Server Fault Stack Exchange
Server Fault Stack Exchange

Questions tagged [oom]

Linux Out-of-memory Killer

The OOM Killer is the Linux kernel's built in mechanism for protecting a machine from using up all memory.

107 questions
3
votes
2 answers

Long page allocation stalls on Linux – why does this happen?

I have a problem (which I can reliably reproduce) on a bunch of Linux hosts, where the system becomes completely unresponsive after a process aggressively consumes memory. I see things like this in the kernel log: 2017-09-14 19:53:51.252365 kernel:…
obeattie
  • 304
  • 1
  • 6
  • 13
3
votes
2 answers

GKE's Container-Optimized OS Out-Of-Memory freezes

I have issue with Container-Optimized OS on GKE. If I run this simple command https://pastebin.com/raw/0WPAnAzn to consume all the RAM, at some point host freezes and doesn't respond to anything. Expected behaviour: the process should be killed by…
nailgun
  • 59
  • 6
3
votes
2 answers

Slab reclaimable memory is not freed when needed

Correct me if I am wrong, but to my understanding slab reclaimable holds cached kernel objects which can be freed if needed. So if application needs to allocate more space, even if the 'free' memory is low, OS will drop some pages from slab…
Horkyze
  • 151
  • 1
  • 4
3
votes
1 answer

Adjust oom_score at process launch

I've got a few servers that have begun oom-killing their backup processes and, while I understand that encountering the oom condition is quite bad in itself, I need this process to not die so that backups happen properly while the memory issue is…
Sammitch
  • 2,111
  • 1
  • 21
  • 35
3
votes
1 answer

How can there ever be an OOM scenario on Linux (heuristics behind OOM killer)?

I am aware of the concept of virtual memory. And with demand paging (depending on vm.overcommit_memory) you are able to allocate more memory than available RAM. Unless you "touch" a page nothing really happens. Else I guess there is a page fault and…
fiction
  • 143
  • 1
  • 5
3
votes
0 answers

Why can't I malloc as much memory as `free` reports as being free?

The following C program allocates slices of 10MB of memory until it is killed by the Out of Memory killer. #include #include #include #include int main() { int counter = 0; int slice_size =…
Confusion
  • 191
  • 1
  • 8
3
votes
3 answers

MySQL - Identifying a never ending, server crashing query

My server keeps crashing from OOM errors cause by MySQL. I am convinced there is a query on this site that is wrong, too long and causes this issue. My server and MySQL logs show very little strain until the spike and issue happens. I would really,…
maestrojed
  • 221
  • 2
  • 2
3
votes
0 answers

Running out of memory with plenty of memory and swap

I have a Debian-based system that is running out of memory but there appears to be plenty of free memory. The box will run for about 6-12 days and then it will begin killing anything allocating memory (usually allocating skbs). Eventually, it kills…
Dom G
  • 31
  • 2
3
votes
4 answers

mysqld crashing almost every hour - mysqld invoked oom-killer

I am running wordpress on a centOS digital ocean droplet my mysql keeps crashing almost every hour -- with an out of memory error manually restarting mysqld brings it back up via sudo service mysqld restart Does anyone know what could be causing…
Alicia R
  • 31
  • 1
  • 6
2
votes
0 answers

What abbreviations in OOM Killer memory statistics report means?

When OOM Killer or kernel reports memory state it uses the next abbreviations Node 0 DMA: 26*4kB (M) 53*8kB (UM) 33*16kB (ME) 23*32kB (UME) 6*64kB (ME) 7*128kB (UME) 1*256kB (M) 2*512kB (ME) 0*1024kB 0*2048kB 0*4096kB = 4352kB Node 0 DMA32: 803*4kB…
Raf
  • 173
  • 7
2
votes
1 answer

OOM killer invoked despite tons of memory available?

I have a server where the OOM killer has been invoked once or twice almost each night since two weeks ago. The server should have more than enough memory it could free (cache/buffers, inactive_file below) as well as more than enough free swap space,…
Moritz Bunkus
  • 121
  • 1
  • 4
2
votes
3 answers

AWS WordPress site - OOM kills Apache

This question was originally asked on StackOverflow.com, and I've duplicated it to the more appropriate ServerFault.com site. The original question, which I've voted to close, can be found here I have a small, low traffic WordPress blog hosted on…
Nick Bull
  • 123
  • 4
2
votes
1 answer

An oom killer that I cannot explain

I am not able to understand why would kernel issue this oom killer when I see enough memory is available: I say enough memory is available after looking at Normal DMA Normal free lines This is an embedded nand flash based device with 256 MB…
Ankur Agarwal
  • 457
  • 1
  • 6
  • 15
2
votes
2 answers

Why is OOM killer hitting here

We have some VMs running kernel 2.26.26-2 under xen 4.0.3 with different CPU and RAM amounts and on some seeing almost random OOM events each rendering the VM unusable. Output is as follows, I have the following questions: What has _cpu_down to do…
tim
  • 1,217
  • 3
  • 11
  • 23
2
votes
1 answer

Using linux oom_score_adj to aim the oom daemon at the right target

On Ubuntu 11.04, /proc/[pid] contains oom_score_adj, but man proc describes the old oom_adj. What I need to arrange is that processes started by 'pbs' or 'gridengine' are killed before anything else gets killed. Can anyone propose an easier scheme…
bmargulies
  • 2,333
  • 3
  • 17
  • 20
1 2
3
4 5 6 7 8