Messages in this thread | | | Date | Mon, 16 Nov 2009 17:57:39 +0000 | From | Mel Gorman <> | Subject | Re: [PATCH 0/5] Reduce GFP_ATOMIC allocation failures, candidate fix V3 |
| |
On Fri, Nov 13, 2009 at 10:04:21AM +0100, Frans Pop wrote: > On Thursday 12 November 2009, Mel Gorman wrote: > > Changelog since V2 > > o Dropped the kswapd-quickly-notice-high-order patch. In more detailed > > testing, it made latencies even worse as kswapd slept more on > > high-order congestion causing order-0 direct reclaims. > > o Added changes to how congestion_wait() works > > o Added a number of new patches altering the behaviour of reclaim > > I have tested this series on top of .32-rc7. First impression is that it > does seem to improve my test case, but does not yet completely solve it. > > My last gitk instance now loads more smoothly for most of the time it takes > to complete, but I still see a choke point where things freeze for a while > and where I get SKB allocation errors from my wireless. > However, that choke point does seem to happen later and to be shorter than > without the patches. >
I haven't fully figured out why this makes a difference yet, but with .32-rc7 and these patches, could you retry the test except beforehand do
cd /sys for SYS in `find -name low_latency`; do echo 0 > $SYS done
I believe the low_latency logic might be interfering with the number of clean pages available for kswapd to reclaim.
Thanks
-- Mel Gorman Part-time Phd Student Linux Technology Center University of Limerick IBM Dublin Software Lab
| |