perf stat: Add --hide-zero-events option to suppress zero-count events
PATCH v2 1/1 perf stat: Add --hide-zero-events option to suppress zero-count events
When monitoring a large number of events (e.g., with wildcards such as --event 'syscalls:sys_enter_*'), many matched events will return a count of zero. This clutters the output, making it difficult to spot the active events.
Add a new option --hide-zero-events to suppress printing events that have a count of zero.
To prevent formatting and diagnostic issues, the zero-skipping logic implements the following rules:
1. In metric-only mode (i.e., --metric-only), columns must remain aligned in the output grid. We evaluate config->metric_only first to avoid skipping zero-valued columns, preventing values from shifting left and aligning under incorrect headers
2. For explicitly requested events, we ensure they are not silently hidden if they are unsupported. We only hide a zero-count event if counter->supported is true, ensuring that unsupported explicit events still report "<not supported>"
---
Changes since v1:
- Add shell test coverage for --hide-zero-events and --metric-only in stat.sh
- Linked to v1: https://lore.kernel.org/lkml/[email protected]/
--- tools/perf/Documentation/perf-stat.txt | 3 ++ tools/perf/builtin-stat.c | 2 ++ tools/perf/tests/shell/stat.sh | 46 ++++++++++++++++++++++++++ tools/perf/util/stat-display.c | 3 ++ tools/perf/util/stat.h | 1 + 5 files changed, 55 insertions(+)
tools/perf/Documentation/perf-stat.txt +3 -0
@@ -162,6 +162,9 @@ null run - Don't start any counters. This can be useful to measure just elapsed wall-clock time - or to assess the raw overhead of perf stat itself, without running any counters. +--hide-zero-events:: +Do not show events with a zero count. + -v:: --verbose:: be more verbose (show counter open errors, etc)
tools/perf/builtin-stat.c +2 -0
@@ -2493,6 +2493,8 @@ int cmd_stat(int argc, const char **argv) "display details about each run (only with -r option)"),OPT_BOOLEAN ('n' ,"null" , &stat_config.null_run,"null run - dont start any counters" ), +OPT_BOOLEAN (0 ,"hide-zero-events" , &stat_config.hide_zero, +"Do not show events with a zero count" ),OPT_INCR ('d' ,"detailed" , &detailed_run,"detailed run - start a lot of events" ), OPT_BOOLEAN('S', "sync", &sync_run,
tools/perf/tests/shell/stat.sh +46 -0
58 lines not on this page · raw message
tools/perf/util/stat-display.c +3 -0
@@ -907,6 +907,9 @@ static bool should_skip_zero_counter(struct perf_stat_config *config,/* Metric only counts won't be displayed but the metric wants to be computed. */ if (config->metric_only)return false; + +if (config->hide_zero && counter->supported) +return true;/* * Skip value 0 when enabling --per-thread globally, * otherwise it will have too many 0 output.
tools/perf/util/stat.h +1 -0
@@ -69,6 +69,7 @@ struct perf_stat_config {bool interval_clear;bool metric_only;bool null_run; +bool hide_zero;bool ru_display;bool big_num;bool hybrid_merge;
Signature · 1 line
2.54.0
Namhyung Kim
maintainerQuoted 21 lines · Aaron Tomlin
When monitoring a large number of events (e.g., with wildcards such as --event 'syscalls:sys_enter_*'), many matched events will return a count of zero. This clutters the output, making it difficult to spot the active events.
Add a new option --hide-zero-events to suppress printing events that have a count of zero.
To prevent formatting and diagnostic issues, the zero-skipping logic implements the following rules:
1. In metric-only mode (i.e., --metric-only), columns must remain aligned in the output grid. We evaluate
config->metric_onlyfirst to avoid skipping zero-valued columns, preventing values from shifting left and aligning under incorrect headers2. For explicitly requested events, we ensure they are not silently hidden if they are unsupported. We only hide a zero-count event if
counter->supportedis true, ensuring that unsupported explicit events still report "<not supported>"
Quoted 7 lines
Signed-off-by Aaron Tomlin <[email protected]>Reviewed-by Ian Rogers <[email protected]>---
Changes since v1:- Add shell test coverage for --hide-zero-events and --metric-only in
stat.sh
Unfortunately the test was updated recently. Can you please rebase?
Thanks,
Namhyung
Quoted 130 lines
- Linked to v1: https://lore.kernel.org/lkml/[email protected]/
--- tools/perf/Documentation/perf-stat.txt | 3 ++ tools/perf/builtin-stat.c | 2 ++ tools/perf/tests/shell/stat.sh | 46 ++++++++++++++++++++++++++ tools/perf/util/stat-display.c | 3 ++ tools/perf/util/stat.h | 1 + 5 files changed, 55 insertions(+)tools/perf/Documentation/perf-stat.txt +3
-0@@ -162,6 +162,9 @@ null run - Don't start any counters. This can be useful to measure just elapsed wall-clock time - or to assess the raw overhead of perf stat itself, without running any counters. +--hide-zero-events:: +Do not show events with a zero count. + -v:: --verbose:: be more verbose (show counter open errors, etc)tools/perf/builtin-stat.c +2
-0@@ -2493,6 +2493,8 @@ int cmd_stat(int argc, const char **argv) "display details about each run (only with -r option)"),OPT_BOOLEAN ('n' ,"null" , &stat_config.null_run,"null run - dont start any counters" ), +OPT_BOOLEAN (0 ,"hide-zero-events" , &stat_config.hide_zero, +"Do not show events with a zero count" ),OPT_INCR ('d' ,"detailed" , &detailed_run,"detailed run - start a lot of events" ), OPT_BOOLEAN('S', "sync", &sync_run,tools/perf/tests/shell/stat.sh +46
-0@@ -535,6 +535,51 @@ test_stat_delay() { echo "stat -D test [Success]" } +test_hide_zero_events_stat() { + echo "Hide zero events stat test" + if ! perf stat -e context-switches,cpu-migrations true > "${stat_output}" 2>&1 + then + echo "Hide zero events stat test [Skipped event parsing failed]" + return + fi + + zero_event="" + if grep -q -E "[[:space:]]+0[[:space:]]+context-switches" "${stat_output}"; then + zero_event="context-switches" + elif grep -q -E "[[:space:]]+0[[:space:]]+cpu-migrations" "${stat_output}"; then + zero_event="cpu-migrations" + fi + + if [ -z "$zero_event" ]; then + echo "Hide zero events stat test [Skipped - no zero count event found]" + return + fi + + if ! perf stat --hide-zero-events -e context-switches,cpu-migrations true > "${stat_output}" 2>&1 + then + echo "Hide zero events stat test [Failed - command failed]" + err=1 + return + fi + + if grep -q -E "$zero_event" "${stat_output}" + then + echo "Hide zero events stat test [Failed - zero event $zero_event was not hidden]" + err=1 + return + fi + + # Check that --metric-only works with --hide-zero-events + if ! perf stat --hide-zero-events --metric-only -e instructions,cycles true > "${stat_output}" 2>&1 + then + echo "Hide zero events stat test [Failed - metric-only command failed]" + err=1 + return + fi + + echo "Hide zero events stat test [Success]" +} + test_default_stat test_null_stat test_offline_cpu_stat@@ -551,6 +596,7 @@ test_stat_detailed test_stat_repeat test_stat_pid test_stat_delay +test_hide_zero_events_stat cleanup exit $errtools/perf/util/stat-display.c +3
-0@@ -907,6 +907,9 @@ static bool should_skip_zero_counter(struct perf_stat_config *config,/* Metric only counts won't be displayed but the metric wants to be computed. */ if (config->metric_only)return false; + +if (config->hide_zero && counter->supported) +return true;/* * Skip value 0 when enabling --per-thread globally, * otherwise it will have too many 0 output. tools/perf/util/stat.h +1
-0@@ -69,6 +69,7 @@ struct perf_stat_config {bool interval_clear;bool metric_only;bool null_run; +bool hide_zero;bool ru_display;bool big_num;bool hybrid_merge;Signature · 1 line
2.54.0
Quoted 6 lines · Namhyung Kim
Quoted 4 lines
Changes since v1:
- Add shell test coverage for --hide-zero-events and --metric-only in
stat.shUnfortunately the test was updated recently. Can you please rebase?
Hi Namhyung,
Will do.
Kind regards,
Signature · 1 line
Aaron Tomlin