diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index c407897f0435..82bffac036e1 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -209,6 +209,10 @@ overrides that and uses per-thread mmaps.  A side-effect of that is that
 inheritance is automatically disabled.  --per-thread is ignored with a warning
 if combined with -a or -C options.
 
+--initial-delay msecs::
+After starting the program, wait msecs before measuring. This is useful to
+filter out the startup phase of the program, which is often very different.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 88600158400e..07d4cf8d3fd3 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -499,7 +499,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	 * (apart from group members) have enable_on_exec=1 set,
 	 * so don't spoil it by prematurely enabling them.
 	 */
-	if (!target__none(&opts->target))
+	if (!target__none(&opts->target) && !opts->initial_delay)
 		perf_evlist__enable(rec->evlist);
 
 	/*
@@ -508,6 +508,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	if (forks)
 		perf_evlist__start_workload(rec->evlist);
 
+	if (opts->initial_delay) {
+		usleep(opts->initial_delay * 1000);
+		perf_evlist__enable(rec->evlist);
+	}
+
 	for (;;) {
 		int hits = rec->samples;
 
@@ -877,6 +882,8 @@ const struct option record_options[] = {
 	OPT_CALLBACK('G', "cgroup", &record.evlist, "name",
 		     "monitor event in cgroup name only",
 		     parse_cgroups),
+	OPT_UINTEGER(0, "initial-delay", &record.opts.initial_delay,
+		  "ms to wait before starting measurement after program start"),
 	OPT_STRING('u', "uid", &record.opts.target.uid_str, "user",
 		   "user to profile"),
 
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index b1cc84b01d5b..af1ce6e14a93 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -269,6 +269,7 @@ struct record_opts {
 	u64	     user_interval;
 	u16	     stack_dump_size;
 	bool	     sample_transaction;
+	unsigned     initial_delay;
 };
 
 #endif
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ade8d9c1c431..cd4630abfa43 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -658,7 +658,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	 * Setting enable_on_exec for independent events and
 	 * group leaders for traced executed by perf.
 	 */
-	if (target__none(&opts->target) && perf_evsel__is_group_leader(evsel))
+	if (target__none(&opts->target) && perf_evsel__is_group_leader(evsel) &&
+		!opts->initial_delay)
 		attr->enable_on_exec = 1;
 }