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=-8.9 required=3.0 tests=DKIMWL_WL_HIGH,DKIM_SIGNED, DKIM_VALID,DKIM_VALID_AU,INCLUDES_PATCH,MAILING_LIST_MULTI,SIGNED_OFF_BY, SPF_PASS,URIBL_BLOCKED,USER_AGENT_MUTT 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 E27DAC64EAD for ; Tue, 9 Oct 2018 13:41:38 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 9253E2086D for ; Tue, 9 Oct 2018 13:41:38 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=kernel.org header.i=@kernel.org header.b="aWnbuNjU" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 9253E2086D Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=kernel.org Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726721AbeJIU6g (ORCPT ); Tue, 9 Oct 2018 16:58:36 -0400 Received: from mail.kernel.org ([198.145.29.99]:39940 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726492AbeJIU6g (ORCPT ); Tue, 9 Oct 2018 16:58:36 -0400 Received: from jouet.infradead.org (unknown [179.97.41.186]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPSA id 862B22086D; Tue, 9 Oct 2018 13:41:34 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1539092494; bh=j/1Eh3Zzi3k0pxhAAf/EnAMGRvjBj/YbgpjiZXIBzhE=; h=Date:From:To:Cc:Subject:References:In-Reply-To:From; b=aWnbuNjU8reZb3ciUWpkl4UUtpVH6MHSC0HAmdMo0EX4WpNfAUT5/lgyo7gcMUGCD C54g0BWaZAKQkN6/kSPrCtBMNCLlRcp8sltobaBw2DF6GeOlhoGjkdNoEdARbusNa6 pUS7uWY8VjrBsgckYs1MnFbh2E18qXJ8+ehccNQw= Received: by jouet.infradead.org (Postfix, from userid 1000) id 58362142C5E; Tue, 9 Oct 2018 10:41:31 -0300 (-03) Date: Tue, 9 Oct 2018 10:41:31 -0300 From: Arnaldo Carvalho de Melo To: Alexey Budankov Cc: Peter Zijlstra , Ingo Molnar , Alexander Shishkin , Jiri Olsa , Namhyung Kim , Andi Kleen , linux-kernel Subject: Re: [PATCH v4] perf record: encode -k clockid frequency into Perf trace Message-ID: <20181009134131.GB10775@kernel.org> References: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: X-Url: http://acmel.wordpress.com User-Agent: Mutt/1.9.2 (2017-12-15) Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Em Tue, Oct 09, 2018 at 09:59:03AM +0300, Alexey Budankov escreveu: > > Store -k clockid frequency into Perf trace to enable timestamps > derived metrics conversion into wall clock time on reporting stage. > > Below is the example of perf report output: Some questions below, left the code for easier reference. > tools/perf/perf record -k raw -- ../../matrix/linux/matrix.gcc > ... > [ perf record: Captured and wrote 31.222 MB perf.data (818054 samples) ] > > tools/perf/perf report --header > # ======== > ... > # event : name = cycles:ppp, , size = 112, { sample_period, sample_freq } = 4000, sample_type = IP|TID|TIME|PERIOD, disabled = 1, inherit = 1, mmap = 1, comm = 1, freq = 1, enable_on_exec = 1, task = 1, precise_ip = 3, sample_id_all = 1, exclude_guest = 1, mmap2 = 1, comm_exec = 1, use_clockid = 1, clockid = 4 > ... > # clockid frequency: 1000 MHz > ... > # ======== > > Signed-off-by: Alexey Budankov > --- > Changes in v4: > - addressed compilation issues on 32bit platforms > Changes in v3: > - moved header's clockid_res_ns initialization out of record__init_features() > - added explicit warning for case of failed clock_getres() call > Changes in v2: > - renamed clockid_freq to clockid_res_ns and get_clockid_freq() to get_clockid_res() > - avoided redundant define of NSEC_IN_SEC, reused linux/time64.h:NSEC_PER_SEC > - moved MHz conversion into print_clockid() and shortened write_clockid() > --- > tools/perf/builtin-record.c | 24 ++++++++++++++++++++++-- > tools/perf/perf.h | 1 + > tools/perf/util/env.h | 1 + > tools/perf/util/header.c | 28 ++++++++++++++++++++++++++++ > tools/perf/util/header.h | 1 + > 5 files changed, 53 insertions(+), 2 deletions(-) > > diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c > index 0980dfe3396b..d803d3264465 100644 > --- a/tools/perf/builtin-record.c > +++ b/tools/perf/builtin-record.c > @@ -592,6 +592,9 @@ static void record__init_features(struct record *rec) > if (!rec->opts.full_auxtrace) > perf_header__clear_feat(&session->header, HEADER_AUXTRACE); > > + if (!(rec->opts.use_clockid && rec->opts.clockid_res_ns)) > + perf_header__clear_feat(&session->header, HEADER_CLOCKID); > + > perf_header__clear_feat(&session->header, HEADER_STAT); > } > > @@ -897,6 +900,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) > > record__init_features(rec); > > + if (rec->opts.use_clockid && rec->opts.clockid_res_ns) > + session->header.env.clockid_res_ns = rec->opts.clockid_res_ns; > + > if (forks) { > err = perf_evlist__prepare_workload(rec->evlist, &opts->target, > argv, data->is_pipe, > @@ -1337,6 +1343,19 @@ static const struct clockid_map clockids[] = { > CLOCKID_END, > }; > > +static int get_clockid_res(clockid_t clk_id, size_t *res_ns) > +{ > + struct timespec res; > + > + *res_ns = 0; > + if (!clock_getres(clk_id, &res)) > + *res_ns = res.tv_nsec + res.tv_sec * NSEC_PER_SEC; > + else > + pr_warning("WARNING: Failed to determine specified clock resolution.\n"); > + > + return 0; > +} > + > static int parse_clockid(const struct option *opt, const char *str, int unset) > { > struct record_opts *opts = (struct record_opts *)opt->value; > @@ -1360,7 +1379,7 @@ static int parse_clockid(const struct option *opt, const char *str, int unset) > > /* if its a number, we're done */ > if (sscanf(str, "%d", &opts->clockid) == 1) > - return 0; > + return get_clockid_res(opts->clockid, &opts->clockid_res_ns); > > /* allow a "CLOCK_" prefix to the name */ > if (!strncasecmp(str, "CLOCK_", 6)) > @@ -1369,7 +1388,8 @@ static int parse_clockid(const struct option *opt, const char *str, int unset) > for (cm = clockids; cm->name; cm++) { > if (!strcasecmp(str, cm->name)) { > opts->clockid = cm->clockid; > - return 0; > + return get_clockid_res(opts->clockid, > + &opts->clockid_res_ns); > } > } > > diff --git a/tools/perf/perf.h b/tools/perf/perf.h > index 21bf7f5a3cf5..981db3c2ed60 100644 > --- a/tools/perf/perf.h > +++ b/tools/perf/perf.h > @@ -81,6 +81,7 @@ struct record_opts { > unsigned initial_delay; > bool use_clockid; > clockid_t clockid; > + size_t clockid_res_ns; > unsigned int proc_map_timeout; > }; > > diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h > index 1f3ccc368530..b167a54d635f 100644 > --- a/tools/perf/util/env.h > +++ b/tools/perf/util/env.h > @@ -63,6 +63,7 @@ struct perf_env { > struct numa_node *numa_nodes; > struct memory_node *memory_nodes; > unsigned long long memory_bsize; > + size_t clockid_res_ns; > }; > > extern struct perf_env perf_env; > diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c > index 1ec1d9bc2d63..702e0cce63da 100644 > --- a/tools/perf/util/header.c > +++ b/tools/perf/util/header.c > @@ -1034,6 +1034,14 @@ static int write_auxtrace(struct feat_fd *ff, > return err; > } > > +static int write_clockid(struct feat_fd *ff, > + struct perf_evlist *evlist __maybe_unused) > +{ > + u64 clockid_res_ns = ff->ph->env.clockid_res_ns; > + > + return do_write(ff, &clockid_res_ns, sizeof(clockid_res_ns)); > +} > + > static int cpu_cache_level__sort(const void *a, const void *b) > { > struct cpu_cache_level *cache_a = (struct cpu_cache_level *)a; > @@ -1508,6 +1516,12 @@ static void print_cpu_topology(struct feat_fd *ff, FILE *fp) > fprintf(fp, "# Core ID and Socket ID information is not available\n"); > } > > +static void print_clockid(struct feat_fd *ff, FILE *fp) > +{ > + fprintf(fp, "# clockid frequency: %zd MHz\n", > + ff->ph->env.clockid_res_ns * 1000); > +} > + > static void free_event_desc(struct perf_evsel *events) > { > struct perf_evsel *evsel; > @@ -2531,6 +2545,19 @@ static int process_mem_topology(struct feat_fd *ff, > return ret; > } > > +static int process_clockid(struct feat_fd *ff, > + void *data __maybe_unused) > +{ > + u64 clockid_res_ns; > + > + if (do_read_u64(ff, &clockid_res_ns)) > + return -1; > + > + ff->ph->env.clockid_res_ns = *(size_t *)&clockid_res_ns; What is wrong with: ff->ph->env.clockid_res_ns = clockid_res_ns; ? Also why have you picked 'size_t' for that nanoseconds variable (clockid_res_ns)? When one looks at things like: struct timespec { time_t tv_sec; /* seconds */ long tv_nsec; /* nanoseconds */ }; that would lead one to use 'long' for a variable holding nanoseconds, no? And 'timespec' is what clock_getres() uses: int clock_getres(clockid_t clk_id, struct timespec *res); Since you're storing this as: +static int get_clockid_res(clockid_t clk_id, size_t *res_ns) +{ + struct timespec res; + + *res_ns = 0; + if (!clock_getres(clk_id, &res)) + *res_ns = res.tv_nsec + res.tv_sec * NSEC_PER_SEC; Why don't you make ff->ph->env.clockid_res_ns an 'u64'? Would simplify the code a bit, no? Am I missing something? - Arnaldo > + return 0; > +} > + > struct feature_ops { > int (*write)(struct feat_fd *ff, struct perf_evlist *evlist); > void (*print)(struct feat_fd *ff, FILE *fp); > @@ -2590,6 +2617,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { > FEAT_OPN(CACHE, cache, true), > FEAT_OPR(SAMPLE_TIME, sample_time, false), > FEAT_OPR(MEM_TOPOLOGY, mem_topology, true), > + FEAT_OPR(CLOCKID, clockid, false) > }; > > struct header_print_data { > diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h > index e17903caa71d..0d553ddca0a3 100644 > --- a/tools/perf/util/header.h > +++ b/tools/perf/util/header.h > @@ -38,6 +38,7 @@ enum { > HEADER_CACHE, > HEADER_SAMPLE_TIME, > HEADER_MEM_TOPOLOGY, > + HEADER_CLOCKID, > HEADER_LAST_FEATURE, > HEADER_FEAT_BITS = 256, > };