linux-kernel - Re: [PATCH] - Improve drain pages performance on large systems

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <alpine.DEB.2.00.1102151858580.19953@chino.kir.corp.google.com>
Date:	Tue, 15 Feb 2011 19:01:34 -0800 (PST)
From:	David Rientjes <rientjes@...gle.com>
To:	Minchan Kim <minchan.kim@...il.com>
cc:	Jack Steiner <steiner@....com>, linux-mm@...ck.org,
	Andrew Morton <akpm@...ux-foundation.org>,
	linux-kernel@...r.kernel.org, Mel Gorman <mel@....ul.ie>
Subject: Re: [PATCH] - Improve drain pages performance on large systems

On Wed, 16 Feb 2011, Minchan Kim wrote:

> > Index: linux/mm/page_alloc.c
> > ===================================================================
> > --- linux.orig/mm/page_alloc.c  2011-02-15 16:28:36.165921713 -0600
> > +++ linux/mm/page_alloc.c       2011-02-15 16:29:43.085502487 -0600
> > @@ -592,10 +592,24 @@ static void free_pcppages_bulk(struct zo
> >        int batch_free = 0;
> >        int to_free = count;
> >
> > +       /*
> > +        * Quick scan of zones. If all are empty, there is nothing to do.
> > +        */
> > +       for (migratetype = 0; migratetype < MIGRATE_PCPTYPES; migratetype++) {
> > +               struct list_head *list;
> > +
> > +               list = &pcp->lists[migratetype];
> > +               if (!list_empty(list))
> > +                       break;
> > +       }
> > +       if (migratetype == MIGRATE_PCPTYPES)
> > +               return;
> > +
> >        spin_lock(&zone->lock);
> >        zone->all_unreclaimable = 0;
> >        zone->pages_scanned = 0;
> >
> > +       migratetype = 0;
> >        while (to_free) {
> >                struct page *page;
> >                struct list_head *list;
> 
> It does make sense to me.
> Although new code looks to be rather costly in small box, anyway we
> use the same logic  in while loop so cache would be hot. so cost would
> be little.
> 

I was going to mention the implications for small machines as well, this 
doesn't look good for callers that know free_pcppages_bulk() will do 
something.

> But how about this? This one never affect fast-critical path.
> 
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index ff7e158..2dfb61a 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -1095,8 +1095,10 @@ static void drain_pages(unsigned int cpu)
>                 pset = per_cpu_ptr(zone->pageset, cpu);
> 
>                 pcp = &pset->pcp;
> -               free_pcppages_bulk(zone, pcp->count, pcp);
> -               pcp->count = 0;
> +               if (pcp->count > 0) {
> +                       free_pcppages_bulk(zone, pcp->count, pcp);
> +                       pcp->count = 0;
> +               }
>                 local_irq_restore(flags);
>         }
>  }

Right, this is 2ff754fa upstream.  I'm wondering if Jack still sees the 
same problem since 2.6.38-rc3.