From 1844dbcbe78503e0f4a8996d69da725d5e7a5177 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 28 May 2014 14:12:18 +0900 Subject: perf tools: Introduce hists__inc_nr_samples() There're some duplicate code for counting number of samples. Add hists__inc_nr_samples() and reuse it. Suggested-by: Jiri Olsa Signed-off-by: Namhyung Kim Link: http://lkml.kernel.org/r/1401335910-16832-2-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa --- tools/perf/util/hist.h | 1 + 1 file changed, 1 insertion(+) (limited to 'tools/perf/util/hist.h') diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index a8418d19808d..03ae1dbb1b15 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -119,6 +119,7 @@ u64 hists__total_period(struct hists *hists); void hists__reset_stats(struct hists *hists); void hists__inc_stats(struct hists *hists, struct hist_entry *h); void hists__inc_nr_events(struct hists *hists, u32 type); +void hists__inc_nr_samples(struct hists *hists, bool filtered); void events_stats__inc(struct events_stats *stats, u32 type); size_t events_stats__fprintf(struct events_stats *stats, FILE *fp); -- cgit v1.2.3 From 69bcb019fc809874f518559c8e5b0a90176f0532 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 30 Oct 2013 09:40:34 +0900 Subject: perf tools: Introduce struct hist_entry_iter There're some duplicate code when adding hist entries. They are different in that some have branch info or mem info but generally do same thing. So introduce new struct hist_entry_iter and add callbacks to customize each case in general way. The new perf_evsel__add_entry() function will look like: iter->prepare_entry(); iter->add_single_entry(); while (iter->next_entry()) iter->add_next_entry(); iter->finish_entry(); This will help further work like the cumulative callchain patchset. Signed-off-by: Namhyung Kim Tested-by: Arun Sharma Tested-by: Rodrigo Campos Cc: David Ahern Cc: Frederic Weisbecker Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1401335910-16832-3-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa --- tools/perf/builtin-report.c | 192 ++++---------------------- tools/perf/tests/hists_filter.c | 16 ++- tools/perf/tests/hists_output.c | 11 +- tools/perf/util/hist.c | 299 ++++++++++++++++++++++++++++++++++++++++ tools/perf/util/hist.h | 33 +++++ 5 files changed, 372 insertions(+), 179 deletions(-) (limited to 'tools/perf/util/hist.h') diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 4a3b84dd4f41..3201bdfa8c3f 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -76,163 +76,16 @@ static int report__config(const char *var, const char *value, void *cb) return perf_default_config(var, value, cb); } -static void report__inc_stats(struct report *rep, struct hist_entry *he) +static void report__inc_stats(struct report *rep, + struct hist_entry *he __maybe_unused) { /* - * The @he is either of a newly created one or an existing one - * merging current sample. We only want to count a new one so - * checking ->nr_events being 1. + * We cannot access @he at this time. Just assume it's a new entry. + * It'll be fixed once we have a callback mechanism in hist_iter. */ - if (he->stat.nr_events == 1) - rep->nr_entries++; - - /* - * Only counts number of samples at this stage as it's more - * natural to do it here and non-sample events are also - * counted in perf_session_deliver_event(). The dump_trace - * requires this info is ready before going to the output tree. - */ - hists__inc_nr_samples(he->hists, he->filtered); -} - -static int report__add_mem_hist_entry(struct report *rep, struct addr_location *al, - struct perf_sample *sample, struct perf_evsel *evsel) -{ - struct symbol *parent = NULL; - struct hist_entry *he; - struct mem_info *mi, *mx; - uint64_t cost; - int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack); - - if (err) - return err; - - mi = sample__resolve_mem(sample, al); - if (!mi) - return -ENOMEM; - - if (rep->hide_unresolved && !al->sym) - return 0; - - cost = sample->weight; - if (!cost) - cost = 1; - - /* - * must pass period=weight in order to get the correct - * sorting from hists__collapse_resort() which is solely - * based on periods. We want sorting be done on nr_events * weight - * and this is indirectly achieved by passing period=weight here - * and the he_stat__add_period() function. - */ - he = __hists__add_entry(&evsel->hists, al, parent, NULL, mi, - cost, cost, 0); - if (!he) - return -ENOMEM; - - if (ui__has_annotation()) { - err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); - if (err) - goto out; - - mx = he->mem_info; - err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx); - if (err) - goto out; - } - - report__inc_stats(rep, he); - - err = hist_entry__append_callchain(he, sample); -out: - return err; -} - -static int report__add_branch_hist_entry(struct report *rep, struct addr_location *al, - struct perf_sample *sample, struct perf_evsel *evsel) -{ - struct symbol *parent = NULL; - unsigned i; - struct hist_entry *he; - struct branch_info *bi, *bx; - int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack); - - if (err) - return err; - - bi = sample__resolve_bstack(sample, al); - if (!bi) - return -ENOMEM; - - for (i = 0; i < sample->branch_stack->nr; i++) { - if (rep->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym)) - continue; - - err = -ENOMEM; - - /* overwrite the 'al' to branch-to info */ - al->map = bi[i].to.map; - al->sym = bi[i].to.sym; - al->addr = bi[i].to.addr; - /* - * The report shows the percentage of total branches captured - * and not events sampled. Thus we use a pseudo period of 1. - */ - he = __hists__add_entry(&evsel->hists, al, parent, &bi[i], NULL, - 1, 1, 0); - if (he) { - if (ui__has_annotation()) { - bx = he->branch_info; - err = addr_map_symbol__inc_samples(&bx->from, - evsel->idx); - if (err) - goto out; - - err = addr_map_symbol__inc_samples(&bx->to, - evsel->idx); - if (err) - goto out; - } - report__inc_stats(rep, he); - } else - goto out; - } - err = 0; -out: - free(bi); - return err; + rep->nr_entries++; } -static int report__add_hist_entry(struct report *rep, struct perf_evsel *evsel, - struct addr_location *al, struct perf_sample *sample) -{ - struct symbol *parent = NULL; - struct hist_entry *he; - int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack); - - if (err) - return err; - - he = __hists__add_entry(&evsel->hists, al, parent, NULL, NULL, - sample->period, sample->weight, - sample->transaction); - if (he == NULL) - return -ENOMEM; - - err = hist_entry__append_callchain(he, sample); - if (err) - goto out; - - if (ui__has_annotation()) - err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); - - report__inc_stats(rep, he); - -out: - return err; -} - - static int process_sample_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -241,6 +94,9 @@ static int process_sample_event(struct perf_tool *tool, { struct report *rep = container_of(tool, struct report, tool); struct addr_location al; + struct hist_entry_iter iter = { + .hide_unresolved = rep->hide_unresolved, + }; int ret; if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) { @@ -255,22 +111,22 @@ static int process_sample_event(struct perf_tool *tool, if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap)) return 0; - if (sort__mode == SORT_MODE__BRANCH) { - ret = report__add_branch_hist_entry(rep, &al, sample, evsel); - if (ret < 0) - pr_debug("problem adding lbr entry, skipping event\n"); - } else if (rep->mem_mode == 1) { - ret = report__add_mem_hist_entry(rep, &al, sample, evsel); - if (ret < 0) - pr_debug("problem adding mem entry, skipping event\n"); - } else { - if (al.map != NULL) - al.map->dso->hit = 1; - - ret = report__add_hist_entry(rep, evsel, &al, sample); - if (ret < 0) - pr_debug("problem incrementing symbol period, skipping event\n"); - } + if (sort__mode == SORT_MODE__BRANCH) + iter.ops = &hist_iter_branch; + else if (rep->mem_mode) + iter.ops = &hist_iter_mem; + else + iter.ops = &hist_iter_normal; + + if (al.map != NULL) + al.map->dso->hit = 1; + + report__inc_stats(rep, NULL); + + ret = hist_entry_iter__add(&iter, &al, evsel, sample, rep->max_stack); + if (ret < 0) + pr_debug("problem adding hist entry, skipping event\n"); + return ret; } diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index 0a71ef4b9158..76b02e1de701 100644 --- a/tools/perf/tests/hists_filter.c +++ b/tools/perf/tests/hists_filter.c @@ -42,11 +42,11 @@ static struct sample fake_samples[] = { { .pid = 300, .ip = 0xf0000 + 800, }, }; -static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) +static int add_hist_entries(struct perf_evlist *evlist, + struct machine *machine __maybe_unused) { struct perf_evsel *evsel; struct addr_location al; - struct hist_entry *he; struct perf_sample sample = { .cpu = 0, }; size_t i; @@ -62,6 +62,10 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) .misc = PERF_RECORD_MISC_USER, }, }; + struct hist_entry_iter iter = { + .ops = &hist_iter_normal, + .hide_unresolved = false, + }; /* make sure it has no filter at first */ evsel->hists.thread_filter = NULL; @@ -71,21 +75,19 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) sample.pid = fake_samples[i].pid; sample.tid = fake_samples[i].pid; sample.ip = fake_samples[i].ip; + sample.period = 100; if (perf_event__preprocess_sample(&event, machine, &al, &sample) < 0) goto out; - he = __hists__add_entry(&evsel->hists, &al, NULL, - NULL, NULL, 100, 1, 0); - if (he == NULL) + if (hist_entry_iter__add(&iter, &al, evsel, &sample, + PERF_MAX_STACK_DEPTH) < 0) goto out; fake_samples[i].thread = al.thread; fake_samples[i].map = al.map; fake_samples[i].sym = al.sym; - - hists__inc_nr_samples(he->hists, he->filtered); } } diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index a16850551797..1308f88a9169 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -46,7 +46,7 @@ static struct sample fake_samples[] = { static int add_hist_entries(struct hists *hists, struct machine *machine) { struct addr_location al; - struct hist_entry *he; + struct perf_evsel *evsel = hists_to_evsel(hists); struct perf_sample sample = { .period = 100, }; size_t i; @@ -56,6 +56,10 @@ static int add_hist_entries(struct hists *hists, struct machine *machine) .misc = PERF_RECORD_MISC_USER, }, }; + struct hist_entry_iter iter = { + .ops = &hist_iter_normal, + .hide_unresolved = false, + }; sample.cpu = fake_samples[i].cpu; sample.pid = fake_samples[i].pid; @@ -66,9 +70,8 @@ static int add_hist_entries(struct hists *hists, struct machine *machine) &sample) < 0) goto out; - he = __hists__add_entry(hists, &al, NULL, NULL, NULL, - sample.period, 1, 0); - if (he == NULL) + if (hist_entry_iter__add(&iter, &al, evsel, &sample, + PERF_MAX_STACK_DEPTH) < 0) goto out; fake_samples[i].thread = al.thread; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 5943ba60f193..d8662356de20 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -4,6 +4,7 @@ #include "session.h" #include "sort.h" #include "evsel.h" +#include "annotate.h" #include static bool hists__filter_entry_by_dso(struct hists *hists, @@ -429,6 +430,304 @@ struct hist_entry *__hists__add_entry(struct hists *hists, return add_hist_entry(hists, &entry, al); } +static int +iter_next_nop_entry(struct hist_entry_iter *iter __maybe_unused, + struct addr_location *al __maybe_unused) +{ + return 0; +} + +static int +iter_add_next_nop_entry(struct hist_entry_iter *iter __maybe_unused, + struct addr_location *al __maybe_unused) +{ + return 0; +} + +static int +iter_prepare_mem_entry(struct hist_entry_iter *iter, struct addr_location *al) +{ + struct perf_sample *sample = iter->sample; + struct mem_info *mi; + + mi = sample__resolve_mem(sample, al); + if (mi == NULL) + return -ENOMEM; + + iter->priv = mi; + return 0; +} + +static int +iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al) +{ + u64 cost; + struct mem_info *mi = iter->priv; + struct hist_entry *he; + + if (mi == NULL) + return -EINVAL; + + cost = iter->sample->weight; + if (!cost) + cost = 1; + + /* + * must pass period=weight in order to get the correct + * sorting from hists__collapse_resort() which is solely + * based on periods. We want sorting be done on nr_events * weight + * and this is indirectly achieved by passing period=weight here + * and the he_stat__add_period() function. + */ + he = __hists__add_entry(&iter->evsel->hists, al, iter->parent, NULL, mi, + cost, cost, 0); + if (!he) + return -ENOMEM; + + iter->he = he; + return 0; +} + +static int +iter_finish_mem_entry(struct hist_entry_iter *iter, struct addr_location *al) +{ + struct perf_evsel *evsel = iter->evsel; + struct hist_entry *he = iter->he; + struct mem_info *mx; + int err = -EINVAL; + + if (he == NULL) + goto out; + + if (ui__has_annotation()) { + err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); + if (err) + goto out; + + mx = he->mem_info; + err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx); + if (err) + goto out; + } + + hists__inc_nr_samples(&evsel->hists, he->filtered); + + err = hist_entry__append_callchain(he, iter->sample); + +out: + /* + * We don't need to free iter->priv (mem_info) here since + * the mem info was either already freed in add_hist_entry() or + * passed to a new hist entry by hist_entry__new(). + */ + iter->priv = NULL; + + iter->he = NULL; + return err; +} + +static int +iter_prepare_branch_entry(struct hist_entry_iter *iter, struct addr_location *al) +{ + struct branch_info *bi; + struct perf_sample *sample = iter->sample; + + bi = sample__resolve_bstack(sample, al); + if (!bi) + return -ENOMEM; + + iter->curr = 0; + iter->total = sample->branch_stack->nr; + + iter->priv = bi; + return 0; +} + +static int +iter_add_single_branch_entry(struct hist_entry_iter *iter __maybe_unused, + struct addr_location *al __maybe_unused) +{ + return 0; +} + +static int +iter_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al) +{ + struct branch_info *bi = iter->priv; + int i = iter->curr; + + if (bi == NULL) + return 0; + + if (iter->curr >= iter->total) + return 0; + + al->map = bi[i].to.map; + al->sym = bi[i].to.sym; + al->addr = bi[i].to.addr; + return 1; +} + +static int +iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al) +{ + struct branch_info *bi, *bx; + struct perf_evsel *evsel = iter->evsel; + struct hist_entry *he = NULL; + int i = iter->curr; + int err = 0; + + bi = iter->priv; + + if (iter->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym)) + goto out; + + /* + * The report shows the percentage of total branches captured + * and not events sampled. Thus we use a pseudo period of 1. + */ + he = __hists__add_entry(&evsel->hists, al, iter->parent, &bi[i], NULL, + 1, 1, 0); + if (he == NULL) + return -ENOMEM; + + if (ui__has_annotation()) { + bx = he->branch_info; + err = addr_map_symbol__inc_samples(&bx->from, evsel->idx); + if (err) + goto out; + + err = addr_map_symbol__inc_samples(&bx->to, evsel->idx); + if (err) + goto out; + } + + hists__inc_nr_samples(&evsel->hists, he->filtered); + +out: + iter->he = he; + iter->curr++; + return err; +} + +static int +iter_finish_branch_entry(struct hist_entry_iter *iter, + struct addr_location *al __maybe_unused) +{ + zfree(&iter->priv); + iter->he = NULL; + + return iter->curr >= iter->total ? 0 : -1; +} + +static int +iter_prepare_normal_entry(struct hist_entry_iter *iter __maybe_unused, + struct addr_location *al __maybe_unused) +{ + return 0; +} + +static int +iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location *al) +{ + struct perf_evsel *evsel = iter->evsel; + struct perf_sample *sample = iter->sample; + struct hist_entry *he; + + he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL, + sample->period, sample->weight, + sample->transaction); + if (he == NULL) + return -ENOMEM; + + iter->he = he; + return 0; +} + +static int +iter_finish_normal_entry(struct hist_entry_iter *iter, struct addr_location *al) +{ + int err; + struct hist_entry *he = iter->he; + struct perf_evsel *evsel = iter->evsel; + struct perf_sample *sample = iter->sample; + + if (he == NULL) + return 0; + + iter->he = NULL; + + if (ui__has_annotation()) { + err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); + if (err) + return err; + } + + hists__inc_nr_samples(&evsel->hists, he->filtered); + + return hist_entry__append_callchain(he, sample); +} + +const struct hist_iter_ops hist_iter_mem = { + .prepare_entry = iter_prepare_mem_entry, + .add_single_entry = iter_add_single_mem_entry, + .next_entry = iter_next_nop_entry, + .add_next_entry = iter_add_next_nop_entry, + .finish_entry = iter_finish_mem_entry, +}; + +const struct hist_iter_ops hist_iter_branch = { + .prepare_entry = iter_prepare_branch_entry, + .add_single_entry = iter_add_single_branch_entry, + .next_entry = iter_next_branch_entry, + .add_next_entry = iter_add_next_branch_entry, + .finish_entry = iter_finish_branch_entry, +}; + +const struct hist_iter_ops hist_iter_normal = { + .prepare_entry = iter_prepare_normal_entry, + .add_single_entry = iter_add_single_normal_entry, + .next_entry = iter_next_nop_entry, + .add_next_entry = iter_add_next_nop_entry, + .finish_entry = iter_finish_normal_entry, +}; + +int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, + struct perf_evsel *evsel, struct perf_sample *sample, + int max_stack_depth) +{ + int err, err2; + + err = sample__resolve_callchain(sample, &iter->parent, evsel, al, + max_stack_depth); + if (err) + return err; + + iter->evsel = evsel; + iter->sample = sample; + + err = iter->ops->prepare_entry(iter, al); + if (err) + goto out; + + err = iter->ops->add_single_entry(iter, al); + if (err) + goto out; + + while (iter->ops->next_entry(iter, al)) { + err = iter->ops->add_next_entry(iter, al); + if (err) + break; + } + +out: + err2 = iter->ops->finish_entry(iter, al); + if (!err) + err = err2; + + return err; +} + int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) { diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 03ae1dbb1b15..8894f184357c 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -96,12 +96,45 @@ struct hists { u16 col_len[HISTC_NR_COLS]; }; +struct hist_entry_iter; + +struct hist_iter_ops { + int (*prepare_entry)(struct hist_entry_iter *, struct addr_location *); + int (*add_single_entry)(struct hist_entry_iter *, struct addr_location *); + int (*next_entry)(struct hist_entry_iter *, struct addr_location *); + int (*add_next_entry)(struct hist_entry_iter *, struct addr_location *); + int (*finish_entry)(struct hist_entry_iter *, struct addr_location *); +}; + +struct hist_entry_iter { + int total; + int curr; + + bool hide_unresolved; + + struct perf_evsel *evsel; + struct perf_sample *sample; + struct hist_entry *he; + struct symbol *parent; + void *priv; + + const struct hist_iter_ops *ops; +}; + +extern const struct hist_iter_ops hist_iter_normal; +extern const struct hist_iter_ops hist_iter_branch; +extern const struct hist_iter_ops hist_iter_mem; + struct hist_entry *__hists__add_entry(struct hists *hists, struct addr_location *al, struct symbol *parent, struct branch_info *bi, struct mem_info *mi, u64 period, u64 weight, u64 transaction); +int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, + struct perf_evsel *evsel, struct perf_sample *sample, + int max_stack_depth); + int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right); int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right); int hist_entry__transaction_len(void); -- cgit v1.2.3 From a0b51af367a6831330564c96dc4cc1ac63413701 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 11 Sep 2012 13:34:27 +0900 Subject: perf hists: Check if accumulated when adding a hist entry To support callchain accumulation, @entry should be recognized if it's accumulated or not when add_hist_entry() called. The period of an accumulated entry should be added to ->stat_acc but not ->stat. Add @sample_self arg for that. Signed-off-by: Namhyung Kim Tested-by: Arun Sharma Tested-by: Rodrigo Campos Cc: Frederic Weisbecker Link: http://lkml.kernel.org/r/1401335910-16832-5-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa --- tools/perf/builtin-annotate.c | 3 ++- tools/perf/builtin-diff.c | 2 +- tools/perf/builtin-top.c | 2 +- tools/perf/tests/hists_link.c | 4 ++-- tools/perf/util/hist.c | 29 ++++++++++++++++++----------- tools/perf/util/hist.h | 3 ++- 6 files changed, 26 insertions(+), 17 deletions(-) (limited to 'tools/perf/util/hist.h') diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index bf52461a88bd..1ec429fef2be 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -65,7 +65,8 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel, return 0; } - he = __hists__add_entry(&evsel->hists, al, NULL, NULL, NULL, 1, 1, 0); + he = __hists__add_entry(&evsel->hists, al, NULL, NULL, NULL, 1, 1, 0, + true); if (he == NULL) return -ENOMEM; diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 8bff543acaab..9a5a035cb426 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -315,7 +315,7 @@ static int hists__add_entry(struct hists *hists, u64 weight, u64 transaction) { if (__hists__add_entry(hists, al, NULL, NULL, NULL, period, weight, - transaction) != NULL) + transaction, true) != NULL) return 0; return -ENOMEM; } diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 51309264d210..12e2e1227e47 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -247,7 +247,7 @@ static struct hist_entry *perf_evsel__add_hist_entry(struct perf_evsel *evsel, pthread_mutex_lock(&evsel->hists.lock); he = __hists__add_entry(&evsel->hists, al, NULL, NULL, NULL, sample->period, sample->weight, - sample->transaction); + sample->transaction, true); pthread_mutex_unlock(&evsel->hists.lock); if (he == NULL) return NULL; diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index 5ffa2c3eb77d..ca6693b37cd7 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -88,7 +88,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) goto out; he = __hists__add_entry(&evsel->hists, &al, NULL, - NULL, NULL, 1, 1, 0); + NULL, NULL, 1, 1, 0, true); if (he == NULL) goto out; @@ -112,7 +112,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) goto out; he = __hists__add_entry(&evsel->hists, &al, NULL, - NULL, NULL, 1, 1, 0); + NULL, NULL, 1, 1, 0, true); if (he == NULL) goto out; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index dfff2ee8effb..b9facf33b224 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -279,7 +279,8 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel) * histogram, sorted on item, collects periods */ -static struct hist_entry *hist_entry__new(struct hist_entry *template) +static struct hist_entry *hist_entry__new(struct hist_entry *template, + bool sample_self) { size_t callchain_size = 0; struct hist_entry *he; @@ -299,6 +300,8 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template) return NULL; } memcpy(he->stat_acc, &he->stat, sizeof(he->stat)); + if (!sample_self) + memset(&he->stat, 0, sizeof(he->stat)); } if (he->ms.map) @@ -351,7 +354,8 @@ static u8 symbol__parent_filter(const struct symbol *parent) static struct hist_entry *add_hist_entry(struct hists *hists, struct hist_entry *entry, - struct addr_location *al) + struct addr_location *al, + bool sample_self) { struct rb_node **p; struct rb_node *parent = NULL; @@ -375,7 +379,8 @@ static struct hist_entry *add_hist_entry(struct hists *hists, cmp = hist_entry__cmp(he, entry); if (!cmp) { - he_stat__add_period(&he->stat, period, weight); + if (sample_self) + he_stat__add_period(&he->stat, period, weight); if (symbol_conf.cumulate_callchain) he_stat__add_period(he->stat_acc, period, weight); @@ -405,14 +410,15 @@ static struct hist_entry *add_hist_entry(struct hists *hists, p = &(*p)->rb_right; } - he = hist_entry__new(entry); + he = hist_entry__new(entry, sample_self); if (!he) return NULL; rb_link_node(&he->rb_node_in, parent, p); rb_insert_color(&he->rb_node_in, hists->entries_in); out: - he_stat__add_cpumode_period(&he->stat, al->cpumode, period); + if (sample_self) + he_stat__add_cpumode_period(&he->stat, al->cpumode, period); if (symbol_conf.cumulate_callchain) he_stat__add_cpumode_period(he->stat_acc, al->cpumode, period); return he; @@ -423,7 +429,8 @@ struct hist_entry *__hists__add_entry(struct hists *hists, struct symbol *sym_parent, struct branch_info *bi, struct mem_info *mi, - u64 period, u64 weight, u64 transaction) + u64 period, u64 weight, u64 transaction, + bool sample_self) { struct hist_entry entry = { .thread = al->thread, @@ -448,7 +455,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists, .transaction = transaction, }; - return add_hist_entry(hists, &entry, al); + return add_hist_entry(hists, &entry, al, sample_self); } static int @@ -501,7 +508,7 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al * and the he_stat__add_period() function. */ he = __hists__add_entry(&iter->evsel->hists, al, iter->parent, NULL, mi, - cost, cost, 0); + cost, cost, 0, true); if (!he) return -ENOMEM; @@ -608,7 +615,7 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a * and not events sampled. Thus we use a pseudo period of 1. */ he = __hists__add_entry(&evsel->hists, al, iter->parent, &bi[i], NULL, - 1, 1, 0); + 1, 1, 0, true); if (he == NULL) return -ENOMEM; @@ -657,7 +664,7 @@ iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL, sample->period, sample->weight, - sample->transaction); + sample->transaction, true); if (he == NULL) return -ENOMEM; @@ -1161,7 +1168,7 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists, p = &(*p)->rb_right; } - he = hist_entry__new(pair); + he = hist_entry__new(pair, true); if (he) { memset(&he->stat, 0, sizeof(he->stat)); he->hists = hists; diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 8894f184357c..bedb24d3643c 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -130,7 +130,8 @@ struct hist_entry *__hists__add_entry(struct hists *hists, struct symbol *parent, struct branch_info *bi, struct mem_info *mi, u64 period, - u64 weight, u64 transaction); + u64 weight, u64 transaction, + bool sample_self); int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, struct perf_evsel *evsel, struct perf_sample *sample, int max_stack_depth); -- cgit v1.2.3 From 7a13aa28aa268359cee006059731f49bcd1f839e Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 11 Sep 2012 14:13:04 +0900 Subject: perf hists: Accumulate hist entry stat based on the callchain Call __hists__add_entry() for each callchain node to get an accumulated stat for an entry. Introduce new cumulative_iter ops to process them properly. Signed-off-by: Namhyung Kim Tested-by: Arun Sharma Tested-by: Rodrigo Campos Cc: Frederic Weisbecker Link: http://lkml.kernel.org/r/1401335910-16832-6-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa --- tools/perf/builtin-report.c | 2 + tools/perf/util/callchain.c | 3 +- tools/perf/util/hist.c | 96 +++++++++++++++++++++++++++++++++++++++++++++ tools/perf/util/hist.h | 1 + 4 files changed, 101 insertions(+), 1 deletion(-) (limited to 'tools/perf/util/hist.h') diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 3201bdfa8c3f..e8fa9fea341f 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -115,6 +115,8 @@ static int process_sample_event(struct perf_tool *tool, iter.ops = &hist_iter_branch; else if (rep->mem_mode) iter.ops = &hist_iter_mem; + else if (symbol_conf.cumulate_callchain) + iter.ops = &hist_iter_cumulative; else iter.ops = &hist_iter_normal; diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 9a42382b3921..2af69c47b725 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -616,7 +616,8 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent if (sample->callchain == NULL) return 0; - if (symbol_conf.use_callchain || sort__has_parent) { + if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain || + sort__has_parent) { return machine__resolve_callchain(al->machine, evsel, al->thread, sample, parent, al, max_stack); } diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index b9facf33b224..6079b5acfb6d 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -696,6 +696,94 @@ iter_finish_normal_entry(struct hist_entry_iter *iter, struct addr_location *al) return hist_entry__append_callchain(he, sample); } +static int +iter_prepare_cumulative_entry(struct hist_entry_iter *iter __maybe_unused, + struct addr_location *al __maybe_unused) +{ + callchain_cursor_commit(&callchain_cursor); + return 0; +} + +static int +iter_add_single_cumulative_entry(struct hist_entry_iter *iter, + struct addr_location *al) +{ + struct perf_evsel *evsel = iter->evsel; + struct perf_sample *sample = iter->sample; + struct hist_entry *he; + int err = 0; + + he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL, + sample->period, sample->weight, + sample->transaction, true); + if (he == NULL) + return -ENOMEM; + + iter->he = he; + + /* + * The iter->he will be over-written after ->add_next_entry() + * called so inc stats for the original entry now. + */ + if (ui__has_annotation()) + err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); + + hists__inc_nr_samples(&evsel->hists, he->filtered); + + return err; +} + +static int +iter_next_cumulative_entry(struct hist_entry_iter *iter, + struct addr_location *al) +{ + struct callchain_cursor_node *node; + + node = callchain_cursor_current(&callchain_cursor); + if (node == NULL) + return 0; + + al->map = node->map; + al->sym = node->sym; + if (node->map) + al->addr = node->map->map_ip(node->map, node->ip); + else + al->addr = node->ip; + + if (iter->hide_unresolved && al->sym == NULL) + return 0; + + callchain_cursor_advance(&callchain_cursor); + return 1; +} + +static int +iter_add_next_cumulative_entry(struct hist_entry_iter *iter, + struct addr_location *al) +{ + struct perf_evsel *evsel = iter->evsel; + struct perf_sample *sample = iter->sample; + struct hist_entry *he; + + he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL, + sample->period, sample->weight, + sample->transaction, false); + if (he == NULL) + return -ENOMEM; + + iter->he = he; + + return 0; +} + +static int +iter_finish_cumulative_entry(struct hist_entry_iter *iter, + struct addr_location *al __maybe_unused) +{ + iter->he = NULL; + return 0; +} + const struct hist_iter_ops hist_iter_mem = { .prepare_entry = iter_prepare_mem_entry, .add_single_entry = iter_add_single_mem_entry, @@ -720,6 +808,14 @@ const struct hist_iter_ops hist_iter_normal = { .finish_entry = iter_finish_normal_entry, }; +const struct hist_iter_ops hist_iter_cumulative = { + .prepare_entry = iter_prepare_cumulative_entry, + .add_single_entry = iter_add_single_cumulative_entry, + .next_entry = iter_next_cumulative_entry, + .add_next_entry = iter_add_next_cumulative_entry, + .finish_entry = iter_finish_cumulative_entry, +}; + int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, struct perf_evsel *evsel, struct perf_sample *sample, int max_stack_depth) diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index bedb24d3643c..78409f95d012 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -124,6 +124,7 @@ struct hist_entry_iter { extern const struct hist_iter_ops hist_iter_normal; extern const struct hist_iter_ops hist_iter_branch; extern const struct hist_iter_ops hist_iter_mem; +extern const struct hist_iter_ops hist_iter_cumulative; struct hist_entry *__hists__add_entry(struct hists *hists, struct addr_location *al, -- cgit v1.2.3 From 594dcbf3186e2e1e5c08fa21e8826b90d347f23f Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 30 Oct 2013 16:06:59 +0900 Subject: perf ui/hist: Add support to accumulated hist stat Print accumulated stat of a hist entry if requested. To do that, add new HPP_PERCENT_ACC_FNS macro and generate a perf_hpp_fmt using it. The __hpp__sort_acc() function sorts entries by accumulated period value. When accumulated periods of two entries are same (i.e. single path callchain) put the caller above since accumulation tends to put callers on higher position for obvious reason. Also add "overhead_children" output field to be selected by user. Signed-off-by: Namhyung Kim Tested-by: Arun Sharma Tested-by: Rodrigo Campos Cc: Frederic Weisbecker Link: http://lkml.kernel.org/r/1401335910-16832-11-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa --- tools/perf/ui/hist.c | 99 ++++++++++++++++++++++++++++++++++++++++++++++++++ tools/perf/util/hist.h | 4 ++ tools/perf/util/sort.c | 1 + 3 files changed, 104 insertions(+) (limited to 'tools/perf/util/hist.h') diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 4484f5bd1b14..0ce3e79b2ca7 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -104,6 +104,18 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, return ret; } +int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he, + hpp_field_fn get_field, const char *fmt, + hpp_snprint_fn print_fn, bool fmt_percent) +{ + if (!symbol_conf.cumulate_callchain) { + return snprintf(hpp->buf, hpp->size, "%*s", + fmt_percent ? 8 : 12, "N/A"); + } + + return __hpp__fmt(hpp, he, get_field, fmt, print_fn, fmt_percent); +} + static int field_cmp(u64 field_a, u64 field_b) { if (field_a > field_b) @@ -160,6 +172,24 @@ out: return ret; } +static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b, + hpp_field_fn get_field) +{ + s64 ret = 0; + + if (symbol_conf.cumulate_callchain) { + /* + * Put caller above callee when they have equal period. + */ + ret = field_cmp(get_field(a), get_field(b)); + if (ret) + return ret; + + ret = b->callchain->max_depth - a->callchain->max_depth; + } + return ret; +} + #define __HPP_HEADER_FN(_type, _str, _min_width, _unit_width) \ static int hpp__header_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ struct perf_hpp *hpp, \ @@ -242,6 +272,34 @@ static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b) \ return __hpp__sort(a, b, he_get_##_field); \ } +#define __HPP_COLOR_ACC_PERCENT_FN(_type, _field) \ +static u64 he_get_acc_##_field(struct hist_entry *he) \ +{ \ + return he->stat_acc->_field; \ +} \ + \ +static int hpp__color_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ + struct perf_hpp *hpp, struct hist_entry *he) \ +{ \ + return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, " %6.2f%%", \ + hpp_color_scnprintf, true); \ +} + +#define __HPP_ENTRY_ACC_PERCENT_FN(_type, _field) \ +static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused, \ + struct perf_hpp *hpp, struct hist_entry *he) \ +{ \ + const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%"; \ + return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, fmt, \ + hpp_entry_scnprintf, true); \ +} + +#define __HPP_SORT_ACC_FN(_type, _field) \ +static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b) \ +{ \ + return __hpp__sort_acc(a, b, he_get_acc_##_field); \ +} + #define __HPP_ENTRY_RAW_FN(_type, _field) \ static u64 he_get_raw_##_field(struct hist_entry *he) \ { \ @@ -270,18 +328,27 @@ __HPP_COLOR_PERCENT_FN(_type, _field) \ __HPP_ENTRY_PERCENT_FN(_type, _field) \ __HPP_SORT_FN(_type, _field) +#define HPP_PERCENT_ACC_FNS(_type, _str, _field, _min_width, _unit_width)\ +__HPP_HEADER_FN(_type, _str, _min_width, _unit_width) \ +__HPP_WIDTH_FN(_type, _min_width, _unit_width) \ +__HPP_COLOR_ACC_PERCENT_FN(_type, _field) \ +__HPP_ENTRY_ACC_PERCENT_FN(_type, _field) \ +__HPP_SORT_ACC_FN(_type, _field) + #define HPP_RAW_FNS(_type, _str, _field, _min_width, _unit_width) \ __HPP_HEADER_FN(_type, _str, _min_width, _unit_width) \ __HPP_WIDTH_FN(_type, _min_width, _unit_width) \ __HPP_ENTRY_RAW_FN(_type, _field) \ __HPP_SORT_RAW_FN(_type, _field) +__HPP_HEADER_FN(overhead_self, "Self", 8, 8) HPP_PERCENT_FNS(overhead, "Overhead", period, 8, 8) HPP_PERCENT_FNS(overhead_sys, "sys", period_sys, 8, 8) HPP_PERCENT_FNS(overhead_us, "usr", period_us, 8, 8) HPP_PERCENT_FNS(overhead_guest_sys, "guest sys", period_guest_sys, 9, 8) HPP_PERCENT_FNS(overhead_guest_us, "guest usr", period_guest_us, 9, 8) +HPP_PERCENT_ACC_FNS(overhead_acc, "Children", period, 8, 8) HPP_RAW_FNS(samples, "Samples", nr_events, 12, 12) HPP_RAW_FNS(period, "Period", period, 12, 12) @@ -303,6 +370,17 @@ static int64_t hpp__nop_cmp(struct hist_entry *a __maybe_unused, .sort = hpp__sort_ ## _name, \ } +#define HPP__COLOR_ACC_PRINT_FNS(_name) \ + { \ + .header = hpp__header_ ## _name, \ + .width = hpp__width_ ## _name, \ + .color = hpp__color_ ## _name, \ + .entry = hpp__entry_ ## _name, \ + .cmp = hpp__nop_cmp, \ + .collapse = hpp__nop_cmp, \ + .sort = hpp__sort_ ## _name, \ + } + #define HPP__PRINT_FNS(_name) \ { \ .header = hpp__header_ ## _name, \ @@ -319,6 +397,7 @@ struct perf_hpp_fmt perf_hpp__format[] = { HPP__COLOR_PRINT_FNS(overhead_us), HPP__COLOR_PRINT_FNS(overhead_guest_sys), HPP__COLOR_PRINT_FNS(overhead_guest_us), + HPP__COLOR_ACC_PRINT_FNS(overhead_acc), HPP__PRINT_FNS(samples), HPP__PRINT_FNS(period) }; @@ -328,16 +407,23 @@ LIST_HEAD(perf_hpp__sort_list); #undef HPP__COLOR_PRINT_FNS +#undef HPP__COLOR_ACC_PRINT_FNS #undef HPP__PRINT_FNS #undef HPP_PERCENT_FNS +#undef HPP_PERCENT_ACC_FNS #undef HPP_RAW_FNS #undef __HPP_HEADER_FN #undef __HPP_WIDTH_FN #undef __HPP_COLOR_PERCENT_FN #undef __HPP_ENTRY_PERCENT_FN +#undef __HPP_COLOR_ACC_PERCENT_FN +#undef __HPP_ENTRY_ACC_PERCENT_FN #undef __HPP_ENTRY_RAW_FN +#undef __HPP_SORT_FN +#undef __HPP_SORT_ACC_FN +#undef __HPP_SORT_RAW_FN void perf_hpp__init(void) @@ -361,6 +447,13 @@ void perf_hpp__init(void) if (field_order) return; + if (symbol_conf.cumulate_callchain) { + perf_hpp__column_enable(PERF_HPP__OVERHEAD_ACC); + + perf_hpp__format[PERF_HPP__OVERHEAD].header = + hpp__header_overhead_self; + } + perf_hpp__column_enable(PERF_HPP__OVERHEAD); if (symbol_conf.show_cpu_utilization) { @@ -383,6 +476,12 @@ void perf_hpp__init(void) list = &perf_hpp__format[PERF_HPP__OVERHEAD].sort_list; if (list_empty(list)) list_add(list, &perf_hpp__sort_list); + + if (symbol_conf.cumulate_callchain) { + list = &perf_hpp__format[PERF_HPP__OVERHEAD_ACC].sort_list; + if (list_empty(list)) + list_add(list, &perf_hpp__sort_list); + } } void perf_hpp__column_register(struct perf_hpp_fmt *format) diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 78409f95d012..efd73e489027 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -228,6 +228,7 @@ enum { PERF_HPP__OVERHEAD_US, PERF_HPP__OVERHEAD_GUEST_SYS, PERF_HPP__OVERHEAD_GUEST_US, + PERF_HPP__OVERHEAD_ACC, PERF_HPP__SAMPLES, PERF_HPP__PERIOD, @@ -254,6 +255,9 @@ typedef int (*hpp_snprint_fn)(struct perf_hpp *hpp, const char *fmt, ...); int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, hpp_field_fn get_field, const char *fmt, hpp_snprint_fn print_fn, bool fmt_percent); +int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he, + hpp_field_fn get_field, const char *fmt, + hpp_snprint_fn print_fn, bool fmt_percent); static inline void advance_hpp(struct perf_hpp *hpp, int inc) { diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 901b9bece2ee..9da8931d2394 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1061,6 +1061,7 @@ static struct hpp_dimension hpp_sort_dimensions[] = { DIM(PERF_HPP__OVERHEAD_US, "overhead_us"), DIM(PERF_HPP__OVERHEAD_GUEST_SYS, "overhead_guest_sys"), DIM(PERF_HPP__OVERHEAD_GUEST_US, "overhead_guest_us"), + DIM(PERF_HPP__OVERHEAD_ACC, "overhead_children"), DIM(PERF_HPP__SAMPLES, "sample"), DIM(PERF_HPP__PERIOD, "period"), }; -- cgit v1.2.3 From 77284de326e6d8c3b8e866cda5b415c86b522e61 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 16 Dec 2013 16:55:13 +0900 Subject: perf tools: Add more hpp helper functions Sometimes it needs to disable some columns at runtime. Add help functions to support that. Signed-off-by: Namhyung Kim Tested-by: Arun Sharma Tested-by: Rodrigo Campos Cc: Frederic Weisbecker Link: http://lkml.kernel.org/r/1401335910-16832-15-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa --- tools/perf/ui/hist.c | 17 +++++++++++++++++ tools/perf/util/hist.h | 4 ++++ 2 files changed, 21 insertions(+) (limited to 'tools/perf/util/hist.h') diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 0ce3e79b2ca7..8ca638754acc 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -489,6 +489,11 @@ void perf_hpp__column_register(struct perf_hpp_fmt *format) list_add_tail(&format->list, &perf_hpp__list); } +void perf_hpp__column_unregister(struct perf_hpp_fmt *format) +{ + list_del(&format->list); +} + void perf_hpp__register_sort_field(struct perf_hpp_fmt *format) { list_add_tail(&format->sort_list, &perf_hpp__sort_list); @@ -500,6 +505,18 @@ void perf_hpp__column_enable(unsigned col) perf_hpp__column_register(&perf_hpp__format[col]); } +void perf_hpp__column_disable(unsigned col) +{ + BUG_ON(col >= PERF_HPP__MAX_INDEX); + perf_hpp__column_unregister(&perf_hpp__format[col]); +} + +void perf_hpp__cancel_cumulate(void) +{ + perf_hpp__column_disable(PERF_HPP__OVERHEAD_ACC); + perf_hpp__format[PERF_HPP__OVERHEAD].header = hpp__header_overhead; +} + void perf_hpp__setup_output_field(void) { struct perf_hpp_fmt *fmt; diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index efd73e489027..99ad3cb433fb 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -237,7 +237,11 @@ enum { void perf_hpp__init(void); void perf_hpp__column_register(struct perf_hpp_fmt *format); +void perf_hpp__column_unregister(struct perf_hpp_fmt *format); void perf_hpp__column_enable(unsigned col); +void perf_hpp__column_disable(unsigned col); +void perf_hpp__cancel_cumulate(void); + void perf_hpp__register_sort_field(struct perf_hpp_fmt *format); void perf_hpp__setup_output_field(void); void perf_hpp__reset_output_field(void); -- cgit v1.2.3 From 9d3c02d7188866299eebe3c4a652c08140a71f40 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 7 Jan 2014 17:02:25 +0900 Subject: perf tools: Add callback function to hist_entry_iter The new ->add_entry_cb() will be called after an entry was added to the histogram. It's used for code sharing between perf report and perf top. Note that ops->add_*_entry() should set iter->he properly in order to call the ->add_entry_cb. Also pass @arg to the callback function. It'll be used by perf top later. Signed-off-by: Namhyung Kim Tested-by: Arun Sharma Tested-by: Rodrigo Campos Cc: Frederic Weisbecker Link: http://lkml.kernel.org/r/87k393g999.fsf@sejong.aot.lge.com Signed-off-by: Jiri Olsa --- tools/perf/builtin-report.c | 61 ++++++++++++++++++++++++++++++++----- tools/perf/tests/hists_filter.c | 2 +- tools/perf/tests/hists_output.c | 2 +- tools/perf/util/hist.c | 67 +++++++++++++++-------------------------- tools/perf/util/hist.h | 5 ++- 5 files changed, 84 insertions(+), 53 deletions(-) (limited to 'tools/perf/util/hist.h') diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 6cac509212ee..21d830bafff3 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -80,14 +80,59 @@ static int report__config(const char *var, const char *value, void *cb) return perf_default_config(var, value, cb); } -static void report__inc_stats(struct report *rep, - struct hist_entry *he __maybe_unused) +static void report__inc_stats(struct report *rep, struct hist_entry *he) { /* - * We cannot access @he at this time. Just assume it's a new entry. - * It'll be fixed once we have a callback mechanism in hist_iter. + * The @he is either of a newly created one or an existing one + * merging current sample. We only want to count a new one so + * checking ->nr_events being 1. */ - rep->nr_entries++; + if (he->stat.nr_events == 1) + rep->nr_entries++; +} + +static int hist_iter__report_callback(struct hist_entry_iter *iter, + struct addr_location *al, bool single, + void *arg) +{ + int err = 0; + struct report *rep = arg; + struct hist_entry *he = iter->he; + struct perf_evsel *evsel = iter->evsel; + struct mem_info *mi; + struct branch_info *bi; + + report__inc_stats(rep, he); + + if (!ui__has_annotation()) + return 0; + + if (sort__mode == SORT_MODE__BRANCH) { + bi = he->branch_info; + err = addr_map_symbol__inc_samples(&bi->from, evsel->idx); + if (err) + goto out; + + err = addr_map_symbol__inc_samples(&bi->to, evsel->idx); + + } else if (rep->mem_mode) { + mi = he->mem_info; + err = addr_map_symbol__inc_samples(&mi->daddr, evsel->idx); + if (err) + goto out; + + err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); + + } else if (symbol_conf.cumulate_callchain) { + if (single) + err = hist_entry__inc_addr_samples(he, evsel->idx, + al->addr); + } else { + err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); + } + +out: + return err; } static int process_sample_event(struct perf_tool *tool, @@ -100,6 +145,7 @@ static int process_sample_event(struct perf_tool *tool, struct addr_location al; struct hist_entry_iter iter = { .hide_unresolved = rep->hide_unresolved, + .add_entry_cb = hist_iter__report_callback, }; int ret; @@ -127,9 +173,8 @@ static int process_sample_event(struct perf_tool *tool, if (al.map != NULL) al.map->dso->hit = 1; - report__inc_stats(rep, NULL); - - ret = hist_entry_iter__add(&iter, &al, evsel, sample, rep->max_stack); + ret = hist_entry_iter__add(&iter, &al, evsel, sample, rep->max_stack, + rep); if (ret < 0) pr_debug("problem adding hist entry, skipping event\n"); diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index 76b02e1de701..3539403bbad4 100644 --- a/tools/perf/tests/hists_filter.c +++ b/tools/perf/tests/hists_filter.c @@ -82,7 +82,7 @@ static int add_hist_entries(struct perf_evlist *evlist, goto out; if (hist_entry_iter__add(&iter, &al, evsel, &sample, - PERF_MAX_STACK_DEPTH) < 0) + PERF_MAX_STACK_DEPTH, NULL) < 0) goto out; fake_samples[i].thread = al.thread; diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index 1308f88a9169..d40461ecd210 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -71,7 +71,7 @@ static int add_hist_entries(struct hists *hists, struct machine *machine) goto out; if (hist_entry_iter__add(&iter, &al, evsel, &sample, - PERF_MAX_STACK_DEPTH) < 0) + PERF_MAX_STACK_DEPTH, NULL) < 0) goto out; fake_samples[i].thread = al.thread; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index c6f5f5251aad..5a0a4b2cadc4 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -517,27 +517,16 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al } static int -iter_finish_mem_entry(struct hist_entry_iter *iter, struct addr_location *al) +iter_finish_mem_entry(struct hist_entry_iter *iter, + struct addr_location *al __maybe_unused) { struct perf_evsel *evsel = iter->evsel; struct hist_entry *he = iter->he; - struct mem_info *mx; int err = -EINVAL; if (he == NULL) goto out; - if (ui__has_annotation()) { - err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); - if (err) - goto out; - - mx = he->mem_info; - err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx); - if (err) - goto out; - } - hists__inc_nr_samples(&evsel->hists, he->filtered); err = hist_entry__append_callchain(he, iter->sample); @@ -575,6 +564,9 @@ static int iter_add_single_branch_entry(struct hist_entry_iter *iter __maybe_unused, struct addr_location *al __maybe_unused) { + /* to avoid calling callback function */ + iter->he = NULL; + return 0; } @@ -599,7 +591,7 @@ iter_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al) static int iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al) { - struct branch_info *bi, *bx; + struct branch_info *bi; struct perf_evsel *evsel = iter->evsel; struct hist_entry *he = NULL; int i = iter->curr; @@ -619,17 +611,6 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a if (he == NULL) return -ENOMEM; - if (ui__has_annotation()) { - bx = he->branch_info; - err = addr_map_symbol__inc_samples(&bx->from, evsel->idx); - if (err) - goto out; - - err = addr_map_symbol__inc_samples(&bx->to, evsel->idx); - if (err) - goto out; - } - hists__inc_nr_samples(&evsel->hists, he->filtered); out: @@ -673,9 +654,9 @@ iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location } static int -iter_finish_normal_entry(struct hist_entry_iter *iter, struct addr_location *al) +iter_finish_normal_entry(struct hist_entry_iter *iter, + struct addr_location *al __maybe_unused) { - int err; struct hist_entry *he = iter->he; struct perf_evsel *evsel = iter->evsel; struct perf_sample *sample = iter->sample; @@ -685,12 +666,6 @@ iter_finish_normal_entry(struct hist_entry_iter *iter, struct addr_location *al) iter->he = NULL; - if (ui__has_annotation()) { - err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); - if (err) - return err; - } - hists__inc_nr_samples(&evsel->hists, he->filtered); return hist_entry__append_callchain(he, sample); @@ -746,13 +721,6 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter, */ callchain_cursor_commit(&callchain_cursor); - /* - * The iter->he will be over-written after ->add_next_entry() - * called so inc stats for the original entry now. - */ - if (ui__has_annotation()) - err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); - hists__inc_nr_samples(&evsel->hists, he->filtered); return err; @@ -802,8 +770,11 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter, * It's possible that it has cycles or recursive calls. */ for (i = 0; i < iter->curr; i++) { - if (hist_entry__cmp(he_cache[i], &he_tmp) == 0) + if (hist_entry__cmp(he_cache[i], &he_tmp) == 0) { + /* to avoid calling callback function */ + iter->he = NULL; return 0; + } } he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL, @@ -863,7 +834,7 @@ const struct hist_iter_ops hist_iter_cumulative = { int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, struct perf_evsel *evsel, struct perf_sample *sample, - int max_stack_depth) + int max_stack_depth, void *arg) { int err, err2; @@ -883,10 +854,22 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, if (err) goto out; + if (iter->he && iter->add_entry_cb) { + err = iter->add_entry_cb(iter, al, true, arg); + if (err) + goto out; + } + while (iter->ops->next_entry(iter, al)) { err = iter->ops->add_next_entry(iter, al); if (err) break; + + if (iter->he && iter->add_entry_cb) { + err = iter->add_entry_cb(iter, al, false, arg); + if (err) + goto out; + } } out: diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 99ad3cb433fb..82b28ff98062 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -119,6 +119,9 @@ struct hist_entry_iter { void *priv; const struct hist_iter_ops *ops; + /* user-defined callback function (optional) */ + int (*add_entry_cb)(struct hist_entry_iter *iter, + struct addr_location *al, bool single, void *arg); }; extern const struct hist_iter_ops hist_iter_normal; @@ -135,7 +138,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists, bool sample_self); int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, struct perf_evsel *evsel, struct perf_sample *sample, - int max_stack_depth); + int max_stack_depth, void *arg); int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right); int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right); -- cgit v1.2.3 From f29984226978313039d7dfe9b45eaa55a3aad03d Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 23 May 2014 17:15:47 +0200 Subject: perf tools: Move elide bool into perf_hpp_fmt struct After output/sort fields refactoring, it's expensive to check the elide bool in its current location inside the 'struct sort_entry'. The perf_hpp__should_skip function gets highly noticable in workloads with high number of output/sort fields, like for: $ perf report -i perf-test.data -F overhead,sample,period,comm,pid,dso,symbol,cpu --stdio Performance report: 9.70% perf [.] perf_hpp__should_skip Moving the elide bool into the 'struct perf_hpp_fmt', which makes the perf_hpp__should_skip just single struct read. Got speedup of around 22% for my test perf.data workload. The change should not harm any other workload types. Performance counter stats for (10 runs): before: 358,319,732,626 cycles ( +- 0.55% ) 467,129,581,515 instructions # 1.30 insns per cycle ( +- 0.00% ) 150.943975206 seconds time elapsed ( +- 0.62% ) now: 278,785,972,990 cycles ( +- 0.12% ) 370,146,797,640 instructions # 1.33 insns per cycle ( +- 0.00% ) 116.416670507 seconds time elapsed ( +- 0.31% ) Acked-by: Namhyung Kim Cc: Arnaldo Carvalho de Melo Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/20140601142622.GA9131@krava.brq.redhat.com Signed-off-by: Jiri Olsa --- tools/perf/ui/browsers/hists.c | 8 ++-- tools/perf/util/hist.h | 8 +++- tools/perf/util/sort.c | 90 ++++++++++++++++++++++++++---------------- tools/perf/util/sort.h | 2 +- 4 files changed, 68 insertions(+), 40 deletions(-) (limited to 'tools/perf/util/hist.h') diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 5905acde5f1d..52c03fbbba17 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -1706,14 +1706,14 @@ zoom_dso: zoom_out_dso: ui_helpline__pop(); browser->hists->dso_filter = NULL; - sort_dso.elide = false; + perf_hpp__set_elide(HISTC_DSO, false); } else { if (dso == NULL) continue; ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s DSO\"", dso->kernel ? "the Kernel" : dso->short_name); browser->hists->dso_filter = dso; - sort_dso.elide = true; + perf_hpp__set_elide(HISTC_DSO, true); pstack__push(fstack, &browser->hists->dso_filter); } hists__filter_by_dso(hists); @@ -1725,13 +1725,13 @@ zoom_thread: zoom_out_thread: ui_helpline__pop(); browser->hists->thread_filter = NULL; - sort_thread.elide = false; + perf_hpp__set_elide(HISTC_THREAD, false); } else { ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"", thread->comm_set ? thread__comm_str(thread) : "", thread->tid); browser->hists->thread_filter = thread; - sort_thread.elide = true; + perf_hpp__set_elide(HISTC_THREAD, false); pstack__push(fstack, &browser->hists->thread_filter); } hists__filter_by_thread(hists); diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 82b28ff98062..d2bf03575d5f 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -205,6 +205,7 @@ struct perf_hpp_fmt { struct list_head list; struct list_head sort_list; + bool elide; }; extern struct list_head perf_hpp__list; @@ -252,7 +253,12 @@ void perf_hpp__append_sort_keys(void); bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format); bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b); -bool perf_hpp__should_skip(struct perf_hpp_fmt *format); + +static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format) +{ + return format->elide; +} + void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists); typedef u64 (*hpp_field_fn)(struct hist_entry *he); diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 2aba620a86f6..45512baaab67 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1157,6 +1157,7 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd) INIT_LIST_HEAD(&hse->hpp.list); INIT_LIST_HEAD(&hse->hpp.sort_list); + hse->hpp.elide = false; return hse; } @@ -1364,27 +1365,64 @@ static int __setup_sorting(void) return ret; } -bool perf_hpp__should_skip(struct perf_hpp_fmt *format) +void perf_hpp__set_elide(int idx, bool elide) { - if (perf_hpp__is_sort_entry(format)) { - struct hpp_sort_entry *hse; + struct perf_hpp_fmt *fmt; + struct hpp_sort_entry *hse; - hse = container_of(format, struct hpp_sort_entry, hpp); - return hse->se->elide; + perf_hpp__for_each_format(fmt) { + if (!perf_hpp__is_sort_entry(fmt)) + continue; + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + if (hse->se->se_width_idx == idx) { + fmt->elide = elide; + break; + } } - return false; } -static void sort_entry__setup_elide(struct sort_entry *se, - struct strlist *list, - const char *list_name, FILE *fp) +static bool __get_elide(struct strlist *list, const char *list_name, FILE *fp) { if (list && strlist__nr_entries(list) == 1) { if (fp != NULL) fprintf(fp, "# %s: %s\n", list_name, strlist__entry(list, 0)->s); - se->elide = true; + return true; + } + return false; +} + +static bool get_elide(int idx, FILE *output) +{ + switch (idx) { + case HISTC_SYMBOL: + return __get_elide(symbol_conf.sym_list, "symbol", output); + case HISTC_DSO: + return __get_elide(symbol_conf.dso_list, "dso", output); + case HISTC_COMM: + return __get_elide(symbol_conf.comm_list, "comm", output); + default: + break; } + + if (sort__mode != SORT_MODE__BRANCH) + return false; + + switch (idx) { + case HISTC_SYMBOL_FROM: + return __get_elide(symbol_conf.sym_from_list, "sym_from", output); + case HISTC_SYMBOL_TO: + return __get_elide(symbol_conf.sym_to_list, "sym_to", output); + case HISTC_DSO_FROM: + return __get_elide(symbol_conf.dso_from_list, "dso_from", output); + case HISTC_DSO_TO: + return __get_elide(symbol_conf.dso_to_list, "dso_to", output); + default: + break; + } + + return false; } void sort__setup_elide(FILE *output) @@ -1392,26 +1430,12 @@ void sort__setup_elide(FILE *output) struct perf_hpp_fmt *fmt; struct hpp_sort_entry *hse; - sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, - "dso", output); - sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, - "comm", output); - sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, - "symbol", output); - - if (sort__mode == SORT_MODE__BRANCH) { - sort_entry__setup_elide(&sort_dso_from, - symbol_conf.dso_from_list, - "dso_from", output); - sort_entry__setup_elide(&sort_dso_to, - symbol_conf.dso_to_list, - "dso_to", output); - sort_entry__setup_elide(&sort_sym_from, - symbol_conf.sym_from_list, - "sym_from", output); - sort_entry__setup_elide(&sort_sym_to, - symbol_conf.sym_to_list, - "sym_to", output); + perf_hpp__for_each_format(fmt) { + if (!perf_hpp__is_sort_entry(fmt)) + continue; + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + fmt->elide = get_elide(hse->se->se_width_idx, output); } /* @@ -1422,8 +1446,7 @@ void sort__setup_elide(FILE *output) if (!perf_hpp__is_sort_entry(fmt)) continue; - hse = container_of(fmt, struct hpp_sort_entry, hpp); - if (!hse->se->elide) + if (!fmt->elide) return; } @@ -1431,8 +1454,7 @@ void sort__setup_elide(FILE *output) if (!perf_hpp__is_sort_entry(fmt)) continue; - hse = container_of(fmt, struct hpp_sort_entry, hpp); - hse->se->elide = false; + fmt->elide = false; } } diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 426b873e16ff..5bf0098d6b06 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -202,7 +202,6 @@ struct sort_entry { int (*se_snprintf)(struct hist_entry *he, char *bf, size_t size, unsigned int width); u8 se_width_idx; - bool elide; }; extern struct sort_entry sort_thread; @@ -213,6 +212,7 @@ int setup_output_field(void); void reset_output_field(void); extern int sort_dimension__add(const char *); void sort__setup_elide(FILE *fp); +void perf_hpp__set_elide(int idx, bool elide); int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset); -- cgit v1.2.3