summaryrefslogtreecommitdiffstats
path: root/tools/perf/builtin-record.c
diff options
context:
space:
mode:
authorAlexey Budankov <alexey.budankov@linux.intel.com>2019-03-18 20:40:26 +0300
committerArnaldo Carvalho de Melo <acme@redhat.com>2019-04-01 15:18:10 -0300
commit470530bbb8fbbf2a09bd1d7150bb92501c5c54e6 (patch)
tree933a18568c19d2fd9753fefd0245e85d799d0ac7 /tools/perf/builtin-record.c
parent3b1c5d9659718263c7f9c93af82f98221c58f171 (diff)
downloadlinux-470530bbb8fbbf2a09bd1d7150bb92501c5c54e6.tar.bz2
perf record: Implement --mmap-flush=<number> option
Implement a --mmap-flush option that specifies minimal number of bytes that is extracted from mmaped kernel buffer to store into a trace. The default option value is 1 byte what means every time trace writing thread finds some new data in the mmaped buffer the data is extracted, possibly compressed and written to a trace. $ tools/perf/perf record --mmap-flush 1024 -e cycles -- matrix.gcc $ tools/perf/perf record --aio --mmap-flush 1K -e cycles -- matrix.gcc The option is independent from -z setting, doesn't vary with compression level and can serve two purposes. The first purpose is to increase the compression ratio of a trace data. Larger data chunks are compressed more effectively so the implemented option allows specifying data chunk size to compress. Also at some cases executing more write syscalls with smaller data size can take longer than executing less write syscalls with bigger data size due to syscall overhead so extracting bigger data chunks specified by the option value could additionally decrease runtime overhead. The second purpose is to avoid self monitoring live-lock issue in system wide (-a) profiling mode. Profiling in system wide mode with compression (-a -z) can additionally induce data into the kernel buffers along with the data from monitored processes. If performance data rate and volume from the monitored processes is high then trace streaming and compression activity in the tool is also high. High tool process activity can lead to subtle live-lock effect when compression of single new byte from some of mmaped kernel buffer leads to generation of the next single byte at some mmaped buffer. So perf tool process ends up in endless self monitoring. Implemented synch parameter is the mean to force data move independently from the specified flush threshold value. Despite the provided flush value the tool needs capability to unconditionally drain memory buffers, at least in the end of the collection. Committer testing: Running with the default value, i.e. as soon as there is something to read go on consuming, we first write the synthesized events, small chunks of about 128 bytes: # perf trace -m 2048 --call-graph dwarf -e write -- perf record <SNIP> 101.142 ( 0.004 ms): perf/25821 write(fd: 3</root/perf.data>, buf: 0x210db60, count: 120) = 120 __libc_write (/usr/lib64/libpthread-2.28.so) ion (/home/acme/bin/perf) record__write (inlined) process_synthesized_event (/home/acme/bin/perf) perf_tool__process_synth_event (inlined) perf_event__synthesize_mmap_events (/home/acme/bin/perf) Then we move to reading the mmap buffers consuming the events put there by the kernel perf infrastructure: 107.561 ( 0.005 ms): perf/25821 write(fd: 3</root/perf.data>, buf: 0x7f1befc02000, count: 336) = 336 __libc_write (/usr/lib64/libpthread-2.28.so) ion (/home/acme/bin/perf) record__write (inlined) record__pushfn (/home/acme/bin/perf) perf_mmap__push (/home/acme/bin/perf) record__mmap_read_evlist (inlined) record__mmap_read_all (inlined) __cmd_record (inlined) cmd_record (/home/acme/bin/perf) 12919.953 ( 0.136 ms): perf/25821 write(fd: 3</root/perf.data>, buf: 0x7f1befc83150, count: 184984) = 184984 <SNIP same backtrace as in the 107.561 timestamp> 12920.094 ( 0.155 ms): perf/25821 write(fd: 3</root/perf.data>, buf: 0x7f1befc02150, count: 261816) = 261816 <SNIP same backtrace as in the 107.561 timestamp> 12920.253 ( 0.093 ms): perf/25821 write(fd: 3</root/perf.data>, buf: 0x7f1befb81120, count: 170832) = 170832 <SNIP same backtrace as in the 107.561 timestamp> If we limit it to write only when more than 16MB are available for reading, it throttles that to a quarter of the --mmap-pages set for 'perf record', which by default get to 528384 bytes, found out using 'record -v': mmap flush: 132096 mmap size 528384B With that in place all the writes coming from record__mmap_read_evlist(), i.e. from the mmap buffers setup by the kernel perf infrastructure were at least 132096 bytes long. Trying with a bigger mmap size: perf trace -e write perf record -v -m 2048 --mmap-flush 16M 74982.928 ( 2.471 ms): perf/26500 write(fd: 3</root/perf.data>, buf: 0x7ff94a6cc000, count: 3580888) = 3580888 74985.406 ( 2.353 ms): perf/26500 write(fd: 3</root/perf.data>, buf: 0x7ff949ecb000, count: 3453256) = 3453256 74987.764 ( 2.629 ms): perf/26500 write(fd: 3</root/perf.data>, buf: 0x7ff9496ca000, count: 3859232) = 3859232 74990.399 ( 2.341 ms): perf/26500 write(fd: 3</root/perf.data>, buf: 0x7ff948ec9000, count: 3769032) = 3769032 74992.744 ( 2.064 ms): perf/26500 write(fd: 3</root/perf.data>, buf: 0x7ff9486c8000, count: 3310520) = 3310520 74994.814 ( 2.619 ms): perf/26500 write(fd: 3</root/perf.data>, buf: 0x7ff947ec7000, count: 4194688) = 4194688 74997.439 ( 2.787 ms): perf/26500 write(fd: 3</root/perf.data>, buf: 0x7ff9476c6000, count: 4029760) = 4029760 Was again limited to a quarter of the mmap size: mmap flush: 2098176 mmap size 8392704B A warning about that would be good to have but can be added later, something like: "max flush is a quarter of the mmap size, if wanting to bump the mmap flush further, bump the mmap size as well using -m/--mmap-pages" Also rename the 'sync' parameters to 'synch' to keep tools/perf building with older glibcs: cc1: warnings being treated as errors builtin-record.c: In function 'record__mmap_read_evlist': builtin-record.c:775: warning: declaration of 'sync' shadows a global declaration /usr/include/unistd.h:933: warning: shadowed declaration is here builtin-record.c: In function 'record__mmap_read_all': builtin-record.c:856: warning: declaration of 'sync' shadows a global declaration /usr/include/unistd.h:933: warning: shadowed declaration is here Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/f6600d72-ecfa-2eb7-7e51-f6954547d500@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'tools/perf/builtin-record.c')
-rw-r--r--tools/perf/builtin-record.c65
1 files changed, 59 insertions, 6 deletions
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4e2d953d4bc5..c5e10552776a 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -337,6 +337,41 @@ static int record__aio_enabled(struct record *rec)
return rec->opts.nr_cblocks > 0;
}
+#define MMAP_FLUSH_DEFAULT 1
+static int record__mmap_flush_parse(const struct option *opt,
+ const char *str,
+ int unset)
+{
+ int flush_max;
+ struct record_opts *opts = (struct record_opts *)opt->value;
+ static struct parse_tag tags[] = {
+ { .tag = 'B', .mult = 1 },
+ { .tag = 'K', .mult = 1 << 10 },
+ { .tag = 'M', .mult = 1 << 20 },
+ { .tag = 'G', .mult = 1 << 30 },
+ { .tag = 0 },
+ };
+
+ if (unset)
+ return 0;
+
+ if (str) {
+ opts->mmap_flush = parse_tag_value(str, tags);
+ if (opts->mmap_flush == (int)-1)
+ opts->mmap_flush = strtol(str, NULL, 0);
+ }
+
+ if (!opts->mmap_flush)
+ opts->mmap_flush = MMAP_FLUSH_DEFAULT;
+
+ flush_max = perf_evlist__mmap_size(opts->mmap_pages);
+ flush_max /= 4;
+ if (opts->mmap_flush > flush_max)
+ opts->mmap_flush = flush_max;
+
+ return 0;
+}
+
static int process_synthesized_event(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
@@ -546,7 +581,8 @@ static int record__mmap_evlist(struct record *rec,
if (perf_evlist__mmap_ex(evlist, opts->mmap_pages,
opts->auxtrace_mmap_pages,
opts->auxtrace_snapshot_mode,
- opts->nr_cblocks, opts->affinity) < 0) {
+ opts->nr_cblocks, opts->affinity,
+ opts->mmap_flush) < 0) {
if (errno == EPERM) {
pr_err("Permission error mapping pages.\n"
"Consider increasing "
@@ -736,7 +772,7 @@ static void record__adjust_affinity(struct record *rec, struct perf_mmap *map)
}
static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist,
- bool overwrite)
+ bool overwrite, bool synch)
{
u64 bytes_written = rec->bytes_written;
int i;
@@ -759,12 +795,19 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
off = record__aio_get_pos(trace_fd);
for (i = 0; i < evlist->nr_mmaps; i++) {
+ u64 flush = 0;
struct perf_mmap *map = &maps[i];
if (map->base) {
record__adjust_affinity(rec, map);
+ if (synch) {
+ flush = map->flush;
+ map->flush = 1;
+ }
if (!record__aio_enabled(rec)) {
if (perf_mmap__push(map, rec, record__pushfn) != 0) {
+ if (synch)
+ map->flush = flush;
rc = -1;
goto out;
}
@@ -777,10 +820,14 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
idx = record__aio_sync(map, false);
if (perf_mmap__aio_push(map, rec, idx, record__aio_pushfn, &off) != 0) {
record__aio_set_pos(trace_fd, off);
+ if (synch)
+ map->flush = flush;
rc = -1;
goto out;
}
}
+ if (synch)
+ map->flush = flush;
}
if (map->auxtrace_mmap.base && !rec->opts.auxtrace_snapshot_mode &&
@@ -806,15 +853,15 @@ out:
return rc;
}
-static int record__mmap_read_all(struct record *rec)
+static int record__mmap_read_all(struct record *rec, bool synch)
{
int err;
- err = record__mmap_read_evlist(rec, rec->evlist, false);
+ err = record__mmap_read_evlist(rec, rec->evlist, false, synch);
if (err)
return err;
- return record__mmap_read_evlist(rec, rec->evlist, true);
+ return record__mmap_read_evlist(rec, rec->evlist, true, synch);
}
static void record__init_features(struct record *rec)
@@ -1340,7 +1387,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
if (trigger_is_hit(&switch_output_trigger) || done || draining)
perf_evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_DATA_PENDING);
- if (record__mmap_read_all(rec) < 0) {
+ if (record__mmap_read_all(rec, false) < 0) {
trigger_error(&auxtrace_snapshot_trigger);
trigger_error(&switch_output_trigger);
err = -1;
@@ -1441,6 +1488,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
record__synthesize_workload(rec, true);
out_child:
+ record__mmap_read_all(rec, true);
record__aio_mmap_read_sync(rec);
if (forks) {
@@ -1846,6 +1894,7 @@ static struct record record = {
.uses_mmap = true,
.default_per_cpu = true,
},
+ .mmap_flush = MMAP_FLUSH_DEFAULT,
},
.tool = {
.sample = process_sample_event,
@@ -1912,6 +1961,9 @@ static struct option __record_options[] = {
OPT_CALLBACK('m', "mmap-pages", &record.opts, "pages[,pages]",
"number of mmap data pages and AUX area tracing mmap pages",
record__parse_mmap_pages),
+ OPT_CALLBACK(0, "mmap-flush", &record.opts, "number",
+ "Minimal number of bytes that is extracted from mmap data pages (default: 1)",
+ record__mmap_flush_parse),
OPT_BOOLEAN(0, "group", &record.opts.group,
"put the counters into a counter group"),
OPT_CALLBACK_NOOPT('g', NULL, &callchain_param,
@@ -2224,6 +2276,7 @@ int cmd_record(int argc, const char **argv)
pr_info("nr_cblocks: %d\n", rec->opts.nr_cblocks);
pr_debug("affinity: %s\n", affinity_tags[rec->opts.affinity]);
+ pr_debug("mmap flush: %d\n", rec->opts.mmap_flush);
err = __cmd_record(&record, argc, argv);
out: