diff --git a/module/zfs/vdev_queue.c b/module/zfs/vdev_queue.c
index bf2e24cb2..d969cfeed 100644
--- a/module/zfs/vdev_queue.c
+++ b/module/zfs/vdev_queue.c
@@ -24,7 +24,7 @@
  */
 
 /*
- * Copyright (c) 2012, 2014 by Delphix. All rights reserved.
+ * Copyright (c) 2012, 2017 by Delphix. All rights reserved.
  */
 
 #include <sys/zfs_context.h>
@@ -554,7 +554,7 @@ vdev_queue_aggregate(vdev_queue_t *vq, zio_t *zio)
 
 	/*
 	 * Walk backwards through sufficiently contiguous I/Os
-	 * recording the last non-option I/O.
+	 * recording the last non-optional I/O.
 	 */
 	while ((dio = AVL_PREV(t, first)) != NULL &&
 	    (dio->io_flags & ZIO_FLAG_AGG_INHERIT) == flags &&
@@ -576,10 +576,14 @@ vdev_queue_aggregate(vdev_queue_t *vq, zio_t *zio)
 
 	/*
 	 * Walk forward through sufficiently contiguous I/Os.
+	 * The aggregation limit does not apply to optional i/os, so that
+	 * we can issue contiguous writes even if they are larger than the
+	 * aggregation limit.
 	 */
 	while ((dio = AVL_NEXT(t, last)) != NULL &&
 	    (dio->io_flags & ZIO_FLAG_AGG_INHERIT) == flags &&
-	    IO_SPAN(first, dio) <= limit &&
+	    (IO_SPAN(first, dio) <= limit ||
+	    (dio->io_flags & ZIO_FLAG_OPTIONAL)) &&
 	    IO_GAP(last, dio) <= maxgap) {
 		last = dio;
 		if (!(last->io_flags & ZIO_FLAG_OPTIONAL))
@@ -610,10 +614,16 @@ vdev_queue_aggregate(vdev_queue_t *vq, zio_t *zio)
 	}
 
 	if (stretch) {
-		/* This may be a no-op. */
+		/*
+		 * We are going to include an optional io in our aggregated
+		 * span, thus closing the write gap.  Only mandatory i/os can
+		 * start aggregated spans, so make sure that the next i/o
+		 * after our span is mandatory.
+		 */
 		dio = AVL_NEXT(t, last);
 		dio->io_flags &= ~ZIO_FLAG_OPTIONAL;
 	} else {
+		/* do not include the optional i/o */
 		while (last != mandatory && last != first) {
 			ASSERT(last->io_flags & ZIO_FLAG_OPTIONAL);
 			last = AVL_PREV(t, last);
@@ -625,7 +635,6 @@ vdev_queue_aggregate(vdev_queue_t *vq, zio_t *zio)
 		return (NULL);
 
 	size = IO_SPAN(first, last);
-	ASSERT3U(size, <=, limit);
 
 	abd = abd_alloc_for_io(size, B_TRUE);
 	if (abd == NULL)