MageMojo incident
One node in USEast under emergency maintenance
MageMojo experienced a notice incident on July 5, 2021 affecting Webscale STRATUS - Northern Virginia, lasting 2m. The incident has been resolved; the full update timeline is below.
Affected components
Webscale STRATUS - Northern Virginia
Update timeline
- monitoring Jul 05, 2021, 11:32 AM UTC
A fix has been implemented and we are monitoring the results.
- resolved Jul 05, 2021, 11:34 AM UTC
This incident has been resolved.
- postmortem Jul 05, 2021, 12:12 PM UTC
An investigation concluded that a comprehensive kernel bug hit the ZFS filesystem and caused the issue with one of the nodes in our fleet. The problem is identified as similar to the [https://github.com/openzfs/zfs/issues/10642](https://github.com/openzfs/zfs/issues/10642) bug already reported. We have captured kernel stack traces during this event, and a solution for prevention is under investigation.