aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorH. Peter Anvin <hpa@zytor.com>2013-06-12 07:37:43 -0700
committerNeilBrown <neilb@suse.de>2013-06-13 14:49:54 +1000
commit5026d7a9b2f3eb1f9bda66c18ac6bc3036ec9020 (patch)
treed87edf6a82c43ec53d43aed19ef6710fac6a1b67
parente2d59925221cd562e07fee38ec8839f7209ae603 (diff)
md/raid1,5,10: Disable WRITE SAME until a recovery strategy is in place
There are cases where the kernel will believe that the WRITE SAME command is supported by a block device which does not, in fact, support WRITE SAME. This currently happens for SATA drivers behind a SAS controller, but there are probably a hundred other ways that can happen, including drive firmware bugs. After receiving an error for WRITE SAME the block layer will retry the request as a plain write of zeroes, but mdraid will consider the failure as fatal and consider the drive failed. This has the effect that all the mirrors containing a specific set of data are each offlined in very rapid succession resulting in data loss. However, just bouncing the request back up to the block layer isn't ideal either, because the whole initial request-retry sequence should be inside the write bitmap fence, which probably means that md needs to do its own conversion of WRITE SAME to write zero. Until the failure scenario has been sorted out, disable WRITE SAME for raid1, raid5, and raid10. [neilb: added raid5] This patch is appropriate for any -stable since 3.7 when write_same support was added. Cc: stable@vger.kernel.org Signed-off-by: H. Peter Anvin <hpa@linux.intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
-rw-r--r--drivers/md/raid1.c4
-rw-r--r--drivers/md/raid10.c3
-rw-r--r--drivers/md/raid5.c4
3 files changed, 6 insertions, 5 deletions
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 5208e9d1aff..e02ad445090 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -2837,8 +2837,8 @@ static int run(struct mddev *mddev)
return PTR_ERR(conf);
if (mddev->queue)
- blk_queue_max_write_same_sectors(mddev->queue,
- mddev->chunk_sectors);
+ blk_queue_max_write_same_sectors(mddev->queue, 0);
+
rdev_for_each(rdev, mddev) {
if (!mddev->gendisk)
continue;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index aa9ed304951..06c2cbe046e 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -3651,8 +3651,7 @@ static int run(struct mddev *mddev)
if (mddev->queue) {
blk_queue_max_discard_sectors(mddev->queue,
mddev->chunk_sectors);
- blk_queue_max_write_same_sectors(mddev->queue,
- mddev->chunk_sectors);
+ blk_queue_max_write_same_sectors(mddev->queue, 0);
blk_queue_io_min(mddev->queue, chunk_size);
if (conf->geo.raid_disks % conf->geo.near_copies)
blk_queue_io_opt(mddev->queue, chunk_size * conf->geo.raid_disks);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 4a7be455d6d..26ee39936a2 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5465,7 +5465,7 @@ static int run(struct mddev *mddev)
if (mddev->major_version == 0 &&
mddev->minor_version > 90)
rdev->recovery_offset = reshape_offset;
-
+
if (rdev->recovery_offset < reshape_offset) {
/* We need to check old and new layout */
if (!only_parity(rdev->raid_disk,
@@ -5588,6 +5588,8 @@ static int run(struct mddev *mddev)
*/
mddev->queue->limits.discard_zeroes_data = 0;
+ blk_queue_max_write_same_sectors(mddev->queue, 0);
+
rdev_for_each(rdev, mddev) {
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);