Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755526AbZFDKGv (ORCPT ); Thu, 4 Jun 2009 06:06:51 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751710AbZFDKGn (ORCPT ); Thu, 4 Jun 2009 06:06:43 -0400 Received: from cmpxchg.org ([85.214.51.133]:42039 "EHLO cmpxchg.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751153AbZFDKGn (ORCPT ); Thu, 4 Jun 2009 06:06:43 -0400 Date: Thu, 4 Jun 2009 12:04:36 +0200 From: Johannes Weiner To: KAMEZAWA Hiroyuki Cc: Andrew Morton , Rik van Riel , Peter Zijlstra , Hugh Dickins , Andi Kleen , linux-mm@kvack.org, linux-kernel@vger.kernel.org Subject: Re: [patch][v2] swap: virtual swap readahead Message-ID: <20090604100436.GA1602@cmpxchg.org> References: <20090602223738.GA15475@cmpxchg.org> <20090604104628.99520342.kamezawa.hiroyu@jp.fujitsu.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20090604104628.99520342.kamezawa.hiroyu@jp.fujitsu.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 724 Lines: 20 On Thu, Jun 04, 2009 at 10:46:28AM +0900, KAMEZAWA Hiroyuki wrote: > I wonder (I just wonder..) can we add code like following here ? > > /* we do _readahead_ here. Then, we don't want to add too much jobs to vm/IO*/ > if (swp != entry) > gfp_mask &= ~__GFP_WAIT > > + page = read_swap_cache_async(swp, gfp_mask, vma, pos); > > too slow ? Good idea, certainly worth evaluating. But not in this patch, I don't want to change _everything_ at once :-) Thanks, Hannes -- 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/