The memory resource controller for cgroups v1 allows for setting limits on memory usage on a particular cgroup using the memory.limit_in_bytes
file. What is the Linux kernel's behavior when this limit is reached?
In particular:
- Does the kernel OOM kill the process and if so is the
oom_score
of the process taken into account, or is it the process that asked for the memory that caused the limit to be hit that gets killed? - Or would the request for memory just be rejected in which case the process would only die if it didn't deal with such an event?
TaskMax
setting) – Tim Jul 2 '18 at 5:53