We have hundreds of redhat based servers (oracle linux to be exact) that have this strange issue. When we ping from one server to another the out put looks something like this.
64 bytes from 10.46.10.10: icmp_seq=1 ttl=254 time=98 ms
64 bytes from 10.46.10.10: icmp_seq=1 ttl=254 time=97 ms
64 bytes from 10.46.10.10: icmp_seq=1 ttl=254 time=96 ms
... continues
64 bytes from 10.46.10.10: icmp_seq=1 ttl=254 time=3 ms
64 bytes from 10.46.10.10: icmp_seq=1 ttl=254 time=2 ms
64 bytes from 10.46.10.10: icmp_seq=1 ttl=254 time=1 ms
64 bytes from 10.46.10.10: icmp_seq=1 ttl=254 time=98 ms
64 bytes from 10.46.10.10: icmp_seq=1 ttl=254 time=97 ms
64 bytes from 10.46.10.10: icmp_seq=1 ttl=254 time=96 ms
All of our nics are using the e1000 controller because vmxnet cards don't pxe boot. Has anyone ever seen this before? It only happens once or twice a month on random servers but its making the app owners and management a bit nervous.
Thanks