Infrastructure:
  • Nagios is passing now
  • Nebraska - network outage that knocked local data servers, not the redirector
  • UCSD - issues w/ CA on uaf-6? Came up 2x by mistake.
    • Removed Xrootd from node for now, should stay down!
  • FNAL:
    • Mixing RPM repositories - caused failures only for Chinese CA users. Fixed.
    • CRL restart issue - fixed upstream, but not deployed.
    • /store/results permission issues.
      • Causing many failures for SUSY group.
      • BB: how do you find stdout on CRAB server?
      • FKW: How to get redirection info? BB: Only allowed to do this in the exception/warning messages, haven't figured it out yet.

Software:

  • UNL new employee - Yaling - at Nebraska. Working on correlating Condor and Xrootd logs.
    • First goal post: Daily reports with the site failure info. Second goal post: Nagios alerts.
  • Need to do various CMSSW improvements:
    • Log in stdout the redirections
    • Monitor stream
    • Statistics
  • Xrootd:
    • CRLs are fixed in git
    • ABH is rewriting the detailed redirection monitoring again.
  • CVMFS:
    • CVMFS as $OSG_APP at UW is working fairly well in production.
      • UNL is going to be testing it.
    • CVMFS integrated with Parrot: Is working. Next step is to try this with parrot.
      • Another week or so to do logging.
    • The point of CVMFS would be able to overflow to non-CMS sites.
    • IS: What platforms is this used for? DB: Unknown, will look.
    • DB: What overhead will this incur? IS: A few years ago, 5-15%.

AOB:

  • MT: Setup ML alarm so he gets emails for auth failures. If we get in summary monitoring rejected file opens, we could also get early notification. MT will check with ABH to see if we get this already in detailed monitoring.
  • MT: Will go to SLAC on 1st and 3rd to work on caching proxy w/ ABH.
  • KB: Two weeks from now, can we go back to the October work plan and review?
  • KB: Who will be at the OSG AHM? FKW, KB, BB, at least.
    • We may want to send ugrads to the OSG meting.
    • At the least, as part of the T2 piece of the week, we can have a joint ATLAS/CMS Xrootd meeting.
  • BB: Should we push FNAL to change access policy?

Action Items:

  • BB will start looking at XrdAdapter
  • MT: Working on caching proxy
  • All: check action against work plan.
Edit | Attach | Watch | Print version | History: r1 | Backlinks | Raw View | WYSIWYG | More topic actions
Topic revision: r1 - 2012-01-12 - BrianBockelman
 
    • Cern Search Icon Cern Search
    • TWiki Search Icon TWiki Search
    • Google Search Icon Google Search

    Main All webs login

This site is powered by the TWiki collaboration platform Powered by PerlCopyright & 2008-2019 by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding TWiki? Send feedback