From cbc917a1b03bce85f385c1e640c9dcb02ffb9ab0 Mon Sep 17 00:00:00 2001 From: Yicong Yang Date: Thu, 8 Feb 2024 10:40:26 +0800 Subject: perf stat: Support per-cluster aggregation Some platforms have 'cluster' topology and CPUs in the cluster will share resources like L3 Cache Tag (for HiSilicon Kunpeng SoC) or L2 cache (for Intel Jacobsville). Currently parsing and building cluster topology have been supported since [1]. perf stat has already supported aggregation for other topologies like die or socket, etc. It'll be useful to aggregate per-cluster to find problems like L3T bandwidth contention. This patch add support for "--per-cluster" option for per-cluster aggregation. Also update the docs and related test. The output will be like: [root@localhost tmp]# perf stat -a -e LLC-load --per-cluster -- sleep 5 Performance counter stats for 'system wide': S56-D0-CLS158 4 1,321,521,570 LLC-load S56-D0-CLS594 4 794,211,453 LLC-load S56-D0-CLS1030 4 41,623 LLC-load S56-D0-CLS1466 4 41,646 LLC-load S56-D0-CLS1902 4 16,863 LLC-load S56-D0-CLS2338 4 15,721 LLC-load S56-D0-CLS2774 4 22,671 LLC-load [...] On a legacy system without cluster or cluster support, the output will be look like: [root@localhost perf]# perf stat -a -e cycles --per-cluster -- sleep 1 Performance counter stats for 'system wide': S56-D0-CLS0 64 18,011,485 cycles S7182-D0-CLS0 64 16,548,835 cycles Note that this patch doesn't mix the cluster information in the outputs of --per-core to avoid breaking any tools/scripts using it. Note that perf recently supports "--per-cache" aggregation, but it's not the same with the cluster although cluster CPUs may share some cache resources. For example on my machine all clusters within a die share the same L3 cache: $ cat /sys/devices/system/cpu/cpu0/cache/index3/shared_cpu_list 0-31 $ cat /sys/devices/system/cpu/cpu0/topology/cluster_cpus_list 0-3 [1] commit c5e22feffdd7 ("topology: Represent clusters of CPUs within a die") Tested-by: Jie Zhan Reviewed-by: Tim Chen Reviewed-by: Ian Rogers Signed-off-by: Yicong Yang Cc: james.clark@arm.com Cc: 21cnbao@gmail.com Cc: prime.zeng@hisilicon.com Cc: Jonathan.Cameron@huawei.com Cc: fanghao11@huawei.com Cc: linuxarm@huawei.com Cc: tim.c.chen@intel.com Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Namhyung Kim Link: https://lore.kernel.org/r/20240208024026.2691-1-yangyicong@huawei.com --- tools/perf/util/stat-display.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'tools/perf/util/stat-display.c') diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 8c61f8627ebc..4dfe7d9517a9 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -201,6 +201,9 @@ static void print_aggr_id_std(struct perf_stat_config *config, snprintf(buf, sizeof(buf), "S%d-D%d-L%d-ID%d", id.socket, id.die, id.cache_lvl, id.cache); break; + case AGGR_CLUSTER: + snprintf(buf, sizeof(buf), "S%d-D%d-CLS%d", id.socket, id.die, id.cluster); + break; case AGGR_DIE: snprintf(buf, sizeof(buf), "S%d-D%d", id.socket, id.die); break; @@ -251,6 +254,10 @@ static void print_aggr_id_csv(struct perf_stat_config *config, fprintf(config->output, "S%d-D%d-L%d-ID%d%s%d%s", id.socket, id.die, id.cache_lvl, id.cache, sep, aggr_nr, sep); break; + case AGGR_CLUSTER: + fprintf(config->output, "S%d-D%d-CLS%d%s%d%s", + id.socket, id.die, id.cluster, sep, aggr_nr, sep); + break; case AGGR_DIE: fprintf(output, "S%d-D%d%s%d%s", id.socket, id.die, sep, aggr_nr, sep); @@ -300,6 +307,10 @@ static void print_aggr_id_json(struct perf_stat_config *config, fprintf(output, "\"cache\" : \"S%d-D%d-L%d-ID%d\", \"aggregate-number\" : %d, ", id.socket, id.die, id.cache_lvl, id.cache, aggr_nr); break; + case AGGR_CLUSTER: + fprintf(output, "\"cluster\" : \"S%d-D%d-CLS%d\", \"aggregate-number\" : %d, ", + id.socket, id.die, id.cluster, aggr_nr); + break; case AGGR_DIE: fprintf(output, "\"die\" : \"S%d-D%d\", \"aggregate-number\" : %d, ", id.socket, id.die, aggr_nr); @@ -1248,6 +1259,7 @@ static void print_header_interval_std(struct perf_stat_config *config, case AGGR_NODE: case AGGR_SOCKET: case AGGR_DIE: + case AGGR_CLUSTER: case AGGR_CACHE: case AGGR_CORE: fprintf(output, "#%*s %-*s cpus", @@ -1550,6 +1562,7 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf switch (config->aggr_mode) { case AGGR_CORE: case AGGR_CACHE: + case AGGR_CLUSTER: case AGGR_DIE: case AGGR_SOCKET: case AGGR_NODE: -- cgit v1.2.3 From 2543947c77e0e224bda86b4e7220c2f6714da463 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 9 Feb 2024 12:49:46 -0800 Subject: perf stat: Avoid metric-only segv Cycles is recognized as part of a hard coded metric in stat-shadow.c, it may call print_metric_only with a NULL fmt string leading to a segfault. Handle the NULL fmt explicitly. Fixes: 088519f318be ("perf stat: Move the display functions to stat-display.c") Signed-off-by: Ian Rogers Reviewed-by: Kan Liang Cc: K Prateek Nayak Cc: James Clark Cc: Kaige Ye Cc: John Garry Signed-off-by: Namhyung Kim Link: https://lore.kernel.org/r/20240209204947.3873294-4-irogers@google.com --- tools/perf/util/stat-display.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/util/stat-display.c') diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 4dfe7d9517a9..ae37395f90c0 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -571,7 +571,7 @@ static void print_metric_only(struct perf_stat_config *config, if (color) mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1; - color_snprintf(str, sizeof(str), color ?: "", fmt, val); + color_snprintf(str, sizeof(str), color ?: "", fmt ?: "", val); fprintf(out, "%*s ", mlen, str); os->first = false; } -- cgit v1.2.3 From bafd4e75c1ac5a9da0aec5c7c52c7a72613a0cf3 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 20 Feb 2024 23:07:54 -0800 Subject: perf stat: Fix metric-only aggregation index Aggregation index was being computed using the evsel's cpumap which may have a different (typically the same or fewer) entries. Before: ``` $ perf stat --metric-only -A -M memory_bandwidth_total -a sleep 1 Performance counter stats for 'system wide': MB/s memory_bandwidth_total MB/s memory_bandwidth_total MB/s memory_bandwidth_total MB/s memory_bandwidth_total MB/s memory_bandwidth_total MB/s memory_bandwidth_total CPU0 12.8 0.0 12.9 12.7 0.0 12.6 CPU1 1.007806367 seconds time elapsed ``` After: ``` $ perf stat --metric-only -A -M memory_bandwidth_total -a sleep 1 Performance counter stats for 'system wide': MB/s memory_bandwidth_total MB/s memory_bandwidth_total MB/s memory_bandwidth_total MB/s memory_bandwidth_total MB/s memory_bandwidth_total MB/s memory_bandwidth_total CPU0 15.4 0.0 15.3 15.0 0.0 14.9 CPU18 0.0 0.0 13.5 5.2 0.0 11.9 1.007858736 seconds time elapsed ``` Signed-off-by: Ian Rogers | Acked-by: Namhyung Kim Cc: K Prateek Nayak Cc: Stephane Eranian Cc: Kaige Ye Cc: Kajol Jain Cc: Alexander Shishkin Cc: Kan Liang Cc: John Garry Signed-off-by: Namhyung Kim Link: https://lore.kernel.org/r/20240221070754.4163916-3-irogers@google.com --- tools/perf/util/stat-display.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'tools/perf/util/stat-display.c') diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index ae37395f90c0..bfc1d705f437 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -1137,11 +1137,16 @@ static void print_no_aggr_metric(struct perf_stat_config *config, u64 ena, run, val; double uval; struct perf_stat_evsel *ps = counter->stats; - int aggr_idx = perf_cpu_map__idx(evsel__cpus(counter), cpu); + int aggr_idx = 0; - if (aggr_idx < 0) + if (!perf_cpu_map__has(evsel__cpus(counter), cpu)) continue; + cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) { + if (config->aggr_map->map[aggr_idx].cpu.cpu == cpu.cpu) + break; + } + os->evsel = counter; os->id = aggr_cpu_id__cpu(cpu, /*data=*/NULL); if (first) { -- cgit v1.2.3