path: root/drivers/block/drbd/drbd_worker.c
diff options
authorLars Ellenberg <lars.ellenberg@linbit.com>2012-09-27 15:18:21 +0200
committerPhilipp Reisner <philipp.reisner@linbit.com>2012-11-09 14:11:41 +0100
commitedc9f5eb7afa3d832f540fcfe10e3e1087e6f527 (patch)
treeeba63d771575a42a6aa81bd55a59f7d6253d18ea /drivers/block/drbd/drbd_worker.c
parente34b677d09ce375a87acd0360537cbed33881b0c (diff)
drbd: always write bitmap on detach
If we detach due to local read-error (which sets a bit in the bitmap), stay Primary, and then re-attach (which re-reads the bitmap from disk), we potentially lost the "out-of-sync" (or, "bad block") information in the bitmap. Always (try to) write out the changed bitmap pages before going diskless. That way, we don't lose the bit for the bad block, the next resync will fetch it from the peer, and rewrite it locally, which may result in block reallocation in some lower layer (or the hardware), and thereby "heal" the bad blocks. If the bitmap writeout errors out as well, we will (again: try to) mark the "we need a full sync" bit in our super block, if it was a READ error; writes are covered by the activity log already. If that superblock does not make it to disk either, we are sorry. Maybe we just lost an entire disk or controller (or iSCSI connection), and there actually are no bad blocks at all, so we don't need to re-fetch from the peer, there is no "auto-healing" necessary. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Diffstat (limited to 'drivers/block/drbd/drbd_worker.c')
1 files changed, 2 insertions, 2 deletions
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index d348260301f..64a7305c678 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -106,7 +106,7 @@ void drbd_endio_read_sec_final(struct drbd_peer_request *peer_req) __releases(lo
if (list_empty(&mdev->read_ee))
if (test_bit(__EE_WAS_ERROR, &peer_req->flags))
- __drbd_chk_io_error(mdev, DRBD_IO_ERROR);
+ __drbd_chk_io_error(mdev, DRBD_READ_ERROR);
spin_unlock_irqrestore(&mdev->tconn->req_lock, flags);
drbd_queue_work(&mdev->tconn->sender_work, &peer_req->w);
@@ -147,7 +147,7 @@ static void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req) __rel
do_wake = list_empty(block_id == ID_SYNCER ? &mdev->sync_ee : &mdev->active_ee);
if (test_bit(__EE_WAS_ERROR, &peer_req->flags))
- __drbd_chk_io_error(mdev, DRBD_IO_ERROR);
+ __drbd_chk_io_error(mdev, DRBD_WRITE_ERROR);
spin_unlock_irqrestore(&mdev->tconn->req_lock, flags);
if (block_id == ID_SYNCER)