We're currently having issues

Resolved
Resolved

All Data Jobs recovered, and the performance of the data pipeline is back to normal. The root cause was identified in the data transformation layer, where one of the computing nodes went down and delayed the Data Jobs execution during its recovery. All systems are now operational.

Recovering

The performance degradation root cause was identified and mitigated. The execution delay of Data Jobs is now recovering.

Investigating

We're currently investigating a major slowdown of the Event Collection system, affecting the execution of all Data Jobs on the eu-1 cluster.

Began at:

Affected components
  • EU-1