Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1751458AbdINQj7 (ORCPT <rfc822;w@1wt.eu>);
        Thu, 14 Sep 2017 12:39:59 -0400
Received: from resqmta-po-08v.sys.comcast.net ([96.114.154.167]:51266 "EHLO
        resqmta-po-08v.sys.comcast.net" rhost-flags-OK-OK-OK-OK)
        by vger.kernel.org with ESMTP id S1751277AbdINQj5 (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Thu, 14 Sep 2017 12:39:57 -0400
Date: Thu, 14 Sep 2017 11:39:53 -0500 (CDT)
From: Christopher Lameter <cl@linux.com>
X-X-Sender: cl@nuc-kabylake
To: Tim Chen <tim.c.chen@linux.intel.com>
cc: Linus Torvalds <torvalds@linux-foundation.org>,
        "Liang, Kan" <kan.liang@intel.com>,
        Mel Gorman <mgorman@techsingularity.net>,
        Peter Zijlstra <peterz@infradead.org>, Ingo Molnar <mingo@elte.hu>,
        Andi Kleen <ak@linux.intel.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Johannes Weiner <hannes@cmpxchg.org>, Jan Kara <jack@suse.cz>,
        "Eric W . Biederman" <ebiederm@xmission.com>,
        Davidlohr Bueso <dave@stgolabs.net>, linux-mm <linux-mm@kvack.org>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 2/2 v2] sched/wait: Introduce lock breaker in
 wake_up_page_bit
In-Reply-To: <a9e74f64-dee6-dc23-128e-8ef8c7383d77@linux.intel.com>
Message-ID: <alpine.DEB.2.20.1709141138340.30688@nuc-kabylake>
References: <83f675ad385d67760da4b99cd95ee912ca7c0b44.1503677178.git.tim.c.chen@linux.intel.com> <f10f4c25-49c0-7ef5-55c2-769c8fd9bf90@linux.intel.com> <CA+55aFzNikMsuPAaExxT1Z8MfOeU6EhSn6UPDkkz-MRqamcemg@mail.gmail.com> <CA+55aFx67j0u=GNRKoCWpsLRDcHdrjfVvWRS067wLUSfzstgoQ@mail.gmail.com>
 <CA+55aFzy981a8Ab+89APi6Qnb9U9xap=0A6XNc+wZsAWngWPzA@mail.gmail.com> <CA+55aFwyCSh1RbJ3d5AXURa4_r5OA_=ZZKQrFX0=Z1J3ZgVJ5g@mail.gmail.com> <CA+55aFy18WCqZGwkxH6dTZR9LD9M5nXWqEN8DBeZ4LvNo4Y0BQ@mail.gmail.com> <37D7C6CF3E00A74B8858931C1DB2F077537A07E9@SHSMSX103.ccr.corp.intel.com>
 <CA+55aFzotfXc07UoVtxvDpQOP8tEt8pgxeYe+cGs=BDUC_A4pA@mail.gmail.com> <37D7C6CF3E00A74B8858931C1DB2F077537A1C19@SHSMSX103.ccr.corp.intel.com> <CA+55aFwECeY-x=_du67qAxkta_0LeUw_BQA1kP337SBV3znN2Q@mail.gmail.com> <bd2d09ea-47d1-c0a7-8d4d-604bb4bc28bc@linux.intel.com>
 <CA+55aFx3WY00yvEDBg7TagX4h_-QO71=HAq5GAT8awtewRXONQ@mail.gmail.com> <a9e74f64-dee6-dc23-128e-8ef8c7383d77@linux.intel.com>
User-Agent: Alpine 2.20 (DEB 67 2015-01-07)
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
X-CMAE-Envelope: MS4wfMgkxv1rZn4EbgWTkrtmbMbE4Psv8eXhaDi1xnGcOYHa5zx0J4C34s/5x5ozpfd+DCi0P3/lwAL7t3iQPFb/S4Z/RR5JpwSgKLYviO4X3248Gzw5QVyO
 9ICksYDOHeCFPoZQu0C/IPXFgP7Xbq2X1rbtB+0v0PDBq7wBkYDU0jTu8j9amweZpNQZzJNwcAnWXE8rTX6wKVjLGHtC/f1RIMFqSoAn3vqrhtgBQ8MYIs+g
 XCprwuVqRCX75EPlDqR9GTuEkPSarVeeyKl64uzi1FG567sQEbcqt5lq63SxPzxclnSf2UUtwP1ERZewKmm3Tk0+Z/uOhCFCF8+QbnuBttZT7445hcCiE2YM
 m0Hc3XfBPLlad4anOnTaA3QiLBQKklkCMB3y4J93SoIyDbGAaFNJfat538XN2bD4u5XbniSf+5IPRyl6WHWoD8A42KSwf7j7XYn8HOjAVIHY+fF6Bp0Rj39i
 FUf+u1xz4zTQaR1RT0Qu0GhpCPFdLHuPWiN19Uv5NOPwWe+qT7RWBXsbjM7pWGQNP6fsnM23j47RXsiikbJrL5mNYvvSdfZMHuM91QcLJbVpgmHANr/ae3pQ
 fp8=
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org
Content-Length: 695
Lines: 12

On Wed, 13 Sep 2017, Tim Chen wrote:

> Here's what the customer think happened and is willing to tell us.
> They have a parent process that spawns off 10 children per core and
> kicked them to run. The child processes all access a common library.
> We have 384 cores so 3840 child processes running.  When migration occur on
> a page in the common library, the first child that access the page will
> page fault and lock the page, with the other children also page faulting
> quickly and pile up in the page wait list, till the first child is done.

I think we need some way to avoid migration in cases like this. This is
crazy. Page migration was not written to deal with something like this.