Cover Detail
Show a cover letter.
GET /api/covers/102135/?format=api
{ "id": 102135, "url": "http://patches.dpdk.org/api/covers/102135/?format=api", "web_url": "http://patches.dpdk.org/project/dpdk/cover/20211019081738.2165150-1-xuemingl@nvidia.com/", "project": { "id": 1, "url": "http://patches.dpdk.org/api/projects/1/?format=api", "name": "DPDK", "link_name": "dpdk", "list_id": "dev.dpdk.org", "list_email": "dev@dpdk.org", "web_url": "http://core.dpdk.org", "scm_url": "git://dpdk.org/dpdk", "webscm_url": "http://git.dpdk.org/dpdk", "list_archive_url": "https://inbox.dpdk.org/dev", "list_archive_url_format": "https://inbox.dpdk.org/dev/{}", "commit_url_format": "" }, "msgid": "<20211019081738.2165150-1-xuemingl@nvidia.com>", "list_archive_url": "https://inbox.dpdk.org/dev/20211019081738.2165150-1-xuemingl@nvidia.com", "date": "2021-10-19T08:17:32", "name": "[v9,0/6] ethdev: introduce shared Rx queue", "submitter": { "id": 1904, "url": "http://patches.dpdk.org/api/people/1904/?format=api", "name": "Xueming Li", "email": "xuemingl@nvidia.com" }, "mbox": "http://patches.dpdk.org/project/dpdk/cover/20211019081738.2165150-1-xuemingl@nvidia.com/mbox/", "series": [ { "id": 19770, "url": "http://patches.dpdk.org/api/series/19770/?format=api", "web_url": "http://patches.dpdk.org/project/dpdk/list/?series=19770", "date": "2021-10-19T08:17:32", "name": "ethdev: introduce shared Rx queue", "version": 9, "mbox": "http://patches.dpdk.org/series/19770/mbox/" } ], "comments": "http://patches.dpdk.org/api/covers/102135/comments/", "headers": { "Return-Path": "<dev-bounces@dpdk.org>", "X-Original-To": "patchwork@inbox.dpdk.org", "Delivered-To": "patchwork@inbox.dpdk.org", "Received": [ "from mails.dpdk.org (mails.dpdk.org [217.70.189.124])\n\tby inbox.dpdk.org (Postfix) with ESMTP id 16F60A0C4E;\n\tTue, 19 Oct 2021 10:18:10 +0200 (CEST)", "from [217.70.189.124] (localhost [127.0.0.1])\n\tby mails.dpdk.org (Postfix) with ESMTP id 98D1D40142;\n\tTue, 19 Oct 2021 10:18:09 +0200 (CEST)", "from NAM10-DM6-obe.outbound.protection.outlook.com\n (mail-dm6nam10on2068.outbound.protection.outlook.com [40.107.93.68])\n by mails.dpdk.org (Postfix) with ESMTP id 430F44003E\n for <dev@dpdk.org>; Tue, 19 Oct 2021 10:18:08 +0200 (CEST)", "from DM5PR07CA0114.namprd07.prod.outlook.com (2603:10b6:4:ae::43) by\n BN6PR12MB1363.namprd12.prod.outlook.com (2603:10b6:404:1f::15) with\n Microsoft\n SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id\n 15.20.4608.16; Tue, 19 Oct 2021 08:18:06 +0000", "from DM6NAM11FT031.eop-nam11.prod.protection.outlook.com\n (2603:10b6:4:ae:cafe::3a) by DM5PR07CA0114.outlook.office365.com\n (2603:10b6:4:ae::43) with Microsoft SMTP Server (version=TLS1_2,\n cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.4608.15 via Frontend\n Transport; Tue, 19 Oct 2021 08:18:06 +0000", "from mail.nvidia.com (216.228.112.34) by\n DM6NAM11FT031.mail.protection.outlook.com (10.13.172.203) with Microsoft SMTP\n Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA384) id\n 15.20.4608.15 via Frontend Transport; Tue, 19 Oct 2021 08:18:04 +0000", "from nvidia.com (172.20.187.5) by HQMAIL107.nvidia.com\n (172.20.187.13) with Microsoft SMTP Server (TLS) id 15.0.1497.18; Tue, 19 Oct\n 2021 08:17:57 +0000" ], "ARC-Seal": "i=1; a=rsa-sha256; s=arcselector9901; d=microsoft.com; cv=none;\n b=O6VujLt1RbW0KIUtuCwfp0XV7hxJUsjmN5YqmdzwxUhRCuzIN5RsTf6Rl6BLkuVX9DdHOphO3oacz9o3j2FCbW4p1Tuz/92QW3CA2KwWiGDHcYjnDsO3IQ9orLLZHQRLH1uQ8nHOsteOq7qF9EU4hAgfmUbzPrrsNWaoEsHM6UyKCnFo3c5ne8es52Y7zvsSjp+YkrrEBkbHAuu/BfnrbZWaUag+ceQ6Mmv1W13UOWPJe4FTBn86qmfGQU6k6C3PT+u6WholJr7l0UO3En5/WTqYBEibRGrxP2OBTP/hBvtzaAgM8simatzW2gvvHNDy3ycZz+043E5ar4J5AgCebg==", "ARC-Message-Signature": "i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com;\n s=arcselector9901;\n 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;\n bh=JpX4o8hzuT9LKYYGfxSeUunsvAHf/nCzdXUyYqjxt6o=;\n b=bI1+HS97dUrkYbDAp4bJ+CfH7sWNtc4RR+QMrOq6Pwxa7tkGmjLgBcIBfyex17BL38T1ZYXBR8mCurEFUFIcEX9u66EINhXy84W7tU1sDHxMABM7a5RFAV17V1VklbtqVIzV16aBAeJTxA6dXaNpzoPh+9r2vEpZd0FiJy0ARAf2YEe48zO0DOvptkoeC95nQMP2kTa6uTfo+l5u/L/cQR6ThAzYVho3jOMpbOSJGXrP+GpVR7BwLf8mMyr1gD0t4r5oFKxbyoUj+gpGADX2tygpqoaVpvZDRFduHtQSM2qqh0dtkX1bo76bndYqcMDLFKm7EPYCBavbG0q+hfxrSg==", "ARC-Authentication-Results": "i=1; mx.microsoft.com 1; spf=pass (sender ip is\n 216.228.112.34) smtp.rcpttodomain=monjalon.net smtp.mailfrom=nvidia.com;\n dmarc=pass (p=quarantine sp=quarantine pct=100) action=none\n header.from=nvidia.com; dkim=none (message not signed); arc=none", "DKIM-Signature": "v=1; a=rsa-sha256; c=relaxed/relaxed; d=Nvidia.com;\n s=selector2;\n h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck;\n bh=JpX4o8hzuT9LKYYGfxSeUunsvAHf/nCzdXUyYqjxt6o=;\n b=EqCBrSvx0VxOzXvfJfG10BR8RptReWgMgptik9m/j4ig4V9003vpgB072gaQ+YKfHKAYDh0mu01NygPBlUCP1eX+IWkD32/rTNDXKfc1gp9x4gw9V6eliBT7XSRp1UdlQmpaROhvu52StW6RZLogXVK3srV6emDYfnIQ2aIGbUT8e0Ao+8ZKz47okRVp+CRjiw2aYBGkLQ90OEmkVceo6NzAhS7kb9N+O+Xg60FByQLkA98Hp5PbCZ/uEetZmGsD9ivMvvaNpHkLWbcPinK3lAwz/d2zSvJhTmVPf7C+Up5m6YnC37pc/dVo9sP8G5rJC0lQYED4khxA/Z+aa0r/MA==", "X-MS-Exchange-Authentication-Results": "spf=pass (sender IP is 216.228.112.34)\n smtp.mailfrom=nvidia.com; monjalon.net; dkim=none (message not signed)\n header.d=none;monjalon.net; dmarc=pass action=none header.from=nvidia.com;", "Received-SPF": "Pass (protection.outlook.com: domain of nvidia.com designates\n 216.228.112.34 as permitted sender) receiver=protection.outlook.com;\n client-ip=216.228.112.34; helo=mail.nvidia.com;", "From": "Xueming Li <xuemingl@nvidia.com>", "To": "<dev@dpdk.org>, Zhang Yuying <yuying.zhang@intel.com>", "CC": "<xuemingl@nvidia.com>, Jerin Jacob <jerinjacobk@gmail.com>, Ferruh Yigit\n <ferruh.yigit@intel.com>, Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>,\n Viacheslav Ovsiienko <viacheslavo@nvidia.com>, Thomas Monjalon\n <thomas@monjalon.net>, Lior Margalit <lmargalit@nvidia.com>, \"Ananyev\n Konstantin\" <konstantin.ananyev@intel.com>, Ajit Khaparde\n <ajit.khaparde@broadcom.com>", "Date": "Tue, 19 Oct 2021 16:17:32 +0800", "Message-ID": "<20211019081738.2165150-1-xuemingl@nvidia.com>", "X-Mailer": "git-send-email 2.33.0", "In-Reply-To": "<20210727034204.20649-1-xuemingl@nvidia.com>", "References": "<20210727034204.20649-1-xuemingl@nvidia.com>", "MIME-Version": "1.0", "Content-Transfer-Encoding": "8bit", "Content-Type": "text/plain", "X-Originating-IP": "[172.20.187.5]", "X-ClientProxiedBy": "HQMAIL111.nvidia.com (172.20.187.18) To\n HQMAIL107.nvidia.com (172.20.187.13)", "X-EOPAttributedMessage": "0", "X-MS-PublicTrafficType": "Email", "X-MS-Office365-Filtering-Correlation-Id": "cf79aa82-2161-4078-fbc9-08d992d8fa09", "X-MS-TrafficTypeDiagnostic": "BN6PR12MB1363:", "X-LD-Processed": "43083d15-7273-40c1-b7db-39efd9ccc17a,ExtAddr", "X-Microsoft-Antispam-PRVS": "\n <BN6PR12MB1363068269951CB9B25F1710A1BD9@BN6PR12MB1363.namprd12.prod.outlook.com>", "X-MS-Oob-TLC-OOBClassifiers": "OLM:8882;", "X-MS-Exchange-SenderADCheck": "1", "X-MS-Exchange-AntiSpam-Relay": "0", "X-Microsoft-Antispam": "BCL:0;", "X-Microsoft-Antispam-Message-Info": "\n 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", "X-Forefront-Antispam-Report": "CIP:216.228.112.34; CTRY:US; LANG:en; SCL:1;\n SRV:;\n IPV:NLI; SFV:NSPM; H:mail.nvidia.com; PTR:schybrid03.nvidia.com; CAT:NONE;\n SFS:(4636009)(36840700001)(46966006)(54906003)(1076003)(82310400003)(36860700001)(83380400001)(55016002)(186003)(4326008)(86362001)(316002)(2906002)(47076005)(7636003)(7696005)(356005)(6666004)(70206006)(336012)(8676002)(26005)(8936002)(110136005)(36756003)(5660300002)(70586007)(6286002)(426003)(508600001)(2616005)(16526019);\n DIR:OUT; SFP:1101;", "X-OriginatorOrg": "Nvidia.com", "X-MS-Exchange-CrossTenant-OriginalArrivalTime": "19 Oct 2021 08:18:04.1723 (UTC)", "X-MS-Exchange-CrossTenant-Network-Message-Id": "\n cf79aa82-2161-4078-fbc9-08d992d8fa09", "X-MS-Exchange-CrossTenant-Id": "43083d15-7273-40c1-b7db-39efd9ccc17a", "X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp": "\n TenantId=43083d15-7273-40c1-b7db-39efd9ccc17a; Ip=[216.228.112.34];\n Helo=[mail.nvidia.com]", "X-MS-Exchange-CrossTenant-AuthSource": "\n DM6NAM11FT031.eop-nam11.prod.protection.outlook.com", "X-MS-Exchange-CrossTenant-AuthAs": "Anonymous", "X-MS-Exchange-CrossTenant-FromEntityHeader": "HybridOnPrem", "X-MS-Exchange-Transport-CrossTenantHeadersStamped": "BN6PR12MB1363", "Subject": "[dpdk-dev] [PATCH v9 0/6] ethdev: introduce shared Rx queue", "X-BeenThere": "dev@dpdk.org", "X-Mailman-Version": "2.1.29", "Precedence": "list", "List-Id": "DPDK patches and discussions <dev.dpdk.org>", "List-Unsubscribe": "<https://mails.dpdk.org/options/dev>,\n <mailto:dev-request@dpdk.org?subject=unsubscribe>", "List-Archive": "<http://mails.dpdk.org/archives/dev/>", "List-Post": "<mailto:dev@dpdk.org>", "List-Help": "<mailto:dev-request@dpdk.org?subject=help>", "List-Subscribe": "<https://mails.dpdk.org/listinfo/dev>,\n <mailto:dev-request@dpdk.org?subject=subscribe>", "Errors-To": "dev-bounces@dpdk.org", "Sender": "\"dev\" <dev-bounces@dpdk.org>" }, "content": "In current DPDK framework, all Rx queues is pre-loaded with mbufs for\nincoming packets. When number of representors scale out in a switch\ndomain, the memory consumption became significant. Further more,\npolling all ports leads to high cache miss, high latency and low\nthroughputs.\n\nThis patch introduces shared Rx queue. PF and representors in same\nRx domain and switch domain could share Rx queue set by specifying\nnon-zero share group value in Rx queue configuration.\n\nAll ports that share Rx queue actually shares hardware descriptor\nqueue and feed all Rx queues with one descriptor supply, memory is saved.\n\nPolling any queue using same shared Rx queue receives packets from all\nmember ports. Source port is identified by mbuf->port.\n\nMultiple groups is supported by group ID. Port queue number in a shared\ngroup should be identical. Queue index is 1:1 mapped in shared group.\nAn example of two share groups:\n Group1, 4 shared Rx queues per member port: PF, repr0, repr1\n Group2, 2 shared Rx queues per member port: repr2, repr3, ... repr127\n Poll first port for each group:\n core\tport\tqueue\n 0\t0\t0\n 1\t0\t1\n 2\t0\t2\n 3\t0\t3\n 4\t2\t0\n 5\t2\t1\n\nShared Rx queue must be polled on single thread or core. If both PF0 and\nrepresentor0 joined same share group, can't poll pf0rxq0 on core1 and\nrep0rxq0 on core2. Actually, polling one port within share group is\nsufficient since polling any port in group will return packets for any\nport in group.\n\nThere was some discussion to aggregate member ports in same group into a\ndummy port, several ways to achieve it. Since it optional, need to collect\nmore feedback and requirement from user, make better decision later.\n\nv1:\n - initial version\nv2:\n - add testpmd patches\nv3:\n - change common forwarding api to macro for performance, thanks Jerin.\n - save global variable accessed in forwarding to flowstream to minimize\n cache miss\n - combined patches for each forwarding engine\n - support multiple groups in testpmd \"--share-rxq\" parameter\n - new api to aggregate shared rxq group\nv4:\n - spelling fixes\n - remove shared-rxq support for all forwarding engines\n - add dedicate shared-rxq forwarding engine\nv5:\n - fix grammars\n - remove aggregate api and leave it for later discussion\n - add release notes\n - add deployment example\nv6:\n - replace RxQ offload flag with device offload capability flag\n - add Rx domain\n - RxQ is shared when share group > 0\n - update testpmd accordingly\nv7:\n - fix testpmd share group id allocation\n - change rx_domain to 16bits\nv8:\n - add new patch for testpmd to show device Rx domain ID and capability\n - new share_qid in RxQ configuration\nv9:\n - fix some spelling\n\nXueming Li (6):\n ethdev: introduce shared Rx queue\n app/testpmd: dump device capability and Rx domain info\n app/testpmd: new parameter to enable shared Rx queue\n app/testpmd: dump port info for shared Rx queue\n app/testpmd: force shared Rx queue polled on same core\n app/testpmd: add forwarding engine for shared Rx queue\n\n app/test-pmd/config.c | 114 +++++++++++++-\n app/test-pmd/meson.build | 1 +\n app/test-pmd/parameters.c | 13 ++\n app/test-pmd/shared_rxq_fwd.c | 148 ++++++++++++++++++\n app/test-pmd/testpmd.c | 25 ++-\n app/test-pmd/testpmd.h | 5 +\n app/test-pmd/util.c | 3 +\n doc/guides/nics/features.rst | 13 ++\n doc/guides/nics/features/default.ini | 1 +\n .../prog_guide/switch_representation.rst | 11 ++\n doc/guides/rel_notes/release_21_11.rst | 6 +\n doc/guides/testpmd_app_ug/run_app.rst | 8 +\n doc/guides/testpmd_app_ug/testpmd_funcs.rst | 5 +-\n lib/ethdev/rte_ethdev.c | 8 +\n lib/ethdev/rte_ethdev.h | 24 +++\n 15 files changed, 379 insertions(+), 6 deletions(-)\n create mode 100644 app/test-pmd/shared_rxq_fwd.c" }