hollalinux
/
linux-sg2042
mirror of https://github.com/sophgo/linux-riscv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

md-cluster: release RESYNC lock after the last resync message 

All the RESYNC messages are sent with resync lock held, the only
exception is resync_finish which releases resync_lockres before
send the last resync message, this should be changed as well.
Otherwise, we can see deadlock issue as follows:

clustermd2-gqjiang2:~ # cat /proc/mdstat
Personalities : [raid10] [raid1]
md0 : active raid1 sdg[0] sdf[1]
      134144 blocks super 1.2 [2/2] [UU]
      [===================>.]  resync = 99.6% (134144/134144) finish=0.0min speed=26K/sec
      bitmap: 1/1 pages [4KB], 65536KB chunk

unused devices: <none>
clustermd2-gqjiang2:~ # ps aux|grep md|grep D
root     20497  0.0  0.0      0     0 ?        D    16:00   0:00 [md0_raid1]
clustermd2-gqjiang2:~ # cat /proc/20497/stack
[<ffffffffc05ff51e>] dlm_lock_sync+0x8e/0xc0 [md_cluster]
[<ffffffffc05ff7e8>] __sendmsg+0x98/0x130 [md_cluster]
[<ffffffffc05ff900>] sendmsg+0x20/0x30 [md_cluster]
[<ffffffffc05ffc35>] resync_info_update+0xb5/0xc0 [md_cluster]
[<ffffffffc0593e84>] md_reap_sync_thread+0x134/0x170 [md_mod]
[<ffffffffc059514c>] md_check_recovery+0x28c/0x510 [md_mod]
[<ffffffffc060c882>] raid1d+0x42/0x800 [raid1]
[<ffffffffc058ab61>] md_thread+0x121/0x150 [md_mod]
[<ffffffff9a0a5b3f>] kthread+0xff/0x140
[<ffffffff9a800235>] ret_from_fork+0x35/0x40
[<ffffffffffffffff>] 0xffffffffffffffff

clustermd-gqjiang1:~ # ps aux|grep md|grep D
root     20531  0.0  0.0      0     0 ?        D    16:00   0:00 [md0_raid1]
root     20537  0.0  0.0      0     0 ?        D    16:00   0:00 [md0_cluster_rec]
root     20676  0.0  0.0      0     0 ?        D    16:01   0:00 [md0_resync]
clustermd-gqjiang1:~ # cat /proc/mdstat
Personalities : [raid10] [raid1]
md0 : active raid1 sdf[1] sdg[0]
      134144 blocks super 1.2 [2/2] [UU]
      [===================>.]  resync = 97.3% (131072/134144) finish=8076.8min speed=0K/sec
      bitmap: 1/1 pages [4KB], 65536KB chunk

unused devices: <none>
clustermd-gqjiang1:~ # cat /proc/20531/stack
[<ffffffffc080974d>] metadata_update_start+0xcd/0xd0 [md_cluster]
[<ffffffffc079c897>] md_update_sb.part.61+0x97/0x820 [md_mod]
[<ffffffffc079f15b>] md_check_recovery+0x29b/0x510 [md_mod]
[<ffffffffc0816882>] raid1d+0x42/0x800 [raid1]
[<ffffffffc0794b61>] md_thread+0x121/0x150 [md_mod]
[<ffffffff9e0a5b3f>] kthread+0xff/0x140
[<ffffffff9e800235>] ret_from_fork+0x35/0x40
[<ffffffffffffffff>] 0xffffffffffffffff
clustermd-gqjiang1:~ # cat /proc/20537/stack
[<ffffffffc0813222>] freeze_array+0xf2/0x140 [raid1]
[<ffffffffc080a56e>] recv_daemon+0x41e/0x580 [md_cluster]
[<ffffffffc0794b61>] md_thread+0x121/0x150 [md_mod]
[<ffffffff9e0a5b3f>] kthread+0xff/0x140
[<ffffffff9e800235>] ret_from_fork+0x35/0x40
[<ffffffffffffffff>] 0xffffffffffffffff
clustermd-gqjiang1:~ # cat /proc/20676/stack
[<ffffffffc080951e>] dlm_lock_sync+0x8e/0xc0 [md_cluster]
[<ffffffffc080957f>] lock_token+0x2f/0xa0 [md_cluster]
[<ffffffffc0809622>] lock_comm+0x32/0x90 [md_cluster]
[<ffffffffc08098f5>] sendmsg+0x15/0x30 [md_cluster]
[<ffffffffc0809c0a>] resync_info_update+0x8a/0xc0 [md_cluster]
[<ffffffffc08130ba>] raid1_sync_request+0xa9a/0xb10 [raid1]
[<ffffffffc079b8ea>] md_do_sync+0xbaa/0xf90 [md_mod]
[<ffffffffc0794b61>] md_thread+0x121/0x150 [md_mod]
[<ffffffff9e0a5b3f>] kthread+0xff/0x140
[<ffffffff9e800235>] ret_from_fork+0x35/0x40
[<ffffffffffffffff>] 0xffffffffffffffff

Reviewed-by: NeilBrown <neilb@suse.com>
Signed-off-by: Guoqing Jiang <gqjiang@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
This commit is contained in:
Guoqing Jiang 2018-08-31 10:05:57 +08:00 committed by Shaohua Li
parent 1d0ffd2642
commit 41a9504112
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
drivers/md/md-cluster.c
View File

@ -1276,18 +1276,18 @@ static int resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi)
static int resync_finish(struct mddev *mddev)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
int ret = 0;
clear_bit(MD_RESYNCING_REMOTE, &mddev->recovery);
dlm_unlock_sync(cinfo->resync_lockres);
/*
* If resync thread is interrupted so we can't say resync is finished,
* another node will launch resync thread to continue.
*/
if (test_bit(MD_CLOSING, &mddev->flags))
return 0;
else
return resync_info_update(mddev, 0, 0);
if (!test_bit(MD_CLOSING, &mddev->flags))
ret = resync_info_update(mddev, 0, 0);
dlm_unlock_sync(cinfo->resync_lockres);
return ret;
}
static int area_resyncing(struct mddev *mddev, int direction,