When array convert to clustered bitmap, the safe_mode_delay doesn't clean and vice versa.
the /sys/block/mdX/md/safe_mode_delay keep original value after changing bitmap type.
in safe_delay_store(), the code forbids setting mddev->safemode_delay when array is clustered.
So in cluster-md env, the expected safemode_delay value should be 0.
reproduction steps:
```
node1 # mdadm --zero-superblock /dev/sd{b,c,d}
node1 # mdadm -C /dev/md0 -b internal -e 1.2 -n 2 -l mirror /dev/sdb /dev/sdc
node1 # cat /sys/block/md0/md/safe_mode_delay
0.204
node1 # mdadm -G /dev/md0 -b none
node1 # mdadm --grow /dev/md0 --bitmap=clustered
node1 # cat /sys/block/md0/md/safe_mode_delay
0.204 <== doesn't change, should ZERO for cluster-md
node1 # mdadm --zero-superblock /dev/sd{b,c,d}
node1 # mdadm -C /dev/md0 -b clustered -e 1.2 -n 2 -l mirror /dev/sdb /dev/sdc
node1 # cat /sys/block/md0/md/safe_mode_delay
0.000
node1 # mdadm -G /dev/md0 -b none
node1 # cat /sys/block/md0/md/safe_mode_delay
0.000 <== doesn't change, should default value
```
Neil said md_setup_cluster/md_cluster_stop are good places to fix.
After investigation, md_setup_cluster() is a good place for setting,
but md_cluster_stop are not pair for restoring.
see below flow:
(user space)
mdadm -C /dev/md0 -b clustered -e 1.2 -n 2 -l mirror /dev/sda /dev/sdb
mdadm --grow /dev/md0 -b none
(kernel space)
SET_ARRAY_INFO
update_array_info
+ mddev->bitmap_info.nodes = 0;
+ md_cluster_ops->leave(mddev)
+ md_bitmap_destroy
md_bitmap_free //won't trigger md_cluster_stop() because above set 0.
Signed-off-by: Zhao Heming <heming.zhao@xxxxxxxx>
---
v2:
- change setting path from location_store to md_setup_cluster
- add restoring path
---
drivers/md/md.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index f567f53..f082f5c 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -101,6 +101,8 @@ static int remove_and_add_spares(struct mddev *mddev,
* count by 2 for every hour elapsed between read errors.
*/
#define MD_DEFAULT_MAX_CORRECTED_READ_ERRORS 20
+/* Default safemode delay: 200 msec */
+#define DEFAULT_SAFEMODE_DELAY ((200 * HZ)/1000 +1)
/*
* Current RAID-1,4,5 parallel reconstruction 'guaranteed speed limit'
* is 1000 KB/sec, so the extra system load does not show up that much.
@@ -5982,7 +5984,7 @@ int md_run(struct mddev *mddev)
if (mddev_is_clustered(mddev))
mddev->safemode_delay = 0;
else
- mddev->safemode_delay = (200 * HZ)/1000 +1; /* 200 msec delay */
+ mddev->safemode_delay = DEFAULT_SAFEMODE_DELAY;
mddev->in_sync = 1;
smp_wmb();
spin_lock(&mddev->lock);
@@ -7361,6 +7363,7 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
mddev->bitmap_info.nodes = 0;
md_cluster_ops->leave(mddev);
+ mddev->safemode_delay = DEFAULT_SAFEMODE_DELAY;
}
mddev_suspend(mddev);
md_bitmap_destroy(mddev);
@@ -8366,6 +8369,7 @@ int md_setup_cluster(struct mddev *mddev, int nodes)
}
spin_unlock(&pers_lock);
+ mddev->safemode_delay = 0;
return md_cluster_ops->join(mddev, nodes);
}
--
1.8.3.1
