summaryrefslogtreecommitdiffstats
path: root/fs/btrfs
diff options
context:
space:
mode:
authorLiu Bo <bo.li.liu@oracle.com>2018-01-02 13:36:41 -0700
committerDavid Sterba <dsterba@suse.com>2018-01-22 16:08:20 +0100
commit8810f7517a3bc4ca2d41d022446d3f5fd6b77c09 (patch)
tree411e57271e5b51b0af8c75ce1a345e8093d0eb73 /fs/btrfs
parent762221f095e3932669093466aaf4b85ed9ad2ac1 (diff)
downloadlinux-8810f7517a3bc4ca2d41d022446d3f5fd6b77c09.tar.bz2
Btrfs: make raid6 rebuild retry more
There is a scenario that can end up with rebuild process failing to return good content, i.e. suppose that all disks can be read without problems and if the content that was read out doesn't match its checksum, currently for raid6 btrfs at most retries twice, - the 1st retry is to rebuild with all other stripes, it'll eventually be a raid5 xor rebuild, - if the 1st fails, the 2nd retry will deliberately fail parity p so that it will do raid6 style rebuild, however, the chances are that another non-parity stripe content also has something corrupted, so that the above retries are not able to return correct content, and users will think of this as data loss. More seriouly, if the loss happens on some important internal btree roots, it could refuse to mount. This extends btrfs to do more retries and each retry fails only one stripe. Since raid6 can tolerate 2 disk failures, if there is one more failure besides the failure on which we're recovering, this can always work. The worst case is to retry as many times as the number of raid6 disks, but given the fact that such a scenario is really rare in practice, it's still acceptable. Signed-off-by: Liu Bo <bo.li.liu@oracle.com> Signed-off-by: David Sterba <dsterba@suse.com>
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/raid56.c18
-rw-r--r--fs/btrfs/volumes.c9
2 files changed, 22 insertions, 5 deletions
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 9fa45e061953..a1dfdd35e7ab 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -2159,11 +2159,21 @@ int raid56_parity_recover(struct btrfs_fs_info *fs_info, struct bio *bio,
}
/*
- * reconstruct from the q stripe if they are
- * asking for mirror 3
+ * Loop retry:
+ * for 'mirror == 2', reconstruct from all other stripes.
+ * for 'mirror_num > 2', select a stripe to fail on every retry.
*/
- if (mirror_num == 3)
- rbio->failb = rbio->real_stripes - 2;
+ if (mirror_num > 2) {
+ /*
+ * 'mirror == 3' is to fail the p stripe and
+ * reconstruct from the q stripe. 'mirror > 3' is to
+ * fail a data stripe and reconstruct from p+q stripe.
+ */
+ rbio->failb = rbio->real_stripes - (mirror_num - 1);
+ ASSERT(rbio->failb > 0);
+ if (rbio->failb <= rbio->faila)
+ rbio->failb--;
+ }
ret = lock_stripe_add(rbio);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index f85991a2585c..7ebf53cb4269 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -5167,7 +5167,14 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
else if (map->type & BTRFS_BLOCK_GROUP_RAID5)
ret = 2;
else if (map->type & BTRFS_BLOCK_GROUP_RAID6)
- ret = 3;
+ /*
+ * There could be two corrupted data stripes, we need
+ * to loop retry in order to rebuild the correct data.
+ *
+ * Fail a stripe at a time on every retry except the
+ * stripe under reconstruction.
+ */
+ ret = map->num_stripes;
else
ret = 1;
free_extent_map(em);