Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754211Ab0A0XqV (ORCPT ); Wed, 27 Jan 2010 18:46:21 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753044Ab0A0XqU (ORCPT ); Wed, 27 Jan 2010 18:46:20 -0500 Received: from smtp-out.google.com ([216.239.44.51]:52057 "EHLO smtp-out.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752644Ab0A0XqT (ORCPT ); Wed, 27 Jan 2010 18:46:19 -0500 DomainKey-Signature: a=rsa-sha1; s=beta; d=google.com; c=nofws; q=dns; h=date:from:x-x-sender:to:cc:subject:in-reply-to:message-id: references:user-agent:mime-version:content-type:x-system-of-record; b=va2IKgS+Lq/5r4J4MFg+Kv+HZ5TO++A99vEhenPVUtwkg5MfjGzo8/h21X/4JgKYU Ys5S+HkAvJIDHCGqXqGcg== Date: Wed, 27 Jan 2010 15:46:15 -0800 (PST) From: David Rientjes X-X-Sender: rientjes@chino.kir.corp.google.com To: KAMEZAWA Hiroyuki cc: Andrew Morton , Balbir Singh , minchan.kim@gmail.com, linux-kernel@vger.kernel.org, linux-mm@kvack.org Subject: Re: [PATCH v3] oom-kill: add lowmem usage aware oom kill handling In-Reply-To: <20100127085355.f5306e78.kamezawa.hiroyu@jp.fujitsu.com> Message-ID: References: <20100121145905.84a362bb.kamezawa.hiroyu@jp.fujitsu.com> <20100122152332.750f50d9.kamezawa.hiroyu@jp.fujitsu.com> <20100125151503.49060e74.kamezawa.hiroyu@jp.fujitsu.com> <20100126151202.75bd9347.akpm@linux-foundation.org> <20100127085355.f5306e78.kamezawa.hiroyu@jp.fujitsu.com> User-Agent: Alpine 2.00 (DEB 1167 2008-08-23) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-System-Of-Record: true Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 937 Lines: 17 On Wed, 27 Jan 2010, KAMEZAWA Hiroyuki wrote: > Yes, I think you're right. But "breaking current behaviro of our servers!" > arguments kills all proposal to this area and this oom-killer or vmscan is > a feature should be tested by real users. Nobody has said we should discount lowmem rss when dealing with a GFP_DMA allocation, it simply wasn't possible until the lowmem rss counters were introduced in -mm. It would prevent the needless killing of innocent tasks which would not allow the page allocation to succeed, so it's a good feature to have. It doesn't need to be configurable at all, we just need to find a way to introduce it into the heuristic without mangling oom_adj. -- 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/