First potential patch... clear mddev->gendisk->queue's
max_write_same_sectors to stop block from sending these cmds...
>From 2607192fe0b8de266c86943b5c5a469e9f7a0e71 Mon Sep 17 00:00:00 2001
From: Joe Lawrence <joe.lawrence@xxxxxxxxxxx>
Date: Mon, 10 Dec 2012 14:21:29 -0500
Subject: [PATCH] MD Raid1 allows WRITE SAME cmds it doesn't currently handle
The MD Raid1 code calls disk_stack_limits to merge limits for its top level
gendisk with each bottom level block device. Since blk_set_stacking_limits
sets the initial max_write_same_sectors to UINT_MAX, disk_stack_limits will
settle on the lowest value of max_write_same_sectors across the underlying
block devices. If this happens to be non-zero, the block layer will pass bios
with REQ_WRITE_SAME set. The MD Raid1 code does not appear to handle this
flag so explicitly turn off WRITE SAME by zeroing the top level MD device
max_write_same_sectors.
Signed-off-by: Joe Lawrence <joe.lawrence@xxxxxxxxxxx>
---
drivers/md/raid1.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 636bae0..0820f4e 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1516,6 +1516,8 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
p = conf->mirrors+mirror;
if (!p->rdev) {
+ /* MD Raid1 doesn't support WRITE SAME. */
+ blk_queue_max_write_same_sectors(mddev->gendisk->queue, 0);
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);
@@ -2822,6 +2824,8 @@ static int run(struct mddev *mddev)
rdev_for_each(rdev, mddev) {
if (!mddev->gendisk)
continue;
+ /* MD Raid1 doesn't support WRITE SAME. */
+ blk_queue_max_write_same_sectors(mddev->gendisk->queue, 0);
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);
if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
--
1.7.11.7
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
