Slow container image pulls in eu-north1
resolved- Started
- Sep 8, 11:36 AM EDT
- Resolved
- Sep 8, 12:42 PM EDT
- Duration
- 1h 6m
Cerebrium's updates (2)
- update · Sep 8, 11:36 AM EDT
We're seeing elevated S3 latency in eu-north1, which is slowing container image pulls. New deploys and cold starts in that region are taking longer than usual. Inference is unaffected: apps with warm replicas are serving traffic, and other regions are running normally. We're currently investigating and will post an update shortly.
- resolved · Sep 8, 12:42 PM EDT
The issue has been resolved.
What our checks recorded
We checked Cerebrium 13 times from Cerebrium's start time to its resolution, once every five minutes. Every one of them reached Cerebrium's site, so this incident did not show up as a failed page load. Our check loads the public site; it cannot see an API error or a broken feature. Median response time was 142 ms, against 202 ms over the 24 hours before. Cerebrium posted the incident at Sep 8, 11:36 AM EDT.
Updates are Cerebrium's own words from its status page (status: resolved); we never add an inferred cause.