| To: | Allan Haywood <Allan.Haywood@xxxxxxxxxxxxx> |
|---|---|
| Subject: | Re: xfs file system corruption |
| From: | Andi Kleen <andi@xxxxxxxxxxxxxx> |
| Date: | Wed, 08 Oct 2008 02:15:29 +0200 |
| Cc: | Dave Chinner <david@xxxxxxxxxxxxx>, "xfs@xxxxxxxxxxx" <xfs@xxxxxxxxxxx> |
| In-reply-to: | <E8DED08235A93F4D8A2AB6CD0ABAB32A0A937FC922@NA-EXMSG-C121.redmond.corp.microsoft.com> (Allan Haywood's message of "Tue, 7 Oct 2008 16:49:40 -0700") |
| References: | <E8DED08235A93F4D8A2AB6CD0ABAB32A0A937FC8EC@NA-EXMSG-C121.redmond.corp.microsoft.com> <20081007233418.GB7342@disturbed> <E8DED08235A93F4D8A2AB6CD0ABAB32A0A937FC922@NA-EXMSG-C121.redmond.corp.microsoft.com> |
| Sender: | xfs-bounce@xxxxxxxxxxx |
| User-agent: | Gnus/5.1008 (Gnus v5.10.8) Emacs/21.3 (gnu/linux) |
Allan Haywood <Allan.Haywood@xxxxxxxxxxxxx> writes: > > Would reloading the xfs module work also, to clear any pending > writes (if I could get it to a point where modprobe -r xfs > would work)? Although I am doubting that if there are pending > writes that it would be easy to get xfs to unload. Linux doesn't have IO cancel and it's hard to stop everything in the IO stack, so the usual way is to fence it at a high level and then wait for all pending IO. But that might take a long time. That is why most HA setups use hard stonith, as in power switch. -Andi -- ak@xxxxxxxxxxxxxxx |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: xfs file system corruption, Dave Chinner |
|---|---|
| Next by Date: | Re: [PATCH 3/3] kill xfs_dinode_core_t, Christoph Hellwig |
| Previous by Thread: | Re: xfs file system corruption, Dave Chinner |
| Next by Thread: | xfsaild centisecs /proc wakeup control?, Linda A. Walsh |
| Indexes: | [Date] [Thread] [Top] [All Lists] |