K
Q

CoreOS VM crash: swap trace printed

11/4/2015

I'm using CoreOS 773.1.0 with kubernetes. Recently it crashes and printed this trace log:

enter image description here

enter image description here

The VM is still running but I cannot ssh to it, kubernetes master node declare it as NotReady. I had to turn it off (not shutdown) and start it.

I'm using Hyper-V as hypervisor, the VM is assiged 12GB RAM, 4GB swap, 4 cores CPU. Especially, I got this error after I moved the disk (.vhd file) to new partition.

-- Quyen Nguyen Tuan
coreos
kubernetes
linux-kernel
page-fault
swap

Similar Questions

Command to delete all pods in all kubernetes namespaces
Cluster Level Logging with Elasticsearch and Kibana does not work in kubernetes
kubectl output different than remote API
kubernetes pod creation pending

3 Answers

11/4/2015

Looks like Kubelet process is stucked. Do you have kubelet log and at which operation, kubelet is stucked?

-- Dawn Chen
Source: StackOverflow
11/4/2015

This is a known issue to CoreOS 717.3.0 with swap: https://github.com/coreos/bugs/issues/429

-- Dawn Chen
Source: StackOverflow
11/4/2015

Based on the stack trace, it looks like the kernel was trying to free up memory. So, probably the node was under severe memory pressure. Kernel bugs tend to crop up under memory pressure.

It also looks like swap was turned on. Kubernetes developers don't recommend turning on swap.

-- Eric Tune
Source: StackOverflow