Web and File Server Outage - Unplanned

 

Several of our public facing web servers and the M: and O: drives (aka /group and /sgroup) were experiencing intermittent outages today between 1:30 p.m. and 2:15 p.m.  The cause was determined to be jobs (1000+) running on the batch farm that were retrieving data from the /group file system.  This greatly degraded the file server's ability to service other requests.  Once the jobs were identified and killed, file services returned to normal.

Please contact the IT Division Help Desk (x7155 or helpdesk@jlab.org) with any additional questions or concerns.