From 06380a849fa89da33d309597890ef26d24095b41 Mon Sep 17 00:00:00 2001 From: Alexey Bayduraev Date: Mon, 17 Jan 2022 21:34:32 +0300 Subject: [PATCH] perf record: Introduce --threads command line option Provide --threads option in perf record command line interface. The option creates a data streaming thread for each CPU in the system. Document --threads option in Documentation/perf-record.txt. Reviewed-by: Riccardo Mancini Signed-off-by: Alexey Bayduraev Tested-by: Jiri Olsa Tested-by: Riccardo Mancini Cc: Adrian Hunter Cc: Alexander Antonov Cc: Alexander Shishkin Cc: Alexei Budankov Cc: Andi Kleen Cc: Ingo Molnar Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/01aeae43b047f428596c4ef9f9342ab94865cedd.1642440724.git.alexey.v.bayduraev@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-record.txt | 4 ++ tools/perf/builtin-record.c | 48 +++++++++++++++++++++++- 2 files changed, 51 insertions(+), 1 deletion(-) diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 9ccc75935bc5..b9c6b112bf46 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -713,6 +713,10 @@ measurements: wait -n ${perf_pid} exit $? +--threads:: +Write collected trace data into several data files using parallel threads. +The option creates a data streaming thread for each CPU in the system. + include::intel-hybrid.txt[] --debuginfod[=URLs]:: diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index d19d0639c3f1..aea45f3cc66c 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -127,6 +127,11 @@ static const char *thread_msg_tags[THREAD_MSG__MAX] = { "UNDEFINED", "READY" }; +enum thread_spec { + THREAD_SPEC__UNDEFINED = 0, + THREAD_SPEC__CPU, +}; + struct record { struct perf_tool tool; struct record_opts opts; @@ -2768,6 +2773,16 @@ static void record__thread_mask_free(struct thread_mask *mask) record__mmap_cpu_mask_free(&mask->affinity); } +static int record__parse_threads(const struct option *opt, const char *str, int unset) +{ + struct record_opts *opts = opt->value; + + if (unset || !str || !strlen(str)) + opts->threads_spec = THREAD_SPEC__CPU; + + return 0; +} + static int parse_output_max_size(const struct option *opt, const char *str, int unset) { @@ -3242,6 +3257,9 @@ static struct option __record_options[] = { &record.debuginfod.set, "debuginfod urls", "Enable debuginfod data retrieval from DEBUGINFOD_URLS or specified urls", "system"), + OPT_CALLBACK_OPTARG(0, "threads", &record.opts, NULL, "spec", + "write collected trace data into several data files using parallel threads", + record__parse_threads), OPT_END() }; @@ -3292,6 +3310,31 @@ static int record__alloc_thread_masks(struct record *rec, int nr_threads, int nr return ret; } +static int record__init_thread_cpu_masks(struct record *rec, struct perf_cpu_map *cpus) +{ + int t, ret, nr_cpus = perf_cpu_map__nr(cpus); + + ret = record__alloc_thread_masks(rec, nr_cpus, cpu__max_cpu().cpu); + if (ret) + return ret; + + rec->nr_threads = nr_cpus; + pr_debug("nr_threads: %d\n", rec->nr_threads); + + for (t = 0; t < rec->nr_threads; t++) { + set_bit(cpus->map[t].cpu, rec->thread_masks[t].maps.bits); + set_bit(cpus->map[t].cpu, rec->thread_masks[t].affinity.bits); + if (verbose) { + pr_debug("thread_masks[%d]: ", t); + mmap_cpu_mask__scnprintf(&rec->thread_masks[t].maps, "maps"); + pr_debug("thread_masks[%d]: ", t); + mmap_cpu_mask__scnprintf(&rec->thread_masks[t].affinity, "affinity"); + } + } + + return 0; +} + static int record__init_thread_default_masks(struct record *rec, struct perf_cpu_map *cpus) { int ret; @@ -3311,7 +3354,10 @@ static int record__init_thread_masks(struct record *rec) { struct perf_cpu_map *cpus = rec->evlist->core.cpus; - return record__init_thread_default_masks(rec, cpus); + if (!record__threads_enabled(rec)) + return record__init_thread_default_masks(rec, cpus); + + return record__init_thread_cpu_masks(rec, cpus); } int cmd_record(int argc, const char **argv)