Missing devices should be recorded and cause array to operate in degraded mode.

When specifying the devices that compose a DM RAID array, it is possible to denote
failed or missing devices with '-'s. When this occurs, we must set mddev->degraded.
Otherwise, if the missing/failed device comes back, the bitmap will not have
recorded what areas of the array need to be recovered - the array will be assumed to
be in-sync! Additionally, we must mark in the superblock which device was specified
as missing/failed. We do this by setting the appropriate bit in the 'failed_devices'
field. Finally, we must also ensure that the superblock is properly recorded by
setting 'MD_CHANGE_DEVS' in raid_resume. If we do not cause the superblock to be
rewritten by the resume function, it is possible for a stale superblock to be
written by an out-going in-active table (during 'raid_dtr').

Signed-off-by: Jonathan Brassow <jbrassow@redhat.com>

Index: linux-upstream/drivers/md/dm-raid.c
================================================== =================
--- linux-upstream.orig/drivers/md/dm-raid.c
+++ linux-upstream/drivers/md/dm-raid.c
@@ -226,6 +226,7 @@ static int dev_parms(struct raid_set *rs
if (rs->dev[i].meta_dev)
return -EINVAL;

+ rs->md.degraded++;
continue;
}

@@ -606,6 +607,7 @@ static int read_disk_sb(struct md_rdev *
if (!sync_page_io(rdev, 0, size, rdev->sb_page, READ, 1)) {
DMERR("Failed to read superblock of device at position %d",
rdev->raid_disk);
+ rdev->mddev->degraded++;
set_bit(Faulty, &rdev->flags);
return -EINVAL;
}
@@ -617,16 +619,18 @@ static int read_disk_sb(struct md_rdev *

static void super_sync(struct mddev *mddev, struct md_rdev *rdev)
{
- struct md_rdev *r;
+ int i;
uint64_t failed_devices;
struct dm_raid_superblock *sb;
+ struct raid_set *rs = container_of(mddev, struct raid_set, md);

sb = page_address(rdev->sb_page);
failed_devices = le64_to_cpu(sb->failed_devices);

- rdev_for_each(r, mddev)
- if ((r->raid_disk >= 0) && test_bit(Faulty, &r->flags))
- failed_devices |= (1ULL << r->raid_disk);
+ for (i = 0; i < mddev->raid_disks; i++)
+ if (!rs->dev[i].data_dev ||
+ test_bit(Faulty, &(rs->dev[i].rdev.flags)))
+ failed_devices |= (1ULL << i);

memset(sb, 0, sizeof(*sb));

@@ -1252,6 +1256,7 @@ static void raid_resume(struct dm_target
{
struct raid_set *rs = ti->private;

+ set_bit(MD_CHANGE_DEVS, &rs->md.flags);
if (!rs->bitmap_loaded) {
bitmap_load(&rs->md);
rs->bitmap_loaded = 1;


--
dm-devel mailing list
dm-devel@redhat.com
https://www.redhat.com/mailman/listinfo/dm-devel