md/raid5: split bio for chunk_aligned_read

If a read request fits entirely in a chunk, it will be passed directly to the
underlying device (providing it hasn't failed of course).  If it doesn't fit,
the slightly less efficient path that uses the stripe_cache is used.
Requests that get to the stripe cache are always completely split up as
necessary.

So with RAID5, ripping out the merge_bvec_fn doesn't cause it to stop work,
but could cause it to take the less efficient path more often.

All that is needed to manage this is for 'chunk_aligned_read' do some bio
splitting, much like the RAID0 code does.

Cc: Neil Brown <neilb@suse.de>
Cc: linux-raid@vger.kernel.org
Acked-by: NeilBrown <neilb@suse.de>
Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 085db93..256cc07 100644 (file)
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -4800,7 +4800,7 @@ static int bio_fits_rdev(struct bio *bi)
        return 1;
 }
 
-static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
+static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 {
        struct r5conf *conf = mddev->private;
        int dd_idx;
@@ -4809,7 +4809,7 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
        sector_t end_sector;
 
        if (!in_chunk_boundary(mddev, raid_bio)) {
-               pr_debug("chunk_aligned_read : non aligned\n");
+               pr_debug("%s: non aligned\n", __func__);
                return 0;
        }
        /*
@@ -4886,6 +4886,31 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
        }
 }
 
+static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio)
+{
+       struct bio *split;
+
+       do {
+               sector_t sector = raid_bio->bi_iter.bi_sector;
+               unsigned chunk_sects = mddev->chunk_sectors;
+               unsigned sectors = chunk_sects - (sector & (chunk_sects-1));
+
+               if (sectors < bio_sectors(raid_bio)) {
+                       split = bio_split(raid_bio, sectors, GFP_NOIO, fs_bio_set);
+                       bio_chain(split, raid_bio);
+               } else
+                       split = raid_bio;
+
+               if (!raid5_read_one_chunk(mddev, split)) {
+                       if (split != raid_bio)
+                               generic_make_request(raid_bio);
+                       return split;
+               }
+       } while (split != raid_bio);
+
+       return NULL;
+}
+
 /* __get_priority_stripe - get the next stripe to process
  *
  * Full stripe writes are allowed to pass preread active stripes up until
@@ -5163,9 +5188,11 @@ static void make_request(struct mddev *mddev, struct bio * bi)
         * data on failed drives.
         */
        if (rw == READ && mddev->degraded == 0 &&
-            mddev->reshape_position == MaxSector &&
-            chunk_aligned_read(mddev,bi))
-               return;
+           mddev->reshape_position == MaxSector) {
+               bi = chunk_aligned_read(mddev, bi);
+               if (!bi)
+                       return;
+       }
 
        if (unlikely(bi->bi_rw & REQ_DISCARD)) {
                make_discard_request(mddev, bi);