login
Header Space

 
 

Mailing list archives

Search results

Found 5 matching messages (0.072 seconds). Page 1 of 1.

Re: kswapd min order, slub max order [was Re: -mm merge plans for 2.6.24]

... Oct 2007, Andrew Morton wrote: > > # > > # slub && antifrag > > # > > have-kswapd-keep-a-minimum- ... to-increase-allocation-order.patch > > slub-reduce-antifrag-max-order.patch > > > > I ... 30%-60% longer with -mm than mainline, and it was > here that ...

linux-kernel - Mel Gorman - Oct 2 2007 - 14:38

kswapd min order, slub max order [was Re: -mm merge plans for 2.6.24]

... Oct 2007, Andrew Morton wrote: > # > # slub && antifrag > # > have-kswapd-keep-a-minimum-order- ... to-increase-allocation-order.patch > slub-reduce-antifrag-max-order.patch > > I think ... 30%-60% longer with -mm than mainline, and it was here that they ...

linux-kernel - Hugh Dickins - Oct 2 2007 - 12:06

Re: kswapd min order, slub max order [was Re: -mm merge plans for 2.6.24]

... Oct 2007, Andrew Morton wrote: > > # > > # slub && antifrag > > # > > have-kswapd-keep-a-minimum-order ... -increase-allocation-order.patch > > slub-reduce-antifrag-max-order.patch > > > > I ... %-60% longer with -mm than mainline, and it was > here that ...

linux-kernel - Nick Piggin - Oct 2 2007 - 05:10

Re: kswapd min order, slub max order [was Re: -mm merge plans for 2.6.24]

... wrote: > The maximum order of allocation used by SLUB may have ... system since small systems (128M was the > case that Peter found) ... Christoph Lameter --- mm/slub.c | 49 +++++++++++++++++++++++++------------------------ 1 file ...

linux-kernel - Christoph Lameter - Oct 2 2007 - 20:37

Re: kswapd min order, slub max order [was Re: -mm merge plans for 2.6.24]

... 60% longer with -mm than mainline, and it was > > here that ... on the expectation > > that higher orders can be used? And it ... effort. The maximum order of allocation used by SLUB may have ... has similar measures to avoid order 1 allocations for small systems ...

linux-kernel - Christoph Lameter - Oct 2 2007 - 14:28

speck-geostationary