Incident Library?

API · MCP 한국어

Incident Library?

API · MCP 한국어

Component ?

CNI plugin

CNI 플러그인 · cni-plugin

1 case · 2023

Root cause ?Configuration change

Contributing factor ?Monitoring blind spot Unrepresentative staging

Symptom ?Service outage Throughput degradation

Cases, by severity

IL-0116 A CNI configuration change incompatible with a hardware variant that exists only in production cut network connectivity in an OpenAI GPU cluster and took text-davinci-003 fully downOpenAI · 2023
Root cause Configuration change

View on the graph