XsWack

Results 102 comments of XsWack

Hi @alculquicondor @Huang-Wei @ahg-g Could you take a look at this? Since It is a small change to loose the validation of priority class

> /assign > > Isn't it sufficient to specify `--skip-nodes-with-local-storage=false`? This should have the same effect. I've tried it but it doesn't work, can you give me some advice?

I also encountered this problem. Have you solved it? @jewelzqiu

理论上来说,每秒90个写请求不应该会占用这么高的cpu,你能贴下kube-apiserver、cloudcore的日志和监控信息吗?你的孪生数据消息体有多大呢?我分析一下

I think the default storageWatchListPageSize should be user configurable for kube-apiserver

There is a known problem here. When sending downstream messages, cloudcore will create nodeMessagePool for all nodes, but only the nodeMessagePool of node that connected to this cloudcore instance will...

If this is reasonable, I can help do this.