I was noticing this while stress testing on the new cluster. If overload lasts long enough, celery services start dying off.
Description
Description
Status | Subtype | Assigned | Task | ||
---|---|---|---|---|---|
Resolved | None | T181538 ORES overload incident, 2017-11-28 | |||
Resolved | awight | T181634 Investigate overload condition, seems that we lose nodes |