Re: Major regression on hackbench with SLUB

[Steven Rostedt <rostedt@goodmis.org>]

On Mon, 10 Dec 2007, Björn Steinbrink wrote:
> >
> > The results are here:
> >
> > http://people.redhat.com/srostedt/slub/results/slab.op
> > http://people.redhat.com/srostedt/slub/results/slub.op
>
> Hm, you seem to be hitting the "another_slab" stuff in __slab_alloc
> alot. I wonder if !node_match triggers too often. We always start with
> the per cpu slab, if that one is on the wrong node, you'll always hit
> that "another_slab" path.

Well, I commented out the node_match part and it got 100% worse. It took
30 seconds to complete.

>
> After searching for way too long (given that I have no clue about that
> stuff anyway and just read the code out of curiousness), I noticed that
> the the cpu_to_node stuff on x86_64 seems to be initialized to 0xff
> (arch/x86/mm/numa_64.c), and Google brought me this dmesg output [1],
> which, AFAICT, shows that the per cpu slab setup is done _before_
> cpu_to_node is correctly setup. That would lead to the per cpu slabs all
> having node == 0xff, which looks pretty bad.

I didn't check to see if the internal set up of the node is correct
though.  I can put in some debug to see what I get.

>
> Disclaimer: I read the slub/numa/$WHATEVER_I_SAW_THERE for the first
> time, so this might be total bull ;-)

Well I'm a newbie on NUMA stuff too. I just got lucky enough to be able to
reserve this box ;-)

-- Steve

--
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/