From f36f83f947ede547833e462696893f866df77324 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 4 Jun 2013 14:46:19 +0900 Subject: perf sched: Move struct perf_sched definition out of cmd_sched() For some reason it consumed quite amount of compile time when declared as local variable, and it disappeared when moved out of the function. Moving other variables/tables didn't help. On my system this single-file-change build time reduced from 11s to 3s. Signed-off-by: Namhyung Kim Cc: David Ahern Cc: Ingo Molnar Cc: Jiri Olsa Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1370324779-16921-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-sched.c | 41 +++++++++++++++++++++-------------------- 1 file changed, 21 insertions(+), 20 deletions(-) (limited to 'tools/perf/builtin-sched.c') diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index fed9ae432c16..fba4a940ba31 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -1662,28 +1662,29 @@ static int __cmd_record(int argc, const char **argv) return cmd_record(i, rec_argv, NULL); } +static const char default_sort_order[] = "avg, max, switch, runtime"; +static struct perf_sched sched = { + .tool = { + .sample = perf_sched__process_tracepoint_sample, + .comm = perf_event__process_comm, + .lost = perf_event__process_lost, + .fork = perf_event__process_fork, + .ordered_samples = true, + }, + .cmp_pid = LIST_HEAD_INIT(sched.cmp_pid), + .sort_list = LIST_HEAD_INIT(sched.sort_list), + .start_work_mutex = PTHREAD_MUTEX_INITIALIZER, + .work_done_wait_mutex = PTHREAD_MUTEX_INITIALIZER, + .curr_pid = { [0 ... MAX_CPUS - 1] = -1 }, + .sort_order = default_sort_order, + .replay_repeat = 10, + .profile_cpu = -1, + .next_shortname1 = 'A', + .next_shortname2 = '0', +}; + int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) { - const char default_sort_order[] = "avg, max, switch, runtime"; - struct perf_sched sched = { - .tool = { - .sample = perf_sched__process_tracepoint_sample, - .comm = perf_event__process_comm, - .lost = perf_event__process_lost, - .fork = perf_event__process_fork, - .ordered_samples = true, - }, - .cmp_pid = LIST_HEAD_INIT(sched.cmp_pid), - .sort_list = LIST_HEAD_INIT(sched.sort_list), - .start_work_mutex = PTHREAD_MUTEX_INITIALIZER, - .work_done_wait_mutex = PTHREAD_MUTEX_INITIALIZER, - .curr_pid = { [0 ... MAX_CPUS - 1] = -1 }, - .sort_order = default_sort_order, - .replay_repeat = 10, - .profile_cpu = -1, - .next_shortname1 = 'A', - .next_shortname2 = '0', - }; const struct option latency_options[] = { OPT_STRING('s', "sort", &sched.sort_order, "key[,key2...]", "sort by key(s): runtime, switch, avg, max"), -- cgit v1.2.3 From 380512345e13c3af64e59627f1b993c4faa94a84 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 4 Jul 2013 16:20:31 +0300 Subject: perf tools: struct thread has a tid not a pid As evident from 'machine__process_fork_event()' and 'machine__process_exit_event()' the 'pid' member of struct thread is actually the tid. Rename 'pid' to 'tid' in struct thread accordingly. Signed-off-by: Adrian Hunter Acked-by: David Ahern Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1372944040-32690-13-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-sched.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'tools/perf/builtin-sched.c') diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index fba4a940ba31..948183adb6e5 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -1075,7 +1075,7 @@ static int latency_migrate_task_event(struct perf_sched *sched, if (!atoms) { if (thread_atoms_insert(sched, migrant)) return -1; - register_pid(sched, migrant->pid, migrant->comm); + register_pid(sched, migrant->tid, migrant->comm); atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid); if (!atoms) { pr_err("migration-event: Internal tree error"); @@ -1115,7 +1115,7 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_ sched->all_runtime += work_list->total_runtime; sched->all_count += work_list->nb_atoms; - ret = printf(" %s:%d ", work_list->thread->comm, work_list->thread->pid); + ret = printf(" %s:%d ", work_list->thread->comm, work_list->thread->tid); for (i = 0; i < 24 - ret; i++) printf(" "); @@ -1131,9 +1131,9 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_ static int pid_cmp(struct work_atoms *l, struct work_atoms *r) { - if (l->thread->pid < r->thread->pid) + if (l->thread->tid < r->thread->tid) return -1; - if (l->thread->pid > r->thread->pid) + if (l->thread->tid > r->thread->tid) return 1; return 0; @@ -1321,7 +1321,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, printf("*"); if (sched->curr_thread[cpu]) { - if (sched->curr_thread[cpu]->pid) + if (sched->curr_thread[cpu]->tid) printf("%2s ", sched->curr_thread[cpu]->shortname); else printf(". "); @@ -1332,7 +1332,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, printf(" %12.6f secs ", (double)timestamp/1e9); if (new_shortname) { printf("%s => %s:%d\n", - sched_in->shortname, sched_in->comm, sched_in->pid); + sched_in->shortname, sched_in->comm, sched_in->tid); } else { printf("\n"); } -- cgit v1.2.3 From ad9def7ca020ef5b54968c89194f52d18ef1ef49 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 7 Aug 2013 22:50:44 -0400 Subject: perf sched: Simplify arguments to read_events Destroy argument is not necessary. If session is not returned to caller, then clean it up. Signed-off-by: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1375930261-77273-3-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-sched.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'tools/perf/builtin-sched.c') diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 948183adb6e5..34ce57d24721 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -1445,7 +1445,7 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_ return err; } -static int perf_sched__read_events(struct perf_sched *sched, bool destroy, +static int perf_sched__read_events(struct perf_sched *sched, struct perf_session **psession) { const struct perf_evsel_str_handler handlers[] = { @@ -1480,11 +1480,10 @@ static int perf_sched__read_events(struct perf_sched *sched, bool destroy, sched->nr_lost_chunks = session->stats.nr_events[PERF_RECORD_LOST]; } - if (destroy) - perf_session__delete(session); - if (psession) *psession = session; + else + perf_session__delete(session); return 0; @@ -1529,8 +1528,11 @@ static int perf_sched__lat(struct perf_sched *sched) struct perf_session *session; setup_pager(); - if (perf_sched__read_events(sched, false, &session)) + + /* save session -- references to threads are held in work_list */ + if (perf_sched__read_events(sched, &session)) return -1; + perf_sched__sort_lat(sched); printf("\n ---------------------------------------------------------------------------------------------------------------\n"); @@ -1565,7 +1567,7 @@ static int perf_sched__map(struct perf_sched *sched) sched->max_cpu = sysconf(_SC_NPROCESSORS_CONF); setup_pager(); - if (perf_sched__read_events(sched, true, NULL)) + if (perf_sched__read_events(sched, NULL)) return -1; print_bad_events(sched); return 0; @@ -1580,7 +1582,7 @@ static int perf_sched__replay(struct perf_sched *sched) test_calibrations(sched); - if (perf_sched__read_events(sched, true, NULL)) + if (perf_sched__read_events(sched, NULL)) return -1; printf("nr_run_events: %ld\n", sched->nr_run_events); -- cgit v1.2.3 From ffb273dd7e3bd72e7d964fc0a0f6d441aceb7dae Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 7 Aug 2013 22:50:45 -0400 Subject: perf sched: Remove thread lookup in sample handler Not used in the function, so no sense in doing the lookup here. Thread look up will be done in the timehist command, and no sense in doing it twice. Signed-off-by: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1375930261-77273-4-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-sched.c | 7 ------- 1 file changed, 7 deletions(-) (limited to 'tools/perf/builtin-sched.c') diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 34ce57d24721..52850240583a 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -1425,15 +1425,8 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_ struct perf_evsel *evsel, struct machine *machine) { - struct thread *thread = machine__findnew_thread(machine, sample->tid); int err = 0; - if (thread == NULL) { - pr_debug("problem processing %s event, skipping it.\n", - perf_evsel__name(evsel)); - return -1; - } - evsel->hists.stats.total_period += sample->period; hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE); -- cgit v1.2.3 From 4a957e4df1a212c447fd162d18dc7ee6320c1621 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 7 Aug 2013 22:50:46 -0400 Subject: perf sched: Remove sched_process_exit tracepoint Event is not needed nor analyzed. Since perf-sched leverages perf-record to capture the sched data, we already capture task events like EXIT. Signed-off-by: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1375930261-77273-5-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-sched.c | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'tools/perf/builtin-sched.c') diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 52850240583a..42f45873d8f0 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -1392,15 +1392,6 @@ static int process_sched_fork_event(struct perf_tool *tool, return 0; } -static int process_sched_exit_event(struct perf_tool *tool __maybe_unused, - struct perf_evsel *evsel, - struct perf_sample *sample __maybe_unused, - struct machine *machine __maybe_unused) -{ - pr_debug("sched_exit event %p\n", evsel); - return 0; -} - static int process_sched_migrate_task_event(struct perf_tool *tool, struct perf_evsel *evsel, struct perf_sample *sample, @@ -1447,7 +1438,6 @@ static int perf_sched__read_events(struct perf_sched *sched, { "sched:sched_wakeup", process_sched_wakeup_event, }, { "sched:sched_wakeup_new", process_sched_wakeup_event, }, { "sched:sched_process_fork", process_sched_fork_event, }, - { "sched:sched_process_exit", process_sched_exit_event, }, { "sched:sched_migrate_task", process_sched_migrate_task_event, }, }; struct perf_session *session; @@ -1634,7 +1624,6 @@ static int __cmd_record(int argc, const char **argv) "-e", "sched:sched_stat_sleep", "-e", "sched:sched_stat_iowait", "-e", "sched:sched_stat_runtime", - "-e", "sched:sched_process_exit", "-e", "sched:sched_process_fork", "-e", "sched:sched_wakeup", "-e", "sched:sched_migrate_task", -- cgit v1.2.3 From cb627505ae028a0cd88cc29ed72a4c168a08751d Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 7 Aug 2013 22:50:47 -0400 Subject: perf sched: Remove sched_process_fork tracepoint The PERF_RECORD_FORK event is already collected as part of the use of cmd_record and those events are analyzed as part of the libperf machinery. Using the fork tracepoint as well just duplicates the event load. Signed-off-by: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1375930261-77273-6-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-sched.c | 60 ++++++++++++++++++++++++---------------------- 1 file changed, 31 insertions(+), 29 deletions(-) (limited to 'tools/perf/builtin-sched.c') diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 42f45873d8f0..f809cc7fb7d9 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -109,8 +109,9 @@ struct trace_sched_handler { int (*wakeup_event)(struct perf_sched *sched, struct perf_evsel *evsel, struct perf_sample *sample, struct machine *machine); - int (*fork_event)(struct perf_sched *sched, struct perf_evsel *evsel, - struct perf_sample *sample); + /* PERF_RECORD_FORK event, not sched_process_fork tracepoint */ + int (*fork_event)(struct perf_sched *sched, union perf_event *event, + struct machine *machine); int (*migrate_task_event)(struct perf_sched *sched, struct perf_evsel *evsel, @@ -717,22 +718,29 @@ static int replay_switch_event(struct perf_sched *sched, return 0; } -static int replay_fork_event(struct perf_sched *sched, struct perf_evsel *evsel, - struct perf_sample *sample) +static int replay_fork_event(struct perf_sched *sched, + union perf_event *event, + struct machine *machine) { - const char *parent_comm = perf_evsel__strval(evsel, sample, "parent_comm"), - *child_comm = perf_evsel__strval(evsel, sample, "child_comm"); - const u32 parent_pid = perf_evsel__intval(evsel, sample, "parent_pid"), - child_pid = perf_evsel__intval(evsel, sample, "child_pid"); + struct thread *child, *parent; + + child = machine__findnew_thread(machine, event->fork.tid); + parent = machine__findnew_thread(machine, event->fork.ptid); + + if (child == NULL || parent == NULL) { + pr_debug("thread does not exist on fork event: child %p, parent %p\n", + child, parent); + return 0; + } if (verbose) { - printf("sched_fork event %p\n", evsel); - printf("... parent: %s/%d\n", parent_comm, parent_pid); - printf("... child: %s/%d\n", child_comm, child_pid); + printf("fork event\n"); + printf("... parent: %s/%d\n", parent->comm, parent->tid); + printf("... child: %s/%d\n", child->comm, child->tid); } - register_pid(sched, parent_pid, parent_comm); - register_pid(sched, child_pid, child_comm); + register_pid(sched, parent->tid, parent->comm); + register_pid(sched, child->tid, child->comm); return 0; } @@ -824,14 +832,6 @@ static int thread_atoms_insert(struct perf_sched *sched, struct thread *thread) return 0; } -static int latency_fork_event(struct perf_sched *sched __maybe_unused, - struct perf_evsel *evsel __maybe_unused, - struct perf_sample *sample __maybe_unused) -{ - /* should insert the newcomer */ - return 0; -} - static char sched_out_state(u64 prev_state) { const char *str = TASK_STATE_TO_CHAR_STR; @@ -1379,15 +1379,19 @@ static int process_sched_runtime_event(struct perf_tool *tool, return 0; } -static int process_sched_fork_event(struct perf_tool *tool, - struct perf_evsel *evsel, - struct perf_sample *sample, - struct machine *machine __maybe_unused) +static int perf_sched__process_fork_event(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) { struct perf_sched *sched = container_of(tool, struct perf_sched, tool); + /* run the fork event through the perf machineruy */ + perf_event__process_fork(tool, event, sample, machine); + + /* and then run additional processing needed for this command */ if (sched->tp_handler->fork_event) - return sched->tp_handler->fork_event(sched, evsel, sample); + return sched->tp_handler->fork_event(sched, event, machine); return 0; } @@ -1437,7 +1441,6 @@ static int perf_sched__read_events(struct perf_sched *sched, { "sched:sched_stat_runtime", process_sched_runtime_event, }, { "sched:sched_wakeup", process_sched_wakeup_event, }, { "sched:sched_wakeup_new", process_sched_wakeup_event, }, - { "sched:sched_process_fork", process_sched_fork_event, }, { "sched:sched_migrate_task", process_sched_migrate_task_event, }, }; struct perf_session *session; @@ -1652,7 +1655,7 @@ static struct perf_sched sched = { .sample = perf_sched__process_tracepoint_sample, .comm = perf_event__process_comm, .lost = perf_event__process_lost, - .fork = perf_event__process_fork, + .fork = perf_sched__process_fork_event, .ordered_samples = true, }, .cmp_pid = LIST_HEAD_INIT(sched.cmp_pid), @@ -1714,7 +1717,6 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) .wakeup_event = latency_wakeup_event, .switch_event = latency_switch_event, .runtime_event = latency_runtime_event, - .fork_event = latency_fork_event, .migrate_task_event = latency_migrate_task_event, }; struct trace_sched_handler map_ops = { -- cgit v1.2.3 From 314add6b1f045b59ca39683bd0cbc5310cd203f2 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 27 Aug 2013 11:23:03 +0300 Subject: perf tools: change machine__findnew_thread() to set thread pid Add a new parameter for 'pid' to machine__findnew_thread(). Change callers to pass 'pid' when it is known. Note that callers sometimes want to find the main thread which has the memory maps. The main thread has tid == pid so the usage in that case is: machine__findnew_thread(machine, pid, pid) whereas the usage to find the specific thread is: machine__findnew_thread(machine, pid, tid) Signed-off-by: Adrian Hunter Acked-by: David Ahern Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1377591794-30553-2-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-sched.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) (limited to 'tools/perf/builtin-sched.c') diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index f809cc7fb7d9..d8c51b2f263f 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -724,8 +724,10 @@ static int replay_fork_event(struct perf_sched *sched, { struct thread *child, *parent; - child = machine__findnew_thread(machine, event->fork.tid); - parent = machine__findnew_thread(machine, event->fork.ptid); + child = machine__findnew_thread(machine, event->fork.pid, + event->fork.tid); + parent = machine__findnew_thread(machine, event->fork.ppid, + event->fork.ptid); if (child == NULL || parent == NULL) { pr_debug("thread does not exist on fork event: child %p, parent %p\n", @@ -934,8 +936,8 @@ static int latency_switch_event(struct perf_sched *sched, return -1; } - sched_out = machine__findnew_thread(machine, prev_pid); - sched_in = machine__findnew_thread(machine, next_pid); + sched_out = machine__findnew_thread(machine, 0, prev_pid); + sched_in = machine__findnew_thread(machine, 0, next_pid); out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid); if (!out_events) { @@ -978,7 +980,7 @@ static int latency_runtime_event(struct perf_sched *sched, { const u32 pid = perf_evsel__intval(evsel, sample, "pid"); const u64 runtime = perf_evsel__intval(evsel, sample, "runtime"); - struct thread *thread = machine__findnew_thread(machine, pid); + struct thread *thread = machine__findnew_thread(machine, 0, pid); struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid); u64 timestamp = sample->time; int cpu = sample->cpu; @@ -1016,7 +1018,7 @@ static int latency_wakeup_event(struct perf_sched *sched, if (!success) return 0; - wakee = machine__findnew_thread(machine, pid); + wakee = machine__findnew_thread(machine, 0, pid); atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid); if (!atoms) { if (thread_atoms_insert(sched, wakee)) @@ -1070,7 +1072,7 @@ static int latency_migrate_task_event(struct perf_sched *sched, if (sched->profile_cpu == -1) return 0; - migrant = machine__findnew_thread(machine, pid); + migrant = machine__findnew_thread(machine, 0, pid); atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid); if (!atoms) { if (thread_atoms_insert(sched, migrant)) @@ -1289,8 +1291,8 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, return -1; } - sched_out = machine__findnew_thread(machine, prev_pid); - sched_in = machine__findnew_thread(machine, next_pid); + sched_out = machine__findnew_thread(machine, 0, prev_pid); + sched_in = machine__findnew_thread(machine, 0, next_pid); sched->curr_thread[this_cpu] = sched_in; -- cgit v1.2.3