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.
signature.asc
Description: This is a digitally signed message part
_______________________________________________ Lustre-discuss mailing list [email protected] http://lists.lustre.org/mailman/listinfo/lustre-discuss
