From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-16.8 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 9A7FAC4338F for ; Tue, 17 Aug 2021 08:24:00 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 7DA3960FA0 for ; Tue, 17 Aug 2021 08:24:00 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S239299AbhHQIY2 (ORCPT ); Tue, 17 Aug 2021 04:24:28 -0400 Received: from mga07.intel.com ([134.134.136.100]:11537 "EHLO mga07.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S239265AbhHQIYU (ORCPT ); Tue, 17 Aug 2021 04:24:20 -0400 X-IronPort-AV: E=McAfee;i="6200,9189,10078"; a="279763198" X-IronPort-AV: E=Sophos;i="5.84,328,1620716400"; d="scan'208";a="279763198" Received: from orsmga008.jf.intel.com ([10.7.209.65]) by orsmga105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 17 Aug 2021 01:23:47 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.84,328,1620716400"; d="scan'208";a="471080216" Received: from nntpat99-84.inn.intel.com ([10.125.99.84]) by orsmga008.jf.intel.com with ESMTP; 17 Aug 2021 01:23:44 -0700 From: Alexey Bayduraev To: Arnaldo Carvalho de Melo Cc: Jiri Olsa , Namhyung Kim , Alexander Shishkin , Peter Zijlstra , Ingo Molnar , linux-kernel , Andi Kleen , Adrian Hunter , Alexander Antonov , Alexei Budankov , Riccardo Mancini Subject: [PATCH v11 05/24] perf record: Introduce thread local variable Date: Tue, 17 Aug 2021 11:23:08 +0300 Message-Id: <43eedb206c84d3ea57bb9746105e7e5268b5cd31.1629186429.git.alexey.v.bayduraev@linux.intel.com> X-Mailer: git-send-email 2.19.0 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Introduce thread local variable and use it for threaded trace streaming. Use thread affinity mask instead or record affinity mask in affinity modes. Acked-by: Andi Kleen Acked-by: Namhyung Kim Reviewed-by: Riccardo Mancini Tested-by: Riccardo Mancini Signed-off-by: Alexey Bayduraev --- tools/perf/builtin-record.c | 139 ++++++++++++++++++++++++------------ 1 file changed, 93 insertions(+), 46 deletions(-) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 50bdf544eeeb..9d6f6f8d788a 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -110,6 +110,8 @@ struct record_thread { unsigned long waking; }; +static __thread struct record_thread *thread; + struct record { struct perf_tool tool; struct record_opts opts; @@ -132,7 +134,6 @@ struct record { bool timestamp_boundary; struct switch_output switch_output; unsigned long long samples; - struct mmap_cpu_mask affinity_mask; unsigned long output_max_size; /* = 0: unlimited */ int nr_threads; struct thread_mask *thread_masks; @@ -574,7 +575,7 @@ static int record__pushfn(struct mmap *map, void *to, void *bf, size_t size) bf = map->data; } - rec->samples++; + thread->samples++; return record__write(rec, map, bf, size); } @@ -1317,19 +1318,29 @@ static struct perf_event_header finished_round_event = { .type = PERF_RECORD_FINISHED_ROUND, }; -static void record__adjust_affinity(struct record *rec, struct mmap *map) +static int record__adjust_affinity(struct record *rec, struct mmap *map) { + int ret = 0; + if (rec->opts.affinity != PERF_AFFINITY_SYS && - !bitmap_equal(rec->affinity_mask.bits, map->affinity_mask.bits, - rec->affinity_mask.nbits)) { - bitmap_zero(rec->affinity_mask.bits, rec->affinity_mask.nbits); - bitmap_or(rec->affinity_mask.bits, rec->affinity_mask.bits, - map->affinity_mask.bits, rec->affinity_mask.nbits); - sched_setaffinity(0, MMAP_CPU_MASK_BYTES(&rec->affinity_mask), - (cpu_set_t *)rec->affinity_mask.bits); - if (verbose == 2) - mmap_cpu_mask__scnprintf(&rec->affinity_mask, "thread"); + !bitmap_equal(thread->mask->affinity.bits, map->affinity_mask.bits, + thread->mask->affinity.nbits)) { + bitmap_zero(thread->mask->affinity.bits, thread->mask->affinity.nbits); + bitmap_or(thread->mask->affinity.bits, thread->mask->affinity.bits, + map->affinity_mask.bits, thread->mask->affinity.nbits); + ret = sched_setaffinity(0, MMAP_CPU_MASK_BYTES(&thread->mask->affinity), + (cpu_set_t *)thread->mask->affinity.bits); + if (ret) + pr_err("threads[%d]: sched_setaffinity() call failed: %s\n", + thread->tid, strerror(errno)); + if (verbose == 2) { + pr_debug("threads[%d]: addr=", thread->tid); + mmap_cpu_mask__scnprintf(&thread->mask->affinity, "thread"); + pr_debug("threads[%d]: on cpu=%d\n", thread->tid, sched_getcpu()); + } } + + return ret; } static size_t process_comp_header(void *record, size_t increment) @@ -1369,14 +1380,17 @@ static int record__mmap_read_evlist(struct record *rec, struct evlist *evlist, u64 bytes_written = rec->bytes_written; int i; int rc = 0; - struct mmap *maps; + int nr_mmaps; + struct mmap **maps; int trace_fd = rec->data.file.fd; off_t off = 0; if (!evlist) return 0; - maps = overwrite ? evlist->overwrite_mmap : evlist->mmap; + nr_mmaps = thread->nr_mmaps; + maps = overwrite ? thread->overwrite_maps : thread->maps; + if (!maps) return 0; @@ -1386,9 +1400,9 @@ static int record__mmap_read_evlist(struct record *rec, struct evlist *evlist, if (record__aio_enabled(rec)) off = record__aio_get_pos(trace_fd); - for (i = 0; i < evlist->core.nr_mmaps; i++) { + for (i = 0; i < nr_mmaps; i++) { u64 flush = 0; - struct mmap *map = &maps[i]; + struct mmap *map = maps[i]; if (map->core.base) { record__adjust_affinity(rec, map); @@ -1451,6 +1465,15 @@ static int record__mmap_read_all(struct record *rec, bool synch) return record__mmap_read_evlist(rec, rec->evlist, true, synch); } +static void record__thread_munmap_filtered(struct fdarray *fda, int fd, + void *arg __maybe_unused) +{ + struct perf_mmap *map = fda->priv[fd].ptr; + + if (map) + perf_mmap__put(map); +} + static void record__init_features(struct record *rec) { struct perf_session *session = rec->session; @@ -1865,6 +1888,33 @@ static void record__uniquify_name(struct record *rec) } } +static int record__start_threads(struct record *rec) +{ + struct record_thread *thread_data = rec->thread_data; + + thread = &thread_data[0]; + + pr_debug("threads[%d]: started on cpu=%d\n", thread->tid, sched_getcpu()); + + return 0; +} + +static int record__stop_threads(struct record *rec, unsigned long *waking) +{ + int t; + struct record_thread *thread_data = rec->thread_data; + + for (t = 0; t < rec->nr_threads; t++) { + rec->samples += thread_data[t].samples; + *waking += thread_data[t].waking; + pr_debug("threads[%d]: samples=%lld, wakes=%ld, trasferred=%ld, compressed=%ld\n", + thread_data[t].tid, thread_data[t].samples, thread_data[t].waking, + rec->session->bytes_transferred, rec->session->bytes_compressed); + } + + return 0; +} + static int __cmd_record(struct record *rec, int argc, const char **argv) { int err; @@ -1973,7 +2023,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) if (record__open(rec) != 0) { err = -1; - goto out_child; + goto out_free_threads; } session->header.env.comp_mmap_len = session->evlist->core.mmap_len; @@ -1981,7 +2031,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) err = record__kcore_copy(&session->machines.host, data); if (err) { pr_err("ERROR: Failed to copy kcore\n"); - goto out_child; + goto out_free_threads; } } @@ -1992,7 +2042,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) bpf__strerror_apply_obj_config(err, errbuf, sizeof(errbuf)); pr_err("ERROR: Apply config to BPF failed: %s\n", errbuf); - goto out_child; + goto out_free_threads; } /* @@ -2010,11 +2060,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) if (data->is_pipe) { err = perf_header__write_pipe(fd); if (err < 0) - goto out_child; + goto out_free_threads; } else { err = perf_session__write_header(session, rec->evlist, fd, false); if (err < 0) - goto out_child; + goto out_free_threads; } err = -1; @@ -2022,16 +2072,16 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) && !perf_header__has_feat(&session->header, HEADER_BUILD_ID)) { pr_err("Couldn't generate buildids. " "Use --no-buildid to profile anyway.\n"); - goto out_child; + goto out_free_threads; } err = record__setup_sb_evlist(rec); if (err) - goto out_child; + goto out_free_threads; err = record__synthesize(rec, false); if (err < 0) - goto out_child; + goto out_free_threads; if (rec->realtime_prio) { struct sched_param param; @@ -2040,10 +2090,13 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) if (sched_setscheduler(0, SCHED_FIFO, ¶m)) { pr_err("Could not set realtime priority.\n"); err = -1; - goto out_child; + goto out_free_threads; } } + if (record__start_threads(rec)) + goto out_free_threads; + /* * When perf is starting the traced process, all the events * (apart from group members) have enable_on_exec=1 set, @@ -2114,7 +2167,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) trigger_ready(&switch_output_trigger); perf_hooks__invoke_record_start(); for (;;) { - unsigned long long hits = rec->samples; + unsigned long long hits = thread->samples; /* * rec->evlist->bkw_mmap_state is possible to be @@ -2183,20 +2236,24 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) alarm(rec->switch_output.time); } - if (hits == rec->samples) { + if (hits == thread->samples) { if (done || draining) break; - err = evlist__poll(rec->evlist, -1); + err = fdarray__poll(&thread->pollfd, -1); /* * Propagate error, only if there's any. Ignore positive * number of returned events and interrupt error. */ if (err > 0 || (err < 0 && errno == EINTR)) err = 0; - waking++; + thread->waking++; - if (evlist__filter_pollfd(rec->evlist, POLLERR | POLLHUP) == 0) + if (fdarray__filter(&thread->pollfd, POLLERR | POLLHUP, + record__thread_munmap_filtered, NULL) == 0) draining = true; + + evlist__ctlfd_update(rec->evlist, + &thread->pollfd.entries[thread->ctlfd_pos]); } if (evlist__ctlfd_process(rec->evlist, &cmd) > 0) { @@ -2249,18 +2306,20 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) goto out_child; } - if (!quiet) - fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking); - if (target__none(&rec->opts.target)) record__synthesize_workload(rec, true); out_child: - evlist__finalize_ctlfd(rec->evlist); + record__stop_threads(rec, &waking); record__mmap_read_all(rec, true); +out_free_threads: record__free_thread_data(rec); + evlist__finalize_ctlfd(rec->evlist); record__aio_mmap_read_sync(rec); + if (!quiet) + fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking); + if (rec->session->bytes_transferred && rec->session->bytes_compressed) { ratio = (float)rec->session->bytes_transferred/(float)rec->session->bytes_compressed; session->header.env.comp_ratio = ratio + 0.5; @@ -3130,17 +3189,6 @@ int cmd_record(int argc, const char **argv) symbol__init(NULL); - if (rec->opts.affinity != PERF_AFFINITY_SYS) { - rec->affinity_mask.nbits = cpu__max_cpu(); - rec->affinity_mask.bits = bitmap_alloc(rec->affinity_mask.nbits); - if (!rec->affinity_mask.bits) { - pr_err("Failed to allocate thread mask for %zd cpus\n", rec->affinity_mask.nbits); - err = -ENOMEM; - goto out_opts; - } - pr_debug2("thread mask[%zd]: empty\n", rec->affinity_mask.nbits); - } - err = record__auxtrace_init(rec); if (err) goto out; @@ -3278,7 +3326,6 @@ int cmd_record(int argc, const char **argv) err = __cmd_record(&record, argc, argv); out: - bitmap_free(rec->affinity_mask.bits); evlist__delete(rec->evlist); symbol__exit(); auxtrace_record__free(rec->itr); -- 2.19.0