We saw out of memory issues related to metrics last week. We want to reduce this cost to ensure stability.
Description
Details
| Subject | Author | Repo | Branch | Lines +/- | |
|---|---|---|---|---|---|
| cirrus: Update container image | Ebernhardson | operations/deployment-charts | master | +1 -1 |
Related Objects
- Mentioned In
- T399721: SUP: OOM from prometheus
Event Timeline
pfischer opened https://gitlab.wikimedia.org/repos/search-platform/cirrus-streaming-updater/-/merge_requests/178
Consumer: reduce HTTP metrics
ebernhardson merged https://gitlab.wikimedia.org/repos/search-platform/cirrus-streaming-updater/-/merge_requests/178
Consumer: reduce HTTP metrics
Change #1128505 had a related patch set uploaded (by Ebernhardson; author: Ebernhardson):
[operations/deployment-charts@master] cirrus: Update container image
Change #1128505 merged by jenkins-bot:
[operations/deployment-charts@master] cirrus: Update container image
Metrics changes deployed to all consumers (and producer, but it doesn't do anything there afaict). Dashboards for http metrics now show _OTHER as expected.
Thanks! There is no significant effect on task manager memory consumption. CODFW uses almost the same (~2GiB), only EQIAD is now down 100 MiB.