Google Cloud: RESOLVED: Multiple services were experiencing issues in the europe-west2 region.
A production outage affecting GCP services in the europe-west2 region, reported on HN. No specific version or command provided.
– UTC
Here's why. Incidents from Wednesday, October 21, 2026 (UTC), ranked byBreakage Velocity.What is Breakage Velocity?A live score of how fast an outage or regression is spreading. The more people hit it, and the faster, the higher it climbs; it cools off as things calm down.Open-ended scale: under 25 low · 25+ elevated · 100+ high · 300+ extreme.
23 outages, 3 still active today. Worst: Google Cloud (15 d 22 h).
A production outage affecting GCP services in the europe-west2 region, reported on HN. No specific version or command provided.
– UTC
GitHub Actions service is experiencing degraded availability, affecting all users who rely on this service. The issue has been resolved with ongoing monitoring.
– UTC
The Hetzner object storage service has been unavailable since last 10 days in the HEL data center, affecting all users who use this service.
– UTC
A major outage affecting the railway system was reported. No specific technical details or affected versions were provided in the reports.
– UTC
A bug in PostgreSQL's recovery_prefetch feature caused production outages, affecting all affected versions of the database.
since
Elevated error rates have been observed for requests to Claude Fable 5. The issue affecting other Claude models has been resolved.
– UTC
FedRAMP API error rates for OpenAI's Astra and Sol services have been elevated, affecting all impacted services. The issue has now resolved.
– UTC
GitHub Actions experiences degraded performance, causing delays in Pull Request updates and Webhook deliveries. Increased load on the event streaming platform is contributing to hotspots.
– UTC
The OpenAI gpt-5.6-luna API experienced elevated error rates affecting chat completions and responses, which have now fully recovered.
– UTC
A production release of nodejs/node version 22.23.4 'Jod' has been deployed to address several security vulnerabilities and improve agent data guard, DNS validation, TLS handling, permission checks, random cache resets, and realpathSync functionality.
since
Fireworks AI experienced a service degradation affecting DeepSeek V4.1 Flash 1017. The incident has been resolved and the service is now operational.
– UTC
Fireworks AI experienced a service degradation affecting Deepseek V4.1 Flash. The incident has been resolved and the affected service is now operational.
– UTC