All of lore.kernel.org
 help / color / mirror / Atom feed
From: Wu Fengguang <fengguang.wu@intel.com>
To: Chris Frost <frost@cs.ucla.edu>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Steve Dickson <steved@redhat.com>,
	David Howells <dhowells@redhat.com>,
	Xu Chenfeng <xcf@ustc.edu.cn>,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	Steve VanDeBogart <vandebo-lkml@nerdbox.net>
Subject: Re: [PATCH] mm/readahead.c: update the LRU positions of in-core pages, too
Date: Tue, 26 Jan 2010 21:32:17 +0800	[thread overview]
Message-ID: <20100126133217.GB25407@localhost> (raw)
In-Reply-To: <20100125223635.GC2822@frostnet.net>

On Mon, Jan 25, 2010 at 03:36:35PM -0700, Chris Frost wrote:
> I changed Wu's patch to add a PageLRU() guard that I believe is required
> and optimized zone lock acquisition to only unlock and lock at zone changes.
> This optimization seems to provide a 10-20% system time improvement for
> some of my GIMP benchmarks and no improvement for other benchmarks.

> +			del_page_from_lru_list(zone, page, lru);
> +			add_page_to_lru_list(zone, page, lru);
> +		}
> +		put_page(page);

Hmm. put_page() inside lru_lock can deadlock. So you need to further
optimize the code to do pagevec_lookup() and pagevec_release() plus
cond_resched().

Thanks,
Fengguang

WARNING: multiple messages have this Message-ID (diff)
From: Wu Fengguang <fengguang.wu@intel.com>
To: Chris Frost <frost@cs.ucla.edu>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Steve Dickson <steved@redhat.com>,
	David Howells <dhowells@redhat.com>,
	Xu Chenfeng <xcf@ustc.edu.cn>,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	Steve VanDeBogart <vandebo-lkml@nerdbox.net>
Subject: Re: [PATCH] mm/readahead.c: update the LRU positions of in-core pages, too
Date: Tue, 26 Jan 2010 21:32:17 +0800	[thread overview]
Message-ID: <20100126133217.GB25407@localhost> (raw)
In-Reply-To: <20100125223635.GC2822@frostnet.net>

On Mon, Jan 25, 2010 at 03:36:35PM -0700, Chris Frost wrote:
> I changed Wu's patch to add a PageLRU() guard that I believe is required
> and optimized zone lock acquisition to only unlock and lock at zone changes.
> This optimization seems to provide a 10-20% system time improvement for
> some of my GIMP benchmarks and no improvement for other benchmarks.

> +			del_page_from_lru_list(zone, page, lru);
> +			add_page_to_lru_list(zone, page, lru);
> +		}
> +		put_page(page);

Hmm. put_page() inside lru_lock can deadlock. So you need to further
optimize the code to do pagevec_lookup() and pagevec_release() plus
cond_resched().

Thanks,
Fengguang

--
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: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  parent reply	other threads:[~2010-01-26 13:32 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-01-20 21:55 [PATCH] mm/readahead.c: update the LRU positions of in-core pages, too Chris Frost
2010-01-20 21:55 ` Chris Frost
2010-01-21  5:47 ` Wu Fengguang
2010-01-21  5:47   ` Wu Fengguang
2010-01-23  4:03   ` Chris Frost
2010-01-23  4:03     ` Chris Frost
2010-01-23 10:22     ` Wu Fengguang
2010-01-23 10:22       ` Wu Fengguang
2010-01-25  0:42       ` KAMEZAWA Hiroyuki
2010-01-25  0:42         ` KAMEZAWA Hiroyuki
2010-01-25  2:45         ` Wu Fengguang
2010-01-25  2:45           ` Wu Fengguang
2010-01-25 22:36           ` Chris Frost
2010-01-25 22:36             ` Chris Frost
2010-01-26 13:02             ` Wu Fengguang
2010-01-26 13:02               ` Wu Fengguang
2010-01-26 13:32             ` Wu Fengguang [this message]
2010-01-26 13:32               ` Wu Fengguang
2010-01-31 14:31               ` Wu Fengguang
2010-01-31 14:31                 ` Wu Fengguang
2010-02-01  2:06                 ` Chris Frost
2010-02-01  2:06                   ` Chris Frost
2010-02-01  2:17                   ` Wu Fengguang
2010-02-01  2:17                     ` Wu Fengguang
2010-02-02  0:15                     ` Chris Frost
2010-02-02  0:15                       ` Chris Frost
2010-01-27  7:09   ` Minchan Kim
2010-01-27  7:09     ` Minchan Kim
2010-01-27 12:21     ` Wu Fengguang
2010-01-27 12:21       ` Wu Fengguang
2010-01-28  7:16     ` Steve VanDeBogart
2010-01-28  7:16       ` Steve VanDeBogart
2010-01-28  8:09       ` Minchan Kim
2010-01-28  8:09         ` Minchan Kim

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20100126133217.GB25407@localhost \
    --to=fengguang.wu@intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=dhowells@redhat.com \
    --cc=frost@cs.ucla.edu \
    --cc=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=steved@redhat.com \
    --cc=vandebo-lkml@nerdbox.net \
    --cc=xcf@ustc.edu.cn \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.