From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753087Ab1A2Mr5 (ORCPT ); Sat, 29 Jan 2011 07:47:57 -0500 Received: from mail-pz0-f46.google.com ([209.85.210.46]:41515 "EHLO mail-pz0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752416Ab1A2Mr4 (ORCPT ); Sat, 29 Jan 2011 07:47:56 -0500 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type; b=nR/U2p44ERWq1L3ULJSWcURoPVpfXCH5KjiHPoXws2fw0/rGfYjvrydmspn606NOCi 6Ytv3bf3vXbHSlFvlr++winiMhAxQR1pMf3dI9MYAcgrqlHtDD+q4QWyYdM4ggvPBdT7 4PtG9TaV0Xrk9bf+vmvkZjsjSfM8ntgCadJ4g= MIME-Version: 1.0 In-Reply-To: <20110128122229.6a4c74a2.kamezawa.hiroyu@jp.fujitsu.com> References: <20110128122229.6a4c74a2.kamezawa.hiroyu@jp.fujitsu.com> Date: Sat, 29 Jan 2011 18:17:56 +0530 X-Google-Sender-Auth: 304ybpkDzBIT3Uc8LCdcaLHLMH0 Message-ID: Subject: Re: [BUGFIX][PATCH 0/4] Fixes for memcg with THP From: Balbir Singh To: KAMEZAWA Hiroyuki Cc: "linux-mm@kvack.org" , "linux-kernel@vger.kernel.org" , "hannes@cmpxchg.org" , "nishimura@mxp.nes.nec.co.jp" Content-Type: text/plain; charset=ISO-8859-1 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Jan 28, 2011 at 8:52 AM, KAMEZAWA Hiroyuki wrote: > > On recent -mm, when I run make -j 8 under 200M limit of memcg, as > == > # mount -t cgroup none /cgroup/memory -o memory > # mkdir /cgroup/memory/A > # echo 200M > /cgroup/memory/A/memory.limit_in_bytes > # echo $$ > /cgroup/memory/A/tasks > # make -j 8 kernel > == > > I see hangs with khugepaged. That's because memcg's memory reclaim > routine doesn't handle HUGE_PAGE request in proper way. And khugepaged > doesn't know about memcg. > > This patch set is for fixing above hang. Patch 1-3 seems obvious and > has the same concept as patches in RHEL. Do you have any backtraces? Are they in the specific patches? Balbir From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail191.messagelabs.com (mail191.messagelabs.com [216.82.242.19]) by kanga.kvack.org (Postfix) with ESMTP id D23EE8D0039 for ; Sat, 29 Jan 2011 07:47:58 -0500 (EST) Received: by pzk27 with SMTP id 27so735192pzk.14 for ; Sat, 29 Jan 2011 04:47:56 -0800 (PST) MIME-Version: 1.0 In-Reply-To: <20110128122229.6a4c74a2.kamezawa.hiroyu@jp.fujitsu.com> References: <20110128122229.6a4c74a2.kamezawa.hiroyu@jp.fujitsu.com> Date: Sat, 29 Jan 2011 18:17:56 +0530 Message-ID: Subject: Re: [BUGFIX][PATCH 0/4] Fixes for memcg with THP From: Balbir Singh Content-Type: text/plain; charset=ISO-8859-1 Sender: owner-linux-mm@kvack.org To: KAMEZAWA Hiroyuki Cc: "linux-mm@kvack.org" , "linux-kernel@vger.kernel.org" , "hannes@cmpxchg.org" , "nishimura@mxp.nes.nec.co.jp" List-ID: On Fri, Jan 28, 2011 at 8:52 AM, KAMEZAWA Hiroyuki wrote: > > On recent -mm, when I run make -j 8 under 200M limit of memcg, as > == > # mount -t cgroup none /cgroup/memory -o memory > # mkdir /cgroup/memory/A > # echo 200M > /cgroup/memory/A/memory.limit_in_bytes > # echo $$ > /cgroup/memory/A/tasks > # make -j 8 kernel > == > > I see hangs with khugepaged. That's because memcg's memory reclaim > routine doesn't handle HUGE_PAGE request in proper way. And khugepaged > doesn't know about memcg. > > This patch set is for fixing above hang. Patch 1-3 seems obvious and > has the same concept as patches in RHEL. Do you have any backtraces? Are they in the specific patches? Balbir -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/ Don't email: email@kvack.org