From 63e39aa6ae103451dfffe578c38e219d731e5cca Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Tue, 2 Feb 2021 12:09:12 -0800 Subject: perf stat: Support L2 Topdown events The TMA method level 2 metrics is supported from the Intel Sapphire Rapids server, which expose four L2 Topdown metrics events to user space. There are eight L2 events in total. The other four L2 Topdown metrics events are calculated from the corresponding L1 and the exposed L2 events. Now, the --topdown prints the complete top-down metrics that supported by the CPU. For the Intel Sapphire Rapids server, there are 4 L1 events and 8 L2 events displyed in one line. Add a new option, --td-level, to display the top-down statistics that equal to or lower than the input level. The L2 event is marked only when both its L1 parent event and itself crosse the threshold. Here is an example: $ perf stat --topdown --td-level=2 --no-metric-only sleep 1 Topdown accuracy may decrease when measuring long periods. Please print the result regularly, e.g. -I1000 Performance counter stats for 'sleep 1': 16,734,390 slots 2,100,001 topdown-retiring # 12.6% retiring 2,034,376 topdown-bad-spec # 12.3% bad speculation 4,003,128 topdown-fe-bound # 24.1% frontend bound 328,125 topdown-heavy-ops # 2.0% heavy operations # 10.6% light operations 1,968,751 topdown-br-mispredict # 11.9% branch mispredict # 0.4% machine clears 2,953,127 topdown-fetch-lat # 17.8% fetch latency # 6.3% fetch bandwidth 5,906,255 topdown-mem-bound # 35.6% memory bound # 15.4% core bound Signed-off-by: Kan Liang Cc: Andi Kleen Cc: Jin Yao Cc: Jiri Olsa Cc: Madhavan Srinivasan Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lore.kernel.org/lkml/1612296553-21962-9-git-send-email-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 34 +++++++++++++++++++++++++++++++--- 1 file changed, 31 insertions(+), 3 deletions(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index b009dde5c601..2e2e4a8345ea 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -138,6 +138,19 @@ static const char *topdown_metric_attrs[] = { NULL, }; +static const char *topdown_metric_L2_attrs[] = { + "slots", + "topdown-retiring", + "topdown-bad-spec", + "topdown-fe-bound", + "topdown-be-bound", + "topdown-heavy-ops", + "topdown-br-mispredict", + "topdown-fetch-lat", + "topdown-mem-bound", + NULL, +}; + static const char *smi_cost_attrs = { "{" "msr/aperf/," @@ -1202,7 +1215,9 @@ static struct option stat_options[] = { OPT_BOOLEAN(0, "metric-no-merge", &stat_config.metric_no_merge, "don't try to share events between metrics in a group"), OPT_BOOLEAN(0, "topdown", &topdown_run, - "measure topdown level 1 statistics"), + "measure top-down statistics"), + OPT_UINTEGER(0, "td-level", &stat_config.topdown_level, + "Set the metrics level for the top-down statistics (0: max level)"), OPT_BOOLEAN(0, "smi-cost", &smi_cost, "measure SMI cost"), OPT_CALLBACK('M', "metrics", &evsel_list, "metric/metric group list", @@ -1755,17 +1770,30 @@ static int add_default_attributes(void) } if (topdown_run) { + const char **metric_attrs = topdown_metric_attrs; + unsigned int max_level = 1; char *str = NULL; bool warn = false; if (!force_metric_only) stat_config.metric_only = true; - if (topdown_filter_events(topdown_metric_attrs, &str, 1) < 0) { + if (pmu_have_event("cpu", topdown_metric_L2_attrs[5])) { + metric_attrs = topdown_metric_L2_attrs; + max_level = 2; + } + + if (stat_config.topdown_level > max_level) { + pr_err("Invalid top-down metrics level. The max level is %u.\n", max_level); + return -1; + } else if (!stat_config.topdown_level) + stat_config.topdown_level = max_level; + + if (topdown_filter_events(metric_attrs, &str, 1) < 0) { pr_err("Out of memory\n"); return -1; } - if (topdown_metric_attrs[0] && str) { + if (metric_attrs[0] && str) { if (!stat_config.interval && !stat_config.metric_only) { fprintf(stat_config.output, "Topdown accuracy may decrease when measuring long periods.\n" -- cgit v1.2.1