LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Gang He <ghe@suse.com>
To: Joseph Qi <joseph.qi@linux.alibaba.com>,
	mark@fasheh.com, jlbec@evilplan.org,
	Wengang Wang <wen.gang.wang@oracle.com>
Cc: linux-kernel@vger.kernel.org, ocfs2-devel@oss.oracle.com,
	akpm@linux-foundation.org
Subject: Re: [PATCH] ocfs2: reflink deadlock when clone file to the same directory simultaneously
Date: Thu, 19 Aug 2021 09:51:59 +0800	[thread overview]
Message-ID: <a0a9710f-461a-99c8-92f6-a99bb11b3a4e@suse.com> (raw)
In-Reply-To: <86e3d724-3147-ccaa-998f-0f857c575f7e@linux.alibaba.com>



On 2021/8/18 19:20, Joseph Qi wrote:
> 
> 
> On 8/18/21 5:20 PM, Gang He wrote:
>>
>>
>> On 2021/8/13 17:54, Joseph Qi wrote:
>>>
>>>
>>> On 8/9/21 6:08 PM, Gang He wrote:
>>>> Hi Joseph and All,
>>>>
>>>> The deadlock is caused by self-locking on one node.
>>>> There is three node cluster (mounted to /mnt/shared), the user run reflink command to clone the file to the same directory repeatedly,
>>>> e.g.
>>>>    reflink "/mnt/shared/test" \
>>>>    "/mnt/shared/.snapshots/test.`date +%m%d%H%M%S`.`hostname`"
>>>>
>>>> After a while, the reflink process on each node is hung, the file system cannot be listed.
>>>> The problematic reflink command process is blocked by itself, e.g. the reflink process is hung at ghe-sle15sp2-nd2,
>>>> kernel: task:reflink         state:D stack:    0 pid:16992 ppid:  4530
>>>> kernel: Call Trace:
>>>> kernel:  __schedule+0x2fd/0x750
>>>> kernel:  ? try_to_wake_up+0x17b/0x4e0
>>>> kernel:  schedule+0x2f/0xa0
>>>> kernel:  schedule_timeout+0x1cc/0x310
>>>> kernel:  ? __wake_up_common+0x74/0x120
>>>> kernel:  wait_for_completion+0xba/0x140
>>>> kernel:  ? wake_up_q+0xa0/0xa0
>>>> kernel:  __ocfs2_cluster_lock.isra.41+0x3b5/0x820 [ocfs2]
>>>> kernel:  ? ocfs2_inode_lock_full_nested+0x1fc/0x960 [ocfs2]
>>>> kernel:  ocfs2_inode_lock_full_nested+0x1fc/0x960 [ocfs2]
>>>> kernel:  ocfs2_init_security_and_acl+0xbe/0x1d0 [ocfs2]
>>>> kernel:  ocfs2_reflink+0x436/0x4c0 [ocfs2]
>>>> kernel:  ? ocfs2_reflink_ioctl+0x2ca/0x360 [ocfs2]
>>>> kernel:  ocfs2_reflink_ioctl+0x2ca/0x360 [ocfs2]
>>>> kernel:  ocfs2_ioctl+0x25e/0x670 [ocfs2]
>>>> kernel:  do_vfs_ioctl+0xa0/0x680
>>>> kernel:  ksys_ioctl+0x70/0x80
>>>>
>>>> In fact, the destination directory(.snapshots) inode dlm lock was acquired by ghe-sle15sp2-nd2, next there is bast message from other nodes to ask ghe-sle15sp2-nd2 downconvert lock, but the operation failed, the kernel message is printed like,
>>>> kernel: (ocfs2dc-AA35DD9,2560,3):ocfs2_downconvert_lock:3660 ERROR: DLM error -16 while calling ocfs2_dlm_lock on resource M0000000000000000046e0200000000
>>>> kernel: (ocfs2dc-AA35DD9,2560,3):ocfs2_unblock_lock:3904 ERROR: status = -16
>>>> kernel: (ocfs2dc-AA35DD9,2560,3):ocfs2_process_blocked_lock:4303 ERROR: status = -16
>>>>
>>>> Then, the reflink process tries to acquire this directory inode dlm lock, the process is blocked, the dlm lock resource in memory looks like
>>>>
>>>>       l_name = "M0000000000000000046e0200000000",
>>>>       l_ro_holders = 0,
>>>>       l_ex_holders = 0,
>>>>       l_level = 5 '\005',
>>>>       l_requested = 0 '\000',
>>>>       l_blocking = 5 '\005',
>>>>       l_type = 0 '\000',
>>>>       l_action = 0 '\000',
>>>>       l_unlock_action = 0 '\000',
>>>>       l_pending_gen = 645948,
>>>>
>>>>
>>>> So far, I do not know what makes dlm lock function failed, it also looks we do not handle this failure case in dlmglue layer, but I always reproduce this hang with my test script, e.g.
>>>>
>>>>     loop=1
>>>>     while ((loop++)) ; do
>>>>           for i in `seq 1 100`; do
>>>>             reflink "/mnt/shared/test" "/mnt/shared/.snapshots /test.${loop}.${i}.`date +%m%d%H%M%S`.`hostname`"
>>>>           done
>>>>           usleep 500000
>>>>           rm -f /mnt/shared/.snapshots/testnode1.qcow2.*.`hostname`
>>>>     done
>>>>
>>>> My patch changes multiple acquiring dest directory inode dlm lock during in ocfs2_reflink function, it avoids the hang issue happen again.The code change also can improve reflink performance in this case.
>>>>
>>>> Thanks
>>>> Gang
>>>
>>> 'status = -16' implies DLM_CANCELGRANT.
>>> Do you use stack user instead of o2cb? If yes, can you try o2cb with
>>> your reproducer?
>>
>> I setup o2cb based ocfs2 clusters with sle15sp2 and oracleLinux8u4.
>> After two day testing with the same script, I did not encounter dlm_lock downconvert failure, the hang issue did not happen.
>> After my patch was applied, there was not any side effect, the reflink performance was doubled in the case.
>>
> 
> Do you mean the hang only happens on stack user?
Yes.
Why? since o2cb based dlm_lock did not return error -16 when downcovert 
dlm lock during the whole testing.
But pmck based dlm_lock retuned error -16 during the testing, then we 
did not handle this error further in dlmglue layer, next encounter the 
hang issue when dlm_lock acquire the lock. Maybe there is a race 
condition when using dlm_lock/dlm_unlock(cancel) in dlmglue layer.
Anyway, the problem belongs to ocfs2 own parts.

> IMO, we'd better directly fix the stack user hang first, and then optimize
> reflink performance.
Before we fix the potential problem in dlmglue layer, I suggest to 
accept this patch first. Since the dlmglue layer code is kind of 
compliant, we need to carefully modify this part of the code. But this 
patch can workaround dlm_lock failure(-16) problem for pcmk stack, 
meanwhile, it also can improve the performance.

Thanks
Gang


> 
> Thanks,
> Joseph
> 


  reply	other threads:[~2021-08-19  1:50 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-29 11:02 Gang He
2021-07-29 22:07 ` [Ocfs2-devel] " Wengang Wang
2021-07-30  6:16   ` Gang He
2021-07-30 16:35     ` Wengang Wang
2021-08-02  4:35       ` Gang He
2021-08-02 18:22         ` Wengang Wang
2021-08-03  1:00           ` Gang He
2021-08-04  1:57 ` Joseph Qi
2021-08-09 10:08   ` Gang He
2021-08-13  9:54     ` Joseph Qi
2021-08-18  9:20       ` Gang He
2021-08-18 11:20         ` Joseph Qi
2021-08-19  1:51           ` Gang He [this message]
2021-08-19  2:02             ` Joseph Qi
2021-08-19  6:31               ` Gang He
2021-08-26  5:56                 ` [Ocfs2-devel] " Gang He

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=a0a9710f-461a-99c8-92f6-a99bb11b3a4e@suse.com \
    --to=ghe@suse.com \
    --cc=akpm@linux-foundation.org \
    --cc=jlbec@evilplan.org \
    --cc=joseph.qi@linux.alibaba.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mark@fasheh.com \
    --cc=ocfs2-devel@oss.oracle.com \
    --cc=wen.gang.wang@oracle.com \
    --subject='Re: [PATCH] ocfs2: reflink deadlock when clone file to the same directory simultaneously' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).