Jump to content
  • Announcements

    • admin

      PBS Forum Has Closed   06/12/17

      The PBS Works Support Forum is no longer active.  For PBS community-oriented questions and support, please join the discussion at http://community.pbspro.org.  Any new security advisories related to commercially-licensed products will be posted in the PBS User Area (https://secure.altair.com/UserArea/). 

Search the Community

Showing results for tags 'queues'.



More search options

  • Search By Tags

    Type tags separated by commas.
  • Search By Author

Content Type


Forums

  • A Test Category
  • FAQs and Tech Notes
    • FAQs
    • Tutorials
    • Tech Notes
    • SECURITY ADVISORIES
  • Downloads, Plug-Ins, Add-Ons
    • Hooks
    • Application Definitions
    • Configurations
  • Community Discussions
    • Troubleshooting
    • Admins
    • Users
    • Bugs and RFE's
  • Application Integration
  • Admin
  • Users
  • Bugs and RFE‚Äôs

Found 3 results

  1. So while trying to configure some queues for another problem (http://forum.pbsworks.com/index.php?/topic/631-pbs-queue-for-limited-walltime-and-exclusive-nodes/), I seem to have hit some unexpected behavior. I was attempting to assign exclusive nodes to a queue. The system I use has 32 cores, on 4 nodes. I want our "small" queue to use 2 nodes. Our server has the nodes listed as server[0], server[1], server[2], and server[3]. We have a route queue (as default queue) set up as well to use the small queue. What we tried was this (following from examples seen in the linked problem and elsewhere): set node server[0] queue = small set node server[1] queue = small I assigned a walltime limit (max of 8 hours) for this queue as well. I then submitted 3 jobs without specifying the queue (only walltime) and the following happened: job1 (<8 hours requested walltime) ---> immediately runs on small queue on node server[3] job2 (>8 hours requested walltime) ---> immediately runs on other queue on node server[2] job3 (<8 hours requested walltime) ---> not enough resources, job is queued I was expecting job1 to go to small queue on node server[0] or server[1], and I'd expect job3 to as well. It is as if the set node command has blocked me from assigning any jobs to those nodes. Any idea as to what went wrong?
  2. I had a question about setting up a queue on exclusive nodes and accepting jobs with limited walltime. I am more interseted in "what happens when..." for this scenario. I saw this example (http://forum.pbsworks.com/index.php?/topic/251-assign-exclusive-nodes-to-a-queue/) for setting exclusive nodes to a queue, and it is very clear to me. I read through the documentation for assigning a max walltime for a queue as well using a route queue. This also makes sense to me. It's combining these that has me scratching my head. So let's say I want a queue with 4 exclusive nodes (but my system has plenty other nodes), but to only accept jobs with a walltime less than 6 hours. If I set up the queue to with the exclusive nodes I want, and set up a routing queue to send all jobs with less than 6 hours of requested walltime to that same queue, what will happen if I submit a job requesting more than 4 nodes but less than 6 hours of walltime. Will the job get rejected for requesting too many resources? Will PBS be smart enough to just send it to a queue with non exclusive nodes (which would be most desirable)? Or will I need to create a hook to handle this? In other words, I want a queue with N exclusive nodes than only accepts jobs with requested walltime less than M, but if a jobs has a requested walltime less than M, but requests more than N nodes, I don't want to to get rejected for there not being enough resources. Is this a legitamit concern, or does PBS handle this appropriately without hooks (or any other intervention).
  3. Dear support Another one here. I have two destination queues and a routing queue. Simple schema: create queue routing set queue routing queue_type = Route set queue routing route_destinations = workq set queue routing route_destinations += fastq [...] create queue workq set queue workq queue_type = Execution set queue workq Priority = 200 set queue workq from_route_only = True set queue workq resources_min.walltime = 01:00:01 [...] create queue fastq set queue fastq queue_type = Execution set queue fastq Priority = 150 set queue fastq resources_max.walltime = 01:00:00 set queue fastq max_run_res.ncpus = [u:PBS_GENERIC=2] Should be enough to understand the environment. Given this situation, a job requesting walltime <= 1 hour, goes in fastq, everything else goes in workq. But, unfortunately, a job requesting walltime=50' and 4 cores, stays in Q forever due to the cpu limitation on the fastq. I would like to route a job in fastq if it requires walltime <= 1H and cores <= 2. Is it correct if I say that I need a hook in the presubmit phase to do this? Can you give me an example of this kind of hook? Any help will be VERY appreciated.
×