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 X-Spam-Level: X-Spam-Status: No, score=-2.7 required=3.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS,HTML_FONT_LOW_CONTRAST, HTML_MESSAGE,MAILING_LIST_MULTI,MSGID_FROM_MTA_HEADER,SPF_HELO_NONE,SPF_PASS, T_KAM_HTML_FONT_INVALID autolearn=no autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 19D46C433ED for ; Wed, 28 Apr 2021 04:03:32 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id 7A0A46140B for ; Wed, 28 Apr 2021 04:03:31 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 7A0A46140B Authentication-Results: mail.kernel.org; dmarc=fail (p=quarantine dis=none) header.from=oppo.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id CE0A36B0036; Wed, 28 Apr 2021 00:03:30 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id CB6C56B006E; Wed, 28 Apr 2021 00:03:30 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id ABBE76B0070; Wed, 28 Apr 2021 00:03:30 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0125.hostedemail.com [216.40.44.125]) by kanga.kvack.org (Postfix) with ESMTP id 8485D6B0036 for ; Wed, 28 Apr 2021 00:03:30 -0400 (EDT) Received: from smtpin12.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay05.hostedemail.com (Postfix) with ESMTP id 39ACC181AF5C4 for ; Wed, 28 Apr 2021 04:03:30 +0000 (UTC) X-FDA: 78080431380.12.AD345C3 Received: from APC01-SG2-obe.outbound.protection.outlook.com (mail-eopbgr1310053.outbound.protection.outlook.com [40.107.131.53]) by imf12.hostedemail.com (Postfix) with ESMTP id 67F4213A for ; Wed, 28 Apr 2021 04:03:17 +0000 (UTC) ARC-Seal: i=1; a=rsa-sha256; s=arcselector9901; d=microsoft.com; cv=none; b=BfRZWfKSCdDYE5Rs7Sg4HsHwwF9dF2TwK4jNMKfexW78t5ZABlwI/2OELuiOTcRoVk+NXi0vO4sAS/duCJJFJYof9wZgn3+UWDiw2232mABV7b4I4VHF5sKWY5FC9pyfTXS9tMzlIPxKH02aYnauvEZPiqEYS7usW1aW1RvjrsXUGJJEaXA61d1+J52q8qDzNHcyje3/tyYqNnpmuype667ZdbJ0r4Geo8C/7j0TLLyunNBVmZQGxqrSDS1kCzz6oQx4SCWTs/EyBStJgMMwipYoTPHc04QilXzYWPiDl6DeyQphwy8Y3KJthBILeIQK4XAUSaKuUcfn+vANS3/Cqg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector9901; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=FSCxQrmCB/yLBr3R2JWqxUDJiW4tUl8m/Kpztpu4x6c=; b=k1AetDWEuG/iJ4AvD9xudiAn6jbgYhR44Oy4U2SURs+BrCf5/TqNleMt+QNN1csG5ITaaUWyq3jjM485YRqMWMJcM81CXiX8KwOhlLtMEplNvb4IOhTu1xY1j4oTdpxKreiYv+dTrtRo/E6dGtVy1vG0gsigTr6n0aBYTI0kfV5mMMOzuei2gHldlf6zQUCAHBq1ZHqtKEmpngkBrv8vU6jMRvxxFOm99Ir7bkZdzMb/3en6sf7mPj5u8NLhwqGbx7i0ixU1tmcY7xKB0k6v0S97Vm4bJ0mgwiPzKUAims6lfZNEH1K8J7tbBja52ozTx/XetJY8IzKy9kPnwGOodw== ARC-Authentication-Results: i=1; mx.microsoft.com 1; spf=pass smtp.mailfrom=oppo.com; dmarc=pass action=none header.from=oppo.com; dkim=pass header.d=oppo.com; arc=none DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=oppo.com; s=selector1; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=FSCxQrmCB/yLBr3R2JWqxUDJiW4tUl8m/Kpztpu4x6c=; b=B4D+0gbFb5KJW8cVnt6Vo7YFvz8DfOP3EZIOct96ERAJRIyetd4ikNwKdAyho1e2ayTybSj6Tn2hfvPRrBI14BbqzEEA9Yzmt8b7r1G+fIhXdykDX4H4vNA/828cr9L2gtTIDZ7mNJN/BSUnCpFbx/xMUZu5SU6c0icZJQJDc4U= Authentication-Results: redhat.com; dkim=none (message not signed) header.d=none;redhat.com; dmarc=none action=none header.from=oppo.com; Received: from TY2PR02MB4431.apcprd02.prod.outlook.com (2603:1096:404:8003::13) by TYZPR02MB4816.apcprd02.prod.outlook.com (2603:1096:400:59::6) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.4065.20; Wed, 28 Apr 2021 04:03:20 +0000 Received: from TY2PR02MB4431.apcprd02.prod.outlook.com ([fe80::4c93:7ebd:15c1:e997]) by TY2PR02MB4431.apcprd02.prod.outlook.com ([fe80::4c93:7ebd:15c1:e997%4]) with mapi id 15.20.4065.027; Wed, 28 Apr 2021 04:03:20 +0000 Date: Wed, 28 Apr 2021 12:03:18 +0800 From: "lipeifeng@oppo.com" To: "David Hildenbrand" , "Vlastimil Babka" , peifengl55 , schwidefsky , heiko.carstens , zhangshiming , zhouhuacai , guoweichao , guojian Cc: linux-s390 , linux-kernel , linux-mm Subject: Re: Re: [RFC] mm: support multi_freearea to the reduction of external fragmentation References: <20210414023803.937-1-lipeifeng@oppo.com>, , , <2021042611194631963076@oppo.com>, <7dcc87f5-9ae5-613a-0cf4-820334592b90@redhat.com>, <20210426181947189100132@oppo.com>, <9808e36a-9e4e-d1e2-da49-beb567681a8b@redhat.com> X-GUID: 8B697870-8169-45FF-92DB-E1CE9C74C836 X-Has-Attach: no X-Mailer: Foxmail 7.2.16.188[cn] Message-ID: <2021042812031720737751@oppo.com> Content-Type: multipart/alternative; boundary="----=_001_NextPart151103575751_=----" X-Originating-IP: [58.252.5.70] X-ClientProxiedBy: HKAPR03CA0035.apcprd03.prod.outlook.com (2603:1096:203:c9::22) To TY2PR02MB4431.apcprd02.prod.outlook.com (2603:1096:404:8003::13) MIME-Version: 1.0 X-MS-Exchange-MessageSentRepresentingType: 1 Received: from PA80248179 (58.252.5.70) by HKAPR03CA0035.apcprd03.prod.outlook.com (2603:1096:203:c9::22) with Microsoft SMTP Server (version=TLS1_1, cipher=TLS_RSA_WITH_AES_256_CBC_SHA) id 15.20.4087.17 via Frontend Transport; Wed, 28 Apr 2021 04:03:18 +0000 X-MS-PublicTrafficType: Email X-MS-Office365-Filtering-Correlation-Id: 040664a2-f7ef-4bf7-924c-08d909fa8ee2 X-MS-TrafficTypeDiagnostic: TYZPR02MB4816: X-MS-Exchange-Transport-Forked: True X-Microsoft-Antispam-PRVS: X-MS-Oob-TLC-OOBClassifiers: OLM:10000; X-MS-Exchange-SenderADCheck: 1 X-Microsoft-Antispam: BCL:0; X-Microsoft-Antispam-Message-Info: 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 X-Forefront-Antispam-Report: CIP:255.255.255.255;CTRY:;LANG:en;SCL:1;SRV:;IPV:NLI;SFV:NSPM;H:TY2PR02MB4431.apcprd02.prod.outlook.com;PTR:;CAT:NONE;SFS:(4636009)(136003)(366004)(396003)(376002)(39860400002)(346002)(6636002)(8936002)(52116002)(956004)(2616005)(86362001)(6496006)(38350700002)(186003)(66476007)(16526019)(33964004)(53546011)(4326008)(38100700002)(8676002)(58226001)(66946007)(66556008)(2906002)(36756003)(30864003)(1076003)(98106002)(316002)(5660300002)(26005)(110136005)(83380400001)(37786003)(54906003)(6486002)(478600001)(11606007);DIR:OUT;SFP:1101; X-MS-Exchange-AntiSpam-MessageData: =?utf-8?B?OFVUSlFlOUtNcklTSzVDOVpqQ2d1UzdidzBoWU5odHhlWm1WSVFHZGF3WVpC?= =?utf-8?B?akNpcnZMcHNxbXdGelFnc0ZaUU92V1Z3eTlwdjJ4d1RwYS9sZGJGUFR5WnF3?= =?utf-8?B?UHRuRWM2Z2U5ZFpQNis0c25rSmlJZ2tGU0FVaFVXRmMwNTYrdUtPOTBudC93?= =?utf-8?B?aE1TemNZaW13ODVyRGErWUU0KzU3Y0JPMkJKaUJnZFUwVVlKN2RzTGZGQzBC?= =?utf-8?B?TVF1UEFOcVBnQVJOMEVRbkw5NjBPb0FhSHVkek91cEloOWJaUFJPMFRXZFU0?= =?utf-8?B?cTNkY1RGOWxTRlJqS3VBajNvRVJxaldBZEJxRzhQRnZSYStqTDNJRkFBeFhS?= =?utf-8?B?QWV6VFF4TERKZmowb0RLeG81dmVZNzNMMnZSZHRwL29nRCt2ZURwNUE5QWYr?= =?utf-8?B?U0d6QzFCT3FyWFZRb2VHVVdBbFNHVnB5TmttVS9YWVNnT05oUnpPZkU0UHFX?= =?utf-8?B?NVFFZXFpNVFURThaM1hxdzVhNkpBQlZMeUJYeU5WNjZBSnJDblJJdVZVVUl3?= =?utf-8?B?Q080bzRxeVBadEFLL2wrTm9LMjBYTzJ5L056emYxcHNPaXF2dFRkNWcxaUlu?= =?utf-8?B?cTRQVVVycDZRKzB5MXRzMWc0VTdka0ZISTBVVnVDWEdZc00zL3d0ZjNVS095?= =?utf-8?B?RWIzNHFGMTd0MG1IRUdrSWE5dG9ZaURYZUYxSFpKbGswNGVvV1JyOElzQUty?= =?utf-8?B?cFdNT242b0FEK0tjTDlEcFNLOXZLNWtxdmVicFphM1N3bjB2K0VqS3JrRzJ2?= =?utf-8?B?clhQdko1TkI1aENKS2czQkVZUENtSytpWkVCc3FOTVduWWJzQ3A5enNzV1RU?= =?utf-8?B?L1hKM2lscjdwVUk0OVRaK1VGL3hvWkc0SzlQSGlxYU5GVW5kWmZNcTZBcXF1?= =?utf-8?B?MDFyK25FUDdUTWZudjFwMk9PUUVYM0R0bmZlSmJuSWVUWHVaNUY5RVNhOU1x?= =?utf-8?B?bDZTdXQ1QTk0a0ZGUmFJUmtmaDBxVmJvQzRLRVZYWU5ad1dBU21VRjM0V0tZ?= =?utf-8?B?Q3Zrd24ydU1YWWlXQkVjNXM0MXRURUlCU0VOVTd0S0dhUUt3OFVtc2FiWmJa?= =?utf-8?B?bEZVTXJKald6RjU5R29PVStPK3AyZXlUVFQ0b0NiK2FvWTlBRVJlVnVyUHlM?= =?utf-8?B?VXpOL2RpSjJmTjlJZXc2MlJ0QkFlS3VUTmxnZkZKTFphcWgrQjFBMTZJb0lY?= =?utf-8?B?THRyWENDRVRZTHpUQ2hITGJoejc4K010bWIxQ1hXbzNLMzJ2OHlsd2Ercm5G?= =?utf-8?B?dmpxY2IzUXZHd3lDak95SEVHTjd1aG9hRnVoLzBLajdta1JFL29KNXFQYlNG?= =?utf-8?B?cC8vSkhoRVQ5cFBSSFRrb2tqdkRWSjJpY2tUWnhLU29ZWDRmTW9kQWVVOU1i?= =?utf-8?B?S2duc20xcG54SlA2aFFDZFBMQkQxLzhrOXBiVUJPSXFTVU8xLzRLalFhSkFU?= =?utf-8?B?bW02UmxtdTZQTUZiWHFTS1M3dWdJVk80VEpMaFdnYXZ0Y3U3NmFjYmQ0eU9D?= =?utf-8?B?MzNHcFlMVjlkdTh3NjFPSlUxTUdXcThiWEhLb1QyWUN6Z2V5dDBIZDZUYzF5?= =?utf-8?B?TzVIeG5FM1NodUxMcEJpMnRLYXBpQk0yRkx5bTZuNmVNaGRPL2xXWTFWZU81?= =?utf-8?B?c0lhVk83R0h4SWRGbjQ3RlZRMmYrNTh0d0ZBVUVrV2wxTWhmYnF6K0t6eVFL?= =?utf-8?B?QnhVMmYxSWlyQnZBazR3Vmxkc2MyOUhHcTk2UU16ZDFMRmlLWTZBN2FMQllv?= =?utf-8?Q?WlG1+PIcuNiDimpn2dYrRvKr8Bwb6fVfpI89Kp6?= X-OriginatorOrg: oppo.com X-MS-Exchange-CrossTenant-Network-Message-Id: 040664a2-f7ef-4bf7-924c-08d909fa8ee2 X-MS-Exchange-CrossTenant-AuthSource: TY2PR02MB4431.apcprd02.prod.outlook.com X-MS-Exchange-CrossTenant-AuthAs: Internal X-MS-Exchange-CrossTenant-OriginalArrivalTime: 28 Apr 2021 04:03:19.9993 (UTC) X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted X-MS-Exchange-CrossTenant-Id: f1905eb1-c353-41c5-9516-62b4a54b5ee6 X-MS-Exchange-CrossTenant-MailboxType: HOSTED X-MS-Exchange-CrossTenant-UserPrincipalName: z9R+AP7FJTmnx3kSTcLmokaT2+QQvbcVTYFDMZahZVlgVdFN5FHmwemcaLug19B4joJ+/So32PyawPWIzJluUA== X-MS-Exchange-Transport-CrossTenantHeadersStamped: TYZPR02MB4816 X-Rspamd-Server: rspam05 X-Rspamd-Queue-Id: 67F4213A X-Stat-Signature: e1gf4ec5op6zqxgz1zp5aq1xup3h68gx Received-SPF: none (oppo.com>: No applicable sender policy available) receiver=imf12; identity=mailfrom; envelope-from=""; helo=APC01-SG2-obe.outbound.protection.outlook.com; client-ip=40.107.131.53 X-HE-DKIM-Result: pass/pass X-HE-Tag: 1619582597-391701 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: ------=_001_NextPart151103575751_=---- Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: base64 SGkgRGF2aWQgSGlsZGVuYnJhbmTvvJoNCg0KPj4gT2theSwgYnV0IHRoZW4gSSBhc3N1bWUgdGhl IHRhcmdldCBnb2FsIG9mIHlvdXIgcGF0Y2ggc2V0IGlzIHRvIG1pbmltaXplDQo+PiBDUFUgY29u c3VtcHRpb24vYWxsb2NhdGlvbiBzdGFsbCB0aW1lIHdoZW4gYWxsb2NhdGluZyBsYXJnZXIgb3Jk ZXIgcGFnZXMuDQogDQo+PiBDdXJyZW50bHkgeW91IHN0YXRlICJ0aGUgcHJvYmFibGl0eSBvZiBo aWdoLW9yZGVyLXBhZ2VzIGFsbG9jYXRpb24gd291bGQNCj4+IGJlIGluY3JlYXNlZCBzaWduaWZp Y2FudGx5IiwgYnV0IEkgYXNzdW1lIHRoYXQncyB0aGVuIG5vdCAxMDAlIGNvcnJlY3QuDQo+PiBX aGF0IHlvdSBtZWFzdXJlIGlzIHRoZSBzdGFsbCB0aW1lIHRvIGFsbG9jYXRlIGhpZ2hlciBvcmRl ciBwYWdlcywgbm90DQo+PiB0aGF0IHlvdSBjYW4gYWxsb2NhdGUgdGhlbS4NCg0KWW91IGFyZSBy aWdodCB0aGF0IG11bHRpX2ZyZWVhcmVhIGlzIHRvIHRvIHNwZWVkIHRoZSByYXRlIG9mIGxhcmdl LW9yZGVyLXBhZ2VzDQphbGxvY2F0aW9uIGluc3RlYWQgb2YgaW5jcmVhc2luZyB0aGUgcHJvYmFs aXR5IG9mIGl0IGlmIENPTkZJR19DT01QQUNUSU9OIGlzDQpvcGVuLg0KDQo+PiBPa2F5LCBhZ2Fp biwgdGhpcyBpcyB0aGVuIHNvbWUgb3B0aW1pemF0aW9uIGZvciBhbGxvY2F0aW9uIHNwZWVkOyB3 aGljaA0KPj4gbWFrZXMgaXQgbGVzcyBhdHRyYWN0aXZlIElNSE8gKGF0IGxlYXN0IGZvciBtb3Jl IGludmFzaXZlIGNoYW5nZXMpLA0KPj4gYmVjYXVzZSBJIHN1c3BlY3QgdGhpcyBtb3N0bHkgaGVs cHMgaW4gY29ybmVyIGNhc2VzIChNb25rZXkgYmVuY2htYXJrcw0KPj4gY29ybmVyIGNhc2VzIEFG QUlVKS4NCg0KSSByZWFsbHkgYWdyZWUgd2l0aCB0aGUgcHJlY2lzZW5lc3Mgb2YgdGhlIGNvbW11 bml0eSB0aGF0IGlmIHdlIHdhbnQgdG8gbWVyZ2UgdGhlDQpwYXRjaCBpbiBiYXNlbGluZSwgd2Ug d291bGQgZG8gbW9yZSB0ZXN0IHRvIHByb29mIHRoYXQgdGhlIHBhdGNoIHdpbGwgbm90IGRlZ3Jh ZGVkDQp0byBhIGRlZ3JlZSB0aGF0IHBlb3BsZSBjYXJlLiBCdXQsIG1heWJlIHRoZXJlIGFyZSB0 aGUgZGV0YWlsZWQgdGVzdC1saXN0IGZvciB1cyB0bw0KdGVzdCwgb3Igd2UgcmVhbGx5IGRvbid0 IGtub3cgaG93IHRvIHByb29mIHRoZXJlIGFyZSBubyBhbnkgc2lkZS1lZmZlY3RzIG9uIGFsbCBz aXR1YXRpb24NCm9mIG1lbW9yeS1vcHQuDQpJdCBpcyBhIHF1ZXN0aW9uIHRoYXQgaGFzIHB1enps ZWQgbWUgZm9yIGEgbG9uZyB0aW1lLg0KDQo+PiBFc3NlbnRpYWxseSBDT05GSUdfU1BBUlNFTUVN LCB3aGVyZWJ5IHdlIGNhbiBoYXZlIGh1Z2UgaG9sZXMgaW4gcGh5c2ljYWwNCj4+IG1lbW9yeSBs YXlvdXQgYW5kIG1lbW9yeSBhcmVhcyBjb21pbmcvZ29pbmcgd2l0aCBtZW1vcnkgaG90KHVuKXBs dWcuDQo+PiBVc3VhbGx5IHdlIG1hbmFnZSBhbGwgbWV0YWRhdGEgcGVyIHNlY3Rpb24uIEZvciBl eGFtcGxlLCBwYWdlYmxvY2tzIGFyZQ0KPj4gYWxsb2NhdGVkIHBlciBzZWN0aW9uLiBXZSBhdm9p ZCBhcnJheXMgdGhhdCBkZXBlbmQgb24gdGhlDQo+PiBpbml0aWFsL21heGltdW0gcGh5c2ljYWwg bWVtb3J5IHNpemUuDQoNCkNPTkZJR19TUFJTRU1FTSBoYXMgYmVlbiBvcGVuZWQgaW4gc29tZSBv ZiBvdXIgcHJvZHVjdCB3aXRoIFFjb20tcGxhdGZvcm0gYW5kDQpNVEsgcGxhdGZvcm0uIEFGQUlL LCBtdWx0aV9mcmVlYXJlYSB3b3VsZCBub3QgYnJpbmcgcHJvYmxlbSB0byBpdO+8n2JlY2F1c2Ug dGhlIHBhdGNoDQpqdXN0IG1hbmFnZSB0aGUgcGh5c2ljYWwgbWVtb3J5IG9mIHpvbmUgdG8gc2Vy dmVyYWwgc2VjdGlvbihmcmVlX2FyZWEpIGFuZCBhZGp1c3QgdGhlDQp0aGUgcmFuZ2Ugb2YgcGFn ZXMtUEZOIGZvciBidWRkeS1hbGxvYy1wYWdlcyBieSB0aGUgYWxsb2N0aW9uLW9yZGVyLiBXaXRo IG1lbW9yeQ0KaG90KHVuKXBsdWcsIHdlIHdvdWxkIGluaXRpYWxpemUgdGhlIG1lbWJlcnMgb2Yg Im11bHRpX2ZyZWVhcmVhIiBpbiB6b25lLg0KDQpUaGUgcGF0Y2ggaGFzIGJlZW4gbWVyZ2VkIGlu IHRoZSBiYXNlbGluZSBvZiBvdXIgcHJvZHVjdCB0aGF0IGhhcyBiZWVuIHNvbGQgYWxsIG92ZXIg dGhlDQp3b3JsZCB3aXRoIExpbnV4LTQuNC80LjkvNC4xOSBzbyB0aGF0IGkgZG9uJ3QgdGhpbmsg dGhlcmUgd2lsbCBiZSB0b28gbXVjaCByaXNrLiBPZiBjb3Vyc2UsDQppIG1pZ2h0IGJlIHdyb25n Lg0KDQoNCg0KDQpsaXBlaWZlbmdAb3Bwby5jb20NCiANCkZyb206IERhdmlkIEhpbGRlbmJyYW5k DQpEYXRlOiAyMDIxLTA0LTI3IDIwOjQ2DQpUbzogbGlwZWlmZW5nQG9wcG8uY29tOyBWbGFzdGlt aWwgQmFia2E7IHBlaWZlbmdsNTU7IHNjaHdpZGVmc2t5OyBoZWlrby5jYXJzdGVuczsgemhhbmdz aGltaW5nOyB6aG91aHVhY2FpOyBndW93ZWljaGFvOyBndW9qaWFuDQpDQzogbGludXgtczM5MDsg bGludXgta2VybmVsOyBsaW51eC1tbQ0KU3ViamVjdDogUmU6IFtSRkNdIG1tOiBzdXBwb3J0IG11 bHRpX2ZyZWVhcmVhIHRvIHRoZSByZWR1Y3Rpb24gb2YgZXh0ZXJuYWwgZnJhZ21lbnRhdGlvbg0K T24gMjYuMDQuMjEgMTI6MTksIGxpcGVpZmVuZ0BvcHBvLmNvbSB3cm90ZToNCj4gSGkgRGF2aWQg SGlsZGVuYnJhbmQgPG1haWx0bzpkYXZpZEByZWRoYXQuY29tPu+8mg0KPiANCj4gID4+IEFuZCB5 b3UgZG9uJ3QgbWVudGlvbiB3aGF0IHRoZSBiYXNlbGluZSBjb25maWd1cmF0aW9uIHdhcy4gRm9y IGV4YW1wbGUsDQo+ICA+PiBob3cgd2FzIGNvbXBhY3Rpb24gY29uZmlndXJlZD8NCj4gID4+IEp1 c3QgdG8gY2xhcmlmeSwgd2hhdCBpcyBtb25rZXk/DQo+ICA+PiBNb25rZXkgSFRUUCBzZXJ2ZXI/ IE1vbmtleVRlc3QgZGlzayBiZW5jaG1hcms/IFVJL0FwcGxpY2F0aW9uIEV4ZXJjaXNlcg0KPiAg Pj4gTW9ua2V5Pw0KPiAtLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0t LS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tDQo+IEkgYW0gc29ycnkg dGhhdCBpIGRpZG4ndCAgZ2l2ZSBhIGNsZWFyIGV4cGxhbmF0aW9uIGFib3V0IE1vbmtleS4NCj4g SXQgbWVhbnQgICJVSS9BcHBsaWNhdGlvbiBFeGVyY2lzZXIgTW9ua2V5IiBmcm9tIGdvb2dsZS4N Cj4gDQo+IEV4Y3VzZSBtZSwgbGV0IG1lIGludHJvZHVjZSBvdXIgdGVzdDoNCj4gDQogDQpUaGFu a3MgZm9yIG1vcmUgZGV0YWlscyBvbiB0aGUgdGVzdC4NCiANCj4gMS4gcmVjb3JkIENPTVBBQ1Rf U1RBTEwNCj4gV2UgdGVzdGVkIHRoZSBwYXRjaCBvbiBsaW51eC00LjQvbGludXgtNC45L2xpbnV4 LTQuMTQvbGludXgtNC4xOSBhbmQgdGhlDQo+IHJlc3VsdHMgc2hvd3MgdGhhdCB0aGUgcGF0Y2gg aXMgZWZmZWN0aXZlIGluIHJlZHVjaW5nIENPTVBBQ1RTVEFMTC4NCj4gICAgICAtIG1vbmtleSBm b3IgMTIgaG91cnMuDQo+ICAgICAgLSByZWNvcmQgQ09NUEFDVFNUQUxMIGFmdGVyIHRlc3QuDQo+ IA0KPiBUZXN0LXJlc3VsdDogcmVkdWNlZCBDT01QQUNUU1RBTEwgYnkgOTUuNiUgd2l0aCB0aGUg cGF0Y2guDQo+ICh0aGUgbWFjaGluZSB3aXRoIDQgZ2lnYWJ5dGVzIG9mIHBoeXNpY2FsIG1lbWVy eSBhbmQgaW4gbGludXgtNC4xOS4pDQo+IC0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0t LQ0KPiAgICAgICAgICAgICAgICAgICAgICAgfCAgIENPTVBBQ1RTVEFMTA0KPiAtLS0tLS0tLS0t LS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0NCj4gICAgIG9yaSAgICAgICAgICAgICAgfCAgICAgMjE4 OQ0KPiAtLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0NCj4gb3B0aW1pemF0aW9uIHwg ICAgICA5NQ0KPiAtLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0NCj4gDQo+IEkgZnVs bHkgYWdyZWUgd2l0aCB0aGUgdmFsdWUgb2YgY29tcGFjdGlvbiwgYnV0IGNvbXBhY3Rpb24gYWxz byBicmluZyBjcHUNCj4gY29uc3VtcHRpb24gYW5kIHdpbGwgaW5jcmVhc2UgdGhlIHRpbWUgb2Yg YWxsb2Nfc3RhbGwuIFNvIGlmIHdlIGNhbiBsZXQgbW9yZQ0KPiBmcmVlIGhpZ2gtb3JkZXJzLXBh Z2VzIGluIGJ1ZGR5IGluc3RlYWQgb2Ygc2lnbmFsIHBhZ2VzLCBpdCB3aWxsIGRlY3JlYXNlDQo+ IENPTVBBQ1RfU1RBTEwgYW5kIHNwZWVkIHVwIG1lbW9yeSBhbGxvY2F0aW9uLg0KIA0KT2theSwg YnV0IHRoZW4gSSBhc3N1bWUgdGhlIHRhcmdldCBnb2FsIG9mIHlvdXIgcGF0Y2ggc2V0IGlzIHRv IG1pbmltaXplIA0KQ1BVIGNvbnN1bXB0aW9uL2FsbG9jYXRpb24gc3RhbGwgdGltZSB3aGVuIGFs bG9jYXRpbmcgbGFyZ2VyIG9yZGVyIHBhZ2VzLg0KIA0KQ3VycmVudGx5IHlvdSBzdGF0ZSAidGhl IHByb2JhYmxpdHkgb2YgaGlnaC1vcmRlci1wYWdlcyBhbGxvY2F0aW9uIHdvdWxkIA0KYmUgaW5j cmVhc2VkIHNpZ25pZmljYW50bHkiLCBidXQgSSBhc3N1bWUgdGhhdCdzIHRoZW4gbm90IDEwMCUg Y29ycmVjdC4gDQpXaGF0IHlvdSBtZWFzdXJlIGlzIHRoZSBzdGFsbCB0aW1lIHRvIGFsbG9jYXRl IGhpZ2hlciBvcmRlciBwYWdlcywgbm90IA0KdGhhdCB5b3UgY2FuIGFsbG9jYXRlIHRoZW0uDQog DQo+IA0KPiAyLiByZWNvcmQgdGhlIHNwZWVkIG9mIHRoZSBoaWdoLW9yZGVycy1wYWdlcyBhbGxv Y2F0aW9uKG9yZGVyPTQgYW5kIA0KPiBvcmRlciA9IDgpDQo+IEJlZm9yZSBhbmQgYWZ0ZXIgb3B0 aW1pemF0aW9uLCB3ZSB0ZXN0ZWQgdGhlIHNwZWVkIG9mIHRoZSANCj4gaGlnaC1vcmRlcnMtcGFn ZXMgYWxsb2NhdGlvbg0KPiBhZnRlciAxMjAtaG91cnMtTW9ua2V5IGluIDEwIEFuZHJvaWQgbW9i aWxlIHBob25lcy4gYW5kIHRoZSByZXN1bHQgc2hvdyB0aGF0DQo+IHRoZSBzcGVlZCBoYXMgYmVl biBpbmNyZWFzZWQgYnkgbW9yZSB0aGFuIDE4JS4NCj4gDQo+IEFsc28sIHdlIGRvIHNvbWUgdGVz dCBkZXNpZ25lZCBieSB1czoNCj4gKHRoZSBtYWNoaW5lIHdpdGggNCBnaWdhYnl0ZXMgb2YgcGh5 c2ljYWwgbWVtZXJ5IGFuZCBpbiBsaW51eC00LjE5LikNCj4gbW9kZWwgdGhlIHVzYWdlIG9mIHVz ZXJzLCBhbmQgY29uc3RhbnRseSBzdGFydCBhbmQNCj4gb3BlcmF0ZSB0aGUgZGlmZnJlbnQgYXBw bGljYXRpb24gZm9yIDEyMGgsIGFuZCB3ZSByZWNvcmQgQ09NUEFDVF9TVEFMTCANCj4gaXMgZGVj cmVhc2VkIGJ5DQo+IDkwKyUgYW5kIHNwZWVkIG9mIHRoZSBoaWdoLW9yZGVycy1wYWdlcyBpcyBp bmNyZWFlZCBieSAxNSslLg0KIA0KT2theSwgYWdhaW4sIHRoaXMgaXMgdGhlbiBzb21lIG9wdGlt aXphdGlvbiBmb3IgYWxsb2NhdGlvbiBzcGVlZDsgd2hpY2ggDQptYWtlcyBpdCBsZXNzIGF0dHJh Y3RpdmUgSU1ITyAoYXQgbGVhc3QgZm9yIG1vcmUgaW52YXNpdmUgY2hhbmdlcyksIA0KYmVjYXVz ZSBJIHN1c3BlY3QgdGhpcyBtb3N0bHkgaGVscHMgaW4gY29ybmVyIGNhc2VzIChNb25rZXkgYmVu Y2htYXJrcyANCmNvcm5lciBjYXNlcyBBRkFJVSkuDQogDQo+IA0KPiBhbmQgSSBoYXZlIHNvbWUg cXVlc3Rpb24sIGkgaG9wZSB5b3UgY2FuIGd1aWRlIG1lIGlmIHdoZW4geW91IGFyZSBmcmVlLg0K PiAxKSBXaGF0IGlzIHRoZSBjb21wYWN0aW9uIGNvbmZpZ3VyZWQ/DQo+ICAgICAgRG9zdCBpdCBt ZWFudCB0aGUgbWVtYmVycyBpbiB6b25lPyBsaWtlIGFzIGZvbGxvd3M6DQo+ICAgICAgdW5zaWdu ZWQgaW50IGNvbXBhY3RfY29uc2lkZXJlZDsNCj4gICAgICB1bnNpZ25lZCBpbnQgY29tcGFjdF9k ZWZlcl9zaGlmdDsNCj4gICAgICBpbnQgY29tcGFjdF9vcmRlcl9mYWlsZWQ7DQo+ICAgICAgYm9v bCBjb21wYWN0X2Jsb2Nrc2tpcF9mYWlsZWQ7DQo+ICAgICAgT3IgdGhlIHNvbWUgTWFjcm8gdmFy aWFibGU/IGxpa2UgYXMgZm9sbG93czoNCj4gICAgICBQQUdFX0FMTE9DX0NPU1RMWV9PUkRFUiA9 IDMNCj4gICAgICBNSU5fQ09NUEFDVF9QUklPUklUWSA9IDENCj4gICAgICBNQVhfQ09NUEFDVF9S RVRSSUVTID0gMTYNCj4gDQogDQpSYXRoZXIgaWYgeW91IGhhdmUgcHJvYWN0aXZlIGNvbXBhY3Rp b24gDQooL3Byb2Mvc3lzL3ZtL2NvbXBhY3Rpb25fcHJvYWN0aXZlbmVzcykuIEJ1dCBJIGFzc3Vt ZSBiZWNhdXNlIHlvdSdyZSANCm1lc3Npbmcgd2l0aCBvbGRlciBrZXJuZWxzLCB0aGF0IHlvdSBk aWRuJ3QgY29tcGFyZSBhZ2FpbnN0IHRoYXQgeWV0LiANCldvdWxkIGJlIHdvcnRoIGEgY29tcGFy aXNvbi4NCiANCj4+PiAxKSBtdWx0aSBmcmVlYXJlYSAod2hpY2ggbWlnaHQNCj4gID4+IGJlIHBy b2JsZW1hdGljIHdpdGggc3BhcmNpdHkpDQo+IDIpIENhbiB5b3UgcGxzIHRlbGwgbWUgd2hhdCBp cyBzb2FyY2l0eSBhbmQgd2hhdCBpcyB0aGUgaW1wYWN0IG9mIHRoaXM/DQo+ICAgICAgYW5kIHdo ZXRoZXIgdGhlcmUgYXJlIHNvbWUgZG9jdW1lbnRzIGFib3V0IGl0Pw0KIA0KRXNzZW50aWFsbHkg Q09ORklHX1NQQVJTRU1FTSwgd2hlcmVieSB3ZSBjYW4gaGF2ZSBodWdlIGhvbGVzIGluIHBoeXNp Y2FsIA0KbWVtb3J5IGxheW91dCBhbmQgbWVtb3J5IGFyZWFzIGNvbWluZy9nb2luZyB3aXRoIG1l bW9yeSBob3QodW4pcGx1Zy4gDQpVc3VhbGx5IHdlIG1hbmFnZSBhbGwgbWV0YWRhdGEgcGVyIHNl Y3Rpb24uIEZvciBleGFtcGxlLCBwYWdlYmxvY2tzIGFyZSANCmFsbG9jYXRlZCBwZXIgc2VjdGlv bi4gV2UgYXZvaWQgYXJyYXlzIHRoYXQgZGVwZW5kIG9uIHRoZSANCmluaXRpYWwvbWF4aW11bSBw aHlzaWNhbCBtZW1vcnkgc2l6ZS4NCiANCi0tIA0KVGhhbmtzLA0KIA0KRGF2aWQgLyBkaGlsZGVu Yg0KIA0K ------=_001_NextPart151103575751_=---- Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable body { line-height: 1.5; }blockquote { margin-top: 0px; margin-bottom:= 0px; margin-left: 0.5em; }body { font-size: 10.5pt; font-family: 'Microsof= t YaHei UI'; color: rgb(0, 0, 0); line-height: 1.5; }= =0A=
Hi David Hildenbrand=EF=BC=9A

>> Okay, but then I assume the target goal of your patch= set is to minimize
>> CPU c= onsumption/allocation stall time when allocating larger order pages.=
 
>> Currently you state "the probablity of high-order-pag= es allocation would
>> be in= creased significantly", but I assume that's then not 100% correct.
>> What you measure is the stal= l time to allocate higher order pages, not
>> that you can allocate them.

You are right that multi_freearea is to to speed the rate of large= -order-pages
allocation instead of increasing the probality of it= if CONFIG_COMPACTION is
open.

>> Okay, again, this is then some optimization for= allocation speed; which
>> m= akes it less attractive IMHO (at least for more invasive changes),
>> because I suspect this mostly help= s in corner cases (Monkey benchmarks
>> corner cases AFAIU).

I real= ly agree with the preciseness of the community that if we want to merge the=
patch in baseline, we would do more test to proof that the pat= ch will not degraded
to a degree that people care. But, maybe there are the detaile= d test-list for us to
test, or we really don't know how to proof there are no = any side-effects on all situation
of memory-opt.
It is = a question that has puzzled me for a long time.

>> Essenti= ally CONFIG_SPARSEMEM, whereby we can have huge holes in physical
>> memory layout and memory areas com= ing/going with memory hot(un)plug.
>> Usually we manage all metadata per section. For example, pagebloc= ks are
>> allocated per sect= ion. We avoid arrays that depend on the
>> initial/maximum physical memory size.

CONFIG_SPRSEMEM has been opened in some of our product with= Qcom-platform and
MTK platform. AFAIK, multi_freearea would not bring problem t= o it=EF=BC=9Fbecause the patch
just manage the physical memory of zone to serv= eral section(free_area) and adjust the
the range of pages-PFN for buddy-alloc-= pages by the alloction-order. With memory
hot(un)plug, we would initialize the= members of "multi_freearea" in zone.

=
The patch has been merged in the baseline of our product that has been= sold all over the
world with Linux-4.4/4.9/4.19 so= that i don't think there will be too much risk. Of course,
i might be wrong.

=0A=

=0A=
lipeifeng@oppo.com
=0A=
 
Fr= om: David Hildenbrand
Date: 2021-04-27 20:46
C= C: linux-s390; <= a href=3D"mailto:linux-kernel@vger.kernel.org">linux-kernel; linux-mm
Subject: Re:= [RFC] mm: support multi_freearea to the reduction of external fragmentatio= n
On 26.04.21 12:19, lipeifeng@oppo.com wrote:=0A=
> Hi David Hildenbrand <mailto:david@redhat.com>=EF=BC=9A=0A=
>
=0A=
>  >> And you don't mention what the baseline configurat= ion was. For example,
=0A=
>  >> how was compaction configured?
=0A=
>  >> Just to clarify, what is monkey?
=0A=
>  >> Monkey HTTP server? MonkeyTest disk benchmark? UI/= Application Exerciser
=0A=
>  >> Monkey?
=0A=
> -----------------------------------------------------------------= --------------------
=0A=
> I am sorry that i didn't  give a clear explanation abou= t Monkey.
=0A=
> It meant  "UI/Application Exerciser Monkey" from g= oogle.
=0A=
>
=0A=
> Excuse me, let me introduce our test:
=0A=
>
=0A=
 
=0A=
Thanks for more details on the test.
=0A=
 
=0A=
> 1. record COMPACT_STALL
=0A=
> We tested the patch on linux-4.4/linux-4.9/linux-4.14/linux-4.19 = and the
=0A=
> results shows that the patch is effective in reducing COMPACTSTAL= L.
=0A=
>      - monkey for 12 hours.
=0A=
>      - record COMPACTSTALL after test.
=0A=
>
=0A=
> Test-result: reduced COMPACTSTALL by 95.6% with the patch.
= =0A=
> (the machine with 4 gigabytes of physical memery and in linux-4.1= 9.)
=0A=
> ---------------------------------
=0A=
>            = ;           |  = COMPACTSTALL
=0A=
> ---------------------------------
=0A=
>     ori             =  |     2189
=0A=
> ---------------------------------
=0A=
> optimization |      95
=0A=
> ---------------------------------
=0A=
>
=0A=
> I fully agree with the value of compaction, but compaction also b= ring cpu
=0A=
> consumption and will increase the time of alloc_stall. So if we c= an let more
=0A=
> free high-orders-pages in buddy instead of signal pages, it will = decrease
=0A=
> COMPACT_STALL and speed up memory allocation.
=0A=
 
=0A=
Okay, but then I assume the target goal of your patch set is to minimi= ze
=0A=
CPU consumption/allocation stall time when allocating larger order pag= es.
=0A=
 
=0A=
Currently you state "the probablity of high-order-pages allocatio= n would
=0A=
be increased significantly", but I assume that's then not 100% co= rrect.
=0A=
What you measure is the stall time to allocate higher order pages, not=
=0A=
that you can allocate them.
=0A=
 
=0A=
>
=0A=
> 2. record the speed of the high-orders-pages allocation(order=3D4= and
=0A=
> order =3D 8)
=0A=
> Before and after optimization, we tested the speed of the
= =0A=
> high-orders-pages allocation
=0A=
> after 120-hours-Monkey in 10 Android mobile phones. and the resul= t show that
=0A=
> the speed has been increased by more than 18%.
=0A=
>
=0A=
> Also, we do some test designed by us:
=0A=
> (the machine with 4 gigabytes of physical memery and in linux-4.1= 9.)
=0A=
> model the usage of users, and constantly start and
=0A=
> operate the diffrent application for 120h, and we record COMPACT_= STALL
=0A=
> is decreased by
=0A=
> 90+% and speed of the high-orders-pages is increaed by 15+%.=0A=
 
=0A=
Okay, again, this is then some optimization for allocation speed; whic= h
=0A=
makes it less attractive IMHO (at least for more invasive changes), =0A=
because I suspect this mostly helps in corner cases (Monkey benchmarks=
=0A=
corner cases AFAIU).
=0A=
 
=0A=
>
=0A=
> and I have some question, i hope you can guide me if when you are= free.
=0A=
> 1) What is the compaction configured?
=0A=
>      Dost it meant the members in zone? like as fo= llows:
=0A=
>      unsigned int compact_considered;
=0A=
>      unsigned int compact_defer_shift;
=0A=
>      int compact_order_failed;
=0A=
>      bool compact_blockskip_failed;
=0A=
>      Or the some Macro variable? like as follows:<= /div>=0A=
>      PAGE_ALLOC_COSTLY_ORDER =3D 3
=0A=
>      MIN_COMPACT_PRIORITY =3D 1
=0A=
>      MAX_COMPACT_RETRIES =3D 16
=0A=
>
=0A=
 
=0A=
Rather if you have proactive compaction
=0A=
(/proc/sys/vm/compaction_proactiveness). But I assume because you're <= /div>=0A=
messing with older kernels, that you didn't compare against that yet. =
=0A=
Would be worth a comparison.
=0A=
 
=0A=
>>> 1) multi freearea (which might
=0A=
>  >> be problematic with sparcity)
=0A=
> 2) Can you pls tell me what is soarcity and what is the impact of= this?
=0A=
>      and whether there are some documents about it= ?
=0A=
 
=0A=
Essentially CONFIG_SPARSEMEM, whereby we can have huge holes in physic= al
=0A=
memory layout and memory areas coming/going with memory hot(un)plug. <= /div>=0A=
Usually we manage all metadata per section. For example, pageblocks ar= e
=0A=
allocated per section. We avoid arrays that depend on the
=0A=
initial/maximum physical memory size.
=0A=
 
=0A=
--
=0A=
Thanks,
=0A=
 
=0A=
David / dhildenb
=0A=
 
=0A=
=0A= = ------=_001_NextPart151103575751_=------