From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752594Ab2GBHvH (ORCPT ); Mon, 2 Jul 2012 03:51:07 -0400 Received: from mail-pb0-f46.google.com ([209.85.160.46]:45672 "EHLO mail-pb0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751057Ab2GBHvF (ORCPT ); Mon, 2 Jul 2012 03:51:05 -0400 Message-ID: <4FF152E6.70009@gmail.com> Date: Mon, 02 Jul 2012 15:51:02 +0800 From: Sha Zhengju User-Agent: Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.23) Gecko/20110922 Thunderbird/3.1.15 MIME-Version: 1.0 To: Kamezawa Hiroyuki CC: linux-mm@kvack.org, cgroups@vger.kernel.org, gthelen@google.com, yinghan@google.com, akpm@linux-foundation.org, mhocko@suse.cz, linux-kernel@vger.kernel.org, Sha Zhengju Subject: Re: [PATCH 0/7] Per-cgroup page stat accounting References: <1340880885-5427-1-git-send-email-handai.szj@taobao.com> <4FED6604.9080603@jp.fujitsu.com> In-Reply-To: <4FED6604.9080603@jp.fujitsu.com> Content-Type: text/plain; charset=ISO-2022-JP Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 06/29/2012 04:23 PM, Kamezawa Hiroyuki wrote: > (2012/06/28 19:54), Sha Zhengju wrote: >> This patch series provide the ability for each memory cgroup to have independent >> dirty/writeback page stats. This can provide some information for per-cgroup direct >> reclaim. Meanwhile, we add more detailed dump messages for memcg OOMs. >> >> Three features are included in this patch series: >> (0).prepare patches for page accounting >> 1. memcg dirty page accounting >> 2. memcg writeback page accounting >> 3. memcg OOMs dump info >> >> In (0) prepare patches, we have reworked vfs set page dirty routines to make "modify >> page info" and "dirty page accouting" stay in one function as much as possible for >> the sake of memcg bigger lock. >> >> These patches are cooked based on Andrew's akpm tree. >> > Thank you !, it seems good in general. I'll review in detail, later. > > Do you have any performance comparison between before/after the series ? > I mean, set_page_dirty() is the hot-path and we should be careful to add a new accounting. Not yet, I sent it out as soon as I worked out this solution to check whether it's okay. I can test the series after most of people agree with it. Thanks, Sha From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from psmtp.com (na3sys010amx170.postini.com [74.125.245.170]) by kanga.kvack.org (Postfix) with SMTP id 825A96B0062 for ; Mon, 2 Jul 2012 03:51:05 -0400 (EDT) Received: by dakp5 with SMTP id p5so8599451dak.14 for ; Mon, 02 Jul 2012 00:51:04 -0700 (PDT) Message-ID: <4FF152E6.70009@gmail.com> Date: Mon, 02 Jul 2012 15:51:02 +0800 From: Sha Zhengju MIME-Version: 1.0 Subject: Re: [PATCH 0/7] Per-cgroup page stat accounting References: <1340880885-5427-1-git-send-email-handai.szj@taobao.com> <4FED6604.9080603@jp.fujitsu.com> In-Reply-To: <4FED6604.9080603@jp.fujitsu.com> Content-Type: text/plain; charset=ISO-2022-JP Content-Transfer-Encoding: 7bit Sender: owner-linux-mm@kvack.org List-ID: To: Kamezawa Hiroyuki Cc: linux-mm@kvack.org, cgroups@vger.kernel.org, gthelen@google.com, yinghan@google.com, akpm@linux-foundation.org, mhocko@suse.cz, linux-kernel@vger.kernel.org, Sha Zhengju On 06/29/2012 04:23 PM, Kamezawa Hiroyuki wrote: > (2012/06/28 19:54), Sha Zhengju wrote: >> This patch series provide the ability for each memory cgroup to have independent >> dirty/writeback page stats. This can provide some information for per-cgroup direct >> reclaim. Meanwhile, we add more detailed dump messages for memcg OOMs. >> >> Three features are included in this patch series: >> (0).prepare patches for page accounting >> 1. memcg dirty page accounting >> 2. memcg writeback page accounting >> 3. memcg OOMs dump info >> >> In (0) prepare patches, we have reworked vfs set page dirty routines to make "modify >> page info" and "dirty page accouting" stay in one function as much as possible for >> the sake of memcg bigger lock. >> >> These patches are cooked based on Andrew's akpm tree. >> > Thank you !, it seems good in general. I'll review in detail, later. > > Do you have any performance comparison between before/after the series ? > I mean, set_page_dirty() is the hot-path and we should be careful to add a new accounting. Not yet, I sent it out as soon as I worked out this solution to check whether it's okay. I can test the series after most of people agree with it. Thanks, Sha -- 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/ . Don't email: email@kvack.org From mboxrd@z Thu Jan 1 00:00:00 1970 From: Sha Zhengju Subject: Re: [PATCH 0/7] Per-cgroup page stat accounting Date: Mon, 02 Jul 2012 15:51:02 +0800 Message-ID: <4FF152E6.70009@gmail.com> References: <1340880885-5427-1-git-send-email-handai.szj@taobao.com> <4FED6604.9080603@jp.fujitsu.com> Mime-Version: 1.0 Content-Transfer-Encoding: 7bit Return-path: DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=message-id:date:from:user-agent:mime-version:to:cc:subject :references:in-reply-to:content-type:content-transfer-encoding; bh=Ws2uyHkODZgENTkt6u98i7DpW8CrCzlCrf1+4gHloms=; b=hIp0R66I+NKtH7tsol3LAwMRepsiPTaeS0h8bMM3XYRKKmqVSTQXKKButP7NzB8i8E KDqaZ8VoYYNixTuITiBQUtQB+cg31CD/QuejRwpAzJxpwhsTxaoDhovVdATnfY2YdyT+ 1vsRYCAhJXXdKH4lZGs66RMi/ACmCRUHFRStPJ8ibcMepiAK5n1Rth3IdyEK48j8iYEA rPkH8behtk1kTAE3qB97rpuJUh3GQEDv3AKYxqv7CCqKubNtPjRLAZrm41FxkSR3F/Z2 bTkBl7C8ZMqbsjY1ocL/YuLFkK7oaYYYYrAIrJ4rZodNfputvm14PuBJY/p8E6xM7/D8 diyQ== In-Reply-To: <4FED6604.9080603-+CUm20s59erQFUHtdCDX3A@public.gmane.org> Sender: cgroups-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org List-ID: Content-Type: text/plain; charset="us-ascii" To: Kamezawa Hiroyuki Cc: linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org, cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, gthelen-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org, yinghan-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org, akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org, mhocko-AlSwsSmVLrQ@public.gmane.org, linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Sha Zhengju On 06/29/2012 04:23 PM, Kamezawa Hiroyuki wrote: > (2012/06/28 19:54), Sha Zhengju wrote: >> This patch series provide the ability for each memory cgroup to have independent >> dirty/writeback page stats. This can provide some information for per-cgroup direct >> reclaim. Meanwhile, we add more detailed dump messages for memcg OOMs. >> >> Three features are included in this patch series: >> (0).prepare patches for page accounting >> 1. memcg dirty page accounting >> 2. memcg writeback page accounting >> 3. memcg OOMs dump info >> >> In (0) prepare patches, we have reworked vfs set page dirty routines to make "modify >> page info" and "dirty page accouting" stay in one function as much as possible for >> the sake of memcg bigger lock. >> >> These patches are cooked based on Andrew's akpm tree. >> > Thank you !, it seems good in general. I'll review in detail, later. > > Do you have any performance comparison between before/after the series ? > I mean, set_page_dirty() is the hot-path and we should be careful to add a new accounting. Not yet, I sent it out as soon as I worked out this solution to check whether it's okay. I can test the series after most of people agree with it. Thanks, Sha