OpenVZ Forum


Home » General » Support » OOM Killer strange behavior (OOM Killer kill host processes even that are available RAM and swap on the machine)
OOM Killer strange behavior [message #52996] Thu, 28 September 2017 22:43
dannyg is currently offline  dannyg
Messages: 1
Registered: September 2017
Junior Member
From: *red.bezeqint.net
Hello all,
I will really appreciate assistance with the following issue which is a blocker for us.

We have a product deployed on CentosOS 6.9 with OpenVZ.
Machine RAM size 32 GB + Swap file (16 GB).
The following described issue was reproduced on OpenVZ kernels
2.6.32-042stab125.1 , 2.6.32-042stab123.9 , .6.32-042stab123.2, 2.6.32-042stab120.11

For debugging the single container on the host is stopped.
We observed that OOM Killer is invoked whenever host RAM usage without buffers reach ~13 GB:
Free command output (few seconds before OOM killer invoked):
total used free shared buffers cached
Mem: 32793080 23197272 9595808 920 135992 10276712
-/+ buffers/cache: 12784568 20008512
Swap: 16465916 0 16465916

On the message buffer, we see that the machine memory state just before the OOM killer invocation is:
RAM: 2097074 / 2097152 [1] SWAP: 1048576 / 1048576 [1] KMEM: 227942400 /

Again machine has 32 GB, only 13 GB is used, no swap usage so where those values
came from and why OOM killer is invoked in this stage?

The issue is reproducible with similar results every time.

Is it same way to totally disable the OOM killer?
Should I open a defect for this?

BTW attaching file to this post failed (state that file is too big though it only 33K)
Ill be glad to provide any required detail (like sysctl a output)

Regards,
Danny
Previous Topic: Debian 8 install hangs; config and/or dialog?
Next Topic: openvz webpanel Fehler
Goto Forum:
  


Current Time: Tue Dec 12 20:07:19 GMT 2017