Re: [PATCH -mm 2/2] mm: kswapd carefully invoke compaction

[Rik van Riel]

On 01/11/2012 02:25 AM, KOSAKI Motohiro wrote:
> > With CONFIG_COMPACTION enabled, kswapd does not try to free
> > contiguous free pages, even when it is woken for a higher order
> > request.
> >
> > This could be bad for eg. jumbo frame network allocations, which
> > are done from interrupt context and cannot compact memory themselves.
> > Higher than before allocation failure rates in the network receive
> > path have been observed in kernels with compaction enabled.
> >
> > Teach kswapd to defragment the memory zones in a node, but only
> > if required and compaction is not deferred in a zone.
> >
> > Signed-off-by: Rik van Riel<riel@xxxxxxxxxx>
>
> I agree with we need asynchronous defragmentations feature. But, do we
> really need to use kswapd for compaction? While kswapd take a
> compaction work, it can't work to make free memory.

I believe we do need some background compaction, especially
to help allocations from network interrupts.

If you believe the compaction is better done from some
other thread, I guess we could do that, but truthfully, if
kswapd spends a lot of time doing compaction, I made a
mistake somewhere :)

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