fix: [2.4] Prevent balancer from overloading the same QueryNode #38720
Conversation
mergify
bot
added
dco-passed
|
@weiliu1031 E2e jenkins job failed, comment |
weiliu1031
force-pushed
the
fix_assign_too_much_task_to_qn24
branch
2 times, most recently
from
fdb3bdf to
eaeba70
Compare
|
@weiliu1031 E2e jenkins job failed, comment |
|
/run-cpu-e2e |
|
@weiliu1031 E2e jenkins job failed, comment |
The balancer calculates the workload of executing tasks as an ongoing score for target nodes. However, a logic issue arises when GetSegmentTaskDelta or GetChannelTaskDelta is called with collectionID=-1, which incorrectly returns zero. Due to the incorrect global score, the executing task's workload is not properly reflected for each collection. Consequently, each collection submits its own balance task, leading to the balancer assigning excessive tasks to the same QueryNode. Signed-off-by: Wei Liu <[email protected]>
weiliu1031
force-pushed
the
fix_assign_too_much_task_to_qn24
branch
from
eaeba70 to
1d5a58d
Compare
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## 2.4 #38720 +/- ##
==========================================
+ Coverage 83.40% 83.42% +0.01%
==========================================
Files 809 809
Lines 143068 143115 +47
==========================================
+ Hits 119333 119400 +67
+ Misses 19243 19229 -14
+ Partials 4492 4486 -6
|
Signed-off-by: Wei Liu <[email protected]>
|
/lgtm |
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: weiliu1031, xiaofan-luan The full list of commands accepted by this bot can be found here. The pull request process is described here
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
issue: #38718
pr: #38719
The balancer calculates the workload of executing tasks as an ongoing score for target nodes. However, a logic issue arises when GetSegmentTaskDelta or GetChannelTaskDelta is called with collectionID=-1, which incorrectly returns zero.
Due to the incorrect global score, the executing task's workload is not properly reflected for each collection. Consequently, each collection submits its own balance task, leading to the balancer assigning excessive tasks to the same QueryNode.