I think you are guessing right, Wyatt, that the password will break the RM’s query (good question for your NERSC contacts: why is a password required here?). For remote build, yes, monitoring is not needed. For remote launch, I do know that the control part of the code was developed without the monitoring part, it is very much like flying blind though – you’ll know that your job was submitted, but pretty much nothing after that – One thing I’m really not clear on is how the control and monitoring code is connected, I don’t think it is at the control XML (though it would be nice if it were). Jay From: ptp-dev-bounces@xxxxxxxxxxx [mailto:ptp-dev-bounces@xxxxxxxxxxx] On Behalf Of Wyatt Spear Sent: Tuesday, October 04, 2011 11:40 AM To: Parallel Tools Platform general developers Subject: Re: [ptp-dev] PBS remote resource manager fails on NERSC's Hopper For some reason apstat requires me to enter my password again on Hopper, I'm guessing that would throw off the RM's query. To what extent is this node info needed for the remote build/launch functionality? Right now when this check fails the resource manager fails to start altogether, but it seems like the remote build and launch commands should still be able to work even if we can't see what's happening on the system. =Wyatt On Tue, Oct 4, 2011 at 9:33 AM, Jay Alameda <jalameda@xxxxxxxxxxxxxxxxx> wrote: Then we need to provide a modified lml.da, right? (trying to figure out where this is plumbed in, I believe it is packaged in a plugin). I don’t think there is a place yet, for configuring this in the resource manager xml (really the control xml), but I’m not certain. Jay On Cray the pbsnodes command never gives useful information. On Jaguar it only shows the batch nodes. "apstat -v -n" gives the required information instead. Roland On Tue, Oct 4, 2011 at 12:08 PM, Wyatt Spear <wspear@xxxxxxxxxxxxxx> wrote: On Hopper pbsnodes returns: pbsnodes: Server has no node list MSG=node list is empty - check 'server_priv/nodes' file I'll ask the NERSC-ies about this... Wyatt On Tue, Oct 4, 2011 at 8:48 AM, Jay Alameda <jalameda@xxxxxxxxxxxxxxxxx> wrote: Well, I’m slowly coming up the steep learning curve on the configurable RM. I know that the monitoring code, lml.da is looking at pbsnodes output on machines that support pbs. Maybe start on hopper, and see what pbsnodes returns? There also could be a missing perl module, that would be needed to convert the raw output of pbs nodes into xml that the client monitoring code expects to see. We saw this on one system here at NCSA – Jay I would be happy to dig around and check. Is there a spot where I can do a sysout on what PBS is returning? Wyatt On Tue, Oct 4, 2011 at 7:51 AM, Jay Alameda <jalameda@xxxxxxxxxxxxxxxxx> wrote: I think we tried this out on an older Cray system, Kraken, at NICS. I seem to recall that it worked, including the LML display. I wonder what may be different here?
Jay
-----Original Message----- From: ptp-dev-bounces@xxxxxxxxxxx [mailto:ptp-dev-bounces@xxxxxxxxxxx] On Behalf Of Greg Watson Sent: Tuesday, October 04, 2011 6:37 AM To: Parallel Tools Platform general developers Subject: Re: [ptp-dev] PBS remote resource manager fails on NERSC's Hopper _______________________________________________ ptp-dev mailing list ptp-dev@xxxxxxxxxxx https://dev.eclipse.org/mailman/listinfo/ptp-dev
-- ORNL/UT Center for Molecular Biophysics cmb.ornl.gov 865-241-1537, ORNL PO BOX 2008 MS6309 _______________________________________________ ptp-dev mailing list ptp-dev@xxxxxxxxxxx https://dev.eclipse.org/mailman/listinfo/ptp-dev
|