Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752473AbcC2BFo (ORCPT ); Mon, 28 Mar 2016 21:05:44 -0400 Received: from resqmta-po-09v.sys.comcast.net ([96.114.154.168]:39467 "EHLO resqmta-po-09v.sys.comcast.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750972AbcC2BFo (ORCPT ); Mon, 28 Mar 2016 21:05:44 -0400 Date: Mon, 28 Mar 2016 20:05:41 -0500 (CDT) From: Christoph Lameter X-X-Sender: cl@east.gentwo.org To: js1304@gmail.com cc: Andrew Morton , Pekka Enberg , David Rientjes , Jesper Dangaard Brouer , linux-mm@kvack.org, linux-kernel@vger.kernel.org, Joonsoo Kim Subject: Re: [PATCH 07/11] mm/slab: racy access/modify the slab color In-Reply-To: <1459142821-20303-8-git-send-email-iamjoonsoo.kim@lge.com> Message-ID: References: <1459142821-20303-1-git-send-email-iamjoonsoo.kim@lge.com> <1459142821-20303-8-git-send-email-iamjoonsoo.kim@lge.com> Content-Type: text/plain; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3184 Lines: 95 On Mon, 28 Mar 2016, js1304@gmail.com wrote: > From: Joonsoo Kim > > Slab color isn't needed to be changed strictly. Because locking > for changing slab color could cause more lock contention so this patch > implements racy access/modify the slab color. This is a preparation step > to implement lockless allocation path when there is no free objects in > the kmem_cache. Acked-by: Christoph Lameter The rest of the description does not relate to this patch and does not actually reflect the improvement of applying this patch. Remove the rest? > Below is the result of concurrent allocation/free in slab allocation > benchmark made by Christoph a long time ago. I make the output simpler. > The number shows cycle count during alloc/free respectively so less > is better. > > * Before > Kmalloc N*alloc N*free(32): Average=365/806 > Kmalloc N*alloc N*free(64): Average=452/690 > Kmalloc N*alloc N*free(128): Average=736/886 > Kmalloc N*alloc N*free(256): Average=1167/985 > Kmalloc N*alloc N*free(512): Average=2088/1125 > Kmalloc N*alloc N*free(1024): Average=4115/1184 > Kmalloc N*alloc N*free(2048): Average=8451/1748 > Kmalloc N*alloc N*free(4096): Average=16024/2048 > > * After > Kmalloc N*alloc N*free(32): Average=355/750 > Kmalloc N*alloc N*free(64): Average=452/812 > Kmalloc N*alloc N*free(128): Average=559/1070 > Kmalloc N*alloc N*free(256): Average=1176/980 > Kmalloc N*alloc N*free(512): Average=1939/1189 > Kmalloc N*alloc N*free(1024): Average=3521/1278 > Kmalloc N*alloc N*free(2048): Average=7152/1838 > Kmalloc N*alloc N*free(4096): Average=13438/2013 > > It shows that contention is reduced for object size >= 1024 > and performance increases by roughly 15%. > > Signed-off-by: Joonsoo Kim > --- > mm/slab.c | 26 +++++++++++++------------- > 1 file changed, 13 insertions(+), 13 deletions(-) > > diff --git a/mm/slab.c b/mm/slab.c > index df11757..52fc5e3 100644 > --- a/mm/slab.c > +++ b/mm/slab.c > @@ -2536,20 +2536,7 @@ static int cache_grow(struct kmem_cache *cachep, > } > local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK); > > - /* Take the node list lock to change the colour_next on this node */ > check_irq_off(); > - n = get_node(cachep, nodeid); > - spin_lock(&n->list_lock); > - > - /* Get colour for the slab, and cal the next value. */ > - offset = n->colour_next; > - n->colour_next++; > - if (n->colour_next >= cachep->colour) > - n->colour_next = 0; > - spin_unlock(&n->list_lock); > - > - offset *= cachep->colour_off; > - > if (gfpflags_allow_blocking(local_flags)) > local_irq_enable(); > > @@ -2570,6 +2557,19 @@ static int cache_grow(struct kmem_cache *cachep, > if (!page) > goto failed; > > + n = get_node(cachep, nodeid); > + > + /* Get colour for the slab, and cal the next value. */ > + n->colour_next++; > + if (n->colour_next >= cachep->colour) > + n->colour_next = 0; > + > + offset = n->colour_next; > + if (offset >= cachep->colour) > + offset = 0; > + > + offset *= cachep->colour_off; > + > /* Get slab management. */ > freelist = alloc_slabmgmt(cachep, page, offset, > local_flags & ~GFP_CONSTRAINT_MASK, nodeid); >