You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
What are the difference between the test and valid modes list on the documentation?
Since this is intended to be a reproducible bechmark suite, would it be possible to add clear instructions on which modes are to be run and the impact each step has? For instance, I cannot tell if the test execution mode is optional or if it is generating a target metric (as indicated by "record the estimated offline_target_qps" on the documentation)
The text was updated successfully, but these errors were encountered:
Valid execution mode tries to do a valid run meeting the minimum duration of 10 minutes. But for this it relies on the user provided qps value in offline and server scenarios.
Test execution mode is just for testing (in the documentation it serves to launch the container too). But it also helps in determining the qps for the valid run. If user knows the qps, there's no need to do the test run.
We'll add these in the documentation. Please keep this issue open.
What are the difference between the
test
andvalid
modes list on the documentation?Since this is intended to be a reproducible bechmark suite, would it be possible to add clear instructions on which modes are to be run and the impact each step has? For instance, I cannot tell if the
test
execution mode is optional or if it is generating a target metric (as indicated by "record the estimated offline_target_qps" on the documentation)The text was updated successfully, but these errors were encountered: