From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752760AbdCPTj2 (ORCPT ); Thu, 16 Mar 2017 15:39:28 -0400 Received: from mail-sn1nam01on0102.outbound.protection.outlook.com ([104.47.32.102]:34944 "EHLO NAM01-SN1-obe.outbound.protection.outlook.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1752051AbdCPTjY (ORCPT ); Thu, 16 Mar 2017 15:39:24 -0400 Authentication-Results: intel.com; dkim=none (message not signed) header.d=none;intel.com; dmarc=none action=none header.from=hpe.com; Date: Thu, 16 Mar 2017 14:38:44 -0500 From: Alex Thorlton To: Aaron Lu CC: , , Dave Hansen , Tim Chen , Andrew Morton , Ying Huang , Subject: Re: [PATCH v2 0/5] mm: support parallel free of memory Message-ID: <20170316193844.GA110825@stormcage.americas.sgi.com> References: <1489568404-7817-1-git-send-email-aaron.lu@intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Disposition: inline In-Reply-To: <1489568404-7817-1-git-send-email-aaron.lu@intel.com> User-Agent: Mutt/1.5.21 (2010-09-15) X-Originating-IP: [192.48.192.5] X-ClientProxiedBy: HE1PR0601CA0042.eurprd06.prod.outlook.com (10.166.117.52) To DF4PR84MB0282.NAMPRD84.PROD.OUTLOOK.COM (10.162.193.20) X-MS-Office365-Filtering-Correlation-Id: 579fbfbe-e92e-4a34-15ee-08d46ca41908 X-MS-Office365-Filtering-HT: Tenant X-Microsoft-Antispam: UriScan:;BCL:0;PCL:0;RULEID:(22001)(48565401081);SRVR:DF4PR84MB0282; X-Microsoft-Exchange-Diagnostics: 1;DF4PR84MB0282;3:QuYFdIgDIx1VzJ2xOY8Mr+RmZWc3J2sWQfhHEEdhGTJMPN1nPw60tlBCMbU4E1PuDxJ6ZP+JQzG/oJFopGxcdTk+36vNRncTuBTxdxEylcromP8tTXMkwgl1nIdshgLE7Rauz9ZY+d9v8Yg4TzMsmrW9bSlj5UjHzrYU8L0/x5o4p/51n09HTLTx73JQDvMqrlopERPqV/z6stntYlhm8Hfq2X/hPGTBupyhG1jQeUeHsZsbf+A4ZDPWTXiVKgB6GwHUIOZZE9DwgsACA1Ome5Ss1WzVZXjxWq8JOIq3PNY=;25:mPybH2dLYy9EHw1R5sy+TxUkaHXa0G4fAvXHSFD6wseQwMHynFRu4WgH5+WZCOXAA9G7jnZn3+xIahqsbm2eec37Y8ELHbiMGyogE0iPgqFUMcDLeUh9VVR4qqhvVxj4S3WraOyYBTLN0ZM9qUzZii/iMow7KDuS9SUgkib3kFq38Yo57rpFC+7wBoOa7LnNkYE20O5iDUQSw92GWj305AZnBQZGR5+XuPauMvFR3FY6Ve3nxts67paOwgw846nI/43SwB7KisSt7XmC2u+EeDf4q9v7+KzOKOuLYuLh+sbPJmCQ0g+FuefYd1lRDZNGMwuzN4TM/oAMeBQV+0n0HrgR0d3WL6WEx5UjGCkAQmFOSrbwCucwUMqNj2pjZN3+Y6n93wloVGo5drNSorTdtDtelSzAosvNo0/rlGugF7d3AiUNxDjBoaMEDkGc+74DcEfFvMN2NM8xKeC+xIWBrw== X-Microsoft-Exchange-Diagnostics: 1;DF4PR84MB0282;31:SbJu7bpEi4u9E76AUx+Z30vIk3uefPSUx2SrQnotEhpeAzX9IZ/jKXwbK/0zBcIRgrByj/I+nCDhkgdujcpWB68w+aF/TNl1qzVwjw/VrlbaZ8xFsiC1cuXmwp0lWaRIMZBJxGyYm2KMPQO4PGKXUBIoKVurb2KGe2GIVE0/TiugQI9i01uCOOXxBhC9mNofFqPnl9y7GMgD4iXDcdi3ZT69tjItzG5cIK8EEzzmkH8xRQEGW2M0uULOvF1x/tWB;20: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 X-Microsoft-Antispam-PRVS: X-Exchange-Antispam-Report-Test: UriScan:; X-Exchange-Antispam-Report-CFA-Test: BCL:0;PCL:0;RULEID:(6040375)(601004)(2401047)(8121501046)(5005006)(10201501046)(3002001)(6055026)(6041248)(20161123562025)(20161123558025)(20161123560025)(20161123564025)(20161123555025)(6072148);SRVR:DF4PR84MB0282;BCL:0;PCL:0;RULEID:;SRVR:DF4PR84MB0282; X-Microsoft-Exchange-Diagnostics: 1;DF4PR84MB0282;4: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 X-Forefront-PRVS: 024847EE92 X-Forefront-Antispam-Report: SFV:NSPM;SFS:(10019020)(4630300001)(6009001)(39450400003)(39860400002)(39840400002)(24454002)(97756001)(6506006)(1076002)(6116002)(50466002)(6916009)(6666003)(23726003)(2950100002)(46406003)(4326008)(47776003)(66066001)(229853002)(76176999)(5660300001)(54356999)(50986999)(4001350100001)(8676002)(42186005)(81166006)(83506001)(6306002)(54906002)(86362001)(9686003)(2906002)(33656002)(55016002)(38730400002)(110136004)(189998001)(53936002)(7736002)(6246003)(305945005)(18370500001);DIR:OUT;SFP:1102;SCL:1;SRVR:DF4PR84MB0282;H:stormcage.americas.sgi.com;FPR:;SPF:None;MLV:sfv;LANG:en; X-Microsoft-Exchange-Diagnostics: =?us-ascii?Q?1;DF4PR84MB0282;23:4LMcUjenUJZDSHDfzFmprMteGSFwtuoOA0an2Ma72?= =?us-ascii?Q?ZTbRheQ55Yyz7siYfNNb0gZY7ejYmfDIB0OxQIMevGUXXw1CCrLRjy7R/iFZ?= =?us-ascii?Q?kQSI7SrRndSym8NMEQQtcOz2RUqPVqHmhXp2ZQM1nHMvPeGp4ozYkBQ6AzsF?= =?us-ascii?Q?qu7tHehixyFPOelpDdAQTMVtOmDi0V1SgS/MeI+1owYcxO3xM8SORCgNCthK?= =?us-ascii?Q?N0SrwOYMEdb7b1i3YEdqlViqDry+AJUGPbbq/UrVAsEXInwB/C/9TfRHcNH4?= =?us-ascii?Q?jI7C/FVC/VaospwxJktCksL/EPDop2BoFIFLo71YFCfMhQHWRBToctf3UjWu?= =?us-ascii?Q?0/KXgYcspLy7LCb0WxQw5B8T24TIC1gMD9bM/pXhffrMrHU1KOECJqgkmsmU?= =?us-ascii?Q?TDAs4X3T3S7tl1XagwWV0YaFm/U19RsaHLF2P3QQ+3YRDYHFVCpkYnKga5zW?= =?us-ascii?Q?mcE+3kwnN7XXa0DRJOSzXAQ7GPTV9XGJY3NSb5W/LPf1NnR6OkqUeRUzBMu1?= =?us-ascii?Q?EdtWAnU1TjR61qKjbSmvJgrP3EI6pMH+8N1yLg15Eqiy7ljYv8uI0xsC2gp0?= =?us-ascii?Q?LbTyEa4fOkZmcB57Y+SvCXaeEQdedge/l+ZuF6JxxuLkkPqs9cyHF7sRXmMZ?= =?us-ascii?Q?McoeJP0HqgrWq7Nm0K7gg6XRARjl11cHyC94vXUBMMICYHe1lW8+16Je9xOr?= =?us-ascii?Q?QOPQSaHelUBo/p+gOsTEwhLjPL8jUu+Oy8fF6AhcONyJi51+S1spoxk9jJ25?= =?us-ascii?Q?TDBUzAkr9/uGQm8A/cOMSPQfs2LQ4yh8Mq/nFfx11i/q4u9kkJGgCa3jifke?= =?us-ascii?Q?kCUytufxieCyIx6zypokWCcUCAu3MHFXceeICTuv3WDaKhFopPxVnY2bGSs4?= =?us-ascii?Q?OsYAIcO7wPaKMvaoi/pBQJW92njI42LPiBi7AVJbqCDUUDzuMqYLgmV9CVcn?= =?us-ascii?Q?faj2uTbY7tfFP+dyjqL/fHzZW5cftR2K+GXGsHD4Jz+a3ADnptry8k7KF9ZO?= =?us-ascii?Q?wbSTv8mF+xvhwGaFSWKUaPSudC/6lfydq1P94o0QpbP/lIrWAhIcHSO2Vj4k?= =?us-ascii?Q?GGv3PsXKaeMP181J4r9hKRI5BlBuwaPktrODvQSaKdew27gxA=3D=3D?= X-Microsoft-Exchange-Diagnostics: 1;DF4PR84MB0282;6:22ssAdoiSR4wLPqSHs1DiJ7yiercPJT8JpEIpG3W+M53v/aukMZ2oTg0HRQYbTagPAG2FAwCHeN9EghBrHBWkCuE5UWrPG5HSQcc982FCOz1HuTHrYle2vRJkmzhCml/jg8WiIFpr/rbkfHC30grWSjwezGzznjP7UGaVp9tPog5T/V0xdyY5Vbts1ode5ZrZ+ikwQI/9euJCQTWj6bJ4gLs6SYbRAad7BT134cbmCQ6d1Rj87LijNY8e5juFL6gZyE7YUlnljWyC7lr37/FNldpxlcD4cxLxiRqqCbWbuMZgDjaXauhT4eHFUZMvlVwqCA3P891mbITIyHA4e/0fUO3ho3uxit4al5bWTgK4aJu+ULQrm4/necMzb/2TetZaj5Eg9sb/WvT0K2eThncqmjxjqzTSlEyGUS1P+LMHYY=;5:yfO0eUyEYCM4rAe4tExfoXC9igxgYFKO18JFhwXZMdj6+BZYCOzrAiGzZ2xvD0mOWegls5tRypSourc0JnvDet+prB7orQdSOFZsXrBNhmVl2uhHTDre1ncCQy1i9P3FkehfqQ+t4nBx2MRPA6byVA==;24:T+8041ue9ZgIqcXYH8dTNc4ZGYWS24LN1mdk/pfMlXAKh7FccGaBbRn7VgqNA1LT/tFw+NP5MFK1WaMDoqrs4hKkA4kGcxL/zmvqAxQ5X+4= SpamDiagnosticOutput: 1:99 SpamDiagnosticMetadata: NSPM X-Microsoft-Exchange-Diagnostics: 1;DF4PR84MB0282;7:xrMd+9uv1toTVJXuxjMk6OpAHI86nLuf2QpXqsHutw/BB3vWe6DJuH6v58zhuw0S5ZUa+adG/piz6R7yLehX2Yvl4eW94XhiK3OunILkRXrx3tgGEezPL8JLIqpoYvkhMYH8GVn0EFfWm8dc6l4Rjgyn+e91qPXG/ZPsaNttLqbemh5nkEV+WPKyXTGLg7XoBDIUXG3aoDrs4CIhhQUc4hDB/u2mvUbm2LfOcL1Pb66oMrjBA3VUhopfy2M03C478DkOrR3FEiodPzBz/iT6pBcP5QyZbOph/tWm/e+XYkExUzcYvH1nOzEKPR5RP3ze/kHanS7r5z3wotXUWQAVtw== X-OriginatorOrg: hpe.com X-MS-Exchange-CrossTenant-OriginalArrivalTime: 16 Mar 2017 19:38:58.1008 (UTC) X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted X-MS-Exchange-Transport-CrossTenantHeadersStamped: DF4PR84MB0282 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, Mar 15, 2017 at 04:59:59PM +0800, Aaron Lu wrote: > v2 changes: Nothing major, only minor ones. > - rebased on top of v4.11-rc2-mmotm-2017-03-14-15-41; > - use list_add_tail instead of list_add to add worker to tlb's worker > list so that when doing flush, the first queued worker gets flushed > first(based on the comsumption that the first queued worker has a > better chance of finishing its job than those later queued workers); > - use bool instead of int for variable free_batch_page in function > tlb_flush_mmu_free_batches; > - style change according to ./scripts/checkpatch; > - reword some of the changelogs to make it more readable. > > v1 is here: > https://lkml.org/lkml/2017/2/24/245 I tested v1 on a Haswell system with 64 sockets/1024 cores/2048 threads and 8TB of RAM, with a 1TB malloc. The average free() time for a 1TB malloc on a vanilla kernel was 41.69s, the patched kernel averaged 21.56s for the same test. I am testing v2 now and will report back with results in the next day or so. - Alex From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-pg0-f71.google.com (mail-pg0-f71.google.com [74.125.83.71]) by kanga.kvack.org (Postfix) with ESMTP id 286216B0038 for ; Thu, 16 Mar 2017 15:39:04 -0400 (EDT) Received: by mail-pg0-f71.google.com with SMTP id y17so109182944pgh.2 for ; Thu, 16 Mar 2017 12:39:04 -0700 (PDT) Received: from NAM01-SN1-obe.outbound.protection.outlook.com (mail-sn1nam01on0094.outbound.protection.outlook.com. [104.47.32.94]) by mx.google.com with ESMTPS id 31si6226663pli.135.2017.03.16.12.39.02 for (version=TLS1_2 cipher=ECDHE-RSA-AES128-SHA bits=128/128); Thu, 16 Mar 2017 12:39:03 -0700 (PDT) Date: Thu, 16 Mar 2017 14:38:44 -0500 From: Alex Thorlton Subject: Re: [PATCH v2 0/5] mm: support parallel free of memory Message-ID: <20170316193844.GA110825@stormcage.americas.sgi.com> References: <1489568404-7817-1-git-send-email-aaron.lu@intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Disposition: inline In-Reply-To: <1489568404-7817-1-git-send-email-aaron.lu@intel.com> Sender: owner-linux-mm@kvack.org List-ID: To: Aaron Lu Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org, Dave Hansen , Tim Chen , Andrew Morton , Ying Huang , alex.thorlton@hpe.com On Wed, Mar 15, 2017 at 04:59:59PM +0800, Aaron Lu wrote: > v2 changes: Nothing major, only minor ones. > - rebased on top of v4.11-rc2-mmotm-2017-03-14-15-41; > - use list_add_tail instead of list_add to add worker to tlb's worker > list so that when doing flush, the first queued worker gets flushed > first(based on the comsumption that the first queued worker has a > better chance of finishing its job than those later queued workers); > - use bool instead of int for variable free_batch_page in function > tlb_flush_mmu_free_batches; > - style change according to ./scripts/checkpatch; > - reword some of the changelogs to make it more readable. > > v1 is here: > https://lkml.org/lkml/2017/2/24/245 I tested v1 on a Haswell system with 64 sockets/1024 cores/2048 threads and 8TB of RAM, with a 1TB malloc. The average free() time for a 1TB malloc on a vanilla kernel was 41.69s, the patched kernel averaged 21.56s for the same test. I am testing v2 now and will report back with results in the next day or so. - Alex -- 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