Re: "Out of Memory: Killed process" errors on server running Oracle

[Tom Sightler <ttsig tuxyturvy com>]

On Wed, 2007-07-25 at 11:17 -0600, Eric Sisler wrote:
> > The kernel uses low memory to track allocations of all memory thus system with
> > 16GB of memory will use significantly more low memory than a system with 4GB,
> > perhaps as much as 4 times.  This extra pressure happens from the moment
> > you turn the system on before you do anything at all because the kernel
> > structures have to be sized for the potential of tracking allocations in
> > four times as much memory.
> 
> Thanks for this excellent explanation.  I have a dim recollection of
> this, but apparently not enough to trigger further though
> unassisted.  ;-)

Well, it's not that great of an explanation as it's probably not
factually accurate in the details, but the general idea is correct.

> > > Any idea which would be better - switching to 64-bit or running the
> > > hugemem kernel on 32-bit?
> 
> > The hugemem kernel has some overhead, I would go with 64-bit personally,
> > but it's up to you.  Hugemem is certainly easier because it's just a
> > quick kernel change.
> 
> Unfortunately I can't take the server with 16Gb out of production at the
> moment.  I have a slightly older server with 8Gb of RAM that has
> experienced similar problems that I can take out of service for testing.
> I'll check the values of 'LowTotal' & 'LowFree' with the 32-bit kernel,
> the 32-bit hugemem kernel & the 64-bit kernel, plus stress test the box
> by firing up multiple VMs.  I'll report my findings.

Also, don't ignore the lower_zone_protection settings.  We've found
those to help tremendously in OOM situations involving normal zone
starvation.

Later,
Tom