Re: [Condor-users] 32bit checkpoint servers and 64bit nodes?

["David A. Kotz" <dkotz@xxxxxxxxxxxxx>]

Thanks, Dan.  I guess it's time to add another checkpoint server.

- dave


Dan Bradley wrote:
> There is indeed an incompatibility when checkpoint servers and the 
> condor_shadow when one is 32-bit and the other 64-bit.  We just recently 
> became aware of this.  I'll leave it to those working on a solution to 
> report when that might be ready.
>
> --Dan
>
> David A. Kotz wrote:
> > I've recently converted a part of my Linux Condor pool to 64bit Ubuntu 
> > and 64bit Condor.  Both of my initial 64bit users have reported that 
> > their jobs are failing to checkpoint and continually restarting.  All of 
> > the checkpoint servers in my pool are running 32bit Ubuntu and 32bit 
> > Condor.  Is there any known issue with this configuration?  I'd assumed 
> > that the checkpoint server just received a data stream and dumped it to 
> > disk so that it wouldn't matter.  The checkpoint servers in question are 
> > doing checkpoints for other jobs.
> >
> > The shadow log for the 64bit submit node has lines like these:
> >
> >    2/18 22:35:10 (765.0) (22524):store request to ckpt server failed, 
> > trying again in 320 seconds
> >
> > - dave
> > _______________________________________________
> > Condor-users mailing list
> > To unsubscribe, send a message to condor-users-request@xxxxxxxxxxx with a
> > subject: Unsubscribe
> > You can also unsubscribe by visiting
> > https://lists.cs.wisc.edu/mailman/listinfo/condor-users
> >
> > The archives can be found at: 
> > https://lists.cs.wisc.edu/archive/condor-users/
> >   
> _______________________________________________
> Condor-users mailing list
> To unsubscribe, send a message to condor-users-request@xxxxxxxxxxx with a
> subject: Unsubscribe
> You can also unsubscribe by visiting
> https://lists.cs.wisc.edu/mailman/listinfo/condor-users
>
> The archives can be found at: 
> https://lists.cs.wisc.edu/archive/condor-users/