From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751922AbZH1PEt (ORCPT ); Fri, 28 Aug 2009 11:04:49 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751559AbZH1PEs (ORCPT ); Fri, 28 Aug 2009 11:04:48 -0400 Received: from mail-gx0-f205.google.com ([209.85.217.205]:37380 "EHLO mail-gx0-f205.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751206AbZH1PEr convert rfc822-to-8bit (ORCPT ); Fri, 28 Aug 2009 11:04:47 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; b=J/2Pg0mn+FLGwhMgpRgwMYJ+R+nS1WRIhFwQs8NBcuVh9AiXNi479GHJiOzg35Vp1N DJ0mRCDFOwFkQwYg8FsKuYOnmwxHShIYaCNLTvEKBydHqL0rqOxaYTvksgB6wsyzvSQS smp3jnToBI4LG9r23Ka1QfY3TM0+kDRZLyXPU= MIME-Version: 1.0 In-Reply-To: <1251449067-3109-3-git-send-email-mel@csn.ul.ie> References: <1251449067-3109-1-git-send-email-mel@csn.ul.ie> <1251449067-3109-3-git-send-email-mel@csn.ul.ie> Date: Sat, 29 Aug 2009 00:04:48 +0900 Message-ID: <28c262360908280804r4c40c7baw7bb535dd8c275960@mail.gmail.com> Subject: Re: [PATCH 2/2] page-allocator: Maintain rolling count of pages to free from the PCP From: Minchan Kim To: Mel Gorman Cc: Andrew Morton , Linux Memory Management List , Christoph Lameter , Nick Piggin , Linux Kernel Mailing List Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi, Mel. On Fri, Aug 28, 2009 at 5:44 PM, Mel Gorman wrote: > When round-robin freeing pages from the PCP lists, empty lists may be > encountered. In the event one of the lists has more pages than another, > there may be numerous checks for list_empty() which is undesirable. This > patch maintains a count of pages to free which is incremented when empty > lists are encountered. The intention is that more pages will then be freed > from fuller lists than the empty ones reducing the number of empty list > checks in the free path. > > Signed-off-by: Mel Gorman > --- >  mm/page_alloc.c |   23 ++++++++++++++--------- >  1 files changed, 14 insertions(+), 9 deletions(-) > > diff --git a/mm/page_alloc.c b/mm/page_alloc.c > index 65eedb5..9b86977 100644 > --- a/mm/page_alloc.c > +++ b/mm/page_alloc.c > @@ -536,32 +536,37 @@ static void free_pcppages_bulk(struct zone *zone, int count, >                                        struct per_cpu_pages *pcp) >  { >        int migratetype = 0; > +       int batch_free = 0; > >        spin_lock(&zone->lock); >        zone_clear_flag(zone, ZONE_ALL_UNRECLAIMABLE); >        zone->pages_scanned = 0; > >        __mod_zone_page_state(zone, NR_FREE_PAGES, count); > -       while (count--) { > +       while (count) { >                struct page *page; >                struct list_head *list; > >                /* > -                * Remove pages from lists in a round-robin fashion. This spinning > -                * around potentially empty lists is bloody awful, alternatives that > -                * don't suck are welcome > +                * Remove pages from lists in a round-robin fashion. A batch_free > +                * count is maintained that is incremented when an empty list is > +                * encountered. This is so more pages are freed off fuller lists > +                * instead of spinning excessively around empty lists >                 */ >                do { > +                       batch_free++; >                        if (++migratetype == MIGRATE_PCPTYPES) >                                migratetype = 0; >                        list = &pcp->lists[migratetype]; >                } while (list_empty(list)); How about increasing the weight by batch_free ? batch_free = 1 << (batch_free - 1); It's assumed that if batch_free is big, it means there are contiguous empty lists. Then it is likely to need more time to refill empty lists than one list refill. So I think it can decrease spinning empty list a little more. > > -               page = list_entry(list->prev, struct page, lru); > -               /* have to delete it as __free_one_page list manipulates */ > -               list_del(&page->lru); > -               trace_mm_page_pcpu_drain(page, 0, migratetype); > -               __free_one_page(page, zone, 0, migratetype); > +               do { > +                       page = list_entry(list->prev, struct page, lru); > +                       /* must delete as __free_one_page list manipulates */ > +                       list_del(&page->lru); > +                       __free_one_page(page, zone, 0, migratetype); > +                       trace_mm_page_pcpu_drain(page, 0, migratetype); > +               } while (--count && --batch_free && !list_empty(list)); >        } >        spin_unlock(&zone->lock); >  } > -- > 1.6.3.3 > > -- > 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 > -- Kind regards, Minchan Kim