[PATCH] md: define raid5_mergeable_bvec

This will encourage read request to be on only one device, so we will often be
able to bypass the cache for read requests.
Signed-off-by: Neil Brown <neilb@suse.de>
Cc: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

drivers/md/raid5.c

@@ -2611,6 +2611,28 @@ static int raid5_congested(void *data, int bits)
 	return 0;
 }
 
+/* We want read requests to align with chunks where possible,
+ * but write requests don't need to.
+ */
+static int raid5_mergeable_bvec(request_queue_t *q, struct bio *bio, struct bio_vec *biovec)
+{
+	mddev_t *mddev = q->queuedata;
+	sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
+	int max;
+	unsigned int chunk_sectors = mddev->chunk_size >> 9;
+	unsigned int bio_sectors = bio->bi_size >> 9;
+
+	if (bio_data_dir(bio))
+		return biovec->bv_len; /* always allow writes to be mergeable */
+
+	max =  (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;
+	if (max < 0) max = 0;
+	if (max <= biovec->bv_len && bio_sectors == 0)
+		return biovec->bv_len;
+	else
+		return max;
+}
+
 static int make_request(request_queue_t *q, struct bio * bi)
 {
 	mddev_t *mddev = q->queuedata;
@@ -3320,6 +3342,8 @@ static int run(mddev_t *mddev)
 	mddev->array_size =  mddev->size * (conf->previous_raid_disks -
 					    conf->max_degraded);
 
+	blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec);
+
 	return 0;
 abort:
 	if (conf) {