diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 52462ae..e032716 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -61,6 +61,9 @@
 -r::
 --realtime=::
 	Collect data with this RT SCHED_FIFO priority.
+-D::
+--no-delay::
+	Collect data without buffering.
 -A::
 --append::
 	Append to the output file to do incremental profiling.
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 1210e64..df6064a 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -49,6 +49,7 @@
 static const char		*output_name			= "perf.data";
 static int			group				=      0;
 static int			realtime_prio			=      0;
+static bool			nodelay				=  false;
 static bool			raw_samples			=  false;
 static bool			sample_id_all_avail		=   true;
 static bool			system_wide			=  false;
@@ -307,6 +308,11 @@
 		attr->sample_type	|= PERF_SAMPLE_CPU;
 	}
 
+	if (nodelay) {
+		attr->watermark = 0;
+		attr->wakeup_events = 1;
+	}
+
 	attr->mmap		= track;
 	attr->comm		= track;
 	attr->inherit		= !no_inherit;
@@ -843,6 +849,8 @@
 		    "record events on existing thread id"),
 	OPT_INTEGER('r', "realtime", &realtime_prio,
 		    "collect data with this RT SCHED_FIFO priority"),
+	OPT_BOOLEAN('D', "no-delay", &nodelay,
+		    "collect data without buffering"),
 	OPT_BOOLEAN('R', "raw-samples", &raw_samples,
 		    "collect raw sample records from all opened counters"),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,