[Linux-cluster] GFS filesystem "hang" with cluster-1.03.00
Josef Whiter
jwhiter at redhat.com
Fri Oct 20 13:46:42 UTC 2006
On Fri, Oct 20, 2006 at 03:34:33PM +0200, Ramon van Alteren wrote:
> Yes, this was the previous exchange. In the same exchange I was advised
> by Wendy Cheng to switch to iozone because it would avoid such multiple
> lock calls (less stat on files) instead of bonnie++ which we were
> previously testing with.
>
Ahh I mised that, apologies.
> My test-run last night started at 4AM with 4 different iozone processes
> using a temp file in different directories on the same filesystem /
> logical volume.
>
> AFAIK this would avoid the problem you mention above ?
>
> All iozone processes were in D (uninteruptable sleep) by the time I woke
> up and had a look 8AM this morning.
>
> I would expect gfs to deal with this gracefully and return a performance
> metric on multiple writes because:
>
> * Not in same directory so no dir-lock to pass around
> * Different files
>
Ok if you are hitting this problem then the best thing to do is grab serveral
instances of sysrq-t from all nodes so we can see who/what is hanging and start
poking around. Thank you,
Josef
More information about the Linux-cluster
mailing list