oomd - Userspace Out-Of-Memory (OOM) killer for Linux systems
Contents
Description
oomd leverages PSI and cgroupv2 to monitor a system holistically. oomd then takes corrective action in
userspace before an OOM occurs in kernel space. Corrective action is configured via a flexible plugin
system, in which custom code can be written. By default, this involves killing offending processes. This
enables an unparalleled level of flexibility where each workload can have custom protection rules.
Furthermore, time spent livedlocked in kernelspace is minimized.
Name
oomd - Userspace Out-Of-Memory (OOM) killer for Linux systems
Options
--help,-h
Show this help message and exit
--version,-v
Print version and exit
--config,-CCONFIG
Config file (default: /etc/oomd/oomd.json)
--interval,-iINTERVAL
Event loop polling interval (default: 5)
--cgroup-fs,-fFS
Cgroup2 filesystem mount point (default: /sys/fs/cgroup)
--check-config,-cCONFIG
Check config file (default: /etc/oomd/oomd.json)
--list-plugins,-l
List all available plugins
--drop-in-dir,-wDIR
Directory to watch for drop in configs
--socket-path,-sPATH
Specify stats socket path (default: /run/oomd/oomd-stats.socket)
--dump-stats,-d
Dump accumulated stats
--reset-stats,-r
Reset stats collection
--deviceDEVS
Comma separated <major>:<minor> pairs for IO cost calculation (default: none)
--ssd-coeffsCOEFFS
Comma separated values for SSD IO cost calculation (default: see doc)
--hdd-coeffsCOEFFS
Comma separated values for HDD IO cost calculation (default: see doc)
See Also
https://github.com/facebookincubator/oomd#configuration
Synopsis
oomd [OPTION] ...
