summaryrefslogtreecommitdiff
path: root/drivers
diff options
context:
space:
mode:
authorNeilBrown <neilb@suse.de>2009-11-13 17:47:00 +1100
committerNeilBrown <neilb@suse.de>2009-11-13 17:47:00 +1100
commitc148ffdcda00b6599b70f8b65e6a1fadd1dbb127 (patch)
tree3d50cc9dbef926f62a588dc1f45f1df304e1bf31 /drivers
parent7ef90146a14c2bb1de2e22399f147ebec5b74f0b (diff)
md/raid5: Allow dirty-degraded arrays to be assembled when only party is degraded.
Normally is it not safe to allow a raid5 that is both dirty and degraded to be assembled without explicit request from that admin, as it can cause hidden data corruption. This is because 'dirty' means that the parity cannot be trusted, and 'degraded' means that the parity needs to be used. However, if the device that is missing contains only parity, then there is no issue and assembly can continue. This particularly applies when a RAID5 is being converted to a RAID6 and there is an unclean shutdown while the conversion is happening. So check for whether the degraded space only contains parity, and in that case, allow the assembly. Signed-off-by: NeilBrown <neilb@suse.de>
Diffstat (limited to 'drivers')
-rw-r--r--drivers/md/raid5.c79
1 files changed, 75 insertions, 4 deletions
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index ab40529bdabe..d29215d966da 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -4823,11 +4823,40 @@ static raid5_conf_t *setup_conf(mddev_t *mddev)
return ERR_PTR(-ENOMEM);
}
+
+static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded)
+{
+ switch (algo) {
+ case ALGORITHM_PARITY_0:
+ if (raid_disk < max_degraded)
+ return 1;
+ break;
+ case ALGORITHM_PARITY_N:
+ if (raid_disk >= raid_disks - max_degraded)
+ return 1;
+ break;
+ case ALGORITHM_PARITY_0_6:
+ if (raid_disk == 0 ||
+ raid_disk == raid_disks - 1)
+ return 1;
+ break;
+ case ALGORITHM_LEFT_ASYMMETRIC_6:
+ case ALGORITHM_RIGHT_ASYMMETRIC_6:
+ case ALGORITHM_LEFT_SYMMETRIC_6:
+ case ALGORITHM_RIGHT_SYMMETRIC_6:
+ if (raid_disk == raid_disks - 1)
+ return 1;
+ }
+ return 0;
+}
+
static int run(mddev_t *mddev)
{
raid5_conf_t *conf;
int working_disks = 0, chunk_size;
+ int dirty_parity_disks = 0;
mdk_rdev_t *rdev;
+ sector_t reshape_offset = 0;
if (mddev->recovery_cp != MaxSector)
printk(KERN_NOTICE "raid5: %s is not clean"
@@ -4861,6 +4890,7 @@ static int run(mddev_t *mddev)
"on a stripe boundary\n");
return -EINVAL;
}
+ reshape_offset = here_new * mddev->new_chunk_sectors;
/* here_new is the stripe we will write to */
here_old = mddev->reshape_position;
sector_div(here_old, mddev->chunk_sectors *
@@ -4916,10 +4946,51 @@ static int run(mddev_t *mddev)
/*
* 0 for a fully functional array, 1 or 2 for a degraded array.
*/
- list_for_each_entry(rdev, &mddev->disks, same_set)
- if (rdev->raid_disk >= 0 &&
- test_bit(In_sync, &rdev->flags))
+ list_for_each_entry(rdev, &mddev->disks, same_set) {
+ if (rdev->raid_disk < 0)
+ continue;
+ if (test_bit(In_sync, &rdev->flags))
working_disks++;
+ /* This disc is not fully in-sync. However if it
+ * just stored parity (beyond the recovery_offset),
+ * when we don't need to be concerned about the
+ * array being dirty.
+ * When reshape goes 'backwards', we never have
+ * partially completed devices, so we only need
+ * to worry about reshape going forwards.
+ */
+ /* Hack because v0.91 doesn't store recovery_offset properly. */
+ if (mddev->major_version == 0 &&
+ mddev->minor_version > 90)
+ rdev->recovery_offset = reshape_offset;
+
+ printk("%d: w=%d pa=%d pr=%d m=%d a=%d r=%d op1=%d op2=%d\n",
+ rdev->raid_disk, working_disks, conf->prev_algo,
+ conf->previous_raid_disks, conf->max_degraded,
+ conf->algorithm, conf->raid_disks,
+ only_parity(rdev->raid_disk,
+ conf->prev_algo,
+ conf->previous_raid_disks,
+ conf->max_degraded),
+ only_parity(rdev->raid_disk,
+ conf->algorithm,
+ conf->raid_disks,
+ conf->max_degraded));
+ if (rdev->recovery_offset < reshape_offset) {
+ /* We need to check old and new layout */
+ if (!only_parity(rdev->raid_disk,
+ conf->algorithm,
+ conf->raid_disks,
+ conf->max_degraded))
+ continue;
+ }
+ if (!only_parity(rdev->raid_disk,
+ conf->prev_algo,
+ conf->previous_raid_disks,
+ conf->max_degraded))
+ continue;
+ dirty_parity_disks++;
+ }
mddev->degraded = (max(conf->raid_disks, conf->previous_raid_disks)
- working_disks);
@@ -4935,7 +5006,7 @@ static int run(mddev_t *mddev)
mddev->dev_sectors &= ~(mddev->chunk_sectors - 1);
mddev->resync_max_sectors = mddev->dev_sectors;
- if (mddev->degraded > 0 &&
+ if (mddev->degraded > dirty_parity_disks &&
mddev->recovery_cp != MaxSector) {
if (mddev->ok_start_degraded)
printk(KERN_WARNING