GraphCDN incident

Increased error rates when loading the Stellate Dashboard

Major Resolved View vendor source →

GraphCDN experienced a major incident on December 5, 2022 affecting Dashboard, lasting 49m. The incident has been resolved; the full update timeline is below.

Started
Dec 05, 2022, 09:50 AM UTC
Resolved
Dec 05, 2022, 10:40 AM UTC
Duration
49m
Detected by Pingoru
Dec 05, 2022, 09:50 AM UTC

Affected components

Dashboard

Update timeline

  1. investigating Dec 05, 2022, 09:50 AM UTC

    We are looking into an issue with a service backing our dashboard. This is not affecting CDN services (neither caching, nor the private beta of rate-limiting), however you will see higher error rates when trying to load the Stellate dashboard.

  2. identified Dec 05, 2022, 10:07 AM UTC

    We identified the root cause, which is an issue with our metrics cluster. We have alerted the infrastructure partner operating that cluster for us and they are working on restoring access.

  3. monitoring Dec 05, 2022, 10:25 AM UTC

    Our metrics cluster is back online and accessible again. It will take a short while for it to catch up with queued metrics updates, and you might still see sporadic errors on the dashboard in the next couple of minutes. We are closely monitoring performance and will update this incident as required.

  4. resolved Dec 05, 2022, 10:40 AM UTC

    Metrics queues have caught up and the cluster is operating as expected again.