Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757165Ab0GMUdS (ORCPT ); Tue, 13 Jul 2010 16:33:18 -0400 Received: from mail-bw0-f46.google.com ([209.85.214.46]:62441 "EHLO mail-bw0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753168Ab0GMUdR convert rfc822-to-8bit (ORCPT ); Tue, 13 Jul 2010 16:33:17 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type :content-transfer-encoding; b=lyuwCFq+iRSeYjlvGaIBhCIz4MX4OU8RY2MuPStKDmfJgmCY5HFP7PQEBpYLyzSCTC 9KOHEUFgip6nDQiqf7Xm0inMPsJr8qZpsZlNXVMtphq6UyxGKb94Ps28yZiaPyHXmiRK 9yFk6R9YdXGCCYbEK6OKSA6MXQBgtEUwC6fVM= MIME-Version: 1.0 In-Reply-To: <20100713101747.2835.45722.sendpatchset@danny.redhat> References: <20100713101650.2835.15245.sendpatchset@danny.redhat> <20100713101747.2835.45722.sendpatchset@danny.redhat> Date: Tue, 13 Jul 2010 23:33:14 +0300 X-Google-Sender-Auth: 4uQYfpYHj0XaJ958TKr01jbSIBY Message-ID: Subject: Re: [PATCH -mmotm 05/30] mm: sl[au]b: add knowledge of reserve pages From: Pekka Enberg To: Xiaotian Feng Cc: linux-mm@kvack.org, linux-nfs@vger.kernel.org, netdev@vger.kernel.org, riel@redhat.com, cl@linux-foundation.org, a.p.zijlstra@chello.nl, linux-kernel@vger.kernel.org, lwang@redhat.com, akpm@linux-foundation.org, davem@davemloft.net Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5328 Lines: 160 Hi Xiaotian! I would actually prefer that the SLAB, SLOB, and SLUB changes were in separate patches to make reviewing easier. Looking at SLUB: On Tue, Jul 13, 2010 at 1:17 PM, Xiaotian Feng wrote: > diff --git a/mm/slub.c b/mm/slub.c > index 7bb7940..7a5d6dc 100644 > --- a/mm/slub.c > +++ b/mm/slub.c > @@ -27,6 +27,8 @@ > ?#include > ?#include > ?#include > +#include "internal.h" > + > > ?/* > ?* Lock order: > @@ -1139,7 +1141,8 @@ static void setup_object(struct kmem_cache *s, struct page *page, > ? ? ? ? ? ? ? ?s->ctor(object); > ?} > > -static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) > +static > +struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node, int *reserve) > ?{ > ? ? ? ?struct page *page; > ? ? ? ?void *start; > @@ -1153,6 +1156,8 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) > ? ? ? ?if (!page) > ? ? ? ? ? ? ? ?goto out; > > + ? ? ? *reserve = page->reserve; > + > ? ? ? ?inc_slabs_node(s, page_to_nid(page), page->objects); > ? ? ? ?page->slab = s; > ? ? ? ?page->flags |= 1 << PG_slab; > @@ -1606,10 +1611,20 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, > ?{ > ? ? ? ?void **object; > ? ? ? ?struct page *new; > + ? ? ? int reserve; > > ? ? ? ?/* We handle __GFP_ZERO in the caller */ > ? ? ? ?gfpflags &= ~__GFP_ZERO; > > + ? ? ? if (unlikely(c->reserve)) { > + ? ? ? ? ? ? ? /* > + ? ? ? ? ? ? ? ?* If the current slab is a reserve slab and the current > + ? ? ? ? ? ? ? ?* allocation context does not allow access to the reserves we > + ? ? ? ? ? ? ? ?* must force an allocation to test the current levels. > + ? ? ? ? ? ? ? ?*/ > + ? ? ? ? ? ? ? if (!(gfp_to_alloc_flags(gfpflags) & ALLOC_NO_WATERMARKS)) > + ? ? ? ? ? ? ? ? ? ? ? goto grow_slab; OK, so assume that: (1) c->reserve is set to one (2) GFP flags don't allow dipping into the reserves (3) we've managed to free enough pages so normal allocations are fine (4) the page from reserves is not yet empty we will call flush_slab() and put the "emergency page" on partial list and clear c->reserve. This effectively means that now some other allocation can fetch the partial page and start to use it. Is this OK? Who makes sure the emergency reserves are large enough for the next out-of-memory condition where we swap over NFS? > + ? ? ? } > ? ? ? ?if (!c->page) > ? ? ? ? ? ? ? ?goto new_slab; > > @@ -1623,8 +1638,8 @@ load_freelist: > ? ? ? ?object = c->page->freelist; > ? ? ? ?if (unlikely(!object)) > ? ? ? ? ? ? ? ?goto another_slab; > - ? ? ? if (unlikely(SLABDEBUG && PageSlubDebug(c->page))) > - ? ? ? ? ? ? ? goto debug; > + ? ? ? if (unlikely(SLABDEBUG && PageSlubDebug(c->page) || c->reserve)) > + ? ? ? ? ? ? ? goto slow_path; > > ? ? ? ?c->freelist = get_freepointer(s, object); > ? ? ? ?c->page->inuse = c->page->objects; > @@ -1646,16 +1661,18 @@ new_slab: > ? ? ? ? ? ? ? ?goto load_freelist; > ? ? ? ?} > > +grow_slab: > ? ? ? ?if (gfpflags & __GFP_WAIT) > ? ? ? ? ? ? ? ?local_irq_enable(); > > - ? ? ? new = new_slab(s, gfpflags, node); > + ? ? ? new = new_slab(s, gfpflags, node, &reserve); > > ? ? ? ?if (gfpflags & __GFP_WAIT) > ? ? ? ? ? ? ? ?local_irq_disable(); > > ? ? ? ?if (new) { > ? ? ? ? ? ? ? ?c = __this_cpu_ptr(s->cpu_slab); > + ? ? ? ? ? ? ? c->reserve = reserve; > ? ? ? ? ? ? ? ?stat(s, ALLOC_SLAB); > ? ? ? ? ? ? ? ?if (c->page) > ? ? ? ? ? ? ? ? ? ? ? ?flush_slab(s, c); > @@ -1667,10 +1684,20 @@ new_slab: > ? ? ? ?if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit()) > ? ? ? ? ? ? ? ?slab_out_of_memory(s, gfpflags, node); > ? ? ? ?return NULL; > -debug: > - ? ? ? if (!alloc_debug_processing(s, c->page, object, addr)) > + > +slow_path: > + ? ? ? if (!c->reserve && !alloc_debug_processing(s, c->page, object, addr)) > ? ? ? ? ? ? ? ?goto another_slab; > > + ? ? ? /* > + ? ? ? ?* Avoid the slub fast path in slab_alloc() by not setting > + ? ? ? ?* c->freelist and the fast path in slab_free() by making > + ? ? ? ?* node_match() fail by setting c->node to -1. > + ? ? ? ?* > + ? ? ? ?* We use this for for debug and reserve checks which need > + ? ? ? ?* to be done for each allocation. > + ? ? ? ?*/ > + > ? ? ? ?c->page->inuse++; > ? ? ? ?c->page->freelist = get_freepointer(s, object); > ? ? ? ?c->node = -1; > @@ -2095,10 +2122,11 @@ static void early_kmem_cache_node_alloc(gfp_t gfpflags, int node) > ? ? ? ?struct page *page; > ? ? ? ?struct kmem_cache_node *n; > ? ? ? ?unsigned long flags; > + ? ? ? int reserve; > > ? ? ? ?BUG_ON(kmalloc_caches->size < sizeof(struct kmem_cache_node)); > > - ? ? ? page = new_slab(kmalloc_caches, gfpflags, node); > + ? ? ? page = new_slab(kmalloc_caches, gfpflags, node, &reserve); > > ? ? ? ?BUG_ON(!page); > ? ? ? ?if (page_to_nid(page) != node) { > -- > 1.7.1.1 > > -- > To unsubscribe, send a message with 'unsubscribe linux-mm' in > the body to majordomo@kvack.org. ?For more info on Linux MM, > see: http://www.linux-mm.org/ . > Don't email: email@kvack.org > -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/