From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from BL2PR02CU003.outbound.protection.outlook.com (mail-eastusazon11011021.outbound.protection.outlook.com [52.101.52.21]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id C8C872E1F0E for ; Wed, 9 Sep 2026 02:16:36 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=fail smtp.client-ip=52.101.52.21 ARC-Seal:i=2; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1788920198; cv=fail; b=Ij3N/vKpcKTfyH5t+bPtbXLoZ6JGT7lk+jYUSYS1oGMzrXiKRecHdyPcElXdMIFNddDn+taWO8zCrvq44Zwj22d0biezZJnqbu3aJnNAL7RpY5PgmvBrmC99gWwltPoa2vODlEhbmSoB0D0NZUlWLkHXhmnL5PTQNEfhLG+G16s= ARC-Message-Signature:i=2; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1788920198; c=relaxed/simple; bh=R23HpDv0lWxE4zYH1LOoxYpb54GuZb8r5eWI0oUg9xE=; h=Content-Type:Date:Message-Id:From:Subject:Cc:To:References: In-Reply-To:MIME-Version; b=Yji1lSpuJNKiK5O0IrtjCibg26Q4mf452VyqQ1Ob55YfhVefVf8u+g5tUbZLj40LIIhHek5ytQPEkT/A7d+9FO+5OtMQtlZ1eBOhHxguK/Vmu+EC2tmPvA2miRfzn30Vu9uwL0FTyO9m5SjX3O8wtiY3OyOVMs6306m/c0QLGVY= ARC-Authentication-Results:i=2; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=nvidia.com; spf=fail smtp.mailfrom=nvidia.com; dkim=pass (2048-bit key) header.d=Nvidia.com header.i=@Nvidia.com header.b=IfVIkBGe; arc=fail smtp.client-ip=52.101.52.21 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=nvidia.com Authentication-Results: smtp.subspace.kernel.org; spf=fail smtp.mailfrom=nvidia.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=Nvidia.com header.i=@Nvidia.com header.b="IfVIkBGe" ARC-Seal: i=1; a=rsa-sha256; s=arcselector10001; d=microsoft.com; cv=none; b=Ck/Pv446+xi4iALbe8RLlQaYWC22JesFji+oMdr+jgzgdXP5W6mLwvABZl34LrGCnDnw13lMBlgp2raYtmLEEkuyrpM6mq9AB5k2IYUVJtSpSw/O8scU4IEpSyh/xdINdbOwQC1S2GPYtLdnZpjZCVP7htbLQ4g9Rshm0d6bZ/mDwL2D8/TegueJxMdJ0RVz1QdRBH/GKShWNXjnuibpuq8XcMG3B28MLmssfAwByQlpsrDMnWFeHbr4pVuTzjWX3MCcOTZQ5IdtttErRa6puGLtciLIjGNl0Fhi89HVV8F4wx9U1uXiv8OJR48GHkDY8fX1QIo1YAAesyN5pMKfTA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector10001; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-AntiSpam-MessageData-ChunkCount:X-MS-Exchange-AntiSpam-MessageData-0:X-MS-Exchange-AntiSpam-MessageData-1; bh=bQBf6q+XKtz82AzeK39RAYG0K9DZmCdUs2hXreU/WoA=; b=Bxwi9QFTq9Yf30ZUtfg5T6W2oDm3F8UX9+mYirHWqOMY7FSCD9LjkuUg7VIKAkZwtaxmkxZc7X7BKns6BpfYN/hKMZu/40Q45Wj9hP6I0TXUGuySaORE0sWKVf5mZwEhds7tX4Yu40K3hyr+uuUA6D89hT3bzreUkOR57Egh1yTpSd2sJy48MS6cBPw8p9W3tcXDQjd3u0TNzhxKt6JwtBWE1pNA2SeWyhhoYEukJktptA0ekw4UkQPb/MwyPp58kUCAmrSDZRXeBf9p2rXA7UdkglRWnV/aB3JzVZKFTPLrnXA9T2OCEFx/QL7KJfFtkmXducgy3WYen5PVbWiZgQ== ARC-Authentication-Results: i=1; mx.microsoft.com 1; spf=pass smtp.mailfrom=nvidia.com; dmarc=pass action=none header.from=nvidia.com; dkim=pass header.d=nvidia.com; arc=none DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=Nvidia.com; s=selector2; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=bQBf6q+XKtz82AzeK39RAYG0K9DZmCdUs2hXreU/WoA=; b=IfVIkBGeISXhZRlwNPTCqdX6ng6XAiQdILK1tDD2bPEIbxYx9a5DcItrqPtrkO3eAtdY6xXYZeC9EEjAXwBsnqMuGYZzI08xXvGzysdVigOyddisgsJ4vIRQpcRspP9s5onujfT6ynfWUOWwNmW9CEZwCqFLhLGNzc9nV7QSb6/fYf16jqq/RRS+2yxd496ynh+5Cc+briOJYrwekd15ou+xLQSmw7Uebh/1VcB0J0PHcwhwMyhiMOnj2rxBcAxWTlXO3vBdxILdvxBJn/AWNRUeiaigGqBEYFf5ET2sePw5O3NqfLp5lNqhSR5EskaFK1Olwliq1h0Wb4TvyaEUJA== Authentication-Results: dkim=none (message not signed) header.d=none;dmarc=none action=none header.from=nvidia.com; Received: from IA0PR12MB8374.namprd12.prod.outlook.com (2603:10b6:208:40e::7) by CH1PPF4CBE7339A.namprd12.prod.outlook.com (2603:10b6:61f:fc00::60e) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.21.406.6; Wed, 9 Sep 2026 02:16:30 +0000 Received: from IA0PR12MB8374.namprd12.prod.outlook.com ([fe80::d85f:4c87:ae84:3f16]) by IA0PR12MB8374.namprd12.prod.outlook.com ([fe80::d85f:4c87:ae84:3f16%5]) with mapi id 15.21.0406.005; Wed, 9 Sep 2026 02:16:30 +0000 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset=UTF-8 Date: Tue, 08 Sep 2026 22:16:29 -0400 Message-Id: From: "Zi Yan" Subject: Re: [RFC PATCH 0/3] mm/vmscan: adaptive multi-threaded kswapd for NUMA-aware reclaim Cc: "Buddy Lumpkin" , "Andrew Morton" , "Kairui Song" , "Qi Zheng" , "Shakeel Butt" , "Barry Song" , "Axel Rasmussen" , "Yuanchu Xie" , "Wei Xu" , "David Hildenbrand" , "Lorenzo Stoakes" , "Liam R. Howlett" , "Vlastimil Babka" , "Mike Rapoport" , "Suren Baghdasaryan" , "Michal Hocko" , "Brendan Jackman" , "Johannes Weiner" To: "Ehab Ababneh" , , X-Mailer: aerc 0.22.0 References: <20260908221059.14777-1-ehab.ababneh@intel.com> In-Reply-To: <20260908221059.14777-1-ehab.ababneh@intel.com> X-ClientProxiedBy: MN0P222CA0023.NAMP222.PROD.OUTLOOK.COM (2603:10b6:208:531::27) To IA0PR12MB8374.namprd12.prod.outlook.com (2603:10b6:208:40e::7) Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-MS-PublicTrafficType: Email X-MS-TrafficTypeDiagnostic: IA0PR12MB8374:EE_|CH1PPF4CBE7339A:EE_ X-MS-Office365-Filtering-Correlation-Id: 89594ed3-d77a-4c1c-4f7e-08df0e185c66 X-MS-Exchange-SenderADCheck: 1 X-MS-Exchange-AntiSpam-Relay: 0 X-Microsoft-Antispam: BCL:0;ARA:13230040|366016|376014|23010399003|7416014|1800799024|6133799003|22082099003|18002099003|56012099006|11063799006|10067099003; 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:IA0PR12MB8374.namprd12.prod.outlook.com;PTR:;CAT:NONE;SFS:(13230040)(366016)(376014)(23010399003)(7416014)(1800799024)(6133799003)(22082099003)(18002099003)(56012099006)(11063799006)(10067099003);DIR:OUT;SFP:1101; X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1 X-MS-Exchange-AntiSpam-MessageData-0: =?utf-8?B?ekY2ay9NaGNoRlRrcnJrNi9NUFhOUnpvQ3Q1MEJUbU52anc3OEdxUnJVeGdQ?= =?utf-8?B?UUF1N1ZHZXJqUExmc0xTTG8yTXR2V0pGdFc4Z0VvU0QyT1JXL09kSlZJWmNu?= =?utf-8?B?REtBS1E1RDNwREZzNFYwR1N6eDdrQ0RXMXN4YW5zMzlXSXBUOVZlNjBWd2h1?= =?utf-8?B?KzNGb0VQSG9Sa3lFNFZJOFhQbEx3OGlOSEdiMGN1UGZqaXB6U2gxR0NPK2Nl?= =?utf-8?B?RzNVUnZBRWR3SGh5emxRV3Vsa21aZ2dVdW9RYXplZEJNbVlLZkJTcXZSdnpT?= =?utf-8?B?NGNXTmVSMFk3V3BYQWsyVXNsNVhhenkvUXhrRER4eHphei9QZzMxZnM3dkFl?= =?utf-8?B?RmRzcWFZclpMNlk2SWZ2ZzM2dmoyUzlla3B4MW5aU1JhSDhtclA0WlZpcWt5?= =?utf-8?B?aEFYd1Nka3d4b0UrNGlkRmRNcnF1ZnUrNUVsV3NNZDJHZDNvRm82YmJiSkxO?= =?utf-8?B?V1pMTFhUQ3daU0k4MVVFRmZYRXRhQ2xNNWJndXg4T2VKYTBxMFVNVWR1dmdp?= =?utf-8?B?UUJrcThDT1FLZUJoNEpuSnNBSzRTUmI0MnRxb1d1VkFHdFNFa202S3hIVWx6?= =?utf-8?B?SGtUY1RMdDQrUUlDUytBNE9ibmMwWmk2ZGhQMEdrYVE2QTR2d3JYNGJlYWlr?= =?utf-8?B?ek4xbjV5ZVMxc05mVGQzMjk4WHBQNzJZZ2VTNFpGb1JTd1NBNTdtcW5lZVZB?= =?utf-8?B?cytBc2RIK3ZFTzFLdjAxQnFIdUZqL2NJVmpaeDV0SStlOG5Wbmg1aXpsb1U1?= =?utf-8?B?MUNzNVZxdkQwMkdQSTVqMVlqZURRWjkvdExtaDNZZDBRSGFlaDVPNy9tWFJu?= =?utf-8?B?TU9GU203TGtkbE50azJqY1ZYQnJPL2VxZjlrejIySkxyaXdLYlpXVnA5WmdI?= =?utf-8?B?TU1CaFRGa0hPUzhSV085R1dBZXVaZVF0YVg3NGxVdkd6RC9GbWtFZWFMYVhO?= =?utf-8?B?ZFVCT29VazM2ZGNKMlhqcld0bUJDeFZVMWVReW1VUkl3VnJ2OWZaZEdPTlN3?= =?utf-8?B?ajQ2UHEyeVRxeENOZlVPbkFTVG15QzhlN2RUZExFRmxaWVBTTGlJUGJDbmZI?= =?utf-8?B?SFF1STZ0MTF2ZXJOeitCWVJ2UERrSkswNEpzQ3pSWDljblk1czdPQlFMVHRH?= =?utf-8?B?NHJsWTJMWlRjcVBVdVdKeGhYZEFYZitrc3R6SndCK2I5TEdVNm4rOXd2cU8r?= =?utf-8?B?SmJoZVE0dW5PbEVmWWsrTndaaTUwNnpmZk5yTHgwYjRSZWwvV3VHRUM1bjVr?= =?utf-8?B?RE56VlEycUZpZTUrUWY3MXdLNGhoVW9qcUlaaXFnUnpWT0NHRGVBR0xLa0Zs?= =?utf-8?B?VmZJSXBEcjk5cWcxemhTWm1DcWNnb0xZOGpXbmVCNVJKL2ZSQWc1aldRRGc4?= =?utf-8?B?dXpmOW1zWXFjdUxGSDRaUE9xZFEyV0RlOWJKOUhsa2ZRWW5SOEZiRDFsOVcw?= =?utf-8?B?Sm9UNS84NjNrMkNLMi9UTGhrU25iMU51Z20rL0pEeCttRytXZjZnWCt1YjV3?= =?utf-8?B?bHVRcGJCR0g0WEpEa2hkWVZBTXZGYzhrR012eFA5RnF4cFU4NGdMSVFYN2FO?= =?utf-8?B?WVFyZWRsQkFnaEM0eUZSeFFNaG5TUHdVOTlzdmYxRUlkcGdSalVsKzVjOEU1?= =?utf-8?B?Y2ljN3pTOGxpWmRoRXVYbTlwc0VBbC81MTk5WkkvN3RSUW5OL2E2ZkhOV3RX?= =?utf-8?B?N1NONzlLU0VHREtCSG0yNCtJZTJLR3FXMVM2YUpmU3U2N3lkUC9PNkN0eDN1?= =?utf-8?B?YjQwbkFqYzk4RmFUUmlNVmU1QTJUOEw2LzF6WEtJVlJDNUhVUktNdWdYWGZX?= =?utf-8?B?QTAvTGVXL1NlbzhlMXN0TTJvNm5uYlhxdE45TGR5SDVBVldCYk8yNXhyL2Jp?= =?utf-8?B?dkhUQzFoNll3RXRQMlFLUFdQMVNtdDRBNUhtVFlVTmR3OC9yTzJEWEY4VW5p?= =?utf-8?B?RDVZazVUVU5VNllhRWVFTDY4K2lPcG9JYTI5NnAyRUJsYmdkM0tCZlA4S3VR?= =?utf-8?B?dDhpOWV3Q3ovdmJ3akcycXVRbUhPbU9PYUF3TXJvUTd4ako5a1hZcWQyMEd0?= =?utf-8?B?RThtcmhTNTZpaWxTdnpOdDBmemxuNGdlTFo3Uld5aUtxbXpRN1JMY05QU1k5?= =?utf-8?B?bkprMVJDemlqWmkvVUV3V0RXWjE1SGZqM1F6QlVlVkUzUGtqRUFPaTFHaC9S?= =?utf-8?B?WFpkcy9EYjFQRVR6NGU2NDR6VVBDYXhIK1pMOFI3YmNvT294SVFscDViSEJI?= =?utf-8?B?cVgrZFd0V1NBMmJZSWpxaWpyMDlGVGF6RnBnQXdYNlVpK3o1cUVKeE52SFM0?= =?utf-8?Q?o1GWs0hv+asnT+lMHd?= X-OriginatorOrg: Nvidia.com X-MS-Exchange-CrossTenant-Network-Message-Id: 89594ed3-d77a-4c1c-4f7e-08df0e185c66 X-MS-Exchange-CrossTenant-AuthSource: IA0PR12MB8374.namprd12.prod.outlook.com X-MS-Exchange-CrossTenant-AuthAs: Internal X-MS-Exchange-CrossTenant-OriginalArrivalTime: 09 Sep 2026 02:16:30.3216 (UTC) X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted X-MS-Exchange-CrossTenant-Id: 43083d15-7273-40c1-b7db-39efd9ccc17a X-MS-Exchange-CrossTenant-MailboxType: HOSTED X-MS-Exchange-CrossTenant-UserPrincipalName: NLqU04c5sRQSOsetkBDWRXLiKl4hCRyvuGNAudIymtkN8X6iLDqahL2E9o15fpFB X-MS-Exchange-Transport-CrossTenantHeadersStamped: CH1PPF4CBE7339A On Tue Sep 8, 2026 at 6:10 PM EDT, Ehab Ababneh wrote: > This series revives Buddy Lumpkin's earlier multi-kswapd proposal: > https://lkml.iu.edu/hypermail/linux/kernel/1804.0/00342.html +others Please Cc everyone in the cover letter, so people can know the motivation of the patchset. > > The motivation is stronger now than when the patch was first discussed. > Many current systems have hundreds of cores per NUMA node, not the > single-digit or low-tens core counts that were more common at the time. > When reclaim does not keep up, direct reclaim can still push allocation > latency into application paths and leave substantial CPU capacity waiting > for memory to be freed. > > This patchset adds adaptive multi-threaded kswapd. The wakeup policy uses > node load to decide how many kswapd workers to run, so reclaim can scale > when it helps and stay conservative on already busy nodes. > > Series summary: > > 1. Allow multiple kswapd threads per node and add control plumbing. > 2. Wake an appropriate number of kswapd threads from per-node > runnable load. > > Concerns from the original discussion and how this series addresses some > of them: > > - Concern: Direct reclaim is intended to slow a memory-hogging thread. > Response: That can be acceptable on lower-core systems. On high-core > systems, idling many cores while reclaim catches up can cost more than > allowing reclaim parallelism to scale. It can also block higher-priorit= y > tasks in direct reclaim while they perform reclaim work on behalf of > lower-priority memory-hogging tasks. > > - Concern: More kswapd threads may hide deeper reclaim issues. > Response: This series is additive to ongoing reclaim improvements. In > our testing, multi-threaded kswapd was able to improve performance on > top of what multi-gen LRU already provides. > > - Concern: Existing knobs (such as swappiness and watermarks) should be > preferred. > Response: In our testing, those knobs alone did not reliably hit > performance targets and could increase CPU cost for the same workload > objective. > > - Concern: Need evidence from real workloads. > Response: This cover letter includes Cassandra results showing higher > throughput and lower response latency. > > - Concern: More reclaim threads may increase pressure on well-behaved > tasks. > Response: Adaptive wakeup addresses this by choosing thread count from > node load. > > - Concern: Additional configuration can increase operational complexity. > Response: The user-facing interface is intentionally minimal: > max_kswapds_per_node. > > - Concern: Lock contention may serialize workers. > Response: The Cassandra runs below still show net gains, indicating > contention did not erase the benefit for this workload. The wakeup path > now uses wake_up_nr() against the existing kswapd_wait queue, avoiding > pgdat->kswapd_lock (a sleeping mutex) entirely on the allocation hot > path. > > Real-world workload results (Cassandra): > > Tests were performed on 7.0.0-rc1. > > - max_kswapds_per_node=3D1 > - throughput sample: 171146 > - reference latency value: 6.375 > - op rates: 43256, 42731, 42341, 42818 ops/s > - p99 latency: 6.3, 6.4, 6.4, 6.4 ms > > - max_kswapds_per_node=3D8 > - throughput sample: 183639 > - reference latency value: 6.0 > - op rates: 45791, 45253, 46534, 46061 ops/s > - p99 latency: 6.0, 6.1, 5.9, 6.0 ms > > Observed improvement in these runs was about +7.3% throughput and about > -5.9% response latency, which shows practical benefit for production-styl= e > database workloads. But the result suggested we should not have multi-threaded kswapd, because 7 extra threads give only 7.3% throughput. That is not a good use of CPU cores. I suspect these threads are competing for LRU locks. We might want to partition each LRU list into N first, before N kswapds can work truely in parallel. > > In our runs, performance numbers were essentially unchanged with and > without the adaptive multi-threaded kswapd wakeup policy. In both cases, > they outperformed the single-kswapd-thread baseline. This indicates the > adaptive method preserved the multi-threaded performance improvement. > > Addendum: alternative approaches evaluated > > - PSI per NUMA node. > I prototyped PSI-based node pressure ranges to drive wakeup count. > This became cumbersome because robust PSI-to-thread mappings were not > straightforward across workload types. > > - CPU mask snapshot policy. > I also tested a simple CPU mask snapshot approach. > While functional, it reflects a moment-in-time view and does not captur= e > pressure trends over a broader sampling window. > > Buddy Lumpkin (1): > vmscan: Support multiple kswapd threads per node > > Ehab Ababneh (2): > mm/vmscan: handle racing max_seq advancement > mm/vmscan: make kswapd wakeups NUMA load-aware > > include/linux/mmzone.h | 5 +- > include/trace/events/vmscan.h | 28 +++ > mm/compaction.c | 8 +- > mm/internal.h | 3 + > mm/page_alloc.c | 26 +++ > mm/vmscan.c | 419 ++++++++++++++++++++++++++++++++++++= +++--- > 6 files changed, 465 insertions(+), 24 deletions(-) --=20 Best Regards, Yan, Zi