[
https://issues.apache.org/jira/browse/YUNIKORN-1746?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Peter Bacsko updated YUNIKORN-1746:
-----------------------------------
Description:
Performance data (cpu and heap profiles) indicate that we can improve the
performance of {{nodeInfoListerImpl.List()}}.
This is the code which is located in the shim:
{noformat}
func (n nodeInfoListerImpl) List() ([]*framework.NodeInfo, error) {
nodes := n.cache.GetNodesInfoMap()
nodeList := make([]*framework.NodeInfo, 0, len(nodes))
for _, node := range nodes {
nodeList = append(nodeList, node)
}
return nodeList, nil
}
{noformat}
We're supposed to be having a read lock on the cache, which is done outside
this method.
The problem is, the nodes info map only changes if a node joins or leaves the
cluster. A lot of copying is done here, we generate a lot of waste. This method
is called very frequently, because predicates need this list and predicates
always run for each pod by default.
was:
Performance data (cpu and heap profiles) indicates that we can improve the
performance of {{nodeInfoListerImpl.List()}}.
This is the code which is located in the shim:
{noformat}
func (n nodeInfoListerImpl) List() ([]*framework.NodeInfo, error) {
nodes := n.cache.GetNodesInfoMap()
nodeList := make([]*framework.NodeInfo, 0, len(nodes))
for _, node := range nodes {
nodeList = append(nodeList, node)
}
return nodeList, nil
}
{noformat}
We're supposed to be having a read lock on the cache, which is done outside
this method.
The problem is, the nodes info map only changes if a node joins or leaves the
cluster. A lot of copying is done here, we generate a lot of waste. This method
is called very frequently, because predicates need this list and predicates
always run for each pod by default.
> Improve the performance of nodeInfoListerImpl.List()
> ----------------------------------------------------
>
> Key: YUNIKORN-1746
> URL: https://issues.apache.org/jira/browse/YUNIKORN-1746
> Project: Apache YuniKorn
> Issue Type: Sub-task
> Reporter: Peter Bacsko
> Assignee: Peter Bacsko
> Priority: Major
>
> Performance data (cpu and heap profiles) indicate that we can improve the
> performance of {{nodeInfoListerImpl.List()}}.
> This is the code which is located in the shim:
> {noformat}
> func (n nodeInfoListerImpl) List() ([]*framework.NodeInfo, error) {
> nodes := n.cache.GetNodesInfoMap()
> nodeList := make([]*framework.NodeInfo, 0, len(nodes))
> for _, node := range nodes {
> nodeList = append(nodeList, node)
> }
> return nodeList, nil
> }
> {noformat}
> We're supposed to be having a read lock on the cache, which is done outside
> this method.
> The problem is, the nodes info map only changes if a node joins or leaves the
> cluster. A lot of copying is done here, we generate a lot of waste. This
> method is called very frequently, because predicates need this list and
> predicates always run for each pod by default.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
