From: David Rientjes Subject: Re: [PATCH 3/4] mm: slub: Do not take expensive steps for SLUBs speculative high-order allocations Date: Tue, 17 May 2011 12:35:32 -0700 (PDT) Message-ID: References: <1305295404-12129-1-git-send-email-mgorman@suse.de> <1305295404-12129-4-git-send-email-mgorman@suse.de> <20110517084227.GI5279@suse.de> <20110517162256.GO5279@suse.de> Mime-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Cc: Mel Gorman , Andrew Morton , James Bottomley , Colin King , Raghavendra D Prabhu , Jan Kara , Chris Mason , Pekka Enberg , Rik van Riel , Johannes Weiner , linux-fsdevel , linux-mm , linux-kernel , linux-ext4 To: Christoph Lameter Return-path: In-Reply-To: Sender: linux-fsdevel-owner@vger.kernel.org List-Id: linux-ext4.vger.kernel.org On Tue, 17 May 2011, Christoph Lameter wrote: > > In this particular patch, the success rate for high order allocations > > would likely decrease in low memory conditions albeit the latency when > > calling the page allocator will be lower and the disruption to the > > system will be less (no copying or reclaim of pages). My expectation > > would be that it's cheaper for SLUB to fall back than compact memory > > or reclaim pages even if this means a slab page is smaller until more > > memory is free. However, if the "goodness" criteria is high order > > allocation success rate, the patch shouldn't be merged. > > The criteria is certainly overall system performance and not a high order > allocation rate. > SLUB definitely depends on these higher order allocations being successful for performance, dropping back to the min order is a last resort as opposed to failing the kmalloc(). If it's the last resort, then it makes sense that we'd want to try both compaction and reclaim while we're already in the page allocator as we go down the slub slowpath. Why not try just a little harder (compaction and/or reclaim) to alloc the cache's preferred order?