I am currently working on a Kubernetes cluster, which uses docker. This cluster allows me to launch jobs. For each job, I specify a memory request and a memory limit. The memory limit will be used by Kubernetes to fill the `--memory` option of the docker run command when creating the container. If this container exceeds this limit it will be killed for OOM reason. When writing on disk, pages will be written-back on the RAM before being written to the disk. To do this the system will evaluate how many pages could be written-back using the sysctl `vm.dirty_ratio` (20 % by default) and memory from the root cgroup. In case of intensive IO operations, it leads some containers to OOM errors. xfs should be able to writeback using cgroup.
My nodes are running under RHEL with a kernel 4.14 and I encounter OOM errors when writing with xfs.