From: Namhyung Kim Date: Wed, 30 Apr 2025 20:55:45 +0000 (-0700) Subject: perf hist: Hide unused mem stat columns X-Git-Tag: v6.16-rc1~57^2~107 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=225772c17c9fb7679a4db45837fa9b429d97d6f4;p=thirdparty%2Flinux.git perf hist: Hide unused mem stat columns Some mem_stat types don't use all 8 columns. And there are cases only samples in certain kinds of mem_stat types are available only. For that case hide columns which has no samples. The new output for the previous data would be: $ perf mem report -F overhead,op,comm --stdio ... # ------ Mem Op ------- # Overhead Load Store Other Command # ........ ..................... ............... # 44.85% 21.1% 30.7% 48.3% swapper 26.82% 98.8% 0.3% 0.9% netsli-prober 7.19% 51.7% 13.7% 34.6% perf 5.81% 89.7% 2.2% 8.1% qemu-system-ppc 4.77% 100.0% 0.0% 0.0% notifications_c 1.77% 95.9% 1.2% 3.0% MemoryReleaser 0.77% 71.6% 4.1% 24.3% DefaultEventMan 0.19% 66.7% 22.2% 11.1% gnome-shell ... On Intel machines, the event is only for loads or stores so it'll have only one column: # Mem Op # Overhead Load Command # ........ ....... ............... # 20.55% 100.0% swapper 17.13% 100.0% chrome 9.02% 100.0% data-loop.0 6.26% 100.0% pipewire-pulse 5.63% 100.0% threaded-ml 5.47% 100.0% GraphRunner 5.37% 100.0% AudioIP~allback 5.30% 100.0% Chrome_ChildIOT 3.17% 100.0% Isolated Web Co ... Committer testing: # grep "model name" -m1 /proc/cpuinfo model name : AMD Ryzen 9 9950X3D 16-Core Processo # perf mem report -F overhead,op,comm --stdio # Total Lost Samples: 0 # # Samples: 2K of event 'cycles:P' # Total weight : 2637 # Sort order : local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked,local_ins_lat,local_p_stage_cyc # # ------ Mem Op ------- # Overhead Load Store Other Command # ........ ..................... ............... # 61.02% 14.4% 25.5% 60.1% swapper 5.61% 26.4% 13.5% 60.1% Isolated Web Co 5.50% 21.4% 29.7% 49.0% perf 4.74% 27.2% 15.2% 57.6% gnome-shell 4.63% 33.6% 11.5% 54.9% mdns_service 4.29% 28.3% 12.4% 59.3% ptyxis 2.16% 24.6% 19.3% 56.1% DOM Worker 0.99% 23.1% 34.6% 42.3% firefox 0.72% 26.3% 15.8% 57.9% IPC I/O Parent 0.61% 12.5% 12.5% 75.0% kworker/u130:20 0.61% 37.5% 18.8% 43.8% podman 0.57% 33.3% 6.7% 60.0% Timer 0.53% 14.3% 7.1% 78.6% KMS thread 0.49% 30.8% 7.7% 61.5% kworker/u130:3- 0.46% 41.7% 33.3% 25.0% IPDL Background Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Cc: Ravi Bangoria Link: https://lore.kernel.org/r/20250430205548.789750-9-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 427ce687ad815..661922c4d7863 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -178,6 +178,9 @@ int hpp__fmt_mem_stat(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp * for (int i = 0; i < MEM_STAT_LEN; i++) { u64 val = he->mem_stat[mem_stat_idx].entries[i]; + if (hists->mem_stat_total[mem_stat_idx].entries[i] == 0) + continue; + ret += hpp__call_print_fn(hpp, print_fn, fmtstr, 100.0 * val / total); } @@ -405,12 +408,31 @@ static int hpp__header_mem_stat_fn(struct perf_hpp_fmt *fmt, struct perf_hpp *hp int ret = 0; int len; enum mem_stat_type mst = hpp__mem_stat_type(fmt); + int mem_stat_idx = -1; + + for (int i = 0; i < hists->nr_mem_stats; i++) { + if (hists->mem_stat_types[i] == mst) { + mem_stat_idx = i; + break; + } + } + assert(mem_stat_idx != -1); - (void)hists; if (line == 0) { int left, right; - len = fmt->len; + len = 0; + /* update fmt->len for acutally used columns only */ + for (int i = 0; i < MEM_STAT_LEN; i++) { + if (hists->mem_stat_total[mem_stat_idx].entries[i]) + len += MEM_STAT_PRINT_LEN; + } + fmt->len = len; + + /* print header directly if single column only */ + if (len == MEM_STAT_PRINT_LEN) + return scnprintf(hpp->buf, hpp->size, "%*s", len, fmt->name); + left = (len - strlen(fmt->name)) / 2 - 1; right = len - left - strlen(fmt->name) - 2; @@ -423,10 +445,14 @@ static int hpp__header_mem_stat_fn(struct perf_hpp_fmt *fmt, struct perf_hpp *hp left, graph_dotted_line, fmt->name, right, graph_dotted_line); } + len = hpp->size; for (int i = 0; i < MEM_STAT_LEN; i++) { int printed; + if (hists->mem_stat_total[mem_stat_idx].entries[i] == 0) + continue; + printed = scnprintf(buf, len, "%*s", MEM_STAT_PRINT_LEN, mem_stat_name(mst, i)); ret += printed; @@ -1214,6 +1240,11 @@ int perf_hpp__alloc_mem_stats(struct perf_hpp_list *list, struct evlist *evlist) if (hists->mem_stat_types == NULL) return -ENOMEM; + hists->mem_stat_total = calloc(nr_mem_stats, + sizeof(*hists->mem_stat_total)); + if (hists->mem_stat_total == NULL) + return -ENOMEM; + memcpy(hists->mem_stat_types, mst, nr_mem_stats * sizeof(*mst)); hists->nr_mem_stats = nr_mem_stats; } diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 7759c1818c1ad..afc6855327ab0 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -354,6 +354,7 @@ static int hists__update_mem_stat(struct hists *hists, struct hist_entry *he, assert(0 <= idx && idx < MEM_STAT_LEN); he->mem_stat[i].entries[idx] += period; + hists->mem_stat_total[i].entries[idx] += period; } return 0; } @@ -3054,6 +3055,7 @@ static void hists_evsel__exit(struct evsel *evsel) hists__delete_all_entries(hists); zfree(&hists->mem_stat_types); + zfree(&hists->mem_stat_total); list_for_each_entry_safe(node, tmp, &hists->hpp_formats, list) { perf_hpp_list__for_each_format_safe(&node->hpp, fmt, pos) { diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 3990cfc21b161..fa5e886e5b04e 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -135,6 +135,7 @@ struct hists { int nr_hpp_node; int nr_mem_stats; enum mem_stat_type *mem_stat_types; + struct he_mem_stat *mem_stat_total; }; #define hists__has(__h, __f) (__h)->hpp_list->__f