On Tue, 23 Oct 2007, Alexey Dobriyan wrote:

quoted text
> Nasty OOM killings appear during massive parallel kernel builds with
> SLUB, but not with SLAB. By nasty I mean, cc1 processes are killed --
> object files in .ccache and tree are corrupted which makes me to
> blow up them entirely.

Hmmmm... Memory is corrupted? I guess a race destroys memory? 

quoted text
> 
> With SLAB this workload never went to OOM killer.
> With SLUB and pretty much all debugging enabled, it finishes to the end
> (albeit slowly).
> With SLUB and no debugging, OOM killer kicks in.

Not sure what this is. Maybe the slowing SLUB solves the race.
Could you try and boot with

slub_debug=F

to enable limited debugging?

quoted text
> cc1 invoked oom-killer: gfp_mask=0x1201d2, order=0, oomkilladj=0

Regular Order 0 alloc .... but why is there no memory available , 
reclaimed?

-
unsubscribe notice
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/