2023-07-11: [CNY] FrontendServiceCnyHttpServicesApdexSLOViolation
Customer Impact
Slow git requests in CNY only affecting less than 5% of the total traffic.
Current Status
Response times have been healthy since re-enabling canary stage at 17:25 UTC.
The response time regression had been associated with 3 specific pods, all running on the same GKE node. That node has been removed from the node pool by a scale-down event, and no other nodes appear to exhibit the same CPU contention or scheduling delays. At this time we suspect the regression started during a deploy due to a scale-up event that added a GKE node to the cluster that happened to have a noisy neighbor and performed poorly. The deploy itself does not appear to have caused the regression, so deploys are now unblocked.
More information will be added as we investigate the issue. For customers believed to be affected by this incident, please subscribe to this issue or monitor our status page for further updates.
📝 Summary for CMOC notice / Exec summary:
- Customer Impact: Access checks in staging systems are slower when processing the
/internal/allowed
API endpoint. We have no indicator yet of increased error rates. Due to being on canary systems less than 5% of the users are impacted. - Service Impact: ServiceFrontend
- Impact Duration: 08:07 UTC - 13:05(298 minutes)
- Root cause: RootCauseSaturation
📚 References and helpful links
Recent Events (available internally only):
- Feature Flag Log - Chatops to toggle Feature Flags Documentation
- Infrastructure Configurations
- GCP Events (e.g. host failure)
Deployment Guidance
- Deployments Log | Gitlab.com Latest Updates
- Reach out to Release Managers for S1/S2 incidents to discuss Rollbacks, Hot Patching or speeding up deployments. | Rollback Runbook | Hot Patch Runbook
Use the following links to create related issues to this incident if additional work needs to be completed after it is resolved:
- Corrective action ❙ Infradev
- Incident Review ❙ Infra investigation followup
- Confidential Support contact ❙ QA investigation
Note: In some cases we need to redact information from public view. We only do this in a limited number of documented cases. This might include the summary, timeline or any other bits of information, laid out in out handbook page. Any of this confidential data will be in a linked issue, only visible internally. By default, all information we can share, will be public, in accordance to our transparency value.