[RFC PATCH 0/8] Reduce filesystem writeback from page reclaim v2

[Andrew Lutomirski]

On Fri, Jul 29, 2011 at 5:50 AM, Minchan Kim <minchan.kim at gmail.com> wrote:
> Sorry for missing Ccing.
>
> On Fri, Jul 29, 2011 at 06:48:16PM +0900, Minchan Kim wrote:
>> On Thu, Jul 28, 2011 at 12:38:52PM +0100, Mel Gorman wrote:
>> > On Thu, Jul 28, 2011 at 01:18:21AM +0900, Minchan Kim wrote:
>> > > On Thu, Jul 21, 2011 at 05:28:42PM +0100, Mel Gorman wrote:
>> > > > Note how preventing kswapd reclaiming dirty pages pushes up its CPU
>>
>> <snip>
>>
>> > > > usage as it scans more pages but it does not get excessive due to
>> > > > the throttling.
>> > >
>> > > Good to hear.
>> > > The concern of this patchset was early OOM kill with too many scanning.
>> > > I can throw such concern out from now on.
>> > >
>> >
>> > At least, I haven't been able to trigger a premature OOM.
>>
>> AFAIR, Andrew had a premature OOM problem[1] but I couldn't track down at that time.
>> I think this patch series might solve his problem. Although it doesn't, it should not accelerate
>> his problem, at least.
>>
>> Andrew, Could you test this patchset?

Gladly, but not until Wednesday most likely.  I'm defending my thesis
on Monday :)

--Andy