arnon_rodman
06/25/2024, 7:01 AMpromql
avg(bentoml_service_request_duration_seconds_count{namespace="$namespace", job=~"$job", exported_endpoint!="/", exported_endpoint!="/docs.json", exported_endpoint!="/robots.txt", exported_endpoint!~"/static_content/.*"}) by (runner_name)
and
promql
avg(bentoml_service_request_duration_seconds_sum{namespace="$namespace", job=~"$job", exported_endpoint!="/", exported_endpoint!="/docs.json", exported_endpoint!="/robots.txt", exported_endpoint!~"/static_content/.*"}) by (runner_name)
However, the results seem off We are seeing averages of 3-5 minutes, whereas our logs show that the requests take less than 1 minute.
Any idea what we might be missing or doing wrong?
Thx in advanceJian Shen Yap
06/25/2024, 8:09 AMarnon_rodman
06/25/2024, 8:37 AMJian Shen Yap
06/25/2024, 8:38 AMbentoml_service_request_duration_seconds_sum from the /metrics endpoint?
i would suggest you to fire a simple request and see whether the results agree with observationarnon_rodman
06/25/2024, 9:06 AMarnon_rodman
06/28/2024, 4:07 PMJian Shen Yap
07/01/2024, 5:49 AM/metrics and prometheus that you see. Expected vs actual.arnon_rodman
07/14/2024, 11:27 AM