perf stat: Fix uncore aggregation number
PATCH v4 1/1 perf stat: Fix uncore aggregation number
Follow up:
lore.kernel.org/CAP-5=fVDF4-qYL1Lm7efgiHk7X=_nw_nEFMBZFMcsnOOJgX4Kg@mail.gmail.com/
The patch adds unit aggregation during evsel merge the aggregated uncore counters. Change the name of the column to ctrs and counters for json mode.
Tested on a 2-socket machine with SNC3, uncore_imc_[0-11] and cpumask="0,120"
Before:
perf stat -e clockticks -I 1000 --per-socket
# time socket cpus counts unit events
1.001085024 S0 1 9615386315 clockticks
1.001085024 S1 1 9614287448 clockticks
perf stat -e clockticks -I 1000 --per-node
# time node cpus counts unit events
1.001029867 N0 1 3205726984 clockticks
1.001029867 N1 1 3205444421 clockticks
1.001029867 N2 1 3205234018 clockticks
1.001029867 N3 1 3205224660 clockticks
1.001029867 N4 1 3205207213 clockticks
1.001029867 N5 1 3205528246 clockticks
After:
perf stat -e clockticks -I 1000 --per-socket
# time socket ctrs counts unit events
1.001026071 S0 12 9619677996 clockticks
1.001026071 S1 12 9618612614 clockticks
perf stat -e clockticks -I 1000 --per-node
# time node ctrs counts unit events
1.001027449 N0 4 3207251859 clockticks
1.001027449 N1 4 3207315930 clockticks
1.001027449 N2 4 3206981828 clockticks
1.001027449 N3 4 3206566126 clockticks
1.001027449 N4 4 3206032609 clockticks
1.001027449 N5 4 3205651355 clockticksTested with JSON output linter:
perf test "perf stat JSON output linter"
94: perf stat JSON output linter : Ok
---
v4:
Modify perf-stat.txt and json output lint test
v3: https://lore.kernel.org/[email protected]/
Rename the column to ctrs and counters in json mode.
v2: https://lore.kernel.org/[email protected]/
Rename the column to aggr_nr.
Remove unnecessary comment.
v1: https://lore.kernel.org/[email protected]/
tools/perf/Documentation/perf-stat.txt | 6 ++-- .../tests/shell/lib/perf_json_output_lint.py | 4 +-- tools/perf/util/stat-display.c | 34 +++++++++---------- tools/perf/util/stat.c | 2 +- 4 files changed, 24 insertions(+), 22 deletions(-)
tools/perf/Documentation/perf-stat.txt +4 -2
@@ -640,18 +640,20 @@ JSON FORMAT With -j, perf stat is able to print out a JSON format output that can be used for parsing. -- timestamp : optional usec time stamp in fractions of second (with -I) +- interval : optional timestamp in fractions of second (with -I) - optional aggregate options: - core : core identifier (with --per-core) - die : die identifier (with --per-die) - socket : socket identifier (with --per-socket) - node : node identifier (with --per-node) - thread : thread identifier (with --per-thread) +- counters : number of aggregated PMU counters - counter-value : counter value - unit : unit of the counter value or empty - event : event name - variance : optional variance if multiple values are collected (with -r) -- runtime : run time of counter +- event-runtime : run time of the event +- pcnt-running : percentage of time the event was running - metric-value : optional metric value - metric-unit : optional unit of metric
tools/perf/tests/shell/lib/perf_json_output_lint.py +2 -2
@@ -45,7 +45,7 @@ def is_counter_value(num): def check_json_output(expected_items): checks = { - 'aggregate-number': lambda x: isfloat(x), + 'counters': lambda x: isfloat(x), 'core': lambda x: True, 'counter-value': lambda x: is_counter_value(x), 'cgroup': lambda x: True,
@@ -75,7 +75,7 @@ def check_json_output(expected_items): if count not in expected_items and count >= 1 and count <= 7 and 'metric-value' in item: # Events that generate >1 metric may have isolated metric # values and possibly other prefixes like interval, core, - # aggregate-number, or event-runtime/pcnt-running from multiplexing. + # counters, or event-runtime/pcnt-running from multiplexing. pass elif count not in expected_items and count >= 1 and count <= 5 and 'metricgroup' in item: pass
tools/perf/util/stat-display.c +17 -17
@@ -50,15 +50,15 @@ static int aggr_header_lens[] = { };static const char *aggr_header_csv[] = { - [AGGR_CORE ] ="core,cpus," , - [AGGR_CACHE ] ="cache,cpus," , - [AGGR_CLUSTER ] ="cluster,cpus," , - [AGGR_DIE ] ="die,cpus," , - [AGGR_SOCKET ] ="socket,cpus," , - [AGGR_NONE ] ="cpu," , - [AGGR_THREAD ] ="comm-pid," , - [AGGR_NODE ] ="node," , - [AGGR_GLOBAL ] ="" + [AGGR_CORE ] ="core,ctrs," , + [AGGR_CACHE ] ="cache,ctrs," , + [AGGR_CLUSTER ] ="cluster,ctrs," , + [AGGR_DIE ] ="die,ctrs," , + [AGGR_SOCKET ] ="socket,ctrs," , + [AGGR_NONE ] ="cpu," , + [AGGR_THREAD ] ="comm-pid," , + [AGGR_NODE ] ="node," , + [AGGR_GLOBAL ] ="" };static const char *aggr_header_std[] = {
@@ -304,7 +304,7 @@ static void print_aggr_id_std(struct perf_stat_config *config,return ; } -fprintf (output,"%-*s %*d " , aggr_header_lens[idx], buf,4 , aggr_nr); +fprintf (output,"%-*s %*d " , aggr_header_lens[idx], buf,/*strlen("ctrs")*/ 4 , aggr_nr); } static void print_aggr_id_csv(struct perf_stat_config *config,
@@ -366,27 +366,27 @@ static void print_aggr_id_json(struct perf_stat_config *config, struct outstate {switch (config->aggr_mode) {case AGGR_CORE : -json_out (os,"\"core\" : \"S%d-D%d-C%d\", \"aggregate-number\" : %d" , +json_out (os,"\"core\" : \"S%d-D%d-C%d\", \"counters\" : %d" , id.socket, id.die, id.core, aggr_nr);break ;case AGGR_CACHE : -json_out (os,"\"cache\" : \"S%d-D%d-L%d-ID%d\", \"aggregate-number\" : %d" , +json_out (os,"\"cache\" : \"S%d-D%d-L%d-ID%d\", \"counters\" : %d" , id.socket, id.die, id.cache_lvl, id.cache, aggr_nr);break ;case AGGR_CLUSTER : -json_out (os,"\"cluster\" : \"S%d-D%d-CLS%d\", \"aggregate-number\" : %d" , +json_out (os,"\"cluster\" : \"S%d-D%d-CLS%d\", \"counters\" : %d" , id.socket, id.die, id.cluster, aggr_nr);break ;case AGGR_DIE : -json_out (os,"\"die\" : \"S%d-D%d\", \"aggregate-number\" : %d" , +json_out (os,"\"die\" : \"S%d-D%d\", \"counters\" : %d" , id.socket, id.die, aggr_nr);break ;case AGGR_SOCKET : -json_out (os,"\"socket\" : \"S%d\", \"aggregate-number\" : %d" , +json_out (os,"\"socket\" : \"S%d\", \"counters\" : %d" , id.socket, aggr_nr);break ;case AGGR_NODE : -json_out (os,"\"node\" : \"N%d\", \"aggregate-number\" : %d" , +json_out (os,"\"node\" : \"N%d\", \"counters\" : %d" , id.node, aggr_nr);break ;case AGGR_NONE :
@@ -1317,7 +1317,7 @@ static void print_header_interval_std(struct perf_stat_config *config,case AGGR_CLUSTER :case AGGR_CACHE :case AGGR_CORE : -fprintf (output,"#%*s %-*s cpus" , +fprintf (output,"#%*s %-*s ctrs" ,INTERVAL_LEN -1 ,"time" , aggr_header_lens[config->aggr_mode], aggr_header_std[config->aggr_mode]);
tools/perf/util/stat.c +1 -1
@@ -526,7 +526,7 @@ static int evsel__merge_aggr_counters(struct evsel *evsel, struct evsel *alias)struct perf_counts_values *aggr_counts_a = &ps_a->aggr[i].counts;struct perf_counts_values *aggr_counts_b = &ps_b->aggr[i].counts; -/* NB: don't increase aggr.nr for aliases */ + ps_a->aggr[i].nr += ps_b->aggr[i].nr; aggr_counts_a->val += aggr_counts_b->val; aggr_counts_a->ena += aggr_counts_b->ena;
--
2.50.0.727.gbf7dc18ff4-goog
Quoted 37 lines · Chun-Tse Shao
Follow up:
lore.kernel.org/CAP-5=fVDF4-qYL1Lm7efgiHk7X=_nw_nEFMBZFMcsnOOJgX4Kg@mail.gmail.com/The patch adds unit aggregation during evsel merge the aggregated uncore counters. Change the name of the column to
ctrsandcountersfor json mode.Tested on a 2-socket machine with SNC3, uncore_imc_[0-11] and cpumask="0,120"
Before:
perf stat -e clockticks -I 1000 --per-socket
# time socket cpus counts unit events1.001085024 S0 1 9615386315 clockticks 1.001085024 S1 1 9614287448 clockticks perf stat -e clockticks -I 1000 --per-node # time node cpus counts unit events 1.001029867 N0 1 3205726984 clockticks 1.001029867 N1 1 3205444421 clockticks 1.001029867 N2 1 3205234018 clockticks 1.001029867 N3 1 3205224660 clockticks 1.001029867 N4 1 3205207213 clockticks 1.001029867 N5 1 3205528246 clockticks After: perf stat -e clockticks -I 1000 --per-socket # time socket ctrs counts unit events 1.001026071 S0 12 9619677996 clockticks 1.001026071 S1 12 9618612614 clockticks perf stat -e clockticks -I 1000 --per-node # time node ctrs counts unit events 1.001027449 N0 4 3207251859 clockticks 1.001027449 N1 4 3207315930 clockticks 1.001027449 N2 4 3206981828 clockticks 1.001027449 N3 4 3206566126 clockticks 1.001027449 N4 4 3206032609 clockticks 1.001027449 N5 4 3205651355 clockticks
Quoted 6 lines
Tested with JSON output linter:
perf test "perf stat JSON output linter"
94: perf stat JSON output linter : OkSuggested-by Ian Rogers <[email protected]>Signed-off-by Chun-Tse Shao <[email protected]>
Thanks,
Ian
Quoted 166 lines
---
v4:
Modify perf-stat.txt and json output lint testv3: https://lore.kernel.org/[email protected]/
Rename the column toctrsandcountersin json mode.v2: https://lore.kernel.org/[email protected]/
Rename the column toaggr_nr.
Remove unnecessary comment.v1: https://lore.kernel.org/[email protected]/
tools/perf/Documentation/perf-stat.txt | 6 ++-- .../tests/shell/lib/perf_json_output_lint.py | 4 +-- tools/perf/util/stat-display.c | 34 +++++++++---------- tools/perf/util/stat.c | 2 +- 4 files changed, 24 insertions(+), 22 deletions(-)tools/perf/Documentation/perf-stat.txt +4
-2@@ -640,18 +640,20 @@ JSON FORMAT With -j, perf stat is able to print out a JSON format output that can be used for parsing. -- timestamp : optional usec time stamp in fractions of second (with -I) +- interval : optional timestamp in fractions of second (with -I) - optional aggregate options: - core : core identifier (with --per-core) - die : die identifier (with --per-die) - socket : socket identifier (with --per-socket) - node : node identifier (with --per-node) - thread : thread identifier (with --per-thread) +- counters : number of aggregated PMU counters - counter-value : counter value - unit : unit of the counter value or empty - event : event name - variance : optional variance if multiple values are collected (with -r) -- runtime : run time of counter +- event-runtime : run time of the event +- pcnt-running : percentage of time the event was running - metric-value : optional metric value - metric-unit : optional unit of metrictools/perf/tests/shell/lib/perf_json_output_lint.py +2
-2@@ -45,7 +45,7 @@ def is_counter_value(num): def check_json_output(expected_items): checks = { - 'aggregate-number': lambda x: isfloat(x), + 'counters': lambda x: isfloat(x), 'core': lambda x: True, 'counter-value': lambda x: is_counter_value(x), 'cgroup': lambda x: True,@@ -75,7 +75,7 @@ def check_json_output(expected_items): if count not in expected_items and count >= 1 and count <= 7 and 'metric-value' in item: # Events that generate >1 metric may have isolated metric # values and possibly other prefixes like interval, core, - # aggregate-number, or event-runtime/pcnt-running from multiplexing. + # counters, or event-runtime/pcnt-running from multiplexing. pass elif count not in expected_items and count >= 1 and count <= 5 and 'metricgroup' in item: passtools/perf/util/stat-display.c +17
-17@@ -50,15 +50,15 @@ static int aggr_header_lens[] = { };static const char *aggr_header_csv[] = { - [AGGR_CORE ] ="core,cpus," , - [AGGR_CACHE ] ="cache,cpus," , - [AGGR_CLUSTER ] ="cluster,cpus," , - [AGGR_DIE ] ="die,cpus," , - [AGGR_SOCKET ] ="socket,cpus," , - [AGGR_NONE ] ="cpu," , - [AGGR_THREAD ] ="comm-pid," , - [AGGR_NODE ] ="node," , - [AGGR_GLOBAL ] ="" + [AGGR_CORE ] ="core,ctrs," , + [AGGR_CACHE ] ="cache,ctrs," , + [AGGR_CLUSTER ] ="cluster,ctrs," , + [AGGR_DIE ] ="die,ctrs," , + [AGGR_SOCKET ] ="socket,ctrs," , + [AGGR_NONE ] ="cpu," , + [AGGR_THREAD ] ="comm-pid," , + [AGGR_NODE ] ="node," , + [AGGR_GLOBAL ] ="" };static const char *aggr_header_std[] = {@@ -304,7 +304,7 @@ static void print_aggr_id_std(struct perf_stat_config *config,return ; } -fprintf (output,"%-*s %*d " , aggr_header_lens[idx], buf,4 , aggr_nr); +fprintf (output,"%-*s %*d " , aggr_header_lens[idx], buf,/*strlen("ctrs")*/ 4 , aggr_nr); } static void print_aggr_id_csv(struct perf_stat_config *config,@@ -366,27 +366,27 @@ static void print_aggr_id_json(struct perf_stat_config *config, struct outstate {switch (config->aggr_mode) {case AGGR_CORE : -json_out (os,"\"core\" : \"S%d-D%d-C%d\", \"aggregate-number\" : %d" , +json_out (os,"\"core\" : \"S%d-D%d-C%d\", \"counters\" : %d" , id.socket, id.die, id.core, aggr_nr);break ;case AGGR_CACHE : -json_out (os,"\"cache\" : \"S%d-D%d-L%d-ID%d\", \"aggregate-number\" : %d" , +json_out (os,"\"cache\" : \"S%d-D%d-L%d-ID%d\", \"counters\" : %d" , id.socket, id.die, id.cache_lvl, id.cache, aggr_nr);break ;case AGGR_CLUSTER : -json_out (os,"\"cluster\" : \"S%d-D%d-CLS%d\", \"aggregate-number\" : %d" , +json_out (os,"\"cluster\" : \"S%d-D%d-CLS%d\", \"counters\" : %d" , id.socket, id.die, id.cluster, aggr_nr);break ;case AGGR_DIE : -json_out (os,"\"die\" : \"S%d-D%d\", \"aggregate-number\" : %d" , +json_out (os,"\"die\" : \"S%d-D%d\", \"counters\" : %d" , id.socket, id.die, aggr_nr);break ;case AGGR_SOCKET : -json_out (os,"\"socket\" : \"S%d\", \"aggregate-number\" : %d" , +json_out (os,"\"socket\" : \"S%d\", \"counters\" : %d" , id.socket, aggr_nr);break ;case AGGR_NODE : -json_out (os,"\"node\" : \"N%d\", \"aggregate-number\" : %d" , +json_out (os,"\"node\" : \"N%d\", \"counters\" : %d" , id.node, aggr_nr);break ;case AGGR_NONE :@@ -1317,7 +1317,7 @@ static void print_header_interval_std(struct perf_stat_config *config,case AGGR_CLUSTER :case AGGR_CACHE :case AGGR_CORE : -fprintf (output,"#%*s %-*s cpus" , +fprintf (output,"#%*s %-*s ctrs" ,INTERVAL_LEN -1 ,"time" , aggr_header_lens[config->aggr_mode], aggr_header_std[config->aggr_mode]);tools/perf/util/stat.c +1
-2@@ -526,7 +526,7 @@ static int evsel__merge_aggr_counters(struct evsel *evsel, struct evsel *alias)struct perf_counts_values *aggr_counts_a = &ps_a->aggr[i].counts;struct perf_counts_values *aggr_counts_b = &ps_b->aggr[i].counts; -/* NB: don't increase aggr.nr for aliases */ + ps_a->aggr[i].nr += ps_b->aggr[i].nr; aggr_counts_a->val += aggr_counts_b->val; aggr_counts_a->ena += aggr_counts_b->ena; --2.50.0.727.gbf7dc18ff4-goog
Quoted 8 lines · Chun-Tse Shao
Follow up:
lore.kernel.org/CAP-5=fVDF4-qYL1Lm7efgiHk7X=_nw_nEFMBZFMcsnOOJgX4Kg@mail.gmail.com/The patch adds unit aggregation during evsel merge the aggregated uncore counters. Change the name of the column to
ctrsandcountersfor json mode.[...]
Applied to perf-tools-next, thanks!
Best regards,
Namhyung