[Lustre-discuss] ldlm_enqueue operation failures

[Brian J. Murrell]

On Tue, 2008-02-19 at 08:53 -0500, Charles Taylor wrote:
> One more thing worth mentioning, we have no more callback or watchdog  
> timer expired messages so 1.6.4.2 seems to have  fixed that.      So  
> it just seems like if 512 threads try to open the same file at  
> roughly the same time, we are running out of some resource on the MDS  
> or OSSs that keeps Lustre from satisfying the request.

As Johann said many messages ago in this thread, this looks like bug
13917 which requires that you upgrade the *clients* to 1.6.4.x and since
you are 1.6.4.2 on the servers you might as well be so on the clients.
The bug that causes this problem is a client side bug and was not fixed
until 1.6.4

b.

-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: This is a digitally signed message part
URL: <http://lists.lustre.org/pipermail/lustre-discuss-lustre.org/attachments/20080220/deb0d75e/attachment.pgp>