[GitHub] [helix] richardstartin opened a new issue, #2117: ClusterStatusMonitor is a bottleneck in BestPossibleStateCalcStage.process

Wed, 25 May 2022 01:56:26 -0700 


richardstartin opened a new issue, #2117:
URL: https://github.com/apache/helix/issues/2117

   This profile was taken from an Apache Pinot controller:
   <img width="1425" alt="Screenshot 2022-05-25 at 09 53 04" 
src="https://user-images.githubusercontent.com/16439049/170222935-5b9111b3-1373-4e71-bcc1-edf7be2db84a.png";>
   
   About 18% of the samples were in 
`ClusterStatusMonitor.setPerInstanceResourceStatus` (zoomed in)
   
   <img width="1430" alt="Screenshot 2022-05-25 at 09 53 22" 
src="https://user-images.githubusercontent.com/16439049/170223015-611a084a-3f96-40d5-b5ec-e639886ccb68.png";>
   
   The root causes are:
   
   * inefficient hashCode implementation in 
`PerInstanceResourceMonitor$BeanName`
   * doing twice the work in 
`ClusterStatusMonitor.setPerInstanceResourceStatus` because `containsKey` is 
called before `get`, when the same effect could be achieved efficiently by 
`computeIfAbsent`
   
   


-- 
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]

Reply via email to