FrankChen021 commented on code in PR #19655:
URL: https://github.com/apache/druid/pull/19655#discussion_r3607330665
##########
indexing-service/src/main/java/org/apache/druid/indexing/seekablestream/supervisor/autoscaler/CostBasedAutoScaler.java:
##########
@@ -292,6 +329,12 @@ int computeOptimalTaskCount(CostMetrics metrics)
: startIndex;
}
+ // Emergency (tier 2) lag skips the argmin search entirely: evaluate only
the maximum valid task count.
+ if (emergencyLag) {
Review Comment:
[P1] Bypass the cost-drop gate during tier-2 emergencies
After this emergency branch restricts evaluation to the maximum task count,
execution still reaches the existing `minCostDropPercentForScaling` check at
lines 377-385. With both options configured, a tier-2 lag emergency can
therefore return the current count when the maximum improves cost by less than
the configured percentage, contradicting the stated jump-to-maximum behavior
and potentially leaving an SLA-critical backlog under-provisioned. Tier-2
should bypass that gate or return the maximum directly.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
