No relevant SLOs exist, shellbox latency/php-fpm worker saturation
Impact
For about 10min syntaxhighlighting was slow or returning errors
…
A sudden spike in requests to shellbox-syntaxhighlight overloaded the service leading to slow response times and increased failures.
The majority of requests where originating from jobrunners and api_appservers.
Timeline
All times in UTC.
09:00 OUTAGE BEGINS non paging alerts of failing http-api probes and api_appservers running out of idle workers where observed in #mediawiki-operations; Investigation started
09:03 paging alert: (ProbeDown) firing: Service shellbox-syntaxhighlight:4014 has failed probes (http_shellbox-syntaxhighlight_ip4)
09:05 shellbox-syntaxhighlight req/s increased from ~5 to ~70req/s
09:05 shellbox-syntaxhighlight scaled up from 12 to 40 replicas
09:09 Alerts recovering
09:10 OUTAGE ENDS
09:11 (CirrusSearchJobQueueBacklogTooBig) firing: CirrusSearch job topic eqiad.mediawiki.job.cirrusSearchLinksUpdate is heavily backlogged with 209k messages
09:49 cirrusSearchLinksUpdate backlog was cleared
09:54 shellbox-syntaxhighlight scaled back to 12 replicas
Detection
shellbox-syntaxhighlight grafana dashboard
Initially detected by a human spotting alerts on IRC, closely followed by a page.
Conclusions
What went well?
Problem spotted early and countermeasures where taken quickly
envoy telemetry dashboardOne of the SREs paged knew how to increase the number of syntaxhighlight runners (it's not mentioned on Shellbox)
What went poorly?
shellbox-syntaxhighlight was probably overloaded by our own services (jobrunners), but currently this is an assumption.
Were the people responding to this incident sufficiently different than the previous five incidents?
Yes
Were the people who responded prepared enough to respond effectively
Yes
Were fewer than five people paged?
Yes
Were pages routed to the correct sub-team(s)?
Yes
Were pages routed to online (business hours) engineers? Answer “no” if engineers were paged after business hours.
Yes
Process
Was the "Incident status" section atop the Google Doc kept up-to-date during the incident?
No
no google doc was created, only 3 responders
Was a public wikimediastatus.net entry created?
No
Is there a phabricator task for the incident?
Yes
Are the documented action items assigned?
No
Is this incident sufficiently different from earlier incidents so as not to be a repeat occurrence?
No
Tooling
To the best of your knowledge was the open task queue free of any tasks that would have prevented this incident? Answer “no” if there are
open tasks that would prevent this incident or make mitigation easier if implemented.
No
While they might not have fully prevented this incident, there are (long) outstanding performance issues with syntaxhighlight: task T271751, task T316858
Were the people responding able to communicate effectively during the incident with the existing tooling?
Yes
Did existing monitoring notify the initial responders?
Yes
Were the engineering tools that were to be used during the incident, available and in service?
Yes
Were the steps taken to mitigate guided by an existing runbook?