From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by smtp.lore.kernel.org (Postfix) with ESMTP id 93AE9EB64D9 for ; Thu, 15 Jun 2023 03:58:49 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 2F2E96B0072; Wed, 14 Jun 2023 23:58:49 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 27C4B6B0074; Wed, 14 Jun 2023 23:58:49 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 11DB86B0078; Wed, 14 Jun 2023 23:58:49 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0012.hostedemail.com [216.40.44.12]) by kanga.kvack.org (Postfix) with ESMTP id F229E6B0072 for ; Wed, 14 Jun 2023 23:58:48 -0400 (EDT) Received: from smtpin06.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay03.hostedemail.com (Postfix) with ESMTP id AB1CDA0972 for ; Thu, 15 Jun 2023 03:58:48 +0000 (UTC) X-FDA: 80903625936.06.D3C54FF Received: from out30-119.freemail.mail.aliyun.com (out30-119.freemail.mail.aliyun.com [115.124.30.119]) by imf26.hostedemail.com (Postfix) with ESMTP id 81FA0140002 for ; Thu, 15 Jun 2023 03:58:45 +0000 (UTC) Authentication-Results: imf26.hostedemail.com; dkim=none; dmarc=pass (policy=none) header.from=alibaba.com; spf=pass (imf26.hostedemail.com: domain of baolin.wang@linux.alibaba.com designates 115.124.30.119 as permitted sender) smtp.mailfrom=baolin.wang@linux.alibaba.com ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1686801527; h=from:from:sender:reply-to:subject:subject:date:date: message-id:message-id:to:to:cc:cc:mime-version:mime-version: content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=0u0ecnQjkRg7x5Ki5twvQUTpnMqB16QomNDROEEroxI=; b=1YUwQjVqerJejKGIAa/BAb5VvSOmDOcjK8FlmBlG6bXxWEu//ZeOZbd5icGWWTuqwgze7E fKidG++S6aZHc8Bpfy4Zs4vsUWmWOh0qZ41Etp53yCBHoXmO2xFfb5h/eJvH+WA6Y5ej39 cqIAnyQhkwpl7I6Ldw4d2sX7AD/806Y= ARC-Authentication-Results: i=1; imf26.hostedemail.com; dkim=none; dmarc=pass (policy=none) header.from=alibaba.com; spf=pass (imf26.hostedemail.com: domain of baolin.wang@linux.alibaba.com designates 115.124.30.119 as permitted sender) smtp.mailfrom=baolin.wang@linux.alibaba.com ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1686801527; a=rsa-sha256; cv=none; b=fzFuIR2vIyVvs+5uEM3RaO2Wb+lImJCHOCwoao7p9YdzDQB4l/lEzwYoDLE6s9aMz85EoQ DAut3VF3B/rMY3QRKPhj3sDT0IPmmU/KD2NSc/g4LVpiVbEj1pnwe9bEgOLFrmKvyricxj 3kXoX7ntZ+ue8y+xKstGhEQ0Yscqdok= X-Alimail-AntiSpam:AC=PASS;BC=-1|-1;BR=01201311R201e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=ay29a033018046059;MF=baolin.wang@linux.alibaba.com;NM=1;PH=DS;RN=7;SR=0;TI=SMTPD_---0Vl8reEi_1686801520; Received: from 30.97.48.67(mailfrom:baolin.wang@linux.alibaba.com fp:SMTPD_---0Vl8reEi_1686801520) by smtp.aliyun-inc.com; Thu, 15 Jun 2023 11:58:41 +0800 Message-ID: <5f340d98-4ee0-35a9-58ed-943834d68042@linux.alibaba.com> Date: Thu, 15 Jun 2023 11:59:00 +0800 MIME-Version: 1.0 User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:102.0) Gecko/20100101 Thunderbird/102.11.2 Subject: Re: [PATCH v2] mm: compaction: skip memory hole rapidly when isolating migratable pages To: "Huang, Ying" , Mel Gorman , david@redhat.com Cc: akpm@linux-foundation.org, vbabka@suse.cz, linux-mm@kvack.org, linux-kernel@vger.kernel.org References: <770f9f61472b24b6bc89adbd71a77d9cf62bb54f.1686646361.git.baolin.wang@linux.alibaba.com> <20230614095501.m4porztaibchrgwx@techsingularity.net> <87ilbpo1d9.fsf@yhuang6-desk2.ccr.corp.intel.com> From: Baolin Wang In-Reply-To: <87ilbpo1d9.fsf@yhuang6-desk2.ccr.corp.intel.com> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit X-Rspam-User: X-Stat-Signature: r5a5ra54t6wxffnbap5dr4g54ui9qqrs X-Rspamd-Server: rspam07 X-Rspamd-Queue-Id: 81FA0140002 X-HE-Tag: 1686801525-209116 X-HE-Meta: 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 bH93PweG mv5P/zZDDjGcW7PgeFUPh34jj6GwthcQuswqW2qjP4E47HjT2EeFb4OoDU1SDvsMJt8/bSuyE/u9WsBULkDBlJoaugJmL0EKSz431TjhZjoBPH76TcPQL0ecdIqr8uAfQf2AAA147sBlZIyBpqyoGLZlQJhDDAU1VCKpQEiXQbSo00DfKm+ZP/YCyt2t5Z5h++d3DggSV0Ci++ep6slZPjW/HiJAy1hpXkxylZX7pT8WkDN2AGxIB4D7K3JhR+2aGij/o X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: On 6/15/2023 11:22 AM, Huang, Ying wrote: > Hi, Mel, > > Mel Gorman writes: > >> On Tue, Jun 13, 2023 at 04:55:04PM +0800, Baolin Wang wrote: >>> On some machines, the normal zone can have a large memory hole like >>> below memory layout, and we can see the range from 0x100000000 to >>> 0x1800000000 is a hole. So when isolating some migratable pages, the >>> scanner can meet the hole and it will take more time to skip the large >>> hole. From my measurement, I can see the isolation scanner will take >>> 80us ~ 100us to skip the large hole [0x100000000 - 0x1800000000]. >>> >>> So adding a new helper to fast search next online memory section >>> to skip the large hole can help to find next suitable pageblock >>> efficiently. With this patch, I can see the large hole scanning only >>> takes < 1us. >>> >>> [ 0.000000] Zone ranges: >>> [ 0.000000] DMA [mem 0x0000000040000000-0x00000000ffffffff] >>> [ 0.000000] DMA32 empty >>> [ 0.000000] Normal [mem 0x0000000100000000-0x0000001fa7ffffff] >>> [ 0.000000] Movable zone start for each node >>> [ 0.000000] Early memory node ranges >>> [ 0.000000] node 0: [mem 0x0000000040000000-0x0000000fffffffff] >>> [ 0.000000] node 0: [mem 0x0000001800000000-0x0000001fa3c7ffff] >>> [ 0.000000] node 0: [mem 0x0000001fa3c80000-0x0000001fa3ffffff] >>> [ 0.000000] node 0: [mem 0x0000001fa4000000-0x0000001fa402ffff] >>> [ 0.000000] node 0: [mem 0x0000001fa4030000-0x0000001fa40effff] >>> [ 0.000000] node 0: [mem 0x0000001fa40f0000-0x0000001fa73cffff] >>> [ 0.000000] node 0: [mem 0x0000001fa73d0000-0x0000001fa745ffff] >>> [ 0.000000] node 0: [mem 0x0000001fa7460000-0x0000001fa746ffff] >>> [ 0.000000] node 0: [mem 0x0000001fa7470000-0x0000001fa758ffff] >>> [ 0.000000] node 0: [mem 0x0000001fa7590000-0x0000001fa7ffffff] >>> >>> Signed-off-by: Baolin Wang >> >> This may only be necessary for non-contiguous zones so a check for >> zone_contiguous could be made but I suspect the saving, if any, would be >> marginal. >> >> However, it's subtle that block_end_pfn can end up in an arbirary location >> past the end of the zone or past cc->free_pfn. As the "continue" will update >> cc->migrate_pfn, that might lead to errors in the future. It would be a >> lot safer to pass in cc->free_pfn and do two things with the value. First, >> there is no point scanning for a valid online section past cc->free_pfn so >> terminating after cc->free_pfn may save some cycles. Second, cc->migrate_pfn >> does not end up with an arbitrary value which is a more defensive approach >> to any future programming errors. > > I have thought about this before. Originally, I had thought that we > were safe because cc->free_pfn should be in a online section and > block_end_pfn should reach cc->free_pfn before the end of zone. But > after checking more code and thinking about it again, I found that the > underlying sections may go offline under us during compaction. So that, > cc->free_pfn may be in a offline section or after the end of zone. So, > you are right, we need to consider the range of block_end_pfn. > > But, if we thought in this way (memory online/offline at any time), it > appears that we need to check whether the underlying section was > offlined. For example, is it safe to use "pfn_to_page()" in > "isolate_migratepages_block()"? Is it possible for the underlying > section to be offlined under us? It is possible. There is a previous discussion[1] about the race between pfn_to_online_page() and memory offline. [1] https://lore.kernel.org/lkml/87zgc6buoq.fsf@nvidia.com/T/#m642d91bcc726437e1848b295bc57ce249c7ca399