From 5d67be97f8903d05ce53597fb5f3bc25a45e8026 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 4 Jul 2011 21:57:50 +1000 Subject: perf report/annotate/script: Add option to specify a CPU range Add an option to perf report/annotate/script to specify which CPUs to operate on. This enables us to take a single system wide profile and analyse each CPU (or group of CPUs) in isolation. This was useful when profiling a multiprocess workload where the bottleneck was on one CPU but this was hidden in the overall profile. Per process and per thread breakdowns didn't help because multiple processes were running on each CPU and no single process consumed an entire CPU. The patch converts the list of CPUs returned by cpu_map__new into a bitmap for fast lookup. I wanted to use -C to be consistent with perf top/record/stat, but unfortunately perf report already uses -C . v2: Incorporate suggestions from David Ahern: - Added -c to perf script - Check that SAMPLE_CPU is set when -c is used - Update documentation v3: Create perf_session__cpu_bitmap() Signed-off-by: Anton Blanchard Acked-by: David Ahern Cc: Arnaldo Carvalho de Melo Cc: Peter Zijlstra Cc: Paul Mackerras Link: http://lkml.kernel.org/r/20110704215750.11647eb9@kryten Signed-off-by: Ingo Molnar --- tools/perf/builtin-report.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'tools/perf/builtin-report.c') diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 5d43d0181d63..f854efda7686 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -33,6 +33,8 @@ #include "util/sort.h" #include "util/hist.h" +#include + static char const *input_name = "perf.data"; static bool force, use_tui, use_stdio; @@ -49,6 +51,9 @@ static char callchain_default_opt[] = "fractal,0.5,callee"; static bool inverted_callchain; static symbol_filter_t annotate_init; +static const char *cpu_list; +static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); + static int perf_session__add_hist_entry(struct perf_session *session, struct addr_location *al, struct perf_sample *sample, @@ -117,6 +122,9 @@ static int process_sample_event(union perf_event *event, if (al.filtered || (hide_unresolved && al.sym == NULL)) return 0; + if (cpu_list && !test_bit(sample->cpu, cpu_bitmap)) + return 0; + if (al.map != NULL) al.map->dso->hit = 1; @@ -263,6 +271,12 @@ static int __cmd_report(void) if (session == NULL) return -ENOMEM; + if (cpu_list) { + ret = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap); + if (ret) + goto out_delete; + } + if (show_threads) perf_read_values_init(&show_threads_values); @@ -473,6 +487,7 @@ static const struct option options[] = { "Only display entries resolved to a symbol"), OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory", "Look for files with symbols relative to this directory"), + OPT_STRING('c', "cpu", &cpu_list, "cpu", "list of cpus to profile"), OPT_END() }; -- cgit v1.2.3