-
Notifications
You must be signed in to change notification settings - Fork 3.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[opt](metrics) Remove IntervalHistogramStat #47459
base: master
Are you sure you want to change the base?
[opt](metrics) Remove IntervalHistogramStat #47459
Conversation
Thank you for your contribution to Apache Doris. Please clearly describe your PR:
|
run buildall |
TPC-H: Total hot run time: 32219 ms
|
TPC-DS: Total hot run time: 191969 ms
|
ClickBench: Total hot run time: 30.37 s
|
TeamCity be ut coverage result: |
run buildall |
TPC-H: Total hot run time: 32291 ms
|
TPC-DS: Total hot run time: 192285 ms
|
ClickBench: Total hot run time: 31.1 s
|
TeamCity be ut coverage result: |
run external |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
PR approved by at least one committer and no changes requested. |
PR approved by anyone and no changes requested. |
What problem does this PR solve?
Use prometheus to calculate average value is better.
Related PR: #43144
For example, we use
task_execution_time_ns_avg_in_last_1000_times
which is equal toSUM(cost 0, ... cost 999) / 1000
to represent average execution time, it has two problems:_task_execution_time_ns_statistic
acquires lock.task_execution_time_ns_avg_in_last_1000_times
is not zero if we just finished a set of tasks and no more tasks to run. For example, we have a continuous straight line after all tasks have finished for a while.The problem can be fixed by:
task_execution_time_ns_total
an atomic counter to store total sum of execution time of each iteration.irate
function of prometheus, we can have an equivalent substitution likeirate(doris_be_task_execution_time_ns_total[$__rate_interval])/doris_be_thread_pool_active_threads
After all tasks finished, the curve will be zero, this is more reasonable.
Problem Summary:
Release note
None
Check List (For Author)
Test
Behavior changed:
Does this need documentation?
Check List (For Reviewer who merge this PR)