From c05556421742eb47f80301767653a4bcb19de9de Mon Sep 17 00:00:00 2001 From: Ian Munsie Date: Tue, 13 Apr 2010 18:37:33 +1000 Subject: perf: Fix endianness argument compatibility with OPT_BOOLEAN() and introduce OPT_INCR() Parsing an option from the command line with OPT_BOOLEAN on a bool data type would not work on a big-endian machine due to the manner in which the boolean was being cast into an int and incremented. For example, running 'perf probe --list' on a PowerPC machine would fail to properly set the list_events bool and would therefore print out the usage information and terminate. This patch makes OPT_BOOLEAN work as expected with a bool datatype. For cases where the original OPT_BOOLEAN was intentionally being used to increment an int each time it was passed in on the command line, this patch introduces OPT_INCR with the old behaviour of OPT_BOOLEAN (the verbose variable is currently the only such example of this). I have reviewed every use of OPT_BOOLEAN to verify that a true C99 bool was passed. Where integers were used, I verified that they were only being used for boolean logic and changed them to bools to ensure that they would not be mistakenly used as ints. The major exception was the verbose variable which now uses OPT_INCR instead of OPT_BOOLEAN. Signed-off-by: Ian Munsie Acked-by: David S. Miller Cc: # NOTE: wont apply to .3[34].x cleanly, please backport Cc: Git development list Cc: Ian Munsie Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: KOSAKI Motohiro Cc: Hitoshi Mitake Cc: Rusty Russell Cc: Frederic Weisbecker Cc: Eric B Munson Cc: Valdis.Kletnieks@vt.edu Cc: WANG Cong Cc: Thiago Farina Cc: Masami Hiramatsu Cc: Xiao Guangrong Cc: Jaswinder Singh Rajput Cc: Arjan van de Ven Cc: OGAWA Hirofumi Cc: Mike Galbraith Cc: Tom Zanussi Cc: Anton Blanchard Cc: John Kacur Cc: Li Zefan Cc: Steven Rostedt LKML-Reference: <1271147857-11604-1-git-send-email-imunsie@au.ibm.com> Signed-off-by: Ingo Molnar --- tools/perf/builtin-diff.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools/perf/builtin-diff.c') diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 1ea15d8aeed1..3a1d94d75dce 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -19,7 +19,7 @@ static char const *input_old = "perf.data.old", *input_new = "perf.data"; static char diff__default_sort_order[] = "dso,symbol"; -static int force; +static bool force; static bool show_displacement; static int perf_session__add_hist_entry(struct perf_session *self, @@ -188,7 +188,7 @@ static const char * const diff_usage[] = { }; static const struct option options[] = { - OPT_BOOLEAN('v', "verbose", &verbose, + OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), OPT_BOOLEAN('m', "displacement", &show_displacement, "Show position displacement relative to baseline"), -- cgit v1.2.3 From a1645ce12adb6c9cc9e19d7695466204e3f017fe Mon Sep 17 00:00:00 2001 From: "Zhang, Yanmin" Date: Mon, 19 Apr 2010 13:32:50 +0800 Subject: perf: 'perf kvm' tool for monitoring guest performance from host Here is the patch of userspace perf tool. Signed-off-by: Zhang Yanmin Signed-off-by: Avi Kivity --- tools/perf/builtin-diff.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'tools/perf/builtin-diff.c') diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 3a1d94d75dce..207e860591e2 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -33,7 +33,7 @@ static int perf_session__add_hist_entry(struct perf_session *self, return -ENOMEM; if (hit) - he->count += count; + __perf_session__add_count(he, al, count); return 0; } @@ -225,6 +225,10 @@ int cmd_diff(int argc, const char **argv, const char *prefix __used) input_new = argv[1]; } else input_new = argv[0]; + } else if (symbol_conf.default_guest_vmlinux_name || + symbol_conf.default_guest_kallsyms) { + input_old = "perf.data.host"; + input_new = "perf.data.guest"; } symbol_conf.exclude_other = false; -- cgit v1.2.3 From 454c407ec17a0c63e4023ac0877d687945a7df4a Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Sat, 1 May 2010 01:41:20 -0500 Subject: perf: add perf-inject builtin MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, perf 'live mode' writes build-ids at the end of the session, which isn't actually useful for processing live mode events. What would be better would be to have the build-ids sent before any of the samples that reference them, which can be done by processing the event stream and retrieving the build-ids on the first hit. Doing that in perf-record itself, however, is off-limits. This patch introduces perf-inject, which does the same job while leaving perf-record untouched. Normal mode perf still records the build-ids at the end of the session as it should, but for live mode, perf-inject can be injected in between the record and report steps e.g.: perf record -o - ./hackbench 10 | perf inject -v -b | perf report -v -i - perf-inject reads a perf-record event stream and repipes it to stdout. At any point the processing code can inject other events into the event stream - in this case build-ids (-b option) are read and injected as needed into the event stream. Build-ids are just the first user of perf-inject - potentially anything that needs userspace processing to augment the trace stream with additional information could make use of this facility. Cc: Ingo Molnar Cc: Steven Rostedt Cc: Frédéric Weisbecker LKML-Reference: <1272696080-16435-3-git-send-email-tzanussi@gmail.com> Signed-off-by: Tom Zanussi Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-diff.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools/perf/builtin-diff.c') diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 207e860591e2..4cce68f23686 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -156,8 +156,8 @@ static int __cmd_diff(void) int ret, i; struct perf_session *session[2]; - session[0] = perf_session__new(input_old, O_RDONLY, force); - session[1] = perf_session__new(input_new, O_RDONLY, force); + session[0] = perf_session__new(input_old, O_RDONLY, force, false); + session[1] = perf_session__new(input_new, O_RDONLY, force, false); if (session[0] == NULL || session[1] == NULL) return -ENOMEM; -- cgit v1.2.3 From 28e2a106d16046ca792722795f809e3f80a5af80 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sun, 9 May 2010 13:02:23 -0300 Subject: perf hist: Simplify the insertion of new hist_entry instances MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit And with that fix at least one bug: The first hit for an entry, the one that calls malloc to create a new instance in __perf_session__add_hist_entry, wasn't adding the count to the per cpumode (PERF_RECORD_MISC_USER, etc) total variable. Cc: Frédéric Weisbecker Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Tom Zanussi LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-diff.c | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) (limited to 'tools/perf/builtin-diff.c') diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 4cce68f23686..613a5c4f6d83 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -25,17 +25,9 @@ static bool show_displacement; static int perf_session__add_hist_entry(struct perf_session *self, struct addr_location *al, u64 count) { - bool hit; - struct hist_entry *he = __perf_session__add_hist_entry(&self->hists, - al, NULL, - count, &hit); - if (he == NULL) - return -ENOMEM; - - if (hit) - __perf_session__add_count(he, al, count); - - return 0; + if (__perf_session__add_hist_entry(&self->hists, al, NULL, count) != NULL) + return 0; + return -ENOMEM; } static int diff__process_sample_event(event_t *event, struct perf_session *session) -- cgit v1.2.3 From 1c02c4d2e92f2097f1bba63ec71560b0e05a7f36 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 10 May 2010 13:04:11 -0300 Subject: perf hist: Introduce hists class and move lots of methods to it MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In cbbc79a we introduced support for multiple events by introducing a new "event_stat_id" struct and then made several perf_session methods receive a point to it instead of a pointer to perf_session, and kept the event_stats and hists rb_tree in perf_session. While working on the new newt based browser, I realised that it would be better to introduce a new class, "hists" (short for "histograms"), renaming the "event_stat_id" struct and the perf_session methods that were really "hists" methods, as they manipulate only struct hists members, not touching anything in the other perf_session members. Other optimizations, such as calculating the maximum lenght of a symbol name present in an hists instance will be possible as we add them, avoiding a re-traversal just for finding that information. The rationale for the name "hists" to replace "event_stat_id" is that we may have multiple sets of hists for the same event_stat id, as, for instance, the 'perf diff' tool has, so event stat id is not what characterizes what this struct and the functions that manipulate it do. Cc: Eric B Munson Cc: Frédéric Weisbecker Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Tom Zanussi LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-diff.c | 50 ++++++++++++++++++++++------------------------- 1 file changed, 23 insertions(+), 27 deletions(-) (limited to 'tools/perf/builtin-diff.c') diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 613a5c4f6d83..3a95a0260a5b 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -22,10 +22,10 @@ static char diff__default_sort_order[] = "dso,symbol"; static bool force; static bool show_displacement; -static int perf_session__add_hist_entry(struct perf_session *self, - struct addr_location *al, u64 count) +static int hists__add_entry(struct hists *self, + struct addr_location *al, u64 count) { - if (__perf_session__add_hist_entry(&self->hists, al, NULL, count) != NULL) + if (__hists__add_entry(self, al, NULL, count) != NULL) return 0; return -ENOMEM; } @@ -49,12 +49,12 @@ static int diff__process_sample_event(event_t *event, struct perf_session *sessi event__parse_sample(event, session->sample_type, &data); - if (perf_session__add_hist_entry(session, &al, data.period)) { + if (hists__add_entry(&session->hists, &al, data.period)) { pr_warning("problem incrementing symbol count, skipping event\n"); return -1; } - session->events_stats.total += data.period; + session->hists.stats.total += data.period; return 0; } @@ -87,35 +87,34 @@ static void perf_session__insert_hist_entry_by_name(struct rb_root *root, rb_insert_color(&he->rb_node, root); } -static void perf_session__resort_hist_entries(struct perf_session *self) +static void hists__resort_entries(struct hists *self) { unsigned long position = 1; struct rb_root tmp = RB_ROOT; - struct rb_node *next = rb_first(&self->hists); + struct rb_node *next = rb_first(&self->entries); while (next != NULL) { struct hist_entry *n = rb_entry(next, struct hist_entry, rb_node); next = rb_next(&n->rb_node); - rb_erase(&n->rb_node, &self->hists); + rb_erase(&n->rb_node, &self->entries); n->position = position++; perf_session__insert_hist_entry_by_name(&tmp, n); } - self->hists = tmp; + self->entries = tmp; } -static void perf_session__set_hist_entries_positions(struct perf_session *self) +static void hists__set_positions(struct hists *self) { - perf_session__output_resort(&self->hists, self->events_stats.total); - perf_session__resort_hist_entries(self); + hists__output_resort(self); + hists__resort_entries(self); } -static struct hist_entry * -perf_session__find_hist_entry(struct perf_session *self, - struct hist_entry *he) +static struct hist_entry *hists__find_entry(struct hists *self, + struct hist_entry *he) { - struct rb_node *n = self->hists.rb_node; + struct rb_node *n = self->entries.rb_node; while (n) { struct hist_entry *iter = rb_entry(n, struct hist_entry, rb_node); @@ -132,14 +131,13 @@ perf_session__find_hist_entry(struct perf_session *self, return NULL; } -static void perf_session__match_hists(struct perf_session *old_session, - struct perf_session *new_session) +static void hists__match(struct hists *older, struct hists *newer) { struct rb_node *nd; - for (nd = rb_first(&new_session->hists); nd; nd = rb_next(nd)) { + for (nd = rb_first(&newer->entries); nd; nd = rb_next(nd)) { struct hist_entry *pos = rb_entry(nd, struct hist_entry, rb_node); - pos->pair = perf_session__find_hist_entry(old_session, pos); + pos->pair = hists__find_entry(older, pos); } } @@ -159,15 +157,13 @@ static int __cmd_diff(void) goto out_delete; } - perf_session__output_resort(&session[1]->hists, - session[1]->events_stats.total); + hists__output_resort(&session[1]->hists); if (show_displacement) - perf_session__set_hist_entries_positions(session[0]); + hists__set_positions(&session[0]->hists); - perf_session__match_hists(session[0], session[1]); - perf_session__fprintf_hists(&session[1]->hists, session[0], - show_displacement, stdout, - session[1]->events_stats.total); + hists__match(&session[0]->hists, &session[1]->hists); + hists__fprintf(&session[1]->hists, &session[0]->hists, + show_displacement, stdout); out_delete: for (i = 0; i < 2; ++i) perf_session__delete(session[i]); -- cgit v1.2.3 From cee75ac7ecc27084accdb9d9d6fde65a09f047ae Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 14 May 2010 13:16:55 -0300 Subject: perf hist: Clarify events_stats fields usage MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The events_stats.total field is too generic, rename it to .total_period, and also add a comment explaining that it is the sum of all the .period fields in samples, that is needed because we use auto-freq to avoid sampling artifacts. Ditto for events_stats.lost, that is the sum of all lost_event.lost fields, i.e. the number of events the kernel dropped. Looking at the users, builtin-sched.c can make use of these fields and stop doing it again. Cc: Frédéric Weisbecker Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Tom Zanussi LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-diff.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/builtin-diff.c') diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 3a95a0260a5b..6dd4bdae8a87 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -54,7 +54,7 @@ static int diff__process_sample_event(event_t *event, struct perf_session *sessi return -1; } - session->hists.stats.total += data.period; + session->hists.stats.total_period += data.period; return 0; } -- cgit v1.2.3 From c82ee828aa20487d254a5225d256cd422acee459 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 14 May 2010 14:19:35 -0300 Subject: perf report: Report number of events, not samples MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Number of samples is meaningless after we switched to auto-freq, so report the number of events, i.e. not the sum of the different periods, but the number PERF_RECORD_SAMPLE emitted by the kernel. While doing this I noticed that naming "count" to the sum of all the event periods can be confusing, so rename it to .period, just like in struct sample.data, so that we become more consistent. This helps with the next step, that was to record in struct hist_entry the number of sample events for each instance, we need that because we use it to generate the number of events when applying filters to the tree of hist entries like it is being done in the TUI report browser. Suggested-by: Ingo Molnar Cc: Frédéric Weisbecker Cc: Mike Galbraith Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Tom Zanussi LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-diff.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'tools/perf/builtin-diff.c') diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 6dd4bdae8a87..a6e2fdc7a04e 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -23,9 +23,9 @@ static bool force; static bool show_displacement; static int hists__add_entry(struct hists *self, - struct addr_location *al, u64 count) + struct addr_location *al, u64 period) { - if (__hists__add_entry(self, al, NULL, count) != NULL) + if (__hists__add_entry(self, al, NULL, period) != NULL) return 0; return -ENOMEM; } @@ -50,7 +50,7 @@ static int diff__process_sample_event(event_t *event, struct perf_session *sessi event__parse_sample(event, session->sample_type, &data); if (hists__add_entry(&session->hists, &al, data.period)) { - pr_warning("problem incrementing symbol count, skipping event\n"); + pr_warning("problem incrementing symbol period, skipping event\n"); return -1; } -- cgit v1.2.3