Hi, I'm trying to find more in depth data about how Prometheus manages memory and disk space, my understanding so far is that long-term the data is written in chunks to disk and mmap-ed, and management for that is left for the OS, but I can't find how this mmap data is treated when Prometheus is running in a Kuberentes pod, if the size of the data stored on disk is 16GB for example, and the pod has a memory limit of 8, would at any point a query cause the pod to be OOM killed duo to the map being larger than the memory limit of the pod?
I found this old Prometheus issue about the topic: https://github.com/prometheus/prometheus/issues/3005, but it was closed without any final comments. -- You received this message because you are subscribed to the Google Groups "Prometheus Users" group. To unsubscribe from this group and stop receiving emails from it, send an email to prometheus-users+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/prometheus-users/7fd723ed-be9d-4c3d-a18c-1d4b87b0fe42%40googlegroups.com.
