All of lore.kernel.org
 help / color / mirror / Atom feed
From: Sunil Mushran <sunil.mushran@oracle.com>
To: ocfs2-devel@oss.oracle.com
Subject: [Ocfs2-devel] dlm stress test hangs OCFS2
Date: Mon, 14 Sep 2009 16:57:54 -0700	[thread overview]
Message-ID: <4AAED882.9020601@oracle.com> (raw)
In-Reply-To: <4AAEA64C.3030607@suse.de>

The full trace is available here.
http://oss.oracle.com/~smushran/calltrace_x1

So one sees the following block repeated. It shows that the lock is
being downconverted from EX to NL but also upconverted presumably to EX.

==============================================================
[412.378525] (12732,0):ocfs2_blocking_ast:1025 BAST fired for lockres 
M0000000000000000085e0200000000, blocking 5, level 5 type Meta
[412.378532] (12731,0):ocfs2_process_blocked_lock:3839 lockres 
M0000000000000000085e0200000000 blocked.
[412.378537] (12731,0):ocfs2_prepare_downconvert:3232 lock 
M0000000000000000085e0200000000, new_level = 0, l_blocking = 5
[412.378542] (12731,0):ocfs2_downconvert_lock:3252 lock 
M0000000000000000085e0200000000, level 5 => 0
[412.378554] (12731,0):__lockres_clear_pending:978 lock 
M0000000000000000085e0200000000 Clear; flg=0x557, lpg=268, gen=268
[412.378558] (12731,0):ocfs2_process_blocked_lock:3863 lockres 
M0000000000000000085e0200000000, requeue = no.
[412.378578] (12732,0):ocfs2_locking_ast:1069 lock 
M0000000000000000085e0200000000, action 3, unlock 0
[412.378584] (12732,0):__lockres_clear_pending:972 lock 
M0000000000000000085e0200000000 Abort; flg=0x51, lpg=269, gen=269
[412.378596] (9370,0):__lockres_clear_pending:978 lock 
M0000000000000000085e0200000000 Clear; flg=0x453, lpg=269, gen=269
[412.578719] (12732,0):ocfs2_locking_ast:1069 lock 
M0000000000000000085e0200000000, action 2, unlock 0
[412.578727] (12732,0):__lockres_clear_pending:972 lock 
M0000000000000000085e0200000000 Abort; flg=0x51, lpg=270, gen=270
==============================================================

The BAST
[412.378525] (12732,0):ocfs2_blocking_ast:1025 BAST fired for lockres 
M0000000000000000085e0200000000, blocking 5, level 5 type Meta
[412.378532] (12731,0):ocfs2_process_blocked_lock:3839 lockres 
M0000000000000000085e0200000000 blocked.

Lock is at EX (5) and new level is NL (0).
[412.378537] (12731,0):ocfs2_prepare_downconvert:3232 lock 
M0000000000000000085e0200000000, new_level = 0, l_blocking = 5
[412.378542] (12731,0):ocfs2_downconvert_lock:3252 lock 
M0000000000000000085e0200000000, level 5 => 0

Flags: 0x557 => PENDING QUEUED INITIALIZED NEEDS_REFRESH BLOCKED BUSY 
ATTACHED
[412.378554] (12731,0):__lockres_clear_pending:978 lock 
M0000000000000000085e0200000000 Clear; flg=0x557, lpg=268, gen=268

requeue no means there is no need to delay the downconvert
[412.378558] (12731,0):ocfs2_process_blocked_lock:3863 lockres 
M0000000000000000085e0200000000, requeue = no.

Action 3 means DOWNCONVERT
[412.378578] (12732,0):ocfs2_locking_ast:1069 lock 
M0000000000000000085e0200000000, action 3, unlock 0

Flags: 0x51 => INITIALIZED NEEDS_REFRESH ATTACHED
[412.378584] (12732,0):__lockres_clear_pending:972 lock 
M0000000000000000085e0200000000 Abort; flg=0x51, lpg=269, gen=269

Flags: 0x453 => PENDING INITIALIZED NEEDS_REFRESH BUSY ATTACHED
[412.378596] (9370,0):__lockres_clear_pending:978 lock 
M0000000000000000085e0200000000 Clear; flg=0x453, lpg=269, gen=269

Action 2 means CONVERT
[412.578719] (12732,0):ocfs2_locking_ast:1069 lock 
M0000000000000000085e0200000000, action 2, unlock 0
[412.578727] (12732,0):__lockres_clear_pending:972 lock 
M0000000000000000085e0200000000 Abort; flg=0x51, lpg=270, gen=270

A quick scan shows the CONVERT is consistently 200 usecs (??) after the 
DOWNCONVERT.

Coli, Can you map the pids to the process names.

Sunil

Coly Li wrote:
> Sunil Mushran Wrote:
>   
>> Thanks. Can you email me the _full_ trace log.
>>
>>     
> Hi Sunil,
>
> Here is the full trace log from boot to shutdown, on both nodes.
>
> On node x1, I run 2 make_panic process (the simplified bash script).
> On node x2, I run 1 make_panic process.
>
> The above operation can reproduce the blocking very fast. I wait for several
> minutes, when no any new file created on both nodes. Then I shut the nodes.
>
> Please check the attachment for trace log.
>
> Thanks.
>   

  reply	other threads:[~2009-09-14 23:57 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-08-18 19:26 [Ocfs2-devel] dlm stress test hangs OCFS2 Coly Li
2009-08-18 19:34 ` David Teigland
2009-08-19  3:06 ` Sunil Mushran
2009-09-02 17:11   ` Coly Li
2009-09-02 22:01     ` Sunil Mushran
2009-09-03 16:24       ` Coly Li
2009-09-03 16:24         ` Sunil Mushran
2009-09-09 20:07           ` Coly Li
2009-09-09 21:42             ` Sunil Mushran
2009-09-10  5:38               ` Coly Li
2009-09-11 22:57                 ` Sunil Mushran
2009-09-13 14:08                   ` Coly Li
2009-09-14 19:30                     ` Sunil Mushran
2009-09-14 20:23                       ` Coly Li
2009-09-14 23:57                         ` Sunil Mushran [this message]
2009-09-15  7:11                           ` Coly Li
2009-09-16  0:49                             ` Sunil Mushran
2009-09-21 17:25                               ` Coly Li
2009-09-21 17:25                                 ` Sunil Mushran
2009-09-21 17:31                                   ` Sunil Mushran
2009-09-21 17:43                                     ` Coly Li
2009-09-21 19:03                                     ` Coly Li
2009-09-23  6:32                               ` [Ocfs2-devel] questions of AST and BAST (was Re: dlm stress test hangs OCFS2) Coly Li
2009-09-23 18:21                                 ` Sunil Mushran

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=4AAED882.9020601@oracle.com \
    --to=sunil.mushran@oracle.com \
    --cc=ocfs2-devel@oss.oracle.com \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.