mbox series

[v4,0/2] md/cluster bugs fix

Message ID 1605717954-20173-1-git-send-email-heming.zhao@suse.com
Headers show
Series md/cluster bugs fix | expand

Message

heming.zhao@suse.com Nov. 18, 2020, 4:45 p.m. UTC 
Hello List,

There are two patches to fix md-cluster bugs.

The 2 different bugs can use same test script to trigger:

```
ssh root@node2 "mdadm -S --scan"
mdadm -S --scan
for i in {g,h,i};do dd if=/dev/zero of=/dev/sd$i oflag=direct bs=1M \
count=20; done

echo "mdadm create array"
mdadm -C /dev/md0 -b clustered -e 1.2 -n 2 -l mirror /dev/sdg /dev/sdh \
--bitmap-chunk=1M
echo "set up array on node2"
ssh root@node2 "mdadm -A /dev/md0 /dev/sdg /dev/sdh"

sleep 5

mkfs.xfs /dev/md0
mdadm --manage --add /dev/md0 /dev/sdi
mdadm --wait /dev/md0
mdadm --grow --raid-devices=3 /dev/md0

mdadm /dev/md0 --fail /dev/sdg
mdadm /dev/md0 --remove /dev/sdg
mdadm --grow --raid-devices=2 /dev/md0
```

For detail, please check each patch commit log.

-------
v4:
- revise subject & commit log on both patches
- no change for code
v3:
- patch 1/2
  - no change
- patch 2/2
  - use Xiao's solution to fix
  - revise commit log for the "How to fix" part
v2:
- patch 1/2
  - change patch subject
  - add test result in commit log
  - no change for code
- patch 2/2
  - add test result in commit log
  - add error handling of remove_disk in hot_remove_disk
  - add error handling of lock_comm in all caller
  - remove 5s timeout fix in receive side (for process_metadata_update)
v1:
- create patch
-------
Zhao Heming (2):
  md/cluster: block reshape with remote resync job
  md/cluster: fix deadlock when node is doing resync job

 drivers/md/md-cluster.c | 69 +++++++++++++++++++++++------------------
 drivers/md/md.c         | 14 ++++++---
 2 files changed, 49 insertions(+), 34 deletions(-)