Move gethrtime() calls out of vdev queue lock

This dramatically reduces the lock contention on systems with slower
(non-TSC) timecounters.  With TSC the difference is minimal, but since
this lock is pretty congested, any improvement counts.  Plus I don't
see any reason to do it under the lock other than the latency of the
lock itself, which this change actually reduces.

Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Sponsored-By: iXsystems, Inc.
Closes openzfs#12281

module/zfs/vdev_queue.c

@@ -954,9 +954,9 @@ vdev_queue_io(zio_t *zio)
 	}
 
 	zio->io_flags |= ZIO_FLAG_DONT_CACHE | ZIO_FLAG_DONT_QUEUE;
+	zio->io_timestamp = gethrtime();
 
 	mutex_enter(&vq->vq_lock);
-	zio->io_timestamp = gethrtime();
 	vdev_queue_io_add(vq, zio);
 	nio = vdev_queue_io_to_issue(vq);
 	mutex_exit(&vq->vq_lock);
@@ -978,14 +978,13 @@ vdev_queue_io_done(zio_t *zio)
 	vdev_queue_t *vq = &zio->io_vd->vdev_queue;
 	zio_t *nio;
 
-	mutex_enter(&vq->vq_lock);
+	hrtime_t now = gethrtime();
+	vq->vq_io_complete_ts = now;
+	vq->vq_io_delta_ts = zio->io_delta = now - zio->io_timestamp;
 
+	mutex_enter(&vq->vq_lock);
 	vdev_queue_pending_remove(vq, zio);
 
-	zio->io_delta = gethrtime() - zio->io_timestamp;
-	vq->vq_io_complete_ts = gethrtime();
-	vq->vq_io_delta_ts = vq->vq_io_complete_ts - zio->io_timestamp;
-
 	while ((nio = vdev_queue_io_to_issue(vq)) != NULL) {
 		mutex_exit(&vq->vq_lock);
 		if (nio->io_done == vdev_queue_agg_io_done) {