The current locust test script for Revert Risk models is missing the host header. Consequently, all requests to ML staging will fail.
Description
Details
Related Objects
- Mentioned In
- T361881: Investigate the inconsistent load test results (locust) for revertrisk
rMLIS7af63a06e2ee: locust: fix missing host header for revertrisk load tests
T361238: Update and fix locust load testing for revscoring models - Mentioned Here
- T361881: Investigate the inconsistent load test results (locust) for revertrisk
P58995 load test #1
P58996 load test #2
Event Timeline
Change #1015341 had a related patch set uploaded (by AikoChou; author: AikoChou):
[machinelearning/liftwing/inference-services@main] locust: fix missing host header for revertrisk load tests
@isarantopoulos do you remember the config values in locust.conf when you ran the revertrisk tests? I can't reproduce the result in revertrisk_stats.csv. I haven't deployed RRLA to staging yet, so it's the same model you tested.
With the current locust.conf, I got the result P58995, which has fewer requests.
I also attempted to use the previous locust.conf, but the result P58996 was still different, with a significantly higher number of requests.
The locust.conf was the one that is committed in the repo. I can't recall if anything was different at the moment. However since the host header wasn't there it makes me wonder if the test was ran using the API GW but again that doesn't justify the increased request count.
Change #1015341 merged by AikoChou:
[machinelearning/liftwing/inference-services@main] locust: fix missing host header for revertrisk load tests
This task is complete. I've created T361881 to follow up on the above test results issue.