From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1752552AbbKYU5N (ORCPT <rfc822;w@1wt.eu>);
	Wed, 25 Nov 2015 15:57:13 -0500
Received: from mail-pa0-f46.google.com ([209.85.220.46]:33332 "EHLO
	mail-pa0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1751904AbbKYU5K (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Wed, 25 Nov 2015 15:57:10 -0500
Date: Wed, 25 Nov 2015 12:57:08 -0800 (PST)
From: David Rientjes <rientjes@google.com>
X-X-Sender: rientjes@chino.kir.corp.google.com
To: Michal Hocko <mhocko@kernel.org>
cc: Andrew Morton <akpm@linux-foundation.org>, Mel Gorman <mgorman@suse.de>,
        Johannes Weiner <hannes@cmpxchg.org>, linux-mm@kvack.org,
        LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 1/2] mm, oom: Give __GFP_NOFAIL allocations access to
 memory reserves
In-Reply-To: <20151125111801.GD27283@dhcp22.suse.cz>
Message-ID: <alpine.DEB.2.10.1511251254260.24689@chino.kir.corp.google.com>
References: <1448448054-804-1-git-send-email-mhocko@kernel.org> <1448448054-804-2-git-send-email-mhocko@kernel.org> <alpine.DEB.2.10.1511250248540.32374@chino.kir.corp.google.com> <20151125111801.GD27283@dhcp22.suse.cz>
User-Agent: Alpine 2.10 (DEB 1266 2009-07-14)
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Wed, 25 Nov 2015, Michal Hocko wrote:

> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 8034909faad2..94b04c1e894a 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -2766,8 +2766,13 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
>  			goto out;
>  	}
>  	/* Exhausted what can be done so it's blamo time */
> -	if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL))
> +	if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) {
>  		*did_some_progress = 1;
> +
> +		if (gfp_mask & __GFP_NOFAIL)
> +			page = get_page_from_freelist(gfp_mask, order,
> +					ALLOC_NO_WATERMARKS, ac);
> +	}
>  out:
>  	mutex_unlock(&oom_lock);
>  	return page;

Well, sure, that's one way to do it, but for cpuset users, wouldn't this 
lead to a depletion of the first system zone since you've dropped 
ALLOC_CPUSET and are doing ALLOC_NO_WATERMARKS in the same call?  
get_page_from_freelist() shouldn't be doing any balancing over the set of 
allowed zones.  Can you justify depleting memory reserves on a zone 
outside of the set of allowed cpuset mems rather than trying to drop 
ALLOC_CPUSET first?