Messages in this thread | | | Date | Fri, 5 Mar 1999 13:43:00 -0500 (EST) | From | Jeremy Hansen <> | Subject | Re: Oops with user land nfs now. |
| |
Ok, it's happening about every 20 minutes now. Is there anything I can do to try and fix or at least give some clues that lead to an answer.
Customers aren't liking this too much if you know what I mean. We have about a week we have to wait before we're able to move this to another server that will be using hardware raid.
Thanks -jeremy
> > Also, as suggested by Alan, I caught rpc.nfsd in D state right > before the crashes: > > 140 0 871 1 0 0 1480 960 end D ? 0:00 > rpc.nfsdU > > -jeremy > > > It is likely that this is a Raid0 problem and not an NFS problem. > > > > There is a big FIXME in the front of the raid0_map function. > > Are you using the default read/write sizes? > > > > Allen > > > > >>>Jeremy Hansen said: > > > > > > Got an Oops with user land nfsd now, although this just killed > > > nfsd operations. The machine was still very mucy alive otherwise > > > allowing me to properly reboot it. > > > > > > > - > > To unsubscribe from this list: send the line "unsubscribe linux-kernel" in > > the body of a message to majordomo@vger.rutgers.edu > > Please read the FAQ at http://www.tux.org/lkml/ > > > > > > -------------------------- > Y2K. We're all gonna die. > > > - > To unsubscribe from this list: send the line "unsubscribe linux-kernel" in > the body of a message to majordomo@vger.rutgers.edu > Please read the FAQ at http://www.tux.org/lkml/ >
-------------------------- Y2K. We're all gonna die.
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |