SLACVX Cluster Issues

SLACVX Cluster Issues

• Major Push to Improve Reliability of Cluster
  • Tuned up staging system
    • Reduced load on tape system
  • How to fix page
    • Also a how to report problems page
    • GNATS problem tracking system
  • Log of system problems
    • Automatic paging when problems occur
  • Nightly job checks full MC/recon chain.

• Remaining Issues
  • Track down and fix “fatal drive error”
  • Persuade more users to use Alphas for batch.|
  • Improve debugging on Alpha.
    • Comments/suggestions to Gary Bower

http://www-sld.slac.stanford.edu/sldwww/staging/monitoring.html

http://www-sld.slac.stanford.edu/htbin/syslog

http://www-sld.slac.stanford.edu/sldwww/runinfo/tdint.html

http://www-sld.slac.stanford.edu/sldwww/slacvx/how-to-fix.html

Previous slide

Next slide

Back to the first slide

View Graphic Version