Summit scratch unavailable

Incident Report for CU Boulder RC

Resolved

Access to Summit scratch has remained stable, thought we are continuing to investigate with our network support vendor.

Posted Sep 10, 2021 - 20:58 MDT

Monitoring

Access to Summit scratch has been restored, and some Summit compute nodes are sill recovering (automatically). This appears to have been the result of a network disruption, possibly coinciding with some internal diagnostics. We are engaging with our network support provider for further clarification.

Posted Sep 07, 2021 - 16:33 MDT

Investigating

The GPFS scratch file system has become unavailable. We are researching the cause.

Posted Sep 07, 2021 - 15:46 MDT

This incident affected: RMACC Summit.