Uh oh!
There was an error while loading. Please reload this page.
[fix](cloud) shorten cache lock held time and add metrics - #47472
Conversation
when update bvar metrics, we held block lock in the critical context of cache lock, make the later lock held too long and affect other cache logic. we use unsafe method to update the bvar to boost performance. some key metrics of lock and other meaningful metrics are also added for better monitoring cache time costs. Signed-off-by: zhengyu <zhangzhengyu@selectdb.com>
Thearas
commented
Jan 27, 2025
Thank you for your contribution to Apache Doris. Please clearly describe your PR:
|
freemandealer
commented
Jan 27, 2025
run buildall |
doris-robot
commented
Jan 27, 2025
TPC-H: Total hot run time: 32396 ms |
doris-robot
commented
Jan 27, 2025
TPC-DS: Total hot run time: 192068 ms |
doris-robot
commented
Jan 27, 2025
ClickBench: Total hot run time: 30.08 s |
doris-robot
commented
Jan 27, 2025
TeamCity be ut coverage result: |
PR approved by at least one committer and no changes requested. |
PR approved by anyone and no changes requested. |
| return _download_state; | ||
| } | ||
| FileBlock::State FileBlock::state_unsafe() const { |
| DEFINE_mInt64(cache_lock_wait_long_tail_threshold_us, "30000000"); | ||
| DEFINE_mInt64(cache_lock_held_long_tail_threshold_us, "30000000"); |
There was a problem hiding this comment.
30000000 means 30 seconds, it seems too long...
There was a problem hiding this comment.
yes, it is 'closed' by default.
when update bvar metrics, we held block lock in the critical context of cache lock, make the later lock held too long and affect other cache logic. we use unsafe method to update the bvar to boost performance. some key metrics of lock and other meaningful metrics are also added for better monitoring cache time costs.
when update bvar metrics, we held block lock in the critical context of cache lock, make the later lock held too long and affect other cache logic. we use unsafe method to update the bvar to boost performance. some key metrics of lock and other meaningful metrics are also added for better monitoring cache time costs.
when update bvar metrics, we held block lock in the critical context of cache lock, make the later lock held too long and affect other cache logic. we use unsafe method to update the bvar to boost performance. some key metrics of lock and other meaningful metrics are also added for better monitoring cache time costs.
when update bvar metrics, we held block lock in the critical context of cache lock, make the later lock held too long and affect other cache logic. we use unsafe method to update the bvar to boost performance.
some key metrics of lock and other meaningful metrics are also added for better monitoring cache time costs.
What problem does this PR solve?
Issue Number: close #xxx
Related PR: #xxx
Problem Summary:
Release note
None
Check List (For Author)
Test
Behavior changed:
Does this need documentation?
Check List (For Reviewer who merge this PR)