

>
> diff --git a/tools/perf/util/counts.c b/tools/perf/util/counts.c
> index 7a447d918458..11cd85b278a6 100644
> --- a/tools/perf/util/counts.c
> +++ b/tools/perf/util/counts.c
> @@ -48,7 +48,6 @@ void perf_counts__reset(struct perf_counts *counts)
>  {
>         xyarray__reset(counts->loaded);
>         xyarray__reset(counts->values);
> -       memset(&counts->aggr, 0, sizeof(struct perf_counts_values));
>  }
>
>  void evsel__reset_counts(struct evsel *evsel)
> diff --git a/tools/perf/util/counts.h b/tools/perf/util/counts.h
> index 5de275194f2b..42760242e0df 100644
> --- a/tools/perf/util/counts.h
> +++ b/tools/perf/util/counts.h
> @@ -11,7 +11,6 @@ struct evsel;
>
>  struct perf_counts {
>         s8                        scaled;
> -       struct perf_counts_values aggr;
>         struct xyarray            *values;
>         struct xyarray            *loaded;
>  };
> diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
> index 1652586a4925..0dccfa273fa7 100644
> --- a/tools/perf/util/stat.c
> +++ b/tools/perf/util/stat.c
> @@ -307,8 +307,6 @@ static void evsel__copy_prev_raw_counts(struct evsel *evsel)
>                                 *perf_counts(evsel->prev_raw_counts, idx, thread);
>                 }
>         }
> -
> -       evsel->counts->aggr = evsel->prev_raw_counts->aggr;
>  }
>
>  void evlist__copy_prev_raw_counts(struct evlist *evlist)
> @@ -319,26 +317,6 @@ void evlist__copy_prev_raw_counts(struct evlist *evlist)
>                 evsel__copy_prev_raw_counts(evsel);
>  }
>
> -void evlist__save_aggr_prev_raw_counts(struct evlist *evlist)
> -{
> -       struct evsel *evsel;
> -
> -       /*
> -        * To collect the overall statistics for interval mode,
> -        * we copy the counts from evsel->prev_raw_counts to
> -        * evsel->counts. The perf_stat_process_counter creates
> -        * aggr values from per cpu values, but the per cpu values
> -        * are 0 for AGGR_GLOBAL. So we use a trick that saves the
> -        * previous aggr value to the first member of perf_counts,
> -        * then aggr calculation in process_counter_values can work
> -        * correctly.
> -        */
> -       evlist__for_each_entry(evlist, evsel) {
> -               *perf_counts(evsel->prev_raw_counts, 0, 0) =
> -                       evsel->prev_raw_counts->aggr;
> -       }
> -}
> -
>  static size_t pkg_id_hash(const void *__key, void *ctx __maybe_unused)
>  {
>         uint64_t *key = (uint64_t *) __key;
> @@ -422,7 +400,6 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
>                        int cpu_map_idx, int thread,
>                        struct perf_counts_values *count)
>  {
> -       struct perf_counts_values *aggr = &evsel->counts->aggr;
>         struct perf_stat_evsel *ps = evsel->stats;
>         static struct perf_counts_values zero;
>         bool skip = false;
> @@ -491,12 +468,6 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
>                 }
>         }
>
> -       if (config->aggr_mode == AGGR_GLOBAL) {
> -               aggr->val += count->val;
> -               aggr->ena += count->ena;
> -               aggr->run += count->run;
> -       }
> -
>         return 0;
>  }
>
> @@ -521,13 +492,10 @@ static int process_counter_maps(struct perf_stat_config *config,
>  int perf_stat_process_counter(struct perf_stat_config *config,
>                               struct evsel *counter)
>  {
> -       struct perf_counts_values *aggr = &counter->counts->aggr;
>         struct perf_stat_evsel *ps = counter->stats;
> -       u64 *count = counter->counts->aggr.values;
> +       u64 *count;
>         int ret;
>
> -       aggr->val = aggr->ena = aggr->run = 0;
> -
>         if (counter->per_pkg)
>                 evsel__zero_per_pkg(counter);
>
> @@ -538,6 +506,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
>         if (config->aggr_mode != AGGR_GLOBAL)
>                 return 0;
>
> +       count = ps->aggr[0].counts.values;
>         update_stats(&ps->res_stats, *count);
>
>         if (verbose > 0) {
> --
> 2.38.0.rc1.362.ged0d419d3c-goog
>