Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754551Ab2HGM4L (ORCPT ); Tue, 7 Aug 2012 08:56:11 -0400 Received: from mailhub.sw.ru ([195.214.232.25]:21160 "EHLO relay.sw.ru" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750734Ab2HGM4J (ORCPT ); Tue, 7 Aug 2012 08:56:09 -0400 From: Andrew Vagin To: linux-kernel@vger.kernel.org Cc: Peter Zijlstra , Paul Mackerras , Ingo Molnar , Arnaldo Carvalho de Melo Subject: [PATCH 3/4] perf: teach perf inject to merge sched_stat_* and sched_switch events (v2) Date: Tue, 7 Aug 2012 16:56:04 +0400 Message-Id: <1344344165-369636-4-git-send-email-avagin@openvz.org> X-Mailer: git-send-email 1.7.1 In-Reply-To: <1344344165-369636-1-git-send-email-avagin@openvz.org> References: <1344344165-369636-1-git-send-email-avagin@openvz.org> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5018 Lines: 171 You may want to know where and how long a task is sleeping. A callchain may be found in sched_switch and a time slice in stat_iowait, so I add handler in perf inject for merging this events. My code saves sched_switch event for each process and when it meets stat_iowait, it reports the sched_switch event, because this event contains a correct callchain. By another words it replaces all stat_iowait events on proper sched_switch events. v2: - remove the global variable "session" - hadle errors from malloc() Signed-off-by: Andrew Vagin --- tools/perf/Documentation/perf-inject.txt | 4 ++ tools/perf/builtin-inject.c | 86 ++++++++++++++++++++++++++++++ 2 files changed, 90 insertions(+), 0 deletions(-) diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt index 6be2101..c04e0c6 100644 --- a/tools/perf/Documentation/perf-inject.txt +++ b/tools/perf/Documentation/perf-inject.txt @@ -35,6 +35,10 @@ OPTIONS -o:: --output=:: Output file name. (default: stdout) +-s:: +--sched-stat:: + Merge sched_stat and sched_switch for getting events where and how long + tasks slept. SEE ALSO -------- diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 4c9cdbb..9b3393a 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -8,11 +8,13 @@ #include "builtin.h" #include "perf.h" +#include "util/evsel.h" #include "util/session.h" #include "util/tool.h" #include "util/debug.h" #include "util/parse-options.h" +#include "util/trace-event.h" static const char *input_name = "-"; static const char *output_name = "-"; @@ -21,6 +23,7 @@ static int output; static u64 bytes_written; static bool inject_build_ids; +static bool inject_sched_stat; static int perf_event__repipe_synth(struct perf_tool *tool __used, union perf_event *event, @@ -210,6 +213,83 @@ repipe: return 0; } +struct event_entry { + struct list_head node; + u32 pid; + union perf_event event[0]; +}; + +static LIST_HEAD(samples); + +static int perf_event__sched_stat(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine) +{ + const char *evname = NULL; + uint32_t size; + struct event_entry *ent; + union perf_event *event_sw = NULL; + struct perf_sample sample_sw; + int sched_process_exit; + + size = event->header.size; + + evname = evsel->tp_format->name; + + sched_process_exit = !strcmp(evname, "sched_process_exit"); + + if (!strcmp(evname, "sched_switch") || sched_process_exit) { + list_for_each_entry(ent, &samples, node) + if (sample->pid == ent->pid) + break; + + if (&ent->node != &samples) { + list_del(&ent->node); + free(ent); + } + + if (sched_process_exit) + return 0; + + ent = malloc(size + sizeof(struct event_entry)); + if (ent == NULL) + die("malloc"); + ent->pid = sample->pid; + memcpy(&ent->event, event, size); + list_add(&ent->node, &samples); + return 0; + + } else if (!strncmp(evname, "sched_stat_", 11)) { + u32 pid; + + pid = raw_field_value(evsel->tp_format, + "pid", sample->raw_data); + + list_for_each_entry(ent, &samples, node) { + if (pid == ent->pid) + break; + } + + if (&ent->node == &samples) + return 0; + + event_sw = &ent->event[0]; + perf_evsel__parse_sample(evsel, event_sw, &sample_sw, false); + + sample_sw.period = sample->period; + sample_sw.time = sample->time; + perf_evsel__synthesize_sample(evsel, event_sw, &sample_sw, false); + + perf_event__repipe(tool, event_sw, &sample_sw, machine); + return 0; + } + + perf_event__repipe(tool, event, sample, machine); + + return 0; +} struct perf_tool perf_inject = { .sample = perf_event__repipe_sample, .mmap = perf_event__repipe, @@ -245,6 +325,9 @@ static int __cmd_inject(void) perf_inject.mmap = perf_event__repipe_mmap; perf_inject.fork = perf_event__repipe_task; perf_inject.tracing_data = perf_event__repipe_tracing_data; + } else if (inject_sched_stat) { + perf_inject.sample = perf_event__sched_stat; + perf_inject.ordered_samples = true; } session = perf_session__new(input_name, O_RDONLY, false, true, &perf_inject); @@ -272,6 +355,9 @@ static const char * const report_usage[] = { static const struct option options[] = { OPT_BOOLEAN('b', "build-ids", &inject_build_ids, "Inject build-ids into the output stream"), + OPT_BOOLEAN('s', "sched-stat", &inject_sched_stat, + "Merge sched-stat and sched-switch for getting events " + "where and how long tasks slept"), OPT_STRING('i', "input", &input_name, "file", "input file name"), OPT_STRING('o', "output", &output_name, "file", -- 1.7.1 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/