On Mon, 23 May 2005, Ian Fisk wrote:
> Hi Maarten,
> On May 23, 2005, at 4:18 PM, [log in to unmask] wrote:
>
> > On Mon, 23 May 2005, Ian Fisk wrote:
> >
> >
> >> We are experiencing an interesting problem with the
> >> grid-monitor-manager. It appears to manifest itself in two ways
> >>
> >> 1.) users report problems of jobs never exiting the scheduling state
> >> 2.) Machine memory usage increases until the system goes unstable
> >>
> >> What appears to be happening is under some circumstances the lock
> >> file
> >> in /opt/globus/tmp for the grid-monitor-manager is corrupted. The
> >>
> >
> > In what way? Can you send me examples?
>
> The log gets nulls appended to the start of the lock file. The
> normal lock has something like
>
> 687 1116880933
>
> I think the first is PID and the second is a time stamp. After
> corruption, the file has a series of nulls in front. The more
> starts, the more nulls.
Is /opt/globus/tmp on an NFS?
|