On Wed, 2002-10-30 at 10:21, Christoph Hellwig wrote:
> > 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?
>
Christoph, sorry, I responded off list and sent them the last two
pagebuf changes to try in their tree. I suspect they were being
bitten by at least one of them.
Steve
--
Steve Lord voice: +1-651-683-3511
Principal Engineer, Filesystem Software email: lord@xxxxxxx
|