perf stat: fix per-pkg event reporting bug
PATCH v2 1/1 perf stat: fix per-pkg event reporting bug
Per-pkg events need to be captured once per processor socket. The code in check_per_pkg() ensures only one value per processor package is used. However there is a problem with this function in case the first CPU of the package does not measure anything for the per-pkg event, but other CPUs do.
Consider the following
$ create cgroup FOO; echo $$ >FOO/tasks; taskset -c 1 noploop & $ perf stat -a -I 1000 -e intel_cqm/llc_occupancy/ -G FOO sleep 100 1.00000 <not counted> Bytes intel_cqm/llc_occupancy/ FOO
The reason for this is that CPU0 in the cgrop has nothing running on it. Yet check_per_plg() will mark socket0 as processed and no other event value will be considered for the socket.
This patch fixes the problem by having check_per_pkg() only consider events which actually ran.
--- tools/perf/util/stat.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-)
tools/perf/util/stat.c +14 -2
@@ -196,7 +196,8 @@ static void zero_per_pkg(struct perf_evsel *counter)memset (counter->per_pkg_mask,0 ,MAX_NR_CPUS ); } -static int check_per_pkg (struct perf_evsel *counter,int cpu,bool *skip) +static int check_per_pkg (struct perf_evsel *counter, +struct perf_counts_values *vals,int cpu,bool *skip) {unsigned long *mask = counter->per_pkg_mask;struct cpu_map *cpus =perf_evsel__cpus (counter);
@@ -218,6 +219,17 @@ static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip) counter->per_pkg_mask = mask; } +/* +* we do not consider an event that has not run as a good +* instance to mark a package as used (skip=1). Otherwise +* we may run into a situation where the first CPU in a package +* is not running anything, yet the second is, and this function +* would mark the package as used after the first CPU and would +* not read the values from the second CPU. +*/ +if (!(vals->run && vals->ena)) +return 0 ; + s =cpu_map__get_socket (cpus, cpu);if (s <0 )return -1 ;
@@ -235,7 +247,7 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evselstatic struct perf_counts_values zero;bool skip = false; -if (check_per_pkg (evsel, cpu, &skip)) { +if (check_per_pkg (evsel, count, cpu, &skip)) {pr_err ("failed to read per-pkg counter\n" );return -1 ; }
Signature · 1 line
1.9.1
tip-bot for Stephane Eranian
merge bot[tip:perf/urgent] perf stat: Fix per-pkg event reporting bug
perf stat: Fix per-pkg event reporting bug
Commit-ID: 02d8dabc50f94353075f2f62b1047c1306e8bf92 Gitweb: http://git.kernel.org/tip/02d8dabc50f94353075f2f62b1047c1306e8bf92 Author: Stephane Eranian <[email protected]> AuthorDate: Thu, 3 Sep 2015 15:23:40 +0200 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitDate: Wed, 16 Sep 2015 18:01:03 -0300
perf stat: Fix per-pkg event reporting bug
Per-pkg events need to be captured once per processor socket. The code in check_per_pkg() ensures only one value per processor package is used. However there is a problem with this function in case the first CPU of the package does not measure anything for the per-pkg event, but other CPUs do.
Consider the following:
$ create cgroup FOO; echo $$ >FOO/tasks; taskset -c 1 noploop &
$ perf stat -a -I 1000 -e intel_cqm/llc_occupancy/ -G FOO sleep 100
1.00000 <not counted> Bytes intel_cqm/llc_occupancy/ FOOThe reason for this is that CPU0 in the cgroup has nothing running on it. Yet check_per_plg() will mark socket0 as processed and no other event value will be considered for the socket.
This patch fixes the problem by having check_per_pkg() only consider events which actually ran.
--- tools/perf/util/stat.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-)
tools/perf/util/stat.c +14 -2
@@ -196,7 +196,8 @@ static void zero_per_pkg(struct perf_evsel *counter)memset (counter->per_pkg_mask,0 ,MAX_NR_CPUS ); } -static int check_per_pkg (struct perf_evsel *counter,int cpu,bool *skip) +static int check_per_pkg (struct perf_evsel *counter, +struct perf_counts_values *vals,int cpu,bool *skip) {unsigned long *mask = counter->per_pkg_mask;struct cpu_map *cpus =perf_evsel__cpus (counter);
@@ -218,6 +219,17 @@ static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip) counter->per_pkg_mask = mask; } +/* +* we do not consider an event that has not run as a good +* instance to mark a package as used (skip=1). Otherwise +* we may run into a situation where the first CPU in a package +* is not running anything, yet the second is, and this function +* would mark the package as used after the first CPU and would +* not read the values from the second CPU. +*/ +if (!(vals->run && vals->ena)) +return 0 ; + s =cpu_map__get_socket (cpus, cpu);if (s <0 )return -1 ;
@@ -235,7 +247,7 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evselstatic struct perf_counts_values zero;bool skip = false; -if (check_per_pkg (evsel, cpu, &skip)) { +if (check_per_pkg (evsel, count, cpu, &skip)) {pr_err ("failed to read per-pkg counter\n" );return -1 ; }