From 63e0c7715aab6085faa487d498889f4361dc6542 Mon Sep 17 00:00:00 2001 From: Tom Zanussi <tzanussi@gmail.com> Date: Mon, 3 May 2010 00:14:48 -0500 Subject: perf: record TRACE_INFO only if using tracepoints and SAMPLE_RAW MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The current perf code implicitly assumes SAMPLE_RAW means tracepoints are being used, but doesn't check for that. It happily records the TRACE_INFO even if SAMPLE_RAW is used without tracepoints, but when the perf data is read it won't go any further when it finds TRACE_INFO but no tracepoints, and displays misleading errors. This adds a check for both in perf-record, and won't record TRACE_INFO unless both are true. This at least allows perf report -D to dump raw events, and avoids triggering a misleading error condition in perf trace. It doesn't actually enable the non-tracepoint raw events to be displayed in perf trace, since perf trace currently only deals with tracepoint events. Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1272865861.7932.16.camel@tropicana> Signed-off-by: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> --- tools/perf/builtin-record.c | 35 +++++++++++++++++++++-------------- tools/perf/util/header.c | 1 - tools/perf/util/parse-events.h | 1 + tools/perf/util/trace-event-info.c | 5 +++++ 4 files changed, 27 insertions(+), 15 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index ac989e9..0ff67d1 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -560,11 +560,12 @@ static int __cmd_record(int argc, const char **argv) return err; } - if (raw_samples) { + if (raw_samples && have_tracepoints(attrs, nr_counters)) { perf_header__set_feat(&session->header, HEADER_TRACE_INFO); } else { for (i = 0; i < nr_counters; i++) { - if (attrs[i].sample_type & PERF_SAMPLE_RAW) { + if (attrs[i].sample_type & PERF_SAMPLE_RAW && + attrs[i].type == PERF_TYPE_TRACEPOINT) { perf_header__set_feat(&session->header, HEADER_TRACE_INFO); break; } @@ -662,19 +663,25 @@ static int __cmd_record(int argc, const char **argv) return err; } - err = event__synthesize_tracing_data(output, attrs, - nr_counters, - process_synthesized_event, - session); - /* - * FIXME err <= 0 here actually means that there were no tracepoints - * so its not really an error, just that we don't need to synthesize - * anything. - * We really have to return this more properly and also propagate - * errors that now are calling die() - */ - if (err > 0) + if (have_tracepoints(attrs, nr_counters)) { + /* + * FIXME err <= 0 here actually means that + * there were no tracepoints so its not really + * an error, just that we don't need to + * synthesize anything. We really have to + * return this more properly and also + * propagate errors that now are calling die() + */ + err = event__synthesize_tracing_data(output, attrs, + nr_counters, + process_synthesized_event, + session); + if (err <= 0) { + pr_err("Couldn't record tracing data.\n"); + return err; + } advance_output(err); + } } machine = perf_session__find_host_machine(session); diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 79da0e5..2b9f898 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -436,7 +436,6 @@ static int perf_header__adds_write(struct perf_header *self, int fd) trace_sec->size = lseek(fd, 0, SEEK_CUR) - trace_sec->offset; } - if (perf_header__has_feat(self, HEADER_BUILD_ID)) { struct perf_file_section *buildid_sec; diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index b8c1f64..fc4ab3f 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -13,6 +13,7 @@ struct tracepoint_path { }; extern struct tracepoint_path *tracepoint_id_to_path(u64 config); +extern bool have_tracepoints(struct perf_event_attr *pattrs, int nb_events); extern int nr_counters; diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index 30cd9b5..0a1fb9d 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -487,6 +487,11 @@ get_tracepoints_path(struct perf_event_attr *pattrs, int nb_events) return nr_tracepoints > 0 ? path.next : NULL; } +bool have_tracepoints(struct perf_event_attr *pattrs, int nb_events) +{ + return get_tracepoints_path(pattrs, nb_events) ? true : false; +} + int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events) { char buf[BUFSIZ]; -- cgit v1.1 From 11d232ec285b07860670277c8ab3f6076f7bce1e Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo <acme@redhat.com> Date: Tue, 4 May 2010 10:48:22 -0300 Subject: perf inject: Add missing bits MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit New commands need to have Documentation and be added to command-list.txt so that they can appear when 'perf' is called withouth any subcommand: [root@doppio linux-2.6-tip]# perf usage: perf [--version] [--help] COMMAND [ARGS] The most commonly used perf commands are: annotate Read perf.data (created by perf record) and display annotated code archive Create archive with object files with build-ids found in perf.data file bench General framework for benchmark suites buildid-cache Manage build-id cache. buildid-list List the buildids in a perf.data file diff Read two perf.data files and display the differential profile inject Filter to augment the events stream with additional information kmem Tool to trace/measure kernel memory(slab) properties kvm Tool to trace/measure kvm guest os list List all symbolic event types lock Analyze lock events probe Define new dynamic tracepoints record Run a command and record its profile into perf.data report Read perf.data (created by perf record) and display the profile sched Tool to trace/measure scheduler properties (latencies) stat Run a command and gather performance counter statistics test Runs sanity tests. timechart Tool to visualize total system behavior during a workload top System profiling tool. trace Read perf.data (created by perf record) and display trace output See 'perf help COMMAND' for more information on a specific command. [root@doppio linux-2.6-tip]# The new 'perf inject' command hadn't so it wasn't appearing on that list. Also fix the long option, that should have no spaces in it, rename the faulty one to be '--build-ids', instead of '--inject build-ids'. Reported-by: Ingo Molnar <mingo@elte.hu> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Tom Zanussi <tzanussi@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> --- tools/perf/Documentation/perf-buildid-cache.txt | 4 +-- tools/perf/Documentation/perf-inject.txt | 35 +++++++++++++++++++++++++ tools/perf/builtin-inject.c | 2 +- tools/perf/command-list.txt | 1 + 4 files changed, 39 insertions(+), 3 deletions(-) create mode 100644 tools/perf/Documentation/perf-inject.txt (limited to 'tools') diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt index 88bc3b5..5d1a950 100644 --- a/tools/perf/Documentation/perf-buildid-cache.txt +++ b/tools/perf/Documentation/perf-buildid-cache.txt @@ -8,7 +8,7 @@ perf-buildid-cache - Manage build-id cache. SYNOPSIS -------- [verse] -'perf buildid-list <options>' +'perf buildid-cache <options>' DESCRIPTION ----------- @@ -30,4 +30,4 @@ OPTIONS SEE ALSO -------- -linkperf:perf-record[1], linkperf:perf-report[1] +linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-buildid-list[1] diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt new file mode 100644 index 0000000..025630d --- /dev/null +++ b/tools/perf/Documentation/perf-inject.txt @@ -0,0 +1,35 @@ +perf-inject(1) +============== + +NAME +---- +perf-inject - Filter to augment the events stream with additional information + +SYNOPSIS +-------- +[verse] +'perf inject <options>' + +DESCRIPTION +----------- +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 events stream with additional +information could make use of this facility. + +OPTIONS +------- +-b:: +--build-ids=:: + Inject build-ids into the output stream +-v:: +--verbose:: + Be more verbose. + +SEE ALSO +-------- +linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1] diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 59e981a..8e3e47b 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -204,7 +204,7 @@ static const char * const report_usage[] = { }; static const struct option options[] = { - OPT_BOOLEAN('b', "inject build-ids", &inject_build_ids, + OPT_BOOLEAN('b', "build-ids", &inject_build_ids, "Inject build-ids into the output stream"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show build ids, etc)"), diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt index 80a1a44..949d77f 100644 --- a/tools/perf/command-list.txt +++ b/tools/perf/command-list.txt @@ -8,6 +8,7 @@ perf-bench mainporcelain common perf-buildid-cache mainporcelain common perf-buildid-list mainporcelain common perf-diff mainporcelain common +perf-inject mainporcelain common perf-list mainporcelain common perf-sched mainporcelain common perf-record mainporcelain common -- cgit v1.1 From 02bf60aad7d5912dfcdbe0154f1bd67ea7a8301e Mon Sep 17 00:00:00 2001 From: Anton Blanchard <anton@samba.org> Date: Tue, 4 May 2010 21:19:15 +1000 Subject: perf: Fix performance issue with perf report On a large machine we spend a lot of time in perf_header__find_attr when running perf report. If we are parsing a file without PERF_SAMPLE_ID then for each sample we call perf_header__find_attr and loop through all counter IDs, never finding a match. As the machine gets larger there are more per cpu counters and we spend an awful lot of time in there. The patch below initialises each sample id to -1ULL and checks for this in perf_header__find_attr. We may need to do something more intelligent eventually (eg a hash lookup from counter id to attr) but this at least fixes the most common usage of perf report. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric B Munson <ebmunson@us.ibm.com> Acked-by: Eric B Munson <ebmunson@us.ibm.com> LKML-Reference: <20100504111915.GB14636@kryten> Signed-off-by: Anton Blanchard <anton@samba.org> -- Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> --- tools/perf/util/event.c | 1 + tools/perf/util/header.c | 8 ++++++++ 2 files changed, 9 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 1757b0f..2477270 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -713,6 +713,7 @@ int event__parse_sample(event_t *event, u64 type, struct sample_data *data) array++; } + data->id = -1ULL; if (type & PERF_SAMPLE_ID) { data->id = *array; array++; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 2b9f898..8847bec 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -922,6 +922,14 @@ perf_header__find_attr(u64 id, struct perf_header *header) { int i; + /* + * We set id to -1 if the data file doesn't contain sample + * ids. Check for this and avoid walking through the entire + * list of ids which may be large. + */ + if (id == -1ULL) + return NULL; + for (i = 0; i < header->attrs; i++) { struct perf_header_attr *attr = header->attr[i]; int j; -- cgit v1.1