[PATCH v3 09/12] perf record: document parallel data streaming mode

[Alexey Budankov]

Document --threads option syntax and parallel data streaming modes
in Documentation/perf-record.txt. Implement compatibility checks for
other modes and related command line options: asynchronous(--aio)
trace streaming and affinity (--affinity) modes, pipe mode, AUX
area tracing --snapshot and --aux-sample options, --switch-output,
--switch-output-event, --switch-max-files and --timestamp-filename
options. Parallel data streaming is compatible with Zstd compression
(--compression-level) and external control commands (--control).
Cpu mask provided via -C option filters --threads specification masks.

Signed-off-by: Alexey Budankov <alexey.budankov@xxxxxxxxxxxxxxx>
---
 tools/perf/Documentation/perf-record.txt | 18 ++++++++++
 tools/perf/builtin-record.c              | 43 ++++++++++++++++++++++--
 2 files changed, 58 insertions(+), 3 deletions(-)

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 768888b9326a..baf9428856e6 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -671,6 +671,24 @@ Example of bash shell script to enable and disable events during measurements:
  wait -n ${perf_pid}
  exit $?
 
+--threads=<spec>::
+Write collected trace data into several data files using parallel threads.
+<spec> value can be user defined list of masks. Masks separated by colon
+define cpus to be monitored by a thread and affinity mask of that thread
+is separated by slash. For example user specification like the following:
+<cpus mask 1>/<affinity mask 1>:<cpu mask 2>/<affinity mask 2> specifies
+parallel threads layout that consists of two threads with corresponding
+assigned cpus to be monitored. <spec> value can also be a string meaning
+predefined parallel threads layout:
+    cpu    - create new data streaming thread for every monitored cpu
+    core   - create new thread to monitor cpus grouped by a core
+    socket - create new thread to monitor cpus grouped by a socket
+    numa   - create new threed to monitor cpus grouped by a numa domain
+Predefined layouts can be used on systems with large number of cpus in
+order not to spawn multiple per-cpu streaming threads but still avoid LOST
+events in data directory files. Option specified with no or empty value
+defaults to cpu layout. Masks defined or provided by the option value are
+filtered through the mask provided by -C option.
 
 SEE ALSO
 --------
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index fd0587d636b2..9ea70dfa17d4 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -798,6 +798,12 @@ 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 parallel streaming mode.\n");
+		return -EINVAL;
+	}
+
 	if (!rec->itr) {
 		rec->itr = auxtrace_record__init(rec->evlist, &err);
 		if (err)
@@ -2107,6 +2113,11 @@ 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("Parallel trace streaming is not available in pipe mode.\n");
+		return -1;
+	}
+
 	fd = perf_data__fd(data);
 	rec->session = session;
 
@@ -2853,12 +2864,22 @@ 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 parallel 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 parallel streaming mode.\n");
+		return 0;
+	}
+
 	if (!strcmp(s->str, "signal")) {
 do_signal:
 		s->signal = true;
@@ -3137,8 +3158,8 @@ 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,
@@ -3510,6 +3531,17 @@ 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 (rec->opts.affinity != PERF_AFFINITY_SYS) {
+			pr_err("--affinity option is mutually exclusive to parallel streaming mode.\n");
+			goto out_opts;
+		}
+		if (record__aio_enabled(rec)) {
+			pr_err("Asynchronous streaming mode (--aio) is mutually exclusive to parallel 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");
 		rec->no_buildid = true;
@@ -3543,6 +3575,11 @@ 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 parallel streaming mode.\n");
+	}
+
 	/*
 	 * Allow aliases to facilitate the lookup of symbols for address
 	 * filters. Refer to auxtrace_parse_filters().
-- 
2.24.1