[Jlab-scicomp-briefs] Infiniband Fabric failure - switch being replaced now (27-Jul-2021)

[Bryan Hess]

Access to the Lustre Filesystems (/cache and /volatile)  for The Farm and Lattice QCD was interrupted starting around 7:30 this morning by an infiniband switch hardware failure. Although the switch has redundant components, it appears that the controller failed.

The switch is being replaced with a spare, and the system will be restored as soon as the re-cabling is completed.

We apologize for the unplanned outage and are working with the vendor to understand the cause of the failure.




-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.jlab.org/pipermail/jlab-scicomp-briefs/attachments/20210727/ce822fd5/attachment.html>