partial outage

Incident Report for turbopuffer

Resolved

The issue has been identified and resolved. A node in gcp-us-central1 experienced highly degraded networking between 17:15-17:22 UTC. Our existing network failure handling logic was unable to handle such a major degradation in service. As a result, ~12.5% of query traffic in the region was affected.

We're taking retroactive steps to ensure nodes that encounter these sorts of networking issues are taken out of rotation automatically.
Posted Jul 15, 2024 - 17:22 UTC

Investigating

We are currently investigating this issue.
Posted Jul 15, 2024 - 17:15 UTC
This incident affected: API.