liuzhuo created FLINK-28124:
-------------------------------
Summary: Flink on K8S in hosetNetwork mode, the CPU usage will
spike
Key: FLINK-28124
URL: https://issues.apache.org/jira/browse/FLINK-28124
Project: Flink
Issue Type: Bug
Components: Deployment / Kubernetes, Runtime / Metrics
Reporter: liuzhuo
When using the flink on k8s, in the configuration 'kubernetes. Hostnetwork.
Enabled = true' parameters, If a node is running too many pods
, there will be a node CPU surge problem, The metric module collected the
indicator information of the network card
{code:java}
Class :SystemResourcesCounter
Line 109 :calculateNetworkUsage(hardwareAbstractionLayer.getNetworkIFs());{code}
The problem is with this method
{code:java}
hardwareAbstractionLayer.getNetworkIFs(){code}
this method returns the current all the network card on the machine, each pod
will create a virtual network card (ifr_name = "kube - ipvs0"), In hostNetwork
mode, the network card is visible to the public, resulting in too much network
card information returned by the interface
For example, if a node runs 200 pods, then the method calling this interface in
each POD will return at least 200 nic information. With the default execution
once every 5 seconds, this machine needs to return 200*200=40000 network card
information every 5 seconds, this results in a significant CPU consumption
--
This message was sent by Atlassian Jira
(v8.20.7#820007)
