From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751579AbbIJWJG (ORCPT ); Thu, 10 Sep 2015 18:09:06 -0400 Received: from mail-pa0-f46.google.com ([209.85.220.46]:33340 "EHLO mail-pa0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751018AbbIJWJE (ORCPT ); Thu, 10 Sep 2015 18:09:04 -0400 Date: Thu, 10 Sep 2015 18:08:57 -0400 From: Tejun Heo To: Christoph Lameter Cc: Tang Chen , jiang.liu@linux.intel.com, mika.j.penttila@gmail.com, mingo@redhat.com, akpm@linux-foundation.org, rjw@rjwysocki.net, hpa@zytor.com, yasu.isimatu@gmail.com, isimatu.yasuaki@jp.fujitsu.com, kamezawa.hiroyu@jp.fujitsu.com, izumi.taku@jp.fujitsu.com, gongzhaogang@inspur.com, qiaonuohan@cn.fujitsu.com, x86@kernel.org, linux-acpi@vger.kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, Gu Zheng Subject: Re: [PATCH v2 3/7] x86, gfp: Cache best near node for memory allocation. Message-ID: <20150910220857.GN8114@mtj.duckdns.org> References: <1441859269-25831-1-git-send-email-tangchen@cn.fujitsu.com> <1441859269-25831-4-git-send-email-tangchen@cn.fujitsu.com> <20150910192935.GI8114@mtj.duckdns.org> <20150910193819.GJ8114@mtj.duckdns.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.23 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hello, On Thu, Sep 10, 2015 at 05:02:31PM -0500, Christoph Lameter wrote: > > Also, shouldn't kmalloc_node() or any public allocator fall back > > automatically to a near node w/o GFP_THISNODE? Why is this failing at > > all? I get that cpu id -> node id mapping changing messes up the > > locality but allocations shouldn't fail, right? > > Without a node specification allocations are subject to various > constraints and memory policies. It is not simply going to the next node. > The memory load may require spreading out the allocations over multiple > nodes, the app may have specified which nodes are to be used etc etc. Yeah, sure, but even w/ node specified, it shouldn't fail unless THISNODE, right? Thanks. -- tejun