perf tools: Do not use __perf_session__process_events() directly
Namhyung Kim
maintainerPATCH 1/2 perf tools: Do not use __perf_session__process_events() directly
It's only used for perf record to process build-id because its file size it's not fixed at this time due to remaining header features. However data offset and size is available so that we can use the perf_session__process_events() once we set the file size as the current offset like for now.
--- tools/perf/builtin-record.c | 7 +++---- tools/perf/util/session.c | 6 +++--- tools/perf/util/session.h | 3 --- 3 files changed, 6 insertions(+), 10 deletions(-)
tools/perf/builtin-record.c +3 -4
@@ -194,12 +194,13 @@ static int process_buildids(struct record *rec) {struct perf_data_file *file = &rec->file;struct perf_session *session = rec->session; -u64 start = session->header.data_offset;u64 size =lseek (file->fd,0 ,SEEK_CUR );if (size ==0 )return 0 ; + file->size = size; +/* * During this process, it'll load kernel map and replace the * dso->long_name to a real pathname it found. In this case
@@ -211,9 +212,7 @@ static int process_buildids(struct record *rec)*/ symbol_conf.ignore_vmlinux_buildid = true; -return __perf_session__process_events (session, start, - size - start, - size, &build_id__mark_dso_hit_ops); +return perf_session__process_events (session, &build_id__mark_dso_hit_ops); }static void perf_event__synthesize_guest_os (struct machine *machine,void *data)
tools/perf/util/session.c +3 -3
@@ -1252,9 +1252,9 @@ fetch_mmaped_event(struct perf_session *session,#define NUM_MMAPS 128#endif -int __perf_session__process_events (struct perf_session *session, -u64 data_offset,u64 data_size, -u64 file_size,struct perf_tool *tool) +static int __perf_session__process_events (struct perf_session *session, +u64 data_offset,u64 data_size, +u64 file_size,struct perf_tool *tool) {int fd =perf_data_file__fd (session->file);u64 head, page_offset, file_offset, file_pos, size;
tools/perf/util/session.h +0 -3
@@ -49,9 +49,6 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset,union perf_event **event_ptr, struct perf_sample *sample); -int __perf_session__process_events (struct perf_session *session, -u64 data_offset,u64 data_size,u64 size, -struct perf_tool *tool);int perf_session__process_events (struct perf_session *session,struct perf_tool *tool);
Signature · 1 line
2.1.2
Namhyung Kim
maintainerPATCH 2/2 perf record: Show precise number of samples
After perf record finishes, it prints file size and number of samples in the file but this info is wrong since it assumes typical sample size of 24 bytes and divides file size by the value.
However as we post-process recorded samples for build-id, it can show correct number like below. If build-id post-processing is not requested just omit the wrong number of samples.
$ perf record noploop 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.159 MB perf.data (3989 samples) ]
$ perf report --stdio -n
# To display the perf.data header info, please use --header/--header-only options.
#
# Samples: 3K of event 'cycles'
# Event count (approx.): 3771330663
#
# Overhead Samples Command Shared Object Symbol
# ........ ............ ....... ................ ..........................
#
99.90% 3982 noploop noploop [.] main
0.09% 1 noploop ld-2.17.so [.] _dl_check_map_versions
0.01% 1 noploop [kernel.vmlinux] [k] setup_arg_pages
0.00% 5 noploop [kernel.vmlinux] [k] intel_pmu_enable_all--- tools/perf/builtin-record.c | 50 +++++++++++++++++++++++++++++++++------------ 1 file changed, 37 insertions(+), 13 deletions(-)
tools/perf/builtin-record.c +37 -13
@@ -190,6 +190,19 @@ static int record__open(struct record *rec)return rc; } +static int process_sample_event (struct perf_tool *tool, +union perf_event *event, +struct perf_sample *sample, +struct perf_evsel *evsel, +struct machine *machine) +{ + struct record *rec = container_of(tool, struct record, tool); + + rec->samples++; + +return build_id__mark_dso_hit (tool, event, sample, evsel, machine); +} +static int process_buildids (struct record *rec) {struct perf_data_file *file = &rec->file;
@@ -200,6 +213,7 @@ static int process_buildids(struct record *rec)return 0 ; file->size = size; + rec->samples =0 ;/* * During this process, it'll load kernel map and replace the
@@ -212,7 +226,7 @@ static int process_buildids(struct record *rec)*/ symbol_conf.ignore_vmlinux_buildid = true; -return perf_session__process_events (session, &build_id__mark_dso_hit_ops); +return perf_session__process_events (session, &rec->tool); }static void perf_event__synthesize_guest_os (struct machine *machine,void *data)
@@ -503,19 +517,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) goto out_child; } -if (!quiet) { +if (!quiet)fprintf (stderr,"[ perf record: Woken up %ld times to write data ]\n" , waking); -/* -* Approximate RIP event size: 24 bytes. -*/ -fprintf (stderr, -"[ perf record: Captured and wrote %.3f MB %s (~%" PRIu64" samples) ]\n" , - (double )rec->bytes_written /1024.0 /1024.0 , - file->path, - rec->bytes_written /24 ); - } - out_child:if (forks) {int exit_status;
@@ -537,8 +541,21 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)if (!err && !file->is_pipe) { rec->session->header.data_size += rec->bytes_written; -if (!rec->no_buildid) +if (!rec->no_buildid) {process_buildids (rec); + +if (!quiet) { +fprintf (stderr,"[ perf record: Captured and wrote %.3f MB %s (%" PRIu64" samples) ]\n" , + (double )rec->bytes_written /1024.0 /1024.0 , + file->path, rec->samples); + } + } +if (!quiet) { +fprintf (stderr,"[ perf record: Captured and wrote %.3f MB %s ]\n" , + (double )rec->bytes_written /1024.0 /1024.0 , + file->path); + } +perf_session__write_header (rec->session, rec->evlist, file->fd, true); }
@@ -719,6 +736,13 @@ static struct record record = { .default_per_cpu = true, }, }, + .tool = { + .sample = process_sample_event, + .fork = perf_event__process_fork, + .comm = perf_event__process_comm, + .mmap = perf_event__process_mmap, + .mmap2 = perf_event__process_mmap2, + }, };#define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace) recording: "
Signature · 1 line
2.1.2
Namhyung Kim
maintainerPATCH v2 2/2 perf record: Show precise number of samples
After perf record finishes, it prints file size and number of samples in the file but this info is wrong since it assumes typical sample size of 24 bytes and divides file size by the value.
However as we post-process recorded samples for build-id, it can show correct number like below. If build-id post-processing is not requested just omit the wrong number of samples.
$ perf record noploop 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.159 MB perf.data (3989 samples) ]
$ perf report --stdio -n
# To display the perf.data header info, please use --header/--header-only options.
#
# Samples: 3K of event 'cycles'
# Event count (approx.): 3771330663
#
# Overhead Samples Command Shared Object Symbol
# ........ ............ ....... ................ ..........................
#
99.90% 3982 noploop noploop [.] main
0.09% 1 noploop ld-2.17.so [.] _dl_check_map_versions
0.01% 1 noploop [kernel.vmlinux] [k] setup_arg_pages
0.00% 5 noploop [kernel.vmlinux] [k] intel_pmu_enable_all--- tools/perf/builtin-record.c | 53 ++++++++++++++++++++++++++++++++++----------- 1 file changed, 40 insertions(+), 13 deletions(-)
tools/perf/builtin-record.c +40 -13
@@ -190,6 +190,19 @@ static int record__open(struct record *rec)return rc; } +static int process_sample_event (struct perf_tool *tool, +union perf_event *event, +struct perf_sample *sample, +struct perf_evsel *evsel, +struct machine *machine) +{ + struct record *rec = container_of(tool, struct record, tool); + + rec->samples++; + +return build_id__mark_dso_hit (tool, event, sample, evsel, machine); +} +static int process_buildids (struct record *rec) {struct perf_data_file *file = &rec->file;
@@ -200,6 +213,7 @@ static int process_buildids(struct record *rec)return 0 ; file->size = size; + rec->samples =0 ;/* * During this process, it'll load kernel map and replace the
@@ -212,7 +226,7 @@ static int process_buildids(struct record *rec)*/ symbol_conf.ignore_vmlinux_buildid = true; -return perf_session__process_events (session, &build_id__mark_dso_hit_ops); +return perf_session__process_events (session, &rec->tool); }static void perf_event__synthesize_guest_os (struct machine *machine,void *data)
@@ -503,19 +517,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) goto out_child; } -if (!quiet) { +if (!quiet)fprintf (stderr,"[ perf record: Woken up %ld times to write data ]\n" , waking); -/* -* Approximate RIP event size: 24 bytes. -*/ -fprintf (stderr, -"[ perf record: Captured and wrote %.3f MB %s (~%" PRIu64" samples) ]\n" , - (double )rec->bytes_written /1024.0 /1024.0 , - file->path, - rec->bytes_written /24 ); - } - out_child:if (forks) {int exit_status;
@@ -535,10 +539,26 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) status = err;if (!err && !file->is_pipe) { +bool print_nr_samples = false; + rec->session->header.data_size += rec->bytes_written; -if (!rec->no_buildid) +if (!rec->no_buildid) {process_buildids (rec); + print_nr_samples = true; + } + +if (!quiet) { +fprintf (stderr,"[ perf record: Captured and wrote %.3f MB %s" , + (double )rec->bytes_written /1024.0 /1024.0 , + file->path); + +if (print_nr_samples) +fprintf (stderr," (%" PRIu64" samples)" , rec->samples); + +fputs (" ]\n" , stderr); + } +perf_session__write_header (rec->session, rec->evlist, file->fd, true); }
@@ -719,6 +739,13 @@ static struct record record = { .default_per_cpu = true, }, }, + .tool = { + .sample = process_sample_event, + .fork = perf_event__process_fork, + .comm = perf_event__process_comm, + .mmap = perf_event__process_mmap, + .mmap2 = perf_event__process_mmap2, + }, };#define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace) recording: "
Signature · 1 line
2.1.2
Re: [PATCH v2 2/2] perf record: Show precise number of samples
Quoted 26 lines · Namhyung Kim
After perf record finishes, it prints file size and number of samples in the file but this info is wrong since it assumes typical sample size of 24 bytes and divides file size by the value.
However as we post-process recorded samples for build-id, it can show correct number like below. If build-id post-processing is not requested just omit the wrong number of samples.
$ perf record noploop 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.159 MB perf.data (3989 samples) ]$ perf report --stdio -n # To display the perf.data header info, please use --header/--header-only options. # # Samples: 3K of event 'cycles' # Event count (approx.): 3771330663 # # Overhead Samples Command Shared Object Symbol # ........ ............ ....... ................ .......................... # 99.90% 3982 noploop noploop [.] main 0.09% 1 noploop ld-2.17.so [.] _dl_check_map_versions 0.01% 1 noploop [kernel.vmlinux] [k] setup_arg_pages 0.00% 5 noploop [kernel.vmlinux] [k] intel_pmu_enable_all
Quoted 2 lines
Reported-by Milian Wolff <[email protected]>Signed-off-by Namhyung Kim <[email protected]>
eeeey great, I mean.. finally ;-)
thanks,
jirka
Re: [PATCH v2 2/2] perf record: Show precise number of samples
Quoted 4 lines
Quoted 2 lines
Reported-by Milian Wolff <[email protected]>Signed-off-by Namhyung Kim <[email protected]>eeeey great, I mean.. finally ;-)
Yes I like it too.
BTW it would be nice if we could show down a break down on how many bytes the different options passed to perf record added, by accounting the different header fields. That would guide people who suffer from too large perf.data files.
-Andi
Arnaldo Carvalho de Melo
maintainerRe: [PATCH v2 2/2] perf record: Show precise number of samples
Em Fri, Nov 28, 2014 at 06:56:13PM +0100, Andi Kleen escreveu:
Quoted 11 lines
Quoted 4 lines
Quoted 2 lines
Reported-by Milian Wolff <[email protected]>Signed-off-by Namhyung Kim <[email protected]>eeeey great, I mean.. finally ;-)
Yes I like it too.
BTW it would be nice if we could show down a break down on how many bytes the different options passed to perf record added, by accounting the different header fields. That would guide people who suffer from too large perf.data files.
That is a good idea, after perf_evsel__parse_sample() we add up the things that are variable: callchains, branch_stack, etc.
Will implement if nobody does it first :-)
- Arnaldo