Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756543Ab0F2PUd (ORCPT ); Tue, 29 Jun 2010 11:20:33 -0400 Received: from nlpi129.sbcis.sbc.com ([207.115.36.143]:60027 "EHLO nlpi129.prodigy.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756484Ab0F2PUc (ORCPT ); Tue, 29 Jun 2010 11:20:32 -0400 Date: Tue, 29 Jun 2010 10:19:37 -0500 (CDT) From: Christoph Lameter X-X-Sender: cl@router.home To: Minchan Kim cc: KOSAKI Motohiro , LKML , linux-mm , Andrew Morton , Mel Gorman , Rik van Riel , Johannes Weiner Subject: Re: [PATCH 1/2] vmscan: shrink_slab() require number of lru_pages, not page order In-Reply-To: Message-ID: References: <20100625201915.8067.A69D9226@jp.fujitsu.com> User-Agent: Alpine 2.00 (DEB 1167 2008-08-23) MIME-Version: 1.0 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: 1091 Lines: 29 On Sun, 27 Jun 2010, Minchan Kim wrote: > > What does the "lru_pages" parameter do in shrink_slab()? Looks > > like its only role is as a divison factor in a complex calculation of > > pages to be scanned. > > Yes. But I think it can make others confuse like this. Right. > Except zone_reclaim, lru_pages had been used for balancing slab > reclaim VS page reclaim. > So lru_page naming is a good. It is also good to make zone reclaim more deterministic by using the new counters. So I am not all opposed to the initial patch. Just clear things up a bit and make sure that this does not cause regressions because of too frequent calls to shrink_slab > So you intentionally passed order instead of the number of lru pages > for shrinking many slabs as possible as. Dont remember doing that. I suspect the parameter was renamed at some point. -- 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/