Linode Status

Current Status
Connectivity Issue - Fremont
Incident Report for Linode
Postmortem

Monitoring systems alerted us of link failures between the Santa Clara and Fremont Site, similar to the 2023-02-12 Incident, however unlike the events of 2-12 this presented as a total loss of light across the B-Side span, and at the time of the failure no issue on the A-side was present. Once again the network team engaged the fiber provider and investigations began. At approximately 14:50 UTC, the fiber provider identified this as a fiber cut. At 16:05 UTC, repair work began to splice and restore the fiber, 18:50 UTC the fiber provider reported splicing complete and service to the circuit was restored.

Unfortunately while the B-side was down, we experienced a few very brief hits to the A-side fiber causing it to flap. These hits ranged from sub-second to under 30 seconds. We observed a total of 4 incidents, 06:20, 07:22, 08:28, 11:15 UTC. The fiber provider of the A-side (different provider than the B-side) was engaged to investigate. Internally, all physical segments, equipment and logs across this circuit were investigated, however, outside of the physical interface flaps no additional information was identified, and more than likely was an environmental factor outside our control.

Fiber cuts like the one on February 21st are not uncommon, and can be caused by environmental factors outside our control. In almost all cases these issues are identified, and repaired with no impact to the customer. Unfortunately what is uncommon is for the redundant path (or any fiber circuit) to take sub-second hits as described above.

While the proximity in time of these two events makes it hard to believe that they are not related in some way, the fact of the matter is that it’s a coincidence to experience two failures like this in such a short time span. The failures of the B-side fiber were completely different in nature.

However, as a result, we compelled them to move our circuit to a completely new path and pair.

At this time both circuits are considered stable and we do not expect a recurrence like this to occur in the future.

Posted Mar 16, 2023 - 17:33 UTC

Resolved
The connectivity issues in the US-West region have been resolved.
Posted Feb 21, 2023 - 19:13 UTC
Update
Our team is continuing to work on the fix for the identified issue in our Fremont location. We will continue to monitor for further connectivity issues and will update this page as we have more information.
Posted Feb 21, 2023 - 18:29 UTC
Identified
Our team has identified the issue that impacted the connectivity for our Fremont location. At this time, a fix is be implemented and we will provide additional updates, as we have more information.
Posted Feb 21, 2023 - 14:50 UTC
Update
Our team is still investigating the connectivity issue for our Fremont location. We will provide updates as soon as we have more information.
Posted Feb 21, 2023 - 12:00 UTC
Update
We are continuing to investigate this issue
Posted Feb 21, 2023 - 10:30 UTC
Investigating
From approximately 6:25-6:28 UTC, we observed a 2-3 minute disruption to connectivity in our Fremont location. Currently connectivity is restored, and our team is investigating this issue further. During this time, users may experience intermittent connection timeouts and errors for all services deployed in this data center. We will share additional updates as we have more information.
Posted Feb 21, 2023 - 08:12 UTC
This incident affected: Regions (US-West (Fremont)).