perf stat: Support per-die aggregation
tip-bot for Kan Liang
merge botCommit-ID: db5742b6849ed7f01d764e6755b8ab2b422f29b2 Gitweb: https://git.kernel.org/tip/db5742b6849ed7f01d764e6755b8ab2b422f29b2 Author: Kan Liang <[email protected]> AuthorDate: Tue, 4 Jun 2019 15:50:42 -0700 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitDate: Mon, 10 Jun 2019 16:19:59 -0300
perf stat: Support per-die aggregation
It is useful to aggregate counts per die. E.g. Uncore becomes die-scope on Xeon Cascade Lake-AP.
Introduce a new option "--per-die" to support per-die aggregation.
The global id for each core has been changed to socket + die id + core id. The global id for each die is socket + die id.
Add die information for per-core aggregation. The output of per-core aggregation will be changed from "S0-C0" to "S0-D0-C0". Any scripts which rely on the output format of per-core aggregation probably be broken.
For 'perf stat record/report', there is no die information when processing the old perf.data. The per-die result will be the same as per-socket.
Committer notes:
Renamed 'die' variable to 'die_id' to fix the build in some systems:
CC /tmp/build/perf/builtin-script.o
cc1: warnings being treated as errors
builtin-stat.c: In function 'perf_env__get_die':
builtin-stat.c:963: error: declaration of 'die' shadows a global declaration util/util.h:19: error: shadowed declaration is here
mv: cannot stat `/tmp/build/perf/.builtin-stat.o.tmp': No such file or directory
--- tools/perf/Documentation/perf-stat.txt | 10 ++++ tools/perf/builtin-stat.c | 87 +++++++++++++++++++++++++++++++--- tools/perf/util/cpumap.c | 57 +++++++++++++++++++--- tools/perf/util/cpumap.h | 9 +++- tools/perf/util/stat-display.c | 29 ++++++++++-- tools/perf/util/stat-shadow.c | 1 + tools/perf/util/stat.c | 1 + tools/perf/util/stat.h | 1 + 8 files changed, 177 insertions(+), 18 deletions(-)
tools/perf/Documentation/perf-stat.txt +10 -0
@@ -200,6 +200,13 @@ use --per-socket in addition to -a. (system-wide). The output includes the socket number and the number of online processors on that socket. This is useful to gauge the amount of aggregation. +--per-die:: +Aggregate counts per processor die for system-wide mode measurements. This +is a useful mode to detect imbalance between dies. To enable this mode, +use --per-die in addition to -a. (system-wide). The output includes the +die number and the number of online processors on that die. This is +useful to gauge the amount of aggregation. + --per-core:: Aggregate counts per physical processor for system-wide mode measurements. This is a useful mode to detect imbalance between physical cores. To enable this mode,
@@ -239,6 +246,9 @@ Input file name. --per-socket:: Aggregate counts per processor socket for system-wide mode measurements. +--per-die:: +Aggregate counts per processor die for system-wide mode measurements. + --per-core:: Aggregate counts per physical processor for system-wide mode measurements.
tools/perf/builtin-stat.c +81 -6
150 lines not on this page · raw message
tools/perf/util/cpumap.c +50 -7
86 lines not on this page · raw message
tools/perf/util/cpumap.h +8 -1
@@ -26,9 +26,11 @@ size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);int cpu_map__get_socket_id (int cpu);int cpu_map__get_socket (struct cpu_map *map,int idx,void *data);int cpu_map__get_die_id (int cpu); +int cpu_map__get_die (struct cpu_map *map,int idx,void *data);int cpu_map__get_core_id (int cpu);int cpu_map__get_core (struct cpu_map *map,int idx,void *data);int cpu_map__build_socket_map (struct cpu_map *cpus,struct cpu_map **sockp); +int cpu_map__build_die_map (struct cpu_map *cpus,struct cpu_map **diep);int cpu_map__build_core_map (struct cpu_map *cpus,struct cpu_map **corep);const struct cpu_map *cpu_map__online (void );/* thread unsafe */
@@ -44,7 +46,12 @@ static inline int cpu_map__socket(struct cpu_map *sock, int s)static inline int cpu_map__id_to_socket (int id) { -return id >>16 ; +return id >>24 ; +} + +static inline int cpu_map__id_to_die (int id) +{ +return (id >>16 ) &0xff ; }static inline int cpu_map__id_to_cpu (int id)
tools/perf/util/stat-display.c +25 -4
@@ -69,8 +69,9 @@ static void aggr_printout(struct perf_stat_config *config, {switch (config->aggr_mode) {case AGGR_CORE : - fprintf(config->output, "S%d-C%*d%s%*d%s", + fprintf(config->output, "S%d-D%d-C%*d%s%*d%s", cpu_map__id_to_socket(id), + cpu_map__id_to_die(id), config->csv_output ? 0 : -8, cpu_map__id_to_cpu(id), config->csv_sep,
@@ -78,6 +79,16 @@ static void aggr_printout(struct perf_stat_config *config, nr, config->csv_sep);break ; +case AGGR_DIE : +fprintf (config->output,"S%d-D%*d%s%*d%s" , +cpu_map__id_to_socket (id <<16 ), + config->csv_output ?0 :-8 , +cpu_map__id_to_die (id <<16 ), + config->csv_sep, + config->csv_output ?0 :4 , + nr, + config->csv_sep); +break ;case AGGR_SOCKET : fprintf(config->output, "S%*d%s%*d%s", config->csv_output ? 0 : -5,
@@ -89,8 +100,9 @@ static void aggr_printout(struct perf_stat_config *config,break ;case AGGR_NONE :if (evsel->percore) { -fprintf (config->output,"S%d-C%*d%s" , +fprintf (config->output,"S%d-D%d-C%*d%s" ,cpu_map__id_to_socket (id), +cpu_map__id_to_die (id), config->csv_output ?0 :-5 ,cpu_map__id_to_cpu (id), config->csv_sep); }else {
@@ -407,6 +419,7 @@ static void printout(struct perf_stat_config *config, int id, int nr, [AGGR_THREAD] = 1, [AGGR_NONE] = 1, [AGGR_SOCKET] = 2, + [AGGR_DIE] = 2, [AGGR_CORE] = 2, };
@@ -879,7 +892,8 @@ static void print_no_aggr_metric(struct perf_stat_config *config, }static int aggr_header_lens[] = { - [AGGR_CORE ] =18 , + [AGGR_CORE ] =24 , + [AGGR_DIE ] =18 , [AGGR_SOCKET ] =12 , [AGGR_NONE ] =6 , [AGGR_THREAD ] =24 ,
@@ -888,6 +902,7 @@ static int aggr_header_lens[] = {static const char *aggr_header_csv[] = { [AGGR_CORE ] ="core,cpus," , + [AGGR_DIE ] ="die,cpus" , [AGGR_SOCKET ] ="socket,cpus" , [AGGR_NONE ] ="cpu," , [AGGR_THREAD ] ="comm-pid," ,
@@ -954,8 +969,13 @@ static void print_interval(struct perf_stat_config *config,if (!metric_only)fprintf (output," counts %*s events\n" , unit_width,"unit" );break ; +case AGGR_DIE : +fprintf (output,"# time die cpus" ); +if (!metric_only) +fprintf (output," counts %*s events\n" , unit_width,"unit" ); +break ;case AGGR_CORE : -fprintf (output,"# time core cpus" ); +fprintf (output,"# time core cpus" );if (!metric_only)fprintf (output," counts %*s events\n" , unit_width,"unit" );break ;
@@ -1165,6 +1185,7 @@ perf_evlist__print_counters(struct perf_evlist *evlist,switch (config->aggr_mode) {case AGGR_CORE : +case AGGR_DIE :case AGGR_SOCKET :print_aggr (config, evlist, prefix);break ;
tools/perf/util/stat-shadow.c +1 -0
@@ -12,6 +12,7 @@/* * AGGR_GLOBAL: Use CPU 0 * AGGR_SOCKET: Use first CPU of socket +* AGGR_DIE: Use first CPU of die * AGGR_CORE: Use first CPU of core * AGGR_NONE: Use matching CPU * AGGR_THREAD: Not supported?
tools/perf/util/stat.c +1 -0
@@ -272,6 +272,7 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evselswitch (config->aggr_mode) {case AGGR_THREAD :case AGGR_CORE : +case AGGR_DIE :case AGGR_SOCKET :case AGGR_NONE :if (!evsel->snapshot)
tools/perf/util/stat.h +1 -0
@@ -44,6 +44,7 @@ enum aggr_mode {AGGR_NONE ,AGGR_GLOBAL ,AGGR_SOCKET , +AGGR_DIE ,AGGR_CORE ,AGGR_THREAD , AGGR_UNSET,