| To: | Matthew Wilcox <willy@xxxxxxxxxx> |
|---|---|
| Subject: | Re: FW: unlink deadlock |
| From: | Christoph Hellwig <hch@xxxxxxxxxxxxx> |
| Date: | Wed, 30 Oct 2002 16:21:55 +0000 |
| Cc: | linux-xfs@xxxxxxxxxxx, bob.gobeille@xxxxxx |
| In-reply-to: | <20021030150116.X27461@parcelfarce.linux.theplanet.co.uk>; from willy@debian.org on Wed, Oct 30, 2002 at 03:01:16PM +0000 |
| References: | <20021030150116.X27461@parcelfarce.linux.theplanet.co.uk> |
| Sender: | linux-xfs-bounce@xxxxxxxxxxx |
| User-agent: | Mutt/1.2.5.1i |
> seeing on a 2.4.18 cluster of dual cpu IA-64 nodes. Two processes on each > node are writing (different) checkpoint files to the same directory on an > XFS RAID 0 array and sometimes ending up in a D state and locking the entire > filesystem (can't even do an ls). Each process is writing a 155 MB > checkpoint file A then a 155 MB checkpoint file B then unlinking A and > writing a new A, then unlinks B ... Were trying to reproduce the problem > with a single process writing two large files (1MB to 3,000MB) and unlinking > them over and over again but haven't been successful yet. 2.4.18 is pretty old and some of the functions in your trace don't exist anymore in that form. Any chance you could reproduce it with a current tree? |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | TAKE - fix loop termination logic in xfs_sync, Steve Lord |
|---|---|
| Next by Date: | Re: FW: unlink deadlock, Steve Lord |
| Previous by Thread: | FW: unlink deadlock, Matthew Wilcox |
| Next by Thread: | Re: FW: unlink deadlock, Steve Lord |
| Indexes: | [Date] [Thread] [Top] [All Lists] |