|To:||Dave Chinner <david@xxxxxxxxxxxxx>|
|Subject:||Re: [xfs-masters] xfs deadlock in stable kernel 3.0.4|
|From:||Stefan Priebe - Profihost AG <s.priebe@xxxxxxxxxxxx>|
|Date:||Wed, 21 Sep 2011 13:55:30 +0200|
|Cc:||Christoph Hellwig <hch@xxxxxxxxxxxxx>, "xfs-masters@xxxxxxxxxxx" <xfs-masters@xxxxxxxxxxx>, "xfs@xxxxxxxxxxx" <xfs@xxxxxxxxxxx>|
|References:||<4E75B660.1030502@xxxxxxxxxxxx> <20110918230245.GF15688@dastard> <4E78665E.8030409@xxxxxxxxxxxx> <20110920160226.GA25542@xxxxxxxxxxxxx> <4E78CBF4.1030505@xxxxxxxxxxxx> <20110920172455.GA30757@xxxxxxxxxxxxx> <4E78CEFD.9030603@xxxxxxxxxxxx> <20110920223047.GA13758@xxxxxxxxxxxxx> <20110921021133.GM15688@dastard> <4E7994D3.5020103@xxxxxxxxxxxx> <20110921114237.GP15688@dastard>|
|User-agent:||Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:22.214.171.124) Gecko/20110831 Thunderbird/3.1.13|
Am 21.09.2011 13:42, schrieb Dave Chinner:
OK that matches my findings. It was also mostly in the random delete phase. But i've also seen it on creates.Ok, I got a hang in the random delete phase. Not sure what is wrong yet, but inode reclaim is trying to reclaim inodes but failing, and the AIL is trying to push items but failing. Hence the tail of the log is not being moved forward and new transactions are being blocked until log space bcomes available.
Given this, just triggering a log force is shoul dget everything moving again. Running "echo 2> /proc/sys/vm/drop_caches" gets inode reclaim running in sync mode, which causes pinned inodes to trigger a log force. And once I've done this, everything starts running again.
Oh man i was thinking about trying this. But then i forgot that idea ;-(
So, the log force not triggering in the AIL code looks to be the problem. That, I simply cannot explain right now - it makes no sense but that is what all the stats and trace events point to. I need to do more investigation.
Thanks Dave and great that you were able to repeat it.What helps is to build bonnie++ yourself and just remove the stat tests. I've done this too - so bonnie++ runs a lot faster.
|<Prev in Thread]||Current Thread||[Next in Thread>|
|Previous by Date:||Re: [xfs-masters] xfs deadlock in stable kernel 3.0.4, Dave Chinner|
|Next by Date:||Re: [PATCH v3] xfs: fix possible overflow in xfs_ioc_trim(), Christoph Hellwig|
|Previous by Thread:||Re: [xfs-masters] xfs deadlock in stable kernel 3.0.4, Dave Chinner|
|Next by Thread:||Re: [xfs-masters] xfs deadlock in stable kernel 3.0.4, Christoph Hellwig|
|Indexes:||[Date] [Thread] [Top] [All Lists]|