https://prow.ci.openshift.org/view/gs/origin-ci-test/logs/periodic-ci-openshift-release-master-nightly-4.14-e2e-metal-ipi-sdn-serial-virtualmedia-bond/1719369581786566656

The disruption charts here indicate this job run had absurd disruption numbers for the in-cluster monitoring. Using the dashboard job list and filtering for only runs with over 20k s of pod-to-pod disruption, every hit was this job.

It appears this job may have extreme problems with in-cluster networking. Investigate and get a bug to appropriate teams.