Provide --threads option in perf record command line interface.
Threaded streaming mode mitigates profiling data losses and
resolves scalability issues of serial and asynchronous (--aio) trace
streaming modes on multicore server systems. The implementation is
based on the prototype [1], [2] and the most closely relates to mode 3)
"mode that creates thread for every monitored memory map".
Threaded streaming mode is available with Zstd compression/decompression
(--compression-level) and handling of external commands (--control).
AUX area tracing, related and derived modes like --snapshot or
--aux-sample are not enabled. --switch-output, --switch-output-event,
--switch-max-files and --timestamp-filename options are not enabled.
Threaded trace streaming is not enabled for pipe mode. Asynchronous
(--aio) trace streaming and affinity (--affinity) modes are mutually
exclusive to the exposed threaded streaming mode.
[1] git clone https://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf.git -b perf/record_threads
[2] https://lore.kernel.org/lkml/[email protected]/
Signed-off-by: Alexey Budankov <[email protected]>
---
tools/perf/Documentation/perf-record.txt | 7 ++++
tools/perf/builtin-record.c | 45 +++++++++++++++++++++---
2 files changed, 48 insertions(+), 4 deletions(-)
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 768888b9326a..d8fa387da973 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -671,6 +671,13 @@ Example of bash shell script to enable and disable events during measurements:
wait -n ${perf_pid}
exit $?
+--threads::
+Write collected trace data into per-CPU trace files using parallel threads.
+List of monitored CPUs can be configured by a mask provided via --cpu option.
+Trace writing threads correspond one-to-one to mapped data buffers. Threads
+and buffers are affined to monitored CPUs and NUMA nodes according to system
+topology. Threaded trace streaming mode is mutually exclusive to asynchronous
+trace streaming (--aio) and affinity (--affinity) modes.
SEE ALSO
--------
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 1d41e996a994..575b0b595081 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -780,6 +780,12 @@ static int record__auxtrace_init(struct record *rec)
{
int err;
+ if ((rec->opts.auxtrace_snapshot_opts || rec->opts.auxtrace_sample_opts)
+ && record__threads_enabled(rec)) {
+ pr_err("AUX area tracing options are not available in threaded streaming mode.\n");
+ return -EINVAL;
+ }
+
if (!rec->itr) {
rec->itr = auxtrace_record__init(rec->evlist, &err);
if (err)
@@ -2008,6 +2014,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
return PTR_ERR(session);
}
+ if (record__threads_enabled(rec) && perf_data__is_pipe(&rec->data)) {
+ pr_err("Threaded trace streaming is not available in pipe mode.\n");
+ return -1;
+ }
+
fd = perf_data__fd(data);
rec->session = session;
@@ -2680,12 +2691,22 @@ static int switch_output_setup(struct record *rec)
* --switch-output=signal, as we'll send a SIGUSR2 from the side band
* thread to its parent.
*/
- if (rec->switch_output_event_set)
+ if (rec->switch_output_event_set) {
+ if (record__threads_enabled(rec)) {
+ pr_warning("WARNING: --switch-output-event option is not available in threaded streaming mode.\n");
+ return 0;
+ }
goto do_signal;
+ }
if (!s->set)
return 0;
+ if (record__threads_enabled(rec)) {
+ pr_warning("WARNING: --switch-output option is not available in threaded streaming mode.\n");
+ return 0;
+ }
+
if (!strcmp(s->str, "signal")) {
do_signal:
s->signal = true;
@@ -2964,8 +2985,8 @@ static struct option __record_options[] = {
"Set affinity mask of trace reading thread to NUMA node cpu mask or cpu of processed mmap buffer",
record__parse_affinity),
#ifdef HAVE_ZSTD_SUPPORT
- OPT_CALLBACK_OPTARG('z', "compression-level", &record.opts, &comp_level_default,
- "n", "Compressed records using specified level (default: 1 - fastest compression, 22 - greatest compression)",
+ OPT_CALLBACK_OPTARG('z', "compression-level", &record.opts, &comp_level_default, "n",
+ "Compress records using specified level (default: 1 - fastest compression, 22 - greatest compression)",
record__parse_comp_level),
#endif
OPT_CALLBACK(0, "max-size", &record.output_max_size,
@@ -2984,6 +3005,8 @@ static struct option __record_options[] = {
"\t\t\t Optionally send control command completion ('ack\\n') to ack-fd descriptor.\n"
"\t\t\t Alternatively, ctl-fifo / ack-fifo will be opened and used as ctl-fd / ack-fd.",
parse_control_option),
+ OPT_BOOLEAN(0, "threads", &record.opts.threads,
+ "write collected trace data into per-CPU trace files using parallel threads"),
OPT_END()
};
@@ -3046,8 +3069,17 @@ int cmd_record(int argc, const char **argv)
if (rec->opts.kcore || record__threads_enabled(rec))
rec->data.is_dir = true;
- if (record__threads_enabled(rec))
+ if (record__threads_enabled(rec)) {
+ if (rec->opts.affinity != PERF_AFFINITY_SYS) {
+ pr_err("--affinity option is mutually exclusive to threaded streaming mode.\n");
+ goto out_opts;
+ }
rec->opts.affinity = PERF_AFFINITY_CPU;
+ if (record__aio_enabled(rec)) {
+ pr_err("Asynchronous streaming mode (--aio) is mutually exclusive to threaded streaming mode.\n");
+ goto out_opts;
+ }
+ }
if (rec->opts.comp_level != 0) {
pr_debug("Compression enabled, disabling build id collection at the end of the session.\n");
@@ -3082,6 +3114,11 @@ int cmd_record(int argc, const char **argv)
}
}
+ if (rec->timestamp_filename && record__threads_enabled(rec)) {
+ rec->timestamp_filename = false;
+ pr_warning("WARNING: --timestamp-filename option is not available in threaded streaming mode.\n");
+ }
+
/*
* Allow aliases to facilitate the lookup of symbols for address
* filters. Refer to auxtrace_parse_filters().
--
2.24.1