[
https://issues.apache.org/jira/browse/STORM-1165?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14990162#comment-14990162
]
ASF GitHub Bot commented on STORM-1165:
---------------------------------------
Github user redsanket commented on a diff in the pull request:
https://github.com/apache/storm/pull/856#discussion_r43921298
--- Diff:
storm-core/src/jvm/backtype/storm/scheduler/resource/strategies/ResourceAwareStrategy.java
---
@@ -209,18 +209,18 @@ private WorkerSlot getBestWorker(ExecutorDetails
exec, TopologyDetails td, Strin
for (RAS_Node n : nodes) {
if(n.getFreeSlots().size()>0) {
if (n.getAvailableMemoryResources() >= taskMem
- && n.getAvailableCpuResources() >= taskCPU) {
- double a = Math.pow((taskCPU -
n.getAvailableCpuResources())
- * this.CPU_WEIGHT, 2);
- double b = Math.pow((taskMem -
n.getAvailableMemoryResources())
- * this.MEM_WEIGHT, 2);
- double c = 0.0;
- if(this.refNode != null) {
- c = Math.pow(this.distToNode(this.refNode, n)
- * this.NETWORK_WEIGHT, 2);
- }
- double distance = Math.sqrt(a + b + c);
- nodeRankMap.put(distance, n);
+ && n.getAvailableCpuResources() >= taskCPU) {
+ double a = Math.pow(((taskCPU -
n.getAvailableCpuResources())/(n.getAvailableCpuResources() + 1))
+ * this.CPU_WEIGHT, 2);
+ double b = Math.pow(((taskMem -
n.getAvailableMemoryResources())/(n.getAvailableMemoryResources() + 1))
+ * this.MEM_WEIGHT, 2);
+ double c = 0.0;
+ if(this.refNode != null) {
+ c = Math.pow(this.distToNode(this.refNode, n)
+ * this.NETWORK_WEIGHT, 2);
+ }
+ double distance = Math.sqrt(a + b + c);
+ nodeRankMap.put(distance, n);
--- End diff --
sorry never mind +1 NB
> normalize the scales of CPU/Mem/Net when choosing the best node for Resource
> Aware Scheduler
> --------------------------------------------------------------------------------------------
>
> Key: STORM-1165
> URL: https://issues.apache.org/jira/browse/STORM-1165
> Project: Apache Storm
> Issue Type: Improvement
> Reporter: Boyang Jerry Peng
> Assignee: Boyang Jerry Peng
>
> 1. Describe observed behavior.
> Memory has a default capacity of 2000.0, CPU has 400.0, network has a
> distance value of either 1 or 2 (different rack); and the weights of them are
> the same (1).
> As a result, when choosing the best node for scheduling, the network plays a
> minimal role in the calculation of the geometric square of the three
> dimensions.
> 2. What is the expected behavior?
> Three resources place comparable roles in the node choosing algorithm.
> 3. Outline the steps to reproduce the problem.
> Need to assign appropriate or normalized scales to balance among the three
> dimensions.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
