[{"id":1775894,"web_url":"http://patchwork.ozlabs.org/comment/1775894/","msgid":"<48EB9B23-48D4-4417-B6E9-0D332295BF54@vmware.com>","list_archive_url":null,"date":"2017-09-26T21:58:16","subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","submitter":{"id":68212,"url":"http://patchwork.ozlabs.org/api/people/68212/","name":"Darrell Ball","email":"dball@vmware.com"},"content":"On 9/25/17, 10:37 PM, \"Yuanhan Liu\" wrote:\r\n\r\n Some hightlights in v3\r\n ======================\r\n \r\n Here is the v3, with 2 major changes and further testings (including\r\n many flows). This took more effort than I thought, thus v3 publication\r\n has been delayed for a while.\r\n \r\n The first major change is the mark and id association is done with array\r\n instead of CMAP now. This gives us further performance gain: it could\r\n be up to 70% now (please see the exact number below).\r\n \r\n This change also make the code a bit more complex though, due to the\r\n lock issue. RCU is used (not quite sure it's been used rightly though).\r\n For now, RCU only protects the array base address update (due to\r\n reallocate), it doesn't protect the array item (array[i] = xx]) change.\r\n I think it's buggy and I need rethink about it.\r\n \r\n The second major change is there is a thread introduced to do the real\r\n flow offload. This is for diminishing the overhead by hw flow offload\r\n installation/deletion at data path. See patch 9 for more detailed info.\r\n\r\n[Darrell] There might be other options to handle this such as dividing time\r\nto HWOL in a given PMD. \r\nAnother option to have PMD isolation.\r\n \r\n In the last discussion, RSS action was suggested to use to get rid of\r\n the QUEUE action workaround. Unfortunately, it didn't work. The flow\r\n creation failed with MLX5 PMD driver, and that's the only driver in\r\n DPDK that supports RSS action so far.\r\n\r\n\r\n[Darrell] \r\nI wonder if we should take a pause before jumping into the next version of the code.\r\n\r\nIf workarounds are required in OVS code, then so be it as long as they are not\r\noverly disruptive to the existing code and hard to maintain.\r\nIn the case of RTE_FLOW_ACTION_TYPE_RSS, we might have a reasonable option\r\nto avoid some unpleasant OVS workarounds.\r\nThis would make a significant difference in the code paths, if we supported it, so\r\nwe need to be sure as early as possible.\r\nThe support needed would be in some drivers and seems reasonably doable. \r\nMoreover, this was discussed in the last dpdk meeting and the support was\r\nindicated as existing?, although I only verified the MLX code, myself.\r\n\r\nI had seen the MLX code supporting _RSS action and there are some checks for\r\nsupported cases; when you say “it didn't work”, what was the issue ?\r\nLet us have a discussion also about the Intel nic side and the Napatech side.\r\nIt seems reasonable to ask where the disconnect is and whether this support\r\ncan be added and then make a decision based on the answers. \r\n\r\nWhat do you think?\r\n\r\n \r\n I also tested many flows this time. The result is more exciting: it\r\n could be up to 267% boost, with 512 mega flows (with each has another\r\n 512 exact matching flows, thus it's 512*512=256K flows in total), one\r\n core and one queue doing PHY-PHY forwarding. For the offload case, the\r\n performance keeps the same as with one flow only: because the cost of\r\n the mark to flow translation is constant, no matter how many flows\r\n are inserted (as far as they are all offloaded). However, for the\r\n vanilla ovs-dpdk, the more flows, the worse the performance is. In\r\n another word, the more flows, the bigger difference we will see.\r\n \r\n There were too many discussions in last version. I'm sorry if I missed\r\n some comments and didn't do the corresponding changes in v3. Please let\r\n me know if I made such mistakes.\r\n \r\n And below are the formal cover letter introduction, for someone who\r\n is the first time to see this patchset.\r\n \r\n ---\r\n Hi,\r\n \r\n Here is a joint work from Mellanox and Napatech, to enable the flow hw\r\n offload with the DPDK generic flow interface (rte_flow).\r\n \r\n The basic idea is to associate the flow with a mark id (a unit32_t number).\r\n Later, we then get the flow directly from the mark id, bypassing the heavy\r\n emc processing, including miniflow_extract.\r\n \r\n The association is done with array in patch 1. It also reuses the flow\r\n APIs introduced while adding the tc offloads. The emc bypassing is done\r\n in patch 2. The flow offload is done in patch 4, which mainly does two\r\n things:\r\n \r\n - translate the ovs match to DPDK rte flow patterns\r\n - bind those patterns with a MARK action.\r\n \r\n Afterwards, the NIC will set the mark id in every pkt's mbuf when it\r\n matches the flow. That's basically how we could get the flow directly\r\n from the received mbuf.\r\n \r\n While testing with PHY-PHY forwarding with one core, one queue and one\r\n flow, I got about 70% performance boost. For PHY-vhost forwarding, I got\r\n about 50% performance boost. It's basically the performance I got with v1,\r\n when the tcp_flags is the ignored. In summary, the CMPA to array change\r\n gives up yet another 16% performance boost.\r\n \r\n The major issue mentioned in v1 is also workarounded: the queue index\r\n is never set to 0 blindly anymore, but set to the rxq that first\r\n receives the upcall pkt.\r\n \r\n Note that it's disabled by default, which can be enabled by:\r\n \r\n $ ovs-vsctl set Open_vSwitch . other_config:hw-offload=true\r\n \r\n v3: - The mark and id association is done with array instead of CMAP.\r\n - Added a thread to do hw offload operations\r\n - Removed macros completely\r\n - dropped the patch to set FDIR_CONF, which is a workround some\r\n Intel NICs.\r\n - Added a debug patch to show all flow patterns we have created.\r\n - Misc fixes\r\n \r\n v2: - workaround the queue action issue\r\n - fixed the tcp_flags being skipped issue, which also fixed the\r\n build warnings\r\n - fixed l2 patterns for Intel nic\r\n - Converted some macros to functions\r\n - did not hardcode the max number of flow/action\r\n - rebased on top of the latest code\r\n \r\n Thanks.\r\n \r\n --yliu\r\n \r\n ---\r\n Finn Christensen (2):\r\n netdev-dpdk: implement flow put with rte flow\r\n netdev-dpdk: retry with queue action\r\n \r\n Shachar Beiser (1):\r\n dpif-netdev: record rx queue id for the upcall\r\n \r\n Yuanhan Liu (6):\r\n dpif-netdev: associate flow with a mark id\r\n dpif-netdev: retrieve flow directly from the flow mark\r\n netdev-dpdk: convert ufid to dpdk flow\r\n netdev-dpdk: remove offloaded flow on deletion\r\n netdev-dpdk: add debug for rte flow patterns\r\n dpif-netdev: do hw flow offload in another thread\r\n \r\n lib/dp-packet.h | 14 +\r\n lib/dpif-netdev.c | 421 ++++++++++++++++++++++++++++-\r\n lib/flow.c | 155 ++++++++---\r\n lib/flow.h | 1 +\r\n lib/netdev-dpdk.c | 776 +++++++++++++++++++++++++++++++++++++++++++++++++++++-\r\n lib/netdev.c | 1 +\r\n lib/netdev.h | 7 +\r\n 7 files changed, 1331 insertions(+), 44 deletions(-)\r\n \r\n -- \r\n 2.7.4","headers":{"Return-Path":"","X-Original-To":["incoming@patchwork.ozlabs.org","dev@openvswitch.org"],"Delivered-To":["patchwork-incoming@bilbo.ozlabs.org","ovs-dev@mail.linuxfoundation.org"],"Authentication-Results":["ozlabs.org;\n\tspf=pass (mailfrom) smtp.mailfrom=openvswitch.org\n\t(client-ip=140.211.169.12; helo=mail.linuxfoundation.org;\n\tenvelope-from=ovs-dev-bounces@openvswitch.org;\n\treceiver=)","ozlabs.org;\n\tdkim=fail reason=\"signature verification failed\" (1024-bit key;\n\tunprotected) header.d=onevmw.onmicrosoft.com\n\theader.i=@onevmw.onmicrosoft.com header.b=\"Ls1TAI5m\"; \n\tdkim-atps=neutral","spf=none (sender IP is )\n\tsmtp.mailfrom=dball@vmware.com; "],"Received":["from mail.linuxfoundation.org (mail.linuxfoundation.org\n\t[140.211.169.12])\n\t(using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256\n\tbits)) (No client certificate requested)\n\tby ozlabs.org (Postfix) with ESMTPS id 3y1vwM1MCGz9sPr\n\tfor ;\n\tWed, 27 Sep 2017 07:58:26 +1000 (AEST)","from mail.linux-foundation.org (localhost [127.0.0.1])\n\tby mail.linuxfoundation.org (Postfix) with ESMTP id 64D49A59;\n\tTue, 26 Sep 2017 21:58:23 +0000 (UTC)","from smtp1.linuxfoundation.org (smtp1.linux-foundation.org\n\t[172.17.192.35])\n\tby mail.linuxfoundation.org (Postfix) with ESMTPS id 5413A9F8\n\tfor ; Tue, 26 Sep 2017 21:58:22 +0000 (UTC)","from NAM03-DM3-obe.outbound.protection.outlook.com\n\t(mail-dm3nam03on0085.outbound.protection.outlook.com [104.47.41.85])\n\tby smtp1.linuxfoundation.org (Postfix) with ESMTPS id F294B432\n\tfor ; Tue, 26 Sep 2017 21:58:20 +0000 (UTC)","from MWHPR05MB3406.namprd05.prod.outlook.com (10.174.175.155) by\n\tMWHPR05MB3406.namprd05.prod.outlook.com (10.174.175.155) with\n\tMicrosoft SMTP Server (version=TLS1_2,\n\tcipher=TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA384_P256) id\n\t15.20.77.5; Tue, 26 Sep 2017 21:58:17 +0000","from MWHPR05MB3406.namprd05.prod.outlook.com ([10.174.175.155]) by\n\tMWHPR05MB3406.namprd05.prod.outlook.com ([10.174.175.155]) with\n\tmapi id 15.20.0077.007; Tue, 26 Sep 2017 21:58:17 +0000"],"X-Greylist":"whitelisted by SQLgrey-1.7.6","DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=onevmw.onmicrosoft.com; s=selector1-vmware-com;\n\th=From:Date:Subject:Message-ID:Content-Type:MIME-Version;\n\tbh=CNiOjsSIk7BVutnQNby9czW1YUQvv2wjHtfLPVGOjaI=;\n\tb=Ls1TAI5mzJOQSNNu7hiH5DwPizmcIzMS2Hvn2dMUQX2g4nW81OUa3u6jDG+nJOUdUUGIwgxIfyGQLrTxqFLN1xCVhdhzl0ursSQXYFFvm+RtGBd6p2PuXVV/s51KHXARlfIVq6Gfc24VYJyDUEQvsjdIw6zpvvlXDQxDiXWM+1A=","From":"Darrell Ball ","To":"Yuanhan Liu , \"dev@openvswitch.org\"\n\t","Thread-Topic":"[PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","Thread-Index":"AQHTNomLA1xYF2/wCU28LyYMHmmNz6LHuAiA","Date":"Tue, 26 Sep 2017 21:58:16 +0000","Message-ID":"<48EB9B23-48D4-4417-B6E9-0D332295BF54@vmware.com>","References":"<1506404199-23579-1-git-send-email-yliu@fridaylinux.org>","In-Reply-To":"<1506404199-23579-1-git-send-email-yliu@fridaylinux.org>","Accept-Language":"en-US","Content-Language":"en-US","X-MS-Has-Attach":"","X-MS-TNEF-Correlator":"","user-agent":"Microsoft-MacOutlook/f.26.0.170902","x-originating-ip":"[73.162.236.45]","x-ms-publictraffictype":"Email","x-microsoft-exchange-diagnostics":"1; MWHPR05MB3406;\n\t20:qVSfI58SXdhaNnzFyy+8AYduu8mlzqiHttPR0B6T2oXNfcXG9/EyTYrzWqCXUz0zKkWGMw9kxJ5uFG9OM9duX3O8hYrFvvO9yPJKRq9Pyd3mvCIOlxhu+fpWy1VHcZrOa1OgkezD5KllpRl0Jvlc7Ury36O2y2EXm8FyFKSzLkg=","x-ms-exchange-antispam-srfa-diagnostics":"SSOS;","x-ms-office365-filtering-correlation-id":"1d35c1a8-46d1-43b6-f720-08d50529b165","x-microsoft-antispam":"UriScan:; BCL:0; PCL:0;\n\tRULEID:(22001)(2017030254152)(2017052603199)(201703131423075)(201703031133081)(201702281549075);\n\tSRVR:MWHPR05MB3406; ","x-ms-traffictypediagnostic":"MWHPR05MB3406:","authentication-results":["ozlabs.org;\n\tspf=pass (mailfrom) smtp.mailfrom=openvswitch.org\n\t(client-ip=140.211.169.12; helo=mail.linuxfoundation.org;\n\tenvelope-from=ovs-dev-bounces@openvswitch.org;\n\treceiver=)","ozlabs.org;\n\tdkim=fail reason=\"signature verification failed\" (1024-bit key;\n\tunprotected) header.d=onevmw.onmicrosoft.com\n\theader.i=@onevmw.onmicrosoft.com header.b=\"Ls1TAI5m\"; \n\tdkim-atps=neutral","spf=none (sender IP is )\n\tsmtp.mailfrom=dball@vmware.com; "],"x-exchange-antispam-report-test":"UriScan:;","x-microsoft-antispam-prvs":"","x-exchange-antispam-report-cfa-test":"BCL:0; PCL:0;\n\tRULEID:(100000700101)(100105000095)(100000701101)(100105300095)(100000702101)(100105100095)(6040450)(2401047)(8121501046)(5005006)(100000703101)(100105400095)(93006095)(93001095)(10201501046)(3002001)(6041248)(20161123564025)(20161123555025)(20161123562025)(201703131423075)(201702281528075)(201703061421075)(201703061406153)(20161123560025)(20161123558100)(6072148)(201708071742011)(100000704101)(100105200095)(100000705101)(100105500095);\n\tSRVR:MWHPR05MB3406; BCL:0; PCL:0;\n\tRULEID:(100000800101)(100110000095)(100000801101)(100110300095)(100000802101)(100110100095)(100000803101)(100110400095)(100000804101)(100110200095)(100000805101)(100110500095);\n\tSRVR:MWHPR05MB3406; ","x-forefront-prvs":"0442E569BC","x-forefront-antispam-report":"SFV:NSPM;\n\tSFS:(10009020)(6009001)(376002)(346002)(39860400002)(24454002)(189002)(199003)(54094003)(76104003)(377454003)(99286003)(110136005)(53936002)(4326008)(58126008)(5660300001)(83506001)(316002)(6246003)(2950100002)(66066001)(86362001)(102836003)(82746002)(54906003)(36756003)(2900100001)(53546010)(25786009)(2501003)(189998001)(39060400002)(83716003)(6116002)(3846002)(50986999)(229853002)(478600001)(101416001)(8676002)(97736004)(8936002)(6486002)(81156014)(76176999)(77096006)(6512007)(54356999)(81166006)(33656002)(7736002)(6506006)(68736007)(106356001)(3280700002)(3660700001)(14454004)(6436002)(2906002)(105586002)(305945005);\n\tDIR:OUT; SFP:1101; SCL:1; SRVR:MWHPR05MB3406;\n\tH:MWHPR05MB3406.namprd05.prod.outlook.com; FPR:; SPF:None;\n\tPTR:InfoNoRecords; MX:1; A:1; LANG:en; ","received-spf":"None (protection.outlook.com: vmware.com does not designate\n\tpermitted sender hosts)","spamdiagnosticoutput":"1:99","spamdiagnosticmetadata":"NSPM","Content-ID":"<89D5B36AB485C34699D782AB6E575422@namprd05.prod.outlook.com>","MIME-Version":"1.0","X-OriginatorOrg":"vmware.com","X-MS-Exchange-CrossTenant-originalarrivaltime":"26 Sep 2017 21:58:16.8340\n\t(UTC)","X-MS-Exchange-CrossTenant-fromentityheader":"Hosted","X-MS-Exchange-CrossTenant-id":"b39138ca-3cee-4b4a-a4d6-cd83d9dd62f0","X-MS-Exchange-Transport-CrossTenantHeadersStamped":"MWHPR05MB3406","X-Spam-Status":"No, score=0.0 required=5.0 tests=DKIM_SIGNED,DKIM_VALID,\n\tRCVD_IN_DNSWL_NONE autolearn=disabled version=3.3.1","X-Spam-Checker-Version":"SpamAssassin 3.3.1 (2010-03-16) on\n\tsmtp1.linux-foundation.org","Cc":"Simon Horman ","Subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","X-BeenThere":"ovs-dev@openvswitch.org","X-Mailman-Version":"2.1.12","Precedence":"list","List-Id":"","List-Unsubscribe":",\n\t","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n\t","Content-Type":"text/plain; charset=\"utf-8\"","Content-Transfer-Encoding":"base64","Sender":"ovs-dev-bounces@openvswitch.org","Errors-To":"ovs-dev-bounces@openvswitch.org"}},{"id":1775982,"web_url":"http://patchwork.ozlabs.org/comment/1775982/","msgid":"<20170927012454.GF2251@yliu-home>","list_archive_url":null,"date":"2017-09-27T01:24:54","subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","submitter":{"id":72215,"url":"http://patchwork.ozlabs.org/api/people/72215/","name":"Yuanhan Liu","email":"yliu@fridaylinux.org"},"content":"On Tue, Sep 26, 2017 at 09:58:16PM +0000, Darrell Ball wrote:\n> The second major change is there is a thread introduced to do the real\n> flow offload. This is for diminishing the overhead by hw flow offload\n> installation/deletion at data path. See patch 9 for more detailed info.\n> \n> [Darrell] There might be other options to handle this such as dividing time\n> to HWOL in a given PMD. \n> Another option to have PMD isolation.\n\nGood to know, though I'm not sure I understand it so far. But it can be\ndiscussed later. That's also the reason I put it in the last patch, so\nthat we could easily turn it to another solution, or even simpler (just\nremove it).\n\n> In the last discussion, RSS action was suggested to use to get rid of\n> the QUEUE action workaround. Unfortunately, it didn't work. The flow\n> creation failed with MLX5 PMD driver, and that's the only driver in\n> DPDK that supports RSS action so far.\n> \n> \n> [Darrell] \n> I wonder if we should take a pause before jumping into the next version of the code.\n\nI have no objections.\n\n> If workarounds are required in OVS code, then so be it as long as they are not\n> overly disruptive to the existing code and hard to maintain.\n> In the case of RTE_FLOW_ACTION_TYPE_RSS, we might have a reasonable option\n> to avoid some unpleasant OVS workarounds.\n> This would make a significant difference in the code paths, if we supported it, so\n> we need to be sure as early as possible.\n\nI agree.\n\n> The support needed would be in some drivers and seems reasonably doable. \n> Moreover, this was discussed in the last dpdk meeting and the support was\n> indicated as existing?, although I only verified the MLX code, myself.\n\nFrom the code point of view, yes, the code was there months ago.\n\n> I had seen the MLX code supporting _RSS action and there are some checks for\n> supported cases; when you say “it didn't work”, what was the issue ?\n\nI actually have met the error months ago, I even debugged it. IIRC,\nthe error is from libibverbs, when trying to create the hw flow. I\nthink I need double-confirm it with our colleague who developed this\nfeature.\n\n> Let us have a discussion also about the Intel nic side and the Napatech side.\n\nI think it's not necessary for Napatech, because they can support\nMARK only action.\n\nFor Intel, yes, I think Intel folks could give some comments here.\n\n> It seems reasonable to ask where the disconnect is and whether this support\n> can be added and then make a decision based on the answers. \n\nNo objections.\n\n\t--yliu","headers":{"Return-Path":"","X-Original-To":["incoming@patchwork.ozlabs.org","dev@openvswitch.org"],"Delivered-To":["patchwork-incoming@bilbo.ozlabs.org","ovs-dev@mail.linuxfoundation.org"],"Authentication-Results":["ozlabs.org;\n\tspf=pass (mailfrom) smtp.mailfrom=openvswitch.org\n\t(client-ip=140.211.169.12; helo=mail.linuxfoundation.org;\n\tenvelope-from=ovs-dev-bounces@openvswitch.org;\n\treceiver=)","ozlabs.org;\n\tdkim=fail reason=\"signature verification failed\" (2048-bit key;\n\tunprotected) header.d=fridaylinux-org.20150623.gappssmtp.com\n\theader.i=@fridaylinux-org.20150623.gappssmtp.com\n\theader.b=\"ppaNT1Ag\"; dkim-atps=neutral"],"Received":["from mail.linuxfoundation.org (mail.linuxfoundation.org\n\t[140.211.169.12])\n\t(using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256\n\tbits)) (No client certificate requested)\n\tby ozlabs.org (Postfix) with ESMTPS id 3y20Vw0RyTz9s7f\n\tfor ;\n\tWed, 27 Sep 2017 11:25:12 +1000 (AEST)","from mail.linux-foundation.org (localhost [127.0.0.1])\n\tby mail.linuxfoundation.org (Postfix) with ESMTP id 95DBAB8B;\n\tWed, 27 Sep 2017 01:25:07 +0000 (UTC)","from smtp1.linuxfoundation.org (smtp1.linux-foundation.org\n\t[172.17.192.35])\n\tby mail.linuxfoundation.org (Postfix) with ESMTPS id 6AE86B77\n\tfor ; Wed, 27 Sep 2017 01:25:06 +0000 (UTC)","from mail-pf0-f182.google.com (mail-pf0-f182.google.com\n\t[209.85.192.182])\n\tby smtp1.linuxfoundation.org (Postfix) with ESMTPS id 1BD3717E\n\tfor ; Wed, 27 Sep 2017 01:25:03 +0000 (UTC)","by mail-pf0-f182.google.com with SMTP id z84so6430085pfi.2\n\tfor ; Tue, 26 Sep 2017 18:25:03 -0700 (PDT)","from yliu-home ([45.63.61.64]) by smtp.gmail.com with ESMTPSA id\n\tu20sm16340041pfh.171.2017.09.26.18.24.59\n\t(version=TLS1 cipher=ECDHE-RSA-AES128-SHA bits=128/128);\n\tTue, 26 Sep 2017 18:25:01 -0700 (PDT)"],"X-Greylist":"whitelisted by SQLgrey-1.7.6","DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=fridaylinux-org.20150623.gappssmtp.com; s=20150623;\n\th=date:from:to:cc:subject:message-id:references:mime-version\n\t:content-disposition:content-transfer-encoding:in-reply-to\n\t:user-agent; bh=PrbKw4s7e2R25mmJmc5WjhVHJXaUUC2aAQoALJRniEo=;\n\tb=ppaNT1Ag5qExA6ECLFjnbAaGAtFNrZoWq1YmoiuyNTkbzvB3cgnYs3r3t2sG+n7FiG\n\taEZIJlMhPofpwwXnWlqk0nLXdypPUms4DzaIzkthZASWy07y8pMT+VaSyynPEhT+ZjQD\n\tIK+I6RMkeaoK50tq7bcHprRlN1iQpz+FOOBk8EhM46L7m3HM/hApf2SKCsNjhhhWNp2m\n\tz/Qm/bh3zAE4sdGR2usbytFXAJe8SEUwSikGHzM5nsYpdP0z4N3nePDoHKex4d/uUS6V\n\tg7WqmCdoebdBp/azCcuxgM1kYpTFZIMzglk5aY6Q+mnJSZwvJ3riws/ZAD53B4b4oy+5\n\tg7AQ==","X-Google-DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=1e100.net; s=20161025;\n\th=x-gm-message-state:date:from:to:cc:subject:message-id:references\n\t:mime-version:content-disposition:content-transfer-encoding\n\t:in-reply-to:user-agent;\n\tbh=PrbKw4s7e2R25mmJmc5WjhVHJXaUUC2aAQoALJRniEo=;\n\tb=Qezty0kZX2+inpclFt0xoNG8/esc1AD576qp1+ILWld34LswynaKwynGzLE2y36td9\n\tR0axLJy0fhG0FPxDGzDIFnKwkvpeCvWFxosNF0lEyDNW3TBeOoc9Vu8IFNf39DIMMuH2\n\tHOYxnV4EgvieQspXjN51rn/Ln7R/ddjOlJQxewIYyrbHXz7m9LW+0/aqYM1vAPyOmSGX\n\tDlnXErlEBgOUg/GH2RS1MVEvbGjurQiaLyN6OZPFP7XN2U0E+orpZ/1Z2ihOCZd7Rzl5\n\tAULXmX75X4Dr37B02BoXnj3/+LoD49irjHP1u61I2zVVsMQJ3OByRPSLxa1atY/3vhHp\n\tB4mw==","X-Gm-Message-State":"AHPjjUgRLVD5wn/7shwAKfe/fVNpiKDL9rEhjvNsTmXI7JdjC8dn8WdK\n\tHRM6Nydbqs1RtIqlXR7ZUHSbGw==","X-Google-Smtp-Source":"AOwi7QB7Ycbx3ZNBxXafQVUvQeMVAlAal4liW+/Vx0MGx0xcN/7TlnQ0CxHmXHqBhbS3vYXOoPFNLg==","X-Received":"by 10.98.157.74 with SMTP id i71mr12684910pfd.168.1506475502640; \n\tTue, 26 Sep 2017 18:25:02 -0700 (PDT)","Date":"Wed, 27 Sep 2017 09:24:54 +0800","From":"Yuanhan Liu ","To":"Darrell Ball ","Message-ID":"<20170927012454.GF2251@yliu-home>","References":"<1506404199-23579-1-git-send-email-yliu@fridaylinux.org>\n\t<48EB9B23-48D4-4417-B6E9-0D332295BF54@vmware.com>","MIME-Version":"1.0","Content-Disposition":"inline","In-Reply-To":"<48EB9B23-48D4-4417-B6E9-0D332295BF54@vmware.com>","User-Agent":"Mutt/1.5.24 (2015-08-30)","X-Spam-Status":"No, score=0.0 required=5.0 tests=DKIM_SIGNED,DKIM_VALID,\n\tRCVD_IN_DNSWL_NONE autolearn=disabled version=3.3.1","X-Spam-Checker-Version":"SpamAssassin 3.3.1 (2010-03-16) on\n\tsmtp1.linux-foundation.org","Cc":"\"dev@openvswitch.org\" ,\n\tSimon Horman ","Subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","X-BeenThere":"ovs-dev@openvswitch.org","X-Mailman-Version":"2.1.12","Precedence":"list","List-Id":"","List-Unsubscribe":",\n\t","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n\t","Content-Type":"text/plain; charset=\"utf-8\"","Content-Transfer-Encoding":"base64","Sender":"ovs-dev-bounces@openvswitch.org","Errors-To":"ovs-dev-bounces@openvswitch.org"}},{"id":1775991,"web_url":"http://patchwork.ozlabs.org/comment/1775991/","msgid":"<20170927020920.GG2251@yliu-home>","list_archive_url":null,"date":"2017-09-27T02:09:20","subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","submitter":{"id":72215,"url":"http://patchwork.ozlabs.org/api/people/72215/","name":"Yuanhan Liu","email":"yliu@fridaylinux.org"},"content":"On Wed, Sep 27, 2017 at 09:24:54AM +0800, Yuanhan Liu wrote:\n> > The support needed would be in some drivers and seems reasonably doable. \n> > Moreover, this was discussed in the last dpdk meeting and the support was\n> > indicated as existing?, although I only verified the MLX code, myself.\n> \n> >From the code point of view, yes, the code was there months ago.\n> \n> > I had seen the MLX code supporting _RSS action and there are some checks for\n> > supported cases; when you say “it didn't work”, what was the issue ?\n> \n> I actually have met the error months ago, I even debugged it. IIRC,\n> the error is from libibverbs, when trying to create the hw flow. I\n> think I need double-confirm it with our colleague who developed this\n> feature.\n\nHmm, I think I was wrong, and apparenetly, I think I have did something\nstupid in the last try. I double confirmed it just now, at least the\nflow creation now works. I just need take some time to intergrate it\nto OVS-DPDK, to see how it goes. I will get it back to you when I have\ndone that. Currently, I was occupied by something else.\n\n\t--yliu","headers":{"Return-Path":"","X-Original-To":["incoming@patchwork.ozlabs.org","dev@openvswitch.org"],"Delivered-To":["patchwork-incoming@bilbo.ozlabs.org","ovs-dev@mail.linuxfoundation.org"],"Authentication-Results":["ozlabs.org;\n\tspf=pass (mailfrom) smtp.mailfrom=openvswitch.org\n\t(client-ip=140.211.169.12; helo=mail.linuxfoundation.org;\n\tenvelope-from=ovs-dev-bounces@openvswitch.org;\n\treceiver=)","ozlabs.org;\n\tdkim=fail reason=\"signature verification failed\" (2048-bit key;\n\tunprotected) header.d=fridaylinux-org.20150623.gappssmtp.com\n\theader.i=@fridaylinux-org.20150623.gappssmtp.com\n\theader.b=\"Nx/ArKje\"; dkim-atps=neutral"],"Received":["from mail.linuxfoundation.org (mail.linuxfoundation.org\n\t[140.211.169.12])\n\t(using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256\n\tbits)) (No client certificate requested)\n\tby ozlabs.org (Postfix) with ESMTPS id 3y21V71Tgwz9t3m\n\tfor ;\n\tWed, 27 Sep 2017 12:09:34 +1000 (AEST)","from mail.linux-foundation.org (localhost [127.0.0.1])\n\tby mail.linuxfoundation.org (Postfix) with ESMTP id D6773B79;\n\tWed, 27 Sep 2017 02:09:30 +0000 (UTC)","from smtp1.linuxfoundation.org (smtp1.linux-foundation.org\n\t[172.17.192.35])\n\tby mail.linuxfoundation.org (Postfix) with ESMTPS id F30A9B77\n\tfor ; Wed, 27 Sep 2017 02:09:29 +0000 (UTC)","from mail-pg0-f44.google.com (mail-pg0-f44.google.com\n\t[74.125.83.44])\n\tby smtp1.linuxfoundation.org (Postfix) with ESMTPS id 96719D3\n\tfor ; Wed, 27 Sep 2017 02:09:29 +0000 (UTC)","by mail-pg0-f44.google.com with SMTP id i195so6931701pgd.9\n\tfor ; Tue, 26 Sep 2017 19:09:29 -0700 (PDT)","from yliu-home ([45.63.61.64]) by smtp.gmail.com with ESMTPSA id\n\tq15sm17006182pgc.64.2017.09.26.19.09.26\n\t(version=TLS1 cipher=ECDHE-RSA-AES128-SHA bits=128/128);\n\tTue, 26 Sep 2017 19:09:28 -0700 (PDT)"],"X-Greylist":"whitelisted by SQLgrey-1.7.6","DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=fridaylinux-org.20150623.gappssmtp.com; s=20150623;\n\th=date:from:to:cc:subject:message-id:references:mime-version\n\t:content-disposition:content-transfer-encoding:in-reply-to\n\t:user-agent; bh=n5tZM62MwJfNcWKpT0O7KTxc81dS6pZbKtSCTH/WX+Q=;\n\tb=Nx/ArKjeFwbELLgtyAAEsXK7GA2f9XzriNW1sX6cLyKCmzkOgu54E2lUfiOtJynsHa\n\ti96T1avlD0UVRgg9NiDOSamwouhVDUukkzWCNfbtLLBFJRSith0Buh8ddyKWFLWePcRx\n\t96C1arvm9Igy/gYDCEGI4gLxmtgqVDX2Tfj9xUoPGE5vUrep5s/I0NA+2mYKRZawTcRx\n\tjfdPIBwe73Sg44LPAOj8jTwZqeCwCmuZUhhY9BvTuWu3m1Yk5qfX3/lDGB/q93Tkp0RT\n\tzBGvAqK+j0uKqLF/zuGrswl1+vwZ5P7tAw3v4HAXPquR3cc0K7swHsNI+SGRLRYHZa/F\n\tmcwg==","X-Google-DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=1e100.net; s=20161025;\n\th=x-gm-message-state:date:from:to:cc:subject:message-id:references\n\t:mime-version:content-disposition:content-transfer-encoding\n\t:in-reply-to:user-agent;\n\tbh=n5tZM62MwJfNcWKpT0O7KTxc81dS6pZbKtSCTH/WX+Q=;\n\tb=GPi9kjcYRvRzXFcFOfl0hXef0be/0XA1+b9FN02Uc3BMzcw/8bk+LSXQ7MBW1wQ+d3\n\twmLaRxExtK9T2CUQuEFtNcCvAKidwMX5I+WoJNct2pGCxtl9IfxOSZrDwX8UY8DSM1pp\n\t6QQ5BijBd622vAlPbIg6vgiP8UtDkKldLkWajMX0kjVkJuIMaO86q0zq84U172amtZ8C\n\tlCWCXHdc/vXQ0HZ4xCd4jiesXTlPEGwbiKENcXDPWmeNFXDD1+dlQwM2GNJjPF+LFcvZ\n\tsXKhnDunL8sTHYDyfbrI/6BVGX5yXu9YSIHd+BORdbGMHH+YbtdtOyo0wMZcawjJiv5A\n\takpw==","X-Gm-Message-State":"AHPjjUhf/xUlCh7jLJDhZo1QnXGDtQ4ZJOo1/UmmuoUj+hEiy93E7Ylu\n\tREghrV02lqFiWjGyLki7k4+1sg==","X-Google-Smtp-Source":"AOwi7QD2K/oGOwlKlW7WBkiI1cTvZoiBIR7ecAfD0VUmGZFSxQ9i+RnpCF1KZgBllsZpnTnmHFyC6A==","X-Received":"by 10.84.172.131 with SMTP id n3mr12534098plb.408.1506478169089; \n\tTue, 26 Sep 2017 19:09:29 -0700 (PDT)","Date":"Wed, 27 Sep 2017 10:09:20 +0800","From":"Yuanhan Liu ","To":"Darrell Ball ","Message-ID":"<20170927020920.GG2251@yliu-home>","References":"<1506404199-23579-1-git-send-email-yliu@fridaylinux.org>\n\t<48EB9B23-48D4-4417-B6E9-0D332295BF54@vmware.com>\n\t<20170927012454.GF2251@yliu-home>","MIME-Version":"1.0","Content-Disposition":"inline","In-Reply-To":"<20170927012454.GF2251@yliu-home>","User-Agent":"Mutt/1.5.24 (2015-08-30)","X-Spam-Status":"No, score=0.0 required=5.0 tests=DKIM_SIGNED,DKIM_VALID,\n\tRCVD_IN_DNSWL_NONE autolearn=disabled version=3.3.1","X-Spam-Checker-Version":"SpamAssassin 3.3.1 (2010-03-16) on\n\tsmtp1.linux-foundation.org","Cc":"\"dev@openvswitch.org\" ,\n\tSimon Horman ","Subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","X-BeenThere":"ovs-dev@openvswitch.org","X-Mailman-Version":"2.1.12","Precedence":"list","List-Id":"","List-Unsubscribe":",\n\t","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n\t","Content-Type":"text/plain; charset=\"utf-8\"","Content-Transfer-Encoding":"base64","Sender":"ovs-dev-bounces@openvswitch.org","Errors-To":"ovs-dev-bounces@openvswitch.org"}},{"id":1776001,"web_url":"http://patchwork.ozlabs.org/comment/1776001/","msgid":"","list_archive_url":null,"date":"2017-09-27T03:13:33","subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","submitter":{"id":68212,"url":"http://patchwork.ozlabs.org/api/people/68212/","name":"Darrell Ball","email":"dball@vmware.com"},"content":"On 9/26/17, 6:25 PM, \"Yuanhan Liu\" wrote:\r\n\r\n On Tue, Sep 26, 2017 at 09:58:16PM +0000, Darrell Ball wrote:\r\n > The second major change is there is a thread introduced to do the real\r\n > flow offload. This is for diminishing the overhead by hw flow offload\r\n > installation/deletion at data path. See patch 9 for more detailed info.\r\n > \r\n > [Darrell] There might be other options to handle this such as dividing time\r\n > to HWOL in a given PMD. \r\n > Another option to have PMD isolation.\r\n \r\n Good to know, though I'm not sure I understand it so far. But it can be\r\n discussed later. That's also the reason I put it in the last patch, so\r\n that we could easily turn it to another solution, or even simpler (just\r\n remove it).\r\n \r\n > In the last discussion, RSS action was suggested to use to get rid of\r\n > the QUEUE action workaround. Unfortunately, it didn't work. The flow\r\n > creation failed with MLX5 PMD driver, and that's the only driver in\r\n > DPDK that supports RSS action so far.\r\n > \r\n > \r\n > [Darrell] \r\n > I wonder if we should take a pause before jumping into the next version of the code.\r\n \r\n I have no objections.\r\n \r\n > If workarounds are required in OVS code, then so be it as long as they are not\r\n > overly disruptive to the existing code and hard to maintain.\r\n > In the case of RTE_FLOW_ACTION_TYPE_RSS, we might have a reasonable option\r\n > to avoid some unpleasant OVS workarounds.\r\n > This would make a significant difference in the code paths, if we supported it, so\r\n > we need to be sure as early as possible.\r\n \r\n I agree.\r\n \r\n > The support needed would be in some drivers and seems reasonably doable. \r\n > Moreover, this was discussed in the last dpdk meeting and the support was\r\n > indicated as existing?, although I only verified the MLX code, myself.\r\n \r\n From the code point of view, yes, the code was there months ago.\r\n \r\n > I had seen the MLX code supporting _RSS action and there are some checks for\r\n > supported cases; when you say “it didn't work”, what was the issue ?\r\n \r\n I actually have met the error months ago, I even debugged it. IIRC,\r\n the error is from libibverbs, when trying to create the hw flow. I\r\n think I need double-confirm it with our colleague who developed this\r\n feature.\r\n \r\n > Let us have a discussion also about the Intel nic side and the Napatech side.\r\n \r\n I think it's not necessary for Napatech, because they can support\r\n MARK only action.\r\n \r\nIt is not necessary for Napatech; however to avoid the need to detect the Napatech\r\nspecial (good) case, ‘ideally’ we do the exact same programming even in Napatech case.\r\n\r\n\r\n For Intel, yes, I think Intel folks could give some comments here.\r\n \r\n > It seems reasonable to ask where the disconnect is and whether this support\r\n > can be added and then make a decision based on the answers. \r\n \r\n No objections.\r\n \r\n \t--yliu","headers":{"Return-Path":"","X-Original-To":["incoming@patchwork.ozlabs.org","dev@openvswitch.org"],"Delivered-To":["patchwork-incoming@bilbo.ozlabs.org","ovs-dev@mail.linuxfoundation.org"],"Authentication-Results":["ozlabs.org;\n\tspf=pass (mailfrom) smtp.mailfrom=openvswitch.org\n\t(client-ip=140.211.169.12; helo=mail.linuxfoundation.org;\n\tenvelope-from=ovs-dev-bounces@openvswitch.org;\n\treceiver=)","ozlabs.org;\n\tdkim=fail reason=\"signature verification failed\" (1024-bit key;\n\tunprotected) header.d=onevmw.onmicrosoft.com\n\theader.i=@onevmw.onmicrosoft.com header.b=\"b1NH620t\"; \n\tdkim-atps=neutral","spf=none (sender IP is )\n\tsmtp.mailfrom=dball@vmware.com; "],"Received":["from mail.linuxfoundation.org (mail.linuxfoundation.org\n\t[140.211.169.12])\n\t(using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256\n\tbits)) (No client certificate requested)\n\tby ozlabs.org (Postfix) with ESMTPS id 3y22w86bBBz9t3F\n\tfor ;\n\tWed, 27 Sep 2017 13:13:44 +1000 (AEST)","from mail.linux-foundation.org (localhost [127.0.0.1])\n\tby mail.linuxfoundation.org (Postfix) with ESMTP id 1624CA74;\n\tWed, 27 Sep 2017 03:13:40 +0000 (UTC)","from smtp1.linuxfoundation.org (smtp1.linux-foundation.org\n\t[172.17.192.35])\n\tby mail.linuxfoundation.org (Postfix) with ESMTPS id 8E5AA1BB\n\tfor ; Wed, 27 Sep 2017 03:13:38 +0000 (UTC)","from NAM02-BL2-obe.outbound.protection.outlook.com\n\t(mail-bl2nam02on0068.outbound.protection.outlook.com [104.47.38.68])\n\tby smtp1.linuxfoundation.org (Postfix) with ESMTPS id EFD0E157\n\tfor ; Wed, 27 Sep 2017 03:13:36 +0000 (UTC)","from MWHPR05MB3406.namprd05.prod.outlook.com (10.174.175.155) by\n\tMWHPR05MB3405.namprd05.prod.outlook.com (10.174.175.154) with\n\tMicrosoft SMTP Server (version=TLS1_2,\n\tcipher=TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA384_P256) id\n\t15.20.77.5; Wed, 27 Sep 2017 03:13:34 +0000","from MWHPR05MB3406.namprd05.prod.outlook.com ([10.174.175.155]) by\n\tMWHPR05MB3406.namprd05.prod.outlook.com ([10.174.175.155]) with\n\tmapi id 15.20.0077.007; Wed, 27 Sep 2017 03:13:34 +0000"],"X-Greylist":"whitelisted by SQLgrey-1.7.6","DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=onevmw.onmicrosoft.com; s=selector1-vmware-com;\n\th=From:Date:Subject:Message-ID:Content-Type:MIME-Version;\n\tbh=292AB08l69odRQG0fJ2G43l6aKjvjTDDLTzoqCFDMJg=;\n\tb=b1NH620tafdAKTQ5q+au8QQbqWbYVpljQncgWNWBkFmzpjNLMF8brQO77kc+ifI8UsilXPjiURvSxFpoUV50eYHQEKXVug6wYnKwcqzvAKgPbbBXyBWk6KzooaiVb8cRsg+/BklHpPVOQfyVFjUGM6E+bslOsNPI9S6G6bhyEPk=","From":"Darrell Ball ","To":"Yuanhan Liu ","Thread-Topic":"[PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","Thread-Index":"AQHTNomLA1xYF2/wCU28LyYMHmmNz6LHuAiAgAA5vQCAAB5aAA==","Date":"Wed, 27 Sep 2017 03:13:33 +0000","Message-ID":"","References":"<1506404199-23579-1-git-send-email-yliu@fridaylinux.org>\n\t<48EB9B23-48D4-4417-B6E9-0D332295BF54@vmware.com>\n\t<20170927012454.GF2251@yliu-home>","In-Reply-To":"<20170927012454.GF2251@yliu-home>","Accept-Language":"en-US","Content-Language":"en-US","X-MS-Has-Attach":"","X-MS-TNEF-Correlator":"","user-agent":"Microsoft-MacOutlook/f.26.0.170902","authentication-results":["ozlabs.org;\n\tspf=pass (mailfrom) smtp.mailfrom=openvswitch.org\n\t(client-ip=140.211.169.12; helo=mail.linuxfoundation.org;\n\tenvelope-from=ovs-dev-bounces@openvswitch.org;\n\treceiver=)","ozlabs.org;\n\tdkim=fail reason=\"signature verification failed\" (1024-bit key;\n\tunprotected) header.d=onevmw.onmicrosoft.com\n\theader.i=@onevmw.onmicrosoft.com header.b=\"b1NH620t\"; \n\tdkim-atps=neutral","spf=none (sender IP is )\n\tsmtp.mailfrom=dball@vmware.com; "],"x-originating-ip":"[73.162.236.45]","x-ms-publictraffictype":"Email","x-microsoft-exchange-diagnostics":"1; MWHPR05MB3405;\n\t20:LZurOIyKxH2qwS3UMLtfpTSyBGOoOqHVwBeIypaaDRHYAMJj8BNRdj92eFR7GYvry7V2PyMYziqUX08vUTWzcFrW1no9++uuFXVUh+OX9H9XLaZLs0J04PP9ULWRXYik3yYgwX4tf7aeD+tQm9aEoOEKAk2l4cXG3mmuCnjWGuc=","x-ms-exchange-antispam-srfa-diagnostics":"SSOS;","x-ms-office365-filtering-correlation-id":"d1a1e61a-1c6f-4320-d42b-08d50555bcd9","x-microsoft-antispam":"UriScan:; BCL:0; PCL:0;\n\tRULEID:(22001)(2017030254152)(2017052603199)(201703131423075)(201703031133081)(201702281549075);\n\tSRVR:MWHPR05MB3405; ","x-ms-traffictypediagnostic":"MWHPR05MB3405:","x-exchange-antispam-report-test":"UriScan:;","x-microsoft-antispam-prvs":"","x-exchange-antispam-report-cfa-test":"BCL:0; PCL:0;\n\tRULEID:(100000700101)(100105000095)(100000701101)(100105300095)(100000702101)(100105100095)(6040450)(2401047)(8121501046)(5005006)(10201501046)(100000703101)(100105400095)(93006095)(93001095)(3002001)(6041248)(20161123562025)(20161123560025)(20161123564025)(201703131423075)(201702281528075)(201703061421075)(201703061406153)(20161123555025)(20161123558100)(6072148)(201708071742011)(100000704101)(100105200095)(100000705101)(100105500095);\n\tSRVR:MWHPR05MB3405; BCL:0; PCL:0;\n\tRULEID:(100000800101)(100110000095)(100000801101)(100110300095)(100000802101)(100110100095)(100000803101)(100110400095)(100000804101)(100110200095)(100000805101)(100110500095);\n\tSRVR:MWHPR05MB3405; ","x-forefront-prvs":"04433051BF","x-forefront-antispam-report":"SFV:NSPM;\n\tSFS:(10009020)(6009001)(39860400002)(376002)(346002)(54094003)(189002)(377454003)(199003)(24454002)(83506001)(478600001)(81166006)(3660700001)(97736004)(6486002)(66066001)(105586002)(33656002)(8676002)(54906003)(3846002)(6436002)(76176999)(83716003)(86362001)(2906002)(3280700002)(39060400002)(14454004)(6506006)(68736007)(81156014)(102836003)(6116002)(82746002)(229853002)(2900100001)(36756003)(54356999)(25786009)(4326008)(6246003)(5660300001)(53936002)(101416001)(58126008)(77096006)(53546010)(316002)(2950100002)(99286003)(106356001)(6512007)(305945005)(189998001)(8936002)(7736002)(6916009)(50986999);\n\tDIR:OUT; SFP:1101; SCL:1; SRVR:MWHPR05MB3405;\n\tH:MWHPR05MB3406.namprd05.prod.outlook.com; FPR:; SPF:None;\n\tPTR:InfoNoRecords; MX:1; A:1; LANG:en; ","received-spf":"None (protection.outlook.com: vmware.com does not designate\n\tpermitted sender hosts)","spamdiagnosticoutput":"1:99","spamdiagnosticmetadata":"NSPM","Content-ID":"<5C0D7BB5886501449D7024110BE3A579@namprd05.prod.outlook.com>","MIME-Version":"1.0","X-OriginatorOrg":"vmware.com","X-MS-Exchange-CrossTenant-originalarrivaltime":"27 Sep 2017 03:13:33.9200\n\t(UTC)","X-MS-Exchange-CrossTenant-fromentityheader":"Hosted","X-MS-Exchange-CrossTenant-id":"b39138ca-3cee-4b4a-a4d6-cd83d9dd62f0","X-MS-Exchange-Transport-CrossTenantHeadersStamped":"MWHPR05MB3405","X-Spam-Status":"No, score=0.0 required=5.0 tests=DKIM_SIGNED,DKIM_VALID,\n\tRCVD_IN_DNSWL_NONE autolearn=disabled version=3.3.1","X-Spam-Checker-Version":"SpamAssassin 3.3.1 (2010-03-16) on\n\tsmtp1.linux-foundation.org","Cc":"\"dev@openvswitch.org\" ,\n\tSimon Horman ","Subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","X-BeenThere":"ovs-dev@openvswitch.org","X-Mailman-Version":"2.1.12","Precedence":"list","List-Id":"","List-Unsubscribe":",\n\t","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n\t","Content-Type":"text/plain; charset=\"utf-8\"","Content-Transfer-Encoding":"base64","Sender":"ovs-dev-bounces@openvswitch.org","Errors-To":"ovs-dev-bounces@openvswitch.org"}},{"id":1776010,"web_url":"http://patchwork.ozlabs.org/comment/1776010/","msgid":"<20170927032655.GH2251@yliu-home>","list_archive_url":null,"date":"2017-09-27T03:26:55","subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","submitter":{"id":72215,"url":"http://patchwork.ozlabs.org/api/people/72215/","name":"Yuanhan Liu","email":"yliu@fridaylinux.org"},"content":"On Wed, Sep 27, 2017 at 03:13:33AM +0000, Darrell Ball wrote:\n> \n> \n> On 9/26/17, 6:25 PM, \"Yuanhan Liu\" wrote:\n> \n> On Tue, Sep 26, 2017 at 09:58:16PM +0000, Darrell Ball wrote:\n> > The second major change is there is a thread introduced to do the real\n> > flow offload. This is for diminishing the overhead by hw flow offload\n> > installation/deletion at data path. See patch 9 for more detailed info.\n> > \n> > [Darrell] There might be other options to handle this such as dividing time\n> > to HWOL in a given PMD. \n> > Another option to have PMD isolation.\n> \n> Good to know, though I'm not sure I understand it so far. But it can be\n> discussed later. That's also the reason I put it in the last patch, so\n> that we could easily turn it to another solution, or even simpler (just\n> remove it).\n> \n> > In the last discussion, RSS action was suggested to use to get rid of\n> > the QUEUE action workaround. Unfortunately, it didn't work. The flow\n> > creation failed with MLX5 PMD driver, and that's the only driver in\n> > DPDK that supports RSS action so far.\n> > \n> > \n> > [Darrell] \n> > I wonder if we should take a pause before jumping into the next version of the code.\n> \n> I have no objections.\n> \n> > If workarounds are required in OVS code, then so be it as long as they are not\n> > overly disruptive to the existing code and hard to maintain.\n> > In the case of RTE_FLOW_ACTION_TYPE_RSS, we might have a reasonable option\n> > to avoid some unpleasant OVS workarounds.\n> > This would make a significant difference in the code paths, if we supported it, so\n> > we need to be sure as early as possible.\n> \n> I agree.\n> \n> > The support needed would be in some drivers and seems reasonably doable. \n> > Moreover, this was discussed in the last dpdk meeting and the support was\n> > indicated as existing?, although I only verified the MLX code, myself.\n> \n> From the code point of view, yes, the code was there months ago.\n> \n> > I had seen the MLX code supporting _RSS action and there are some checks for\n> > supported cases; when you say “it didn't work”, what was the issue ?\n> \n> I actually have met the error months ago, I even debugged it. IIRC,\n> the error is from libibverbs, when trying to create the hw flow. I\n> think I need double-confirm it with our colleague who developed this\n> feature.\n> \n> > Let us have a discussion also about the Intel nic side and the Napatech side.\n> \n> I think it's not necessary for Napatech, because they can support\n> MARK only action.\n> \n> It is not necessary for Napatech; however to avoid the need to detect the Napatech\n> special (good) case, ‘ideally’ we do the exact same programming even in Napatech case.\n\nWill following look okay to you (assuming we have the probe ability and DPDK\nhas some basic capability feedback)?\n\n\tif (!pure_mark_cap_probed) {\n\t\tif (dpdk_rte_flow_has_rss_action_support) {\n\t\t\tappend_rss_action();\n\t\t} else {\n\t\t\tfail and return;\n\t\t}\n\t}\n\n\t/* create flow once, with no retries, if fails, let it fail */\n\tflow = rte_flow_create(...);\n\nI assume that's how the code looks like finally. What do you think?\n\n\t--yliu\n\n> For Intel, yes, I think Intel folks could give some comments here.\n> \n> > It seems reasonable to ask where the disconnect is and whether this support\n> > can be added and then make a decision based on the answers. \n> \n> No objections.\n> \n> \t--yliu\n> \n>","headers":{"Return-Path":"","X-Original-To":["incoming@patchwork.ozlabs.org","dev@openvswitch.org"],"Delivered-To":["patchwork-incoming@bilbo.ozlabs.org","ovs-dev@mail.linuxfoundation.org"],"Authentication-Results":["ozlabs.org;\n\tspf=pass (mailfrom) smtp.mailfrom=openvswitch.org\n\t(client-ip=140.211.169.12; helo=mail.linuxfoundation.org;\n\tenvelope-from=ovs-dev-bounces@openvswitch.org;\n\treceiver=)","ozlabs.org;\n\tdkim=fail reason=\"signature verification failed\" (2048-bit key;\n\tunprotected) header.d=fridaylinux-org.20150623.gappssmtp.com\n\theader.i=@fridaylinux-org.20150623.gappssmtp.com\n\theader.b=\"HeVhhfAE\"; dkim-atps=neutral"],"Received":["from mail.linuxfoundation.org (mail.linuxfoundation.org\n\t[140.211.169.12])\n\t(using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256\n\tbits)) (No client certificate requested)\n\tby ozlabs.org (Postfix) with ESMTPS id 3y23DF5RXKz9t4Z\n\tfor ;\n\tWed, 27 Sep 2017 13:27:41 +1000 (AEST)","from mail.linux-foundation.org (localhost [127.0.0.1])\n\tby mail.linuxfoundation.org (Postfix) with ESMTP id E4E79AF3;\n\tWed, 27 Sep 2017 03:27:09 +0000 (UTC)","from smtp1.linuxfoundation.org (smtp1.linux-foundation.org\n\t[172.17.192.35])\n\tby mail.linuxfoundation.org (Postfix) with ESMTPS id 7807BA88\n\tfor ; Wed, 27 Sep 2017 03:27:08 +0000 (UTC)","from mail-pf0-f169.google.com (mail-pf0-f169.google.com\n\t[209.85.192.169])\n\tby smtp1.linuxfoundation.org (Postfix) with ESMTPS id 704AA3DB\n\tfor ; Wed, 27 Sep 2017 03:27:07 +0000 (UTC)","by mail-pf0-f169.google.com with SMTP id m63so6564309pfk.7\n\tfor ; Tue, 26 Sep 2017 20:27:07 -0700 (PDT)","from yliu-home ([45.63.61.64]) by smtp.gmail.com with ESMTPSA id\n\tc30sm17861968pgn.33.2017.09.26.20.27.04\n\t(version=TLS1 cipher=ECDHE-RSA-AES128-SHA bits=128/128);\n\tTue, 26 Sep 2017 20:27:05 -0700 (PDT)"],"X-Greylist":"whitelisted by SQLgrey-1.7.6","DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=fridaylinux-org.20150623.gappssmtp.com; s=20150623;\n\th=date:from:to:cc:subject:message-id:references:mime-version\n\t:content-disposition:content-transfer-encoding:in-reply-to\n\t:user-agent; bh=UhGrSH8K+83MVd8xO3tWfnMGX6NP7BBxsx3Sm4mk4lM=;\n\tb=HeVhhfAEFBTmbKzo2Qkzr2NNQtJAv8M2ZpTTYYPZR1E8w3kENoiHLFjN+f0Xlbanwj\n\tvm+DN4XoRMCTRVk4wtzsvzX69xs4w2qGow9+bgp1830lTXhUUO4aRQAMmNyfAvTjNCET\n\tPf1viYU9frha0qcy1/NjzFFS6jv3m8zWVr4TpVs0315kZKxCcOyPIJoedPWi77dSLHCS\n\tXMStAaSV8sysnHWjONUnTqtIBpDLB8X0KuntcXQw0bpoa0wMH/r2h6VL+JemgUzgR69C\n\tZCA9q9MJKbLbsC+4pcvmw83ik6YAaCaddUrdjq5Nq5qVa/S2lrDMacwGxny0AnvbBg5U\n\thNCA==","X-Google-DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=1e100.net; s=20161025;\n\th=x-gm-message-state:date:from:to:cc:subject:message-id:references\n\t:mime-version:content-disposition:content-transfer-encoding\n\t:in-reply-to:user-agent;\n\tbh=UhGrSH8K+83MVd8xO3tWfnMGX6NP7BBxsx3Sm4mk4lM=;\n\tb=VxMjf7eenWsCWGbgjQm7LR6azX8H15Q8nJaXroqtXvx7W0oSqJrBALHjh5h8saxpHu\n\tncoEnypPJgIzGt0lBpfg9ysYTCkXWSpYY6UH2vTWPeQMOwXHNfJPG5hp08Qkp6B8Uq8k\n\tz7DbVusGaXEgM33WtVZNynr4guQYmf7vcmXz3AljvviWot/duJz9f7pkF2cACXI49PYe\n\tP85oin+k119oFa2Qnc/pdgYxN+ccQ6jZ4YleifbS6+fvnuT6nv5DHvuDK8ttasrYgojm\n\tHt27w6Efm5/yqxFEkQxrSo4n2f1vhVoOcXwoL+LBer4T8dpDJNzjgwVkBYz7LdbC+JH9\n\tkqBw==","X-Gm-Message-State":"AHPjjUh5RZsyWk7skREMIxiGvKTWYGPAr9I3Th/m1XV+qh6uEw3IV22Q\n\t7I0DciBrrwjq5aJEH3t+AN4y8Q==","X-Google-Smtp-Source":"AOwi7QC2+In3CafmfPqVQdGnsuMUfVwkx29VyxlkEl1t/r4yYDpbBg9ojxBVmaSS7QlZbJO9PmqUZQ==","X-Received":"by 10.98.216.202 with SMTP id e193mr23654pfg.344.1506482826977; \n\tTue, 26 Sep 2017 20:27:06 -0700 (PDT)","Date":"Wed, 27 Sep 2017 11:26:55 +0800","From":"Yuanhan Liu ","To":"Darrell Ball ","Message-ID":"<20170927032655.GH2251@yliu-home>","References":"<1506404199-23579-1-git-send-email-yliu@fridaylinux.org>\n\t<48EB9B23-48D4-4417-B6E9-0D332295BF54@vmware.com>\n\t<20170927012454.GF2251@yliu-home>\n\t","MIME-Version":"1.0","Content-Disposition":"inline","In-Reply-To":"","User-Agent":"Mutt/1.5.24 (2015-08-30)","X-Spam-Status":"No, score=0.0 required=5.0 tests=DKIM_SIGNED,DKIM_VALID,\n\tRCVD_IN_DNSWL_NONE autolearn=disabled version=3.3.1","X-Spam-Checker-Version":"SpamAssassin 3.3.1 (2010-03-16) on\n\tsmtp1.linux-foundation.org","Cc":"\"dev@openvswitch.org\" ,\n\tSimon Horman ","Subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","X-BeenThere":"ovs-dev@openvswitch.org","X-Mailman-Version":"2.1.12","Precedence":"list","List-Id":"","List-Unsubscribe":",\n\t","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n\t","Content-Type":"text/plain; charset=\"utf-8\"","Content-Transfer-Encoding":"base64","Sender":"ovs-dev-bounces@openvswitch.org","Errors-To":"ovs-dev-bounces@openvswitch.org"}},{"id":1776019,"web_url":"http://patchwork.ozlabs.org/comment/1776019/","msgid":"<86D9E1E3-DBF7-4CD8-B472-C6CDD156929A@vmware.com>","list_archive_url":null,"date":"2017-09-27T03:54:02","subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","submitter":{"id":68212,"url":"http://patchwork.ozlabs.org/api/people/68212/","name":"Darrell Ball","email":"dball@vmware.com"},"content":"On 9/26/17, 8:27 PM, \"Yuanhan Liu\" wrote:\r\n\r\n On Wed, Sep 27, 2017 at 03:13:33AM +0000, Darrell Ball wrote:\r\n > \r\n > \r\n > On 9/26/17, 6:25 PM, \"Yuanhan Liu\" wrote:\r\n > \r\n > On Tue, Sep 26, 2017 at 09:58:16PM +0000, Darrell Ball wrote:\r\n > > The second major change is there is a thread introduced to do the real\r\n > > flow offload. This is for diminishing the overhead by hw flow offload\r\n > > installation/deletion at data path. See patch 9 for more detailed info.\r\n > > \r\n > > [Darrell] There might be other options to handle this such as dividing time\r\n > > to HWOL in a given PMD. \r\n > > Another option to have PMD isolation.\r\n > \r\n > Good to know, though I'm not sure I understand it so far. But it can be\r\n > discussed later. That's also the reason I put it in the last patch, so\r\n > that we could easily turn it to another solution, or even simpler (just\r\n > remove it).\r\n > \r\n > > In the last discussion, RSS action was suggested to use to get rid of\r\n > > the QUEUE action workaround. Unfortunately, it didn't work. The flow\r\n > > creation failed with MLX5 PMD driver, and that's the only driver in\r\n > > DPDK that supports RSS action so far.\r\n > > \r\n > > \r\n > > [Darrell] \r\n > > I wonder if we should take a pause before jumping into the next version of the code.\r\n > \r\n > I have no objections.\r\n > \r\n > > If workarounds are required in OVS code, then so be it as long as they are not\r\n > > overly disruptive to the existing code and hard to maintain.\r\n > > In the case of RTE_FLOW_ACTION_TYPE_RSS, we might have a reasonable option\r\n > > to avoid some unpleasant OVS workarounds.\r\n > > This would make a significant difference in the code paths, if we supported it, so\r\n > > we need to be sure as early as possible.\r\n > \r\n > I agree.\r\n > \r\n > > The support needed would be in some drivers and seems reasonably doable. \r\n > > Moreover, this was discussed in the last dpdk meeting and the support was\r\n > > indicated as existing?, although I only verified the MLX code, myself.\r\n > \r\n > From the code point of view, yes, the code was there months ago.\r\n > \r\n > > I had seen the MLX code supporting _RSS action and there are some checks for\r\n > > supported cases; when you say “it didn't work”, what was the issue ?\r\n > \r\n > I actually have met the error months ago, I even debugged it. IIRC,\r\n > the error is from libibverbs, when trying to create the hw flow. I\r\n > think I need double-confirm it with our colleague who developed this\r\n > feature.\r\n > \r\n > > Let us have a discussion also about the Intel nic side and the Napatech side.\r\n > \r\n > I think it's not necessary for Napatech, because they can support\r\n > MARK only action.\r\n > \r\n > It is not necessary for Napatech; however to avoid the need to detect the Napatech\r\n > special (good) case, ‘ideally’ we do the exact same programming even in Napatech case.\r\n \r\n Will following look okay to you (assuming we have the probe ability and DPDK\r\n has some basic capability feedback)?\r\n \r\n \tif (!pure_mark_cap_probed) {\r\n \t\tif (dpdk_rte_flow_has_rss_action_support) {\r\n \t\t\tappend_rss_action();\r\n \t\t} else {\r\n \t\t\tfail and return;\r\n \t\t}\r\n \t}\r\n \r\n \t/* create flow once, with no retries, if fails, let it fail */\r\n \tflow = rte_flow_create(...);\r\n \r\n I assume that's how the code looks like finally. What do you think?\r\n\r\n\r\n[Darrell] It looks fine; of course, if we could drop dependencies on cap probe, it would be ideal (. \r\n\r\n \r\n \t--yliu\r\n \r\n > For Intel, yes, I think Intel folks could give some comments here.\r\n > \r\n > > It seems reasonable to ask where the disconnect is and whether this support\r\n > > can be added and then make a decision based on the answers. \r\n > \r\n > No objections.\r\n > \r\n > \t--yliu\r\n > \r\n >","headers":{"Return-Path":"","X-Original-To":["incoming@patchwork.ozlabs.org","dev@openvswitch.org"],"Delivered-To":["patchwork-incoming@bilbo.ozlabs.org","ovs-dev@mail.linuxfoundation.org"],"Authentication-Results":["ozlabs.org;\n\tspf=pass (mailfrom) smtp.mailfrom=openvswitch.org\n\t(client-ip=140.211.169.12; helo=mail.linuxfoundation.org;\n\tenvelope-from=ovs-dev-bounces@openvswitch.org;\n\treceiver=)","ozlabs.org;\n\tdkim=fail reason=\"signature verification failed\" (1024-bit key;\n\tunprotected) header.d=onevmw.onmicrosoft.com\n\theader.i=@onevmw.onmicrosoft.com header.b=\"NNlwXy51\"; \n\tdkim-atps=neutral","spf=none (sender IP is )\n\tsmtp.mailfrom=dball@vmware.com; "],"Received":["from mail.linuxfoundation.org (mail.linuxfoundation.org\n\t[140.211.169.12])\n\t(using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256\n\tbits)) (No client certificate requested)\n\tby ozlabs.org (Postfix) with ESMTPS id 3y23pq4ZMFz9sRg\n\tfor ;\n\tWed, 27 Sep 2017 13:54:11 +1000 (AEST)","from mail.linux-foundation.org (localhost [127.0.0.1])\n\tby mail.linuxfoundation.org (Postfix) with ESMTP id 68A4F955;\n\tWed, 27 Sep 2017 03:54:08 +0000 (UTC)","from smtp1.linuxfoundation.org (smtp1.linux-foundation.org\n\t[172.17.192.35])\n\tby mail.linuxfoundation.org (Postfix) with ESMTPS id 3FA8E94F\n\tfor ; Wed, 27 Sep 2017 03:54:07 +0000 (UTC)","from NAM01-BN3-obe.outbound.protection.outlook.com\n\t(mail-bn3nam01on0045.outbound.protection.outlook.com [104.47.33.45])\n\tby smtp1.linuxfoundation.org (Postfix) with ESMTPS id E35643DB\n\tfor ; Wed, 27 Sep 2017 03:54:05 +0000 (UTC)","from MWHPR05MB3406.namprd05.prod.outlook.com (10.174.175.155) by\n\tMWHPR05MB3407.namprd05.prod.outlook.com (10.174.175.156) with\n\tMicrosoft SMTP Server (version=TLS1_2,\n\tcipher=TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA384_P256) id\n\t15.20.77.5; Wed, 27 Sep 2017 03:54:02 +0000","from MWHPR05MB3406.namprd05.prod.outlook.com ([10.174.175.155]) by\n\tMWHPR05MB3406.namprd05.prod.outlook.com ([10.174.175.155]) with\n\tmapi id 15.20.0077.007; Wed, 27 Sep 2017 03:54:02 +0000"],"X-Greylist":"whitelisted by SQLgrey-1.7.6","DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=onevmw.onmicrosoft.com; s=selector1-vmware-com;\n\th=From:Date:Subject:Message-ID:Content-Type:MIME-Version;\n\tbh=GvjUVar8gb4BQd2IU5VV/05KC3tHGuFcGmRXRKZZhFo=;\n\tb=NNlwXy51Rs5YNYag63Gu4PPWd6Gu/DrR6YtBoYSIX/m/nUIT7k01bw8/Kyvne4zF9ho9+sfq/712k4rZgqWzZyNgCV1W2xdo6E/wOrxujWtKl8+co+AoZZjBk3x/qgOveQH08uAAD+uO5l0ktesmA8b0iQFKPOJr+Ax5RI3c/zI=","From":"Darrell Ball ","To":"Yuanhan Liu ","Thread-Topic":"[PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","Thread-Index":"AQHTNomLA1xYF2/wCU28LyYMHmmNz6LHuAiAgAA5vQCAAB5aAIAAA72AgAAHkoA=","Date":"Wed, 27 Sep 2017 03:54:02 +0000","Message-ID":"<86D9E1E3-DBF7-4CD8-B472-C6CDD156929A@vmware.com>","References":"<1506404199-23579-1-git-send-email-yliu@fridaylinux.org>\n\t<48EB9B23-48D4-4417-B6E9-0D332295BF54@vmware.com>\n\t<20170927012454.GF2251@yliu-home>\n\t\n\t<20170927032655.GH2251@yliu-home>","In-Reply-To":"<20170927032655.GH2251@yliu-home>","Accept-Language":"en-US","Content-Language":"en-US","X-MS-Has-Attach":"","X-MS-TNEF-Correlator":"","user-agent":"Microsoft-MacOutlook/f.26.0.170902","authentication-results":["ozlabs.org;\n\tspf=pass (mailfrom) smtp.mailfrom=openvswitch.org\n\t(client-ip=140.211.169.12; helo=mail.linuxfoundation.org;\n\tenvelope-from=ovs-dev-bounces@openvswitch.org;\n\treceiver=)","ozlabs.org;\n\tdkim=fail reason=\"signature verification failed\" (1024-bit key;\n\tunprotected) header.d=onevmw.onmicrosoft.com\n\theader.i=@onevmw.onmicrosoft.com header.b=\"NNlwXy51\"; \n\tdkim-atps=neutral","spf=none (sender IP is )\n\tsmtp.mailfrom=dball@vmware.com; "],"x-originating-ip":"[73.162.236.45]","x-ms-publictraffictype":"Email","x-microsoft-exchange-diagnostics":"1; MWHPR05MB3407;\n\t20:SBVCXEbZLfKYJK9OwImbheyzbimYGfNLV5nu1AfkhTh7BFlwTpIRca+hNqoRI2enIikM1RPB4RW2vdUtXbC4CBJJAXmD6ih5/aILyIWVmAvrpL3OzsVgarA2aIBckWkWOiG9LcFdgWHdJo9FYQlLPDxVhDRkW0BJzkRM8ILUBOw=","x-ms-exchange-antispam-srfa-diagnostics":"SSOS;","x-ms-office365-filtering-correlation-id":"417beeb2-7d24-4a4b-48c4-08d5055b6479","x-microsoft-antispam":"UriScan:; BCL:0; PCL:0;\n\tRULEID:(22001)(2017030254152)(2017052603199)(201703131423075)(201703031133081)(201702281549075);\n\tSRVR:MWHPR05MB3407; ","x-ms-traffictypediagnostic":"MWHPR05MB3407:","x-exchange-antispam-report-test":"UriScan:;","x-microsoft-antispam-prvs":"","x-exchange-antispam-report-cfa-test":"BCL:0; PCL:0;\n\tRULEID:(100000700101)(100105000095)(100000701101)(100105300095)(100000702101)(100105100095)(6040450)(2401047)(5005006)(8121501046)(3002001)(10201501046)(93006095)(93001095)(100000703101)(100105400095)(6041248)(20161123558100)(20161123564025)(20161123555025)(201703131423075)(201702281528075)(201703061421075)(201703061406153)(20161123560025)(20161123562025)(6072148)(201708071742011)(100000704101)(100105200095)(100000705101)(100105500095);\n\tSRVR:MWHPR05MB3407; BCL:0; PCL:0;\n\tRULEID:(100000800101)(100110000095)(100000801101)(100110300095)(100000802101)(100110100095)(100000803101)(100110400095)(100000804101)(100110200095)(100000805101)(100110500095);\n\tSRVR:MWHPR05MB3407; ","x-forefront-prvs":"04433051BF","x-forefront-antispam-report":"SFV:NSPM;\n\tSFS:(10009020)(6009001)(39860400002)(376002)(346002)(24454002)(377454003)(199003)(76104003)(54094003)(189002)(6436002)(54356999)(76176999)(50986999)(33656002)(101416001)(2900100001)(5660300001)(81166006)(68736007)(39060400002)(3280700002)(6512007)(58126008)(53936002)(54906003)(99286003)(316002)(4326008)(81156014)(7736002)(305945005)(8676002)(6246003)(3660700001)(8936002)(2906002)(93886005)(14454004)(2950100002)(53546010)(6116002)(25786009)(3846002)(102836003)(478600001)(229853002)(97736004)(106356001)(189998001)(6916009)(105586002)(82746002)(6486002)(36756003)(83506001)(77096006)(86362001)(83716003)(66066001)(6506006);\n\tDIR:OUT; SFP:1101; SCL:1; SRVR:MWHPR05MB3407;\n\tH:MWHPR05MB3406.namprd05.prod.outlook.com; FPR:; SPF:None;\n\tPTR:InfoNoRecords; A:1; MX:1; LANG:en; ","received-spf":"None (protection.outlook.com: vmware.com does not designate\n\tpermitted sender hosts)","spamdiagnosticoutput":"1:99","spamdiagnosticmetadata":"NSPM","Content-ID":"<38FB0085750152468AB5FD15D67D2DB7@namprd05.prod.outlook.com>","MIME-Version":"1.0","X-OriginatorOrg":"vmware.com","X-MS-Exchange-CrossTenant-originalarrivaltime":"27 Sep 2017 03:54:02.6751\n\t(UTC)","X-MS-Exchange-CrossTenant-fromentityheader":"Hosted","X-MS-Exchange-CrossTenant-id":"b39138ca-3cee-4b4a-a4d6-cd83d9dd62f0","X-MS-Exchange-Transport-CrossTenantHeadersStamped":"MWHPR05MB3407","X-Spam-Status":"No, score=0.0 required=5.0 tests=DKIM_SIGNED,DKIM_VALID,\n\tRCVD_IN_DNSWL_NONE autolearn=disabled version=3.3.1","X-Spam-Checker-Version":"SpamAssassin 3.3.1 (2010-03-16) on\n\tsmtp1.linux-foundation.org","Cc":"\"dev@openvswitch.org\" ,\n\tSimon Horman ","Subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","X-BeenThere":"ovs-dev@openvswitch.org","X-Mailman-Version":"2.1.12","Precedence":"list","List-Id":"","List-Unsubscribe":",\n\t","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n\t","Content-Type":"text/plain; charset=\"utf-8\"","Content-Transfer-Encoding":"base64","Sender":"ovs-dev-bounces@openvswitch.org","Errors-To":"ovs-dev-bounces@openvswitch.org"}},{"id":1776169,"web_url":"http://patchwork.ozlabs.org/comment/1776169/","msgid":"<10fc4027ed424f919cd0175ab1624439@napatech.com>","list_archive_url":null,"date":"2017-09-27T09:12:49","subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","submitter":{"id":72305,"url":"http://patchwork.ozlabs.org/api/people/72305/","name":"Finn Christensen","email":"fc@napatech.com"},"content":"-----Original Message-----\r\n From: Darrell Ball [mailto:dball@vmware.com]\r\n Sent: 27. september 2017 05:54\r\n To: Yuanhan Liu \r\n Cc: dev@openvswitch.org; Finn Christensen ;\r\n Chandran Sugesh ; Simon Horman\r\n \r\n Subject: Re: [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow\r\n \r\n \r\n \r\n On 9/26/17, 8:27 PM, \"Yuanhan Liu\" wrote:\r\n \r\n On Wed, Sep 27, 2017 at 03:13:33AM +0000, Darrell Ball wrote:\r\n >\r\n >\r\n > On 9/26/17, 6:25 PM, \"Yuanhan Liu\" wrote:\r\n >\r\n > On Tue, Sep 26, 2017 at 09:58:16PM +0000, Darrell Ball wrote:\r\n > > The second major change is there is a thread introduced to do\r\n the real\r\n > > flow offload. This is for diminishing the overhead by hw flow\r\n offload\r\n > > installation/deletion at data path. See patch 9 for more detailed\r\n info.\r\n > >\r\n > > [Darrell] There might be other options to handle this such as\r\n dividing time\r\n > > to HWOL in a given PMD.\r\n > > Another option to have PMD isolation.\r\n >\r\n > Good to know, though I'm not sure I understand it so far. But it can\r\n be\r\n > discussed later. That's also the reason I put it in the last patch, so\r\n > that we could easily turn it to another solution, or even simpler (just\r\n > remove it).\r\n >\r\n > > In the last discussion, RSS action was suggested to use to get rid\r\n of\r\n > > the QUEUE action workaround. Unfortunately, it didn't work. The\r\n flow\r\n > > creation failed with MLX5 PMD driver, and that's the only driver in\r\n > > DPDK that supports RSS action so far.\r\n > >\r\n > >\r\n > > [Darrell]\r\n > > I wonder if we should take a pause before jumping into the next\r\n version of the code.\r\n >\r\n > I have no objections.\r\n >\r\n > > If workarounds are required in OVS code, then so be it as long as\r\n they are not\r\n > > overly disruptive to the existing code and hard to maintain.\r\n > > In the case of RTE_FLOW_ACTION_TYPE_RSS, we might have a\r\n reasonable option\r\n > > to avoid some unpleasant OVS workarounds.\r\n > > This would make a significant difference in the code paths, if we\r\n supported it, so\r\n > > we need to be sure as early as possible.\r\n >\r\n > I agree.\r\n >\r\n > > The support needed would be in some drivers and seems\r\n reasonably doable.\r\n > > Moreover, this was discussed in the last dpdk meeting and the\r\n support was\r\n > > indicated as existing?, although I only verified the MLX code,\r\n myself.\r\n >\r\n > From the code point of view, yes, the code was there months ago.\r\n >\r\n > > I had seen the MLX code supporting _RSS action and there are\r\n some checks for\r\n > > supported cases; when you say “it didn't work”, what was the issue\r\n ?\r\n >\r\n > I actually have met the error months ago, I even debugged it. IIRC,\r\n > the error is from libibverbs, when trying to create the hw flow. I\r\n > think I need double-confirm it with our colleague who developed this\r\n > feature.\r\n >\r\n > > Let us have a discussion also about the Intel nic side and the\r\n Napatech side.\r\n >\r\n > I think it's not necessary for Napatech, because they can support\r\n > MARK only action.\r\n >\r\n > It is not necessary for Napatech; however to avoid the need to detect\r\n the Napatech\r\n > special (good) case, ‘ideally’ we do the exact same programming even\r\n in Napatech case.\r\n \r\n Will following look okay to you (assuming we have the probe ability and\r\n DPDK\r\n has some basic capability feedback)?\r\n \r\n \tif (!pure_mark_cap_probed) {\r\n \t\tif (dpdk_rte_flow_has_rss_action_support) {\r\n \t\t\tappend_rss_action();\r\n \t\t} else {\r\n \t\t\tfail and return;\r\n \t\t}\r\n \t}\r\n \r\n \t/* create flow once, with no retries, if fails, let it fail */\r\n \tflow = rte_flow_create(...);\r\n \r\n I assume that's how the code looks like finally. What do you think?\r\n \r\n \r\n [Darrell] It looks fine; of course, if we could drop dependencies on cap\r\n probe, it would be ideal (.\r\n \r\n\r\n[Finn]\r\nFrom a Napatech point of view, we would definitely want to use the \r\nRTE_FLOW_ACTION_TYPE_RSS if it were implement. It definitely makes good\r\nsense to me. I have 2 reasons for this: \r\n1. It would fit nicely into the way Napatech does flow programming in nic\r\n2. We would be fully RSS controlled through OVS\r\nFurthermore, Future RSS splitting on a per megaflow basis will be possible.\r\nIMO the \"pure_mark_cap_probed\" function is a temp work-around to make it work. \r\nThe RSS seems to be a solution to the queue problem.\r\n\r\n\r\n \r\n \t--yliu\r\n \r\n > For Intel, yes, I think Intel folks could give some comments here.\r\n >\r\n > > It seems reasonable to ask where the disconnect is and whether\r\n this support\r\n > > can be added and then make a decision based on the answers.\r\n >\r\n > No objections.\r\n >\r\n > \t--yliu\r\n >\r\n >","headers":{"Return-Path":"","X-Original-To":["incoming@patchwork.ozlabs.org","dev@openvswitch.org"],"Delivered-To":["patchwork-incoming@bilbo.ozlabs.org","ovs-dev@mail.linuxfoundation.org"],"Authentication-Results":["ozlabs.org;\n\tspf=pass (mailfrom) smtp.mailfrom=openvswitch.org\n\t(client-ip=140.211.169.12; helo=mail.linuxfoundation.org;\n\tenvelope-from=ovs-dev-bounces@openvswitch.org;\n\treceiver=)","ozlabs.org;\n\tdkim=fail reason=\"signature verification failed\" (2048-bit key;\n\tunprotected) header.d=napatech.com header.i=@napatech.com\n\theader.b=\"BTspw0QT\"; dkim-atps=neutral"],"Received":["from mail.linuxfoundation.org (mail.linuxfoundation.org\n\t[140.211.169.12])\n\t(using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256\n\tbits)) (No client certificate requested)\n\tby ozlabs.org (Postfix) with ESMTPS id 3y2Btk3QKFz9tXn\n\tfor ;\n\tWed, 27 Sep 2017 19:13:02 +1000 (AEST)","from mail.linux-foundation.org (localhost [127.0.0.1])\n\tby mail.linuxfoundation.org (Postfix) with ESMTP id 0C537412;\n\tWed, 27 Sep 2017 09:12:59 +0000 (UTC)","from smtp1.linuxfoundation.org (smtp1.linux-foundation.org\n\t[172.17.192.35])\n\tby mail.linuxfoundation.org (Postfix) with ESMTPS id 3A80B97\n\tfor ; Wed, 27 Sep 2017 09:12:58 +0000 (UTC)","from mail01.napatech.com (mail01.napatech.com [188.120.77.121])\n\tby smtp1.linuxfoundation.org (Postfix) with ESMTPS id 5B5863F2\n\tfor ; Wed, 27 Sep 2017 09:12:56 +0000 (UTC)","from cph-gen-exch02.napatech.com (10.240.1.84) by\n\tcph-gen-exch02.napatech.com (10.240.1.84) with Microsoft SMTP Server\n\t(version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA256_P256) id\n\t15.1.1034.26; Wed, 27 Sep 2017 11:12:49 +0200","from cph-gen-exch02.napatech.com ([fe80::581:51a1:ac3f:84e]) by\n\tcph-gen-exch02.napatech.com ([fe80::581:51a1:ac3f:84e%12]) with mapi\n\tid 15.01.1034.026; Wed, 27 Sep 2017 11:12:49 +0200"],"X-Greylist":"domain auto-whitelisted by SQLgrey-1.7.6","DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=napatech.com; i=@napatech.com; q=dns/txt; s=mar2017;\n\tt=1506503576; x=1538039576;\n\th=from:to:cc:subject:date:message-id:references:\n\tin-reply-to:content-transfer-encoding:mime-version;\n\tbh=ZrqSYUlcz2wOxBfQXMtWZKoxX/ZCy06d0VVAOZicaW8=;\n\tb=BTspw0QTsncOZHNni9mdRl+6ot2hLYy2Leml8wtOm5E6CJnFKAo+HkAr\n\tCAQMJKQ4TZkEP4nB7dLpu/1+1hvImfPm/ktte5lQwmrg9mXSVJ6T3ikZf\n\t3almW9dgeSsx7GI+9iaqgKXyP5zB5cmyLW/cqAdvIS5AHyK2D0qDVvMwr\n\t999MbpEVm/5Yh3UNNoZqWG6wmQaVB05AHL6wok5B55fqb61dHnNAs/ddx\n\tWEMA4GaBE2H58SUUgawb2nFKXq/frMZmI5ESs4od+RCHr1ysWD5aqPCjG\n\t/1Ymzt+CkphRdKlac0iJE6HAfYt9I7EkYSWf9BSmvoL8qaBEOI8XAfm+m A==;","IronPort-PHdr":"9a23:hI8qgBwb0uOqUQXXCy+O+j09IxM/srCxBDY+r6Qd2+wWIJqq85mqBkHD//Il1AaPBtSKra0YwLOL+4nbGkU4qa6bt34DdJEeHzQksu4x2zIaPcieFEfgJ+TrZSFpVO5LVVti4m3peRMNQJW2aFLduGC94iAPERvjKwV1Ov71GonPhMiryuy+4ZPebgFMiTanY75/Ixq6oRjRu8ILnYZsN6E9xwfTrHBVYepW32RoJVySnxb4+Mi9+YNo/jpTtfw86cNOSL32cKskQ7NWCjQmKH0169bwtRbfVwuP52ATXXsQnxFVHgXK9hD6XpP2sivnqupw3TSRMMPqQbwoXzmp8rxmQwH0higZKzE58XnXis1ug6JdvBKhvAF0z4rNbI2IKPZyYqbRcNUHTmRDQ8lRTTRMDIOiYYUSE+oPM+VWr4f/qFsPsRSwCgajCfjzyjBThH/6wbE23/gjHAzAwQcuH8gOsHPRrNjtNKkSUOa1zK/Vxjjdb/NWwzb96JPUch8/p/GMRqx/cczMwkQoGQPKkk6dqYr/MDONzOsNr3aU4PZgVe61l2EnrARxryGpy8wxiYfJnpoYxk3Y+Slj3oo4KsG0RFRmbdK+E5ZduDmWO5ZqTs84XW1ltzo2xqcbtZKnZiQG1poqyhrHZ/yJbYeF4Q7vWeOULDp4h39pZbeyihav/Ue61+HxU9O730pEoypLl9TBtX8A2ALV58OaUPVy5F2h1iyK1w3L7+FEJl07mrTDJp46x74wioITsUPeHi/qgEn2jLGZdkEj+uWw7uToeLTmppuGO49ykA7+Kr4hmtChDuskMggCRXSU+eO51LH7/E35RqtFjuEun6XErJzWP9oXq6GlDwNPz4ov8RWyAji+3NQdh3YHLVZFeBydj4juPlHDOP74AuukjlSqijhr3+rJPqH/DZrRLnjPiqvufbF460JE0go80chf545ICrEGOP/8R1H+tMLDAx8+Kwy73eDnCMtm1oIQWGKPHrOWMKPIvV+P/OIvLLrEWIhAlD/nMfUh47bEhHs90QsRd6Ct2bMJbW+xBPkgKEKcNz6ks8oIF2cDuEIaTfGi3EyGUCN7aWyzU6st4jA9FZLgCp3MENODmruEiQm6GJseTWBcC0uQHHHzeoPMD/kHQCSbOsZ9nzcEE7OmTtlyhlmVqAbmxu8/faLv8SoCuMemjYAt6g==","X-IronPort-Anti-Spam-Filtered":"true","X-IronPort-Anti-Spam-Result":"A2FuAAAaa8tZ/1QB8ApbGQEBAQEBAQEBAQEBBwEBAQEBFAEBAQEBAQEBAQEBBwEBAQEBhSoHg2+KH5FyliuCEgqFOwIahHwYAQEBAQEBAQEBAQECgRCCMyQBgkABAQEBAgEjEUUMBAIBCA4DBAEBAQICIwMCAgIwFAEICAIEAQ0FCBOKDqgrgieLAgEBAQEBAQEBAQEBAQEBAQEBAQEBHoEOgh2DU4FqgyiETYNKgmAFiguJGI19lFSTDkiUUgICAgIJAhqBOR+BR3gVhWMcgWd2hWmBMoEQAQEB","X-IPAS-Result":"A2FuAAAaa8tZ/1QB8ApbGQEBAQEBAQEBAQEBBwEBAQEBFAEBAQEBAQEBAQEBBwEBAQEBhSoHg2+KH5FyliuCEgqFOwIahHwYAQEBAQEBAQEBAQECgRCCMyQBgkABAQEBAgEjEUUMBAIBCA4DBAEBAQICIwMCAgIwFAEICAIEAQ0FCBOKDqgrgieLAgEBAQEBAQEBAQEBAQEBAQEBAQEBHoEOgh2DU4FqgyiETYNKgmAFiguJGI19lFSTDkiUUgICAgIJAhqBOR+BR3gVhWMcgWd2hWmBMoEQAQEB","From":"Finn Christensen ","To":"Darrell Ball , Yuanhan Liu ","Thread-Topic":"[PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","Thread-Index":"AQHTNomWAirl91DsckS9/4ffz8FOzqLHloIAgAA5uwCAAB5cgIAAA7yAgAAHkwCAAHK5MA==","Date":"Wed, 27 Sep 2017 09:12:49 +0000","Message-ID":"<10fc4027ed424f919cd0175ab1624439@napatech.com>","References":"<1506404199-23579-1-git-send-email-yliu@fridaylinux.org>\n\t<48EB9B23-48D4-4417-B6E9-0D332295BF54@vmware.com>\n\t<20170927012454.GF2251@yliu-home>\n\t\n\t<20170927032655.GH2251@yliu-home>\n\t<86D9E1E3-DBF7-4CD8-B472-C6CDD156929A@vmware.com>","In-Reply-To":"<86D9E1E3-DBF7-4CD8-B472-C6CDD156929A@vmware.com>","Accept-Language":"da-DK, en-US","Content-Language":"en-US","X-MS-Has-Attach":"","X-MS-TNEF-Correlator":"","x-originating-ip":"[10.240.10.239]","MIME-Version":"1.0","X-Spam-Status":"No, score=-2.4 required=5.0 tests=DKIM_SIGNED,DKIM_VALID,\n\tDKIM_VALID_AU,RCVD_IN_DNSWL_MED,RP_MATCHES_RCVD autolearn=disabled\n\tversion=3.3.1","X-Spam-Checker-Version":"SpamAssassin 3.3.1 (2010-03-16) on\n\tsmtp1.linux-foundation.org","Cc":"\"dev@openvswitch.org\" ,\n\tSimon Horman ","Subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","X-BeenThere":"ovs-dev@openvswitch.org","X-Mailman-Version":"2.1.12","Precedence":"list","List-Id":"","List-Unsubscribe":",\n\t","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n\t","Content-Type":"text/plain; charset=\"utf-8\"","Content-Transfer-Encoding":"base64","Sender":"ovs-dev-bounces@openvswitch.org","Errors-To":"ovs-dev-bounces@openvswitch.org"}},{"id":1776193,"web_url":"http://patchwork.ozlabs.org/comment/1776193/","msgid":"<20170927094712.GK2251@yliu-home>","list_archive_url":null,"date":"2017-09-27T09:47:12","subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","submitter":{"id":72215,"url":"http://patchwork.ozlabs.org/api/people/72215/","name":"Yuanhan Liu","email":"yliu@fridaylinux.org"},"content":"On Wed, Sep 27, 2017 at 09:12:49AM +0000, Finn Christensen wrote:\n> \n> [Darrell] It looks fine; of course, if we could drop dependencies on cap\n> probe, it would be ideal (.\n> \n> \n> [Finn]\n> From a Napatech point of view, we would definitely want to use the\n> RTE_FLOW_ACTION_TYPE_RSS if it were implement. It definitely makes good\n> sense to me. I have 2 reasons for this:\n> 1. It would fit nicely into the way Napatech does flow programming in nic\n> 2. We would be fully RSS controlled through OVS\n> Furthermore, Future RSS splitting on a per megaflow basis will be possible.\n> IMO the \"pure_mark_cap_probed\" function is a temp work-around to make it work.\n> The RSS seems to be a solution to the queue problem.\n\nFinn, that's really good to know! I do agree without this probe, it\nmakes the code simpler and cleaner.\n\nFew questions though. Have Napatech already implemented rss action? If not,\nwhat's the plan? And are you okay with following code?\n\n\tadd_mark_action();\n\tadd_rss_action_unconditionally();\n\n\tflow = rte_create_flow(...);\n\tif (!flow)\n\t\treturn -1;\n\nThat is, no probes, no feedbacks. If it failed, it just failed (flow\noffload then is just skipped).\n\nBut I do think some feedbacks are necessary. If we know the rte_flow\ncap in the begnning, we could simply disable the flow offload for a\nspecific port if we know it doesn't have offload ability. This would\navoid the repeat effort of trying to do hw offload completely.\n\n\t--yliu","headers":{"Return-Path":"","X-Original-To":["incoming@patchwork.ozlabs.org","dev@openvswitch.org"],"Delivered-To":["patchwork-incoming@bilbo.ozlabs.org","ovs-dev@mail.linuxfoundation.org"],"Authentication-Results":["ozlabs.org;\n\tspf=pass (mailfrom) smtp.mailfrom=openvswitch.org\n\t(client-ip=140.211.169.12; helo=mail.linuxfoundation.org;\n\tenvelope-from=ovs-dev-bounces@openvswitch.org;\n\treceiver=)","ozlabs.org;\n\tdkim=fail reason=\"signature verification failed\" (2048-bit key;\n\tunprotected) header.d=fridaylinux-org.20150623.gappssmtp.com\n\theader.i=@fridaylinux-org.20150623.gappssmtp.com\n\theader.b=\"0PSvB/CX\"; dkim-atps=neutral"],"Received":["from mail.linuxfoundation.org (mail.linuxfoundation.org\n\t[140.211.169.12])\n\t(using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256\n\tbits)) (No client certificate requested)\n\tby ozlabs.org (Postfix) with ESMTPS id 3y2CfV6J2Dz9sBd\n\tfor ;\n\tWed, 27 Sep 2017 19:47:29 +1000 (AEST)","from mail.linux-foundation.org (localhost [127.0.0.1])\n\tby mail.linuxfoundation.org (Postfix) with ESMTP id 0EA859AF;\n\tWed, 27 Sep 2017 09:47:23 +0000 (UTC)","from smtp1.linuxfoundation.org (smtp1.linux-foundation.org\n\t[172.17.192.35])\n\tby mail.linuxfoundation.org (Postfix) with ESMTPS id 0A62F95D\n\tfor ; Wed, 27 Sep 2017 09:47:22 +0000 (UTC)","from mail-pg0-f43.google.com (mail-pg0-f43.google.com\n\t[74.125.83.43])\n\tby smtp1.linuxfoundation.org (Postfix) with ESMTPS id 7D0C93FA\n\tfor ; Wed, 27 Sep 2017 09:47:21 +0000 (UTC)","by mail-pg0-f43.google.com with SMTP id i130so7484708pgc.3\n\tfor ; Wed, 27 Sep 2017 02:47:21 -0700 (PDT)","from yliu-home ([45.63.61.64]) by smtp.gmail.com with ESMTPSA id\n\ta29sm21159733pgn.75.2017.09.27.02.47.18\n\t(version=TLS1 cipher=ECDHE-RSA-AES128-SHA bits=128/128);\n\tWed, 27 Sep 2017 02:47:19 -0700 (PDT)"],"X-Greylist":"whitelisted by SQLgrey-1.7.6","DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=fridaylinux-org.20150623.gappssmtp.com; s=20150623;\n\th=date:from:to:cc:subject:message-id:references:mime-version\n\t:content-disposition:in-reply-to:user-agent;\n\tbh=Tjh62GiKmN2coG4iWnC4BjXV8KKslU4LVGK0lpb3UmU=;\n\tb=0PSvB/CXD758ykPq635hD8+ujlPpL17nO98zQnASeusteXwONlXIIoD+Z5VUKpE8bl\n\tDLfhngOfBjRUumttItBj5dVwqp82Z+f+GpfnKHhy+JDQy4v0KyoAGq6jQjXAUbSivX0Q\n\tjyBnbuW/p/2j8eDH9kkLuXC456I3RmVVdgl+/PQzpINEi36nNQltbFZe12BTOARyAj5E\n\t/ayld7x7lZzLvWlAlmlxoWgjBQj5NTLd4fpHLk1K1UweeshP6VHTxXuLBUs2sAK7gxOT\n\tvNDp9fKsPAqHMlbEVE7k1GshLuaa26IRNhtN80HTaHGQqvl26sxCwsYcGA0vsamZN8f+\n\taJAg==","X-Google-DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=1e100.net; s=20161025;\n\th=x-gm-message-state:date:from:to:cc:subject:message-id:references\n\t:mime-version:content-disposition:in-reply-to:user-agent;\n\tbh=Tjh62GiKmN2coG4iWnC4BjXV8KKslU4LVGK0lpb3UmU=;\n\tb=UaL8/HXgUdtHZ9cStO0hc8OsR58og7emMjSlYxYrPjdOto7bezRQvz+AXTWMZWNxyK\n\tRMc7+fkCB28ARhAcc2DlcjMHnQuWSZRl8EzLY6rfLT9jV25cEfDvqyDknUaeXwfu3M8/\n\tb2QVnBl1J5Ve2TS+Z55N4CTdyDbaF63HKbd5HDa9+yCEUugALeydPPGGcwVDt7z7Bf8q\n\tyVx95GPpQcg1Y9WgrmYPVmzCaZYvxVYtdw4WUV7AzZVoSqpkb8RDs8TyjOCMRYK6L3lx\n\tPnAR0kpbXx7HIZ5pOfuG6s7JQY8emfY2Mh5+5lvRVqsguDux5Phb0vS/WYZlzWKmArVd\n\t2bFQ==","X-Gm-Message-State":"AHPjjUh9SVBIXwbmV6f3NPtz7miirrEniJjdRA1hC+6BcuDv3D6C3Z67\n\tsNxljUBbVxEMV1SBri8FsdIS7g==","X-Google-Smtp-Source":"AOwi7QAxkolpPjnAON4701XMzhMtk+0LiwVKz2RmpkhWtRdGDcsTthpdnR7x4pMwSZ0ikWsyOjDyCA==","X-Received":"by 10.84.225.130 with SMTP id u2mr794255plj.44.1506505641079;\n\tWed, 27 Sep 2017 02:47:21 -0700 (PDT)","Date":"Wed, 27 Sep 2017 17:47:12 +0800","From":"Yuanhan Liu ","To":"Finn Christensen ","Message-ID":"<20170927094712.GK2251@yliu-home>","References":"<1506404199-23579-1-git-send-email-yliu@fridaylinux.org>\n\t<48EB9B23-48D4-4417-B6E9-0D332295BF54@vmware.com>\n\t<20170927012454.GF2251@yliu-home>\n\t\n\t<20170927032655.GH2251@yliu-home>\n\t<86D9E1E3-DBF7-4CD8-B472-C6CDD156929A@vmware.com>\n\t<10fc4027ed424f919cd0175ab1624439@napatech.com>","MIME-Version":"1.0","Content-Disposition":"inline","In-Reply-To":"<10fc4027ed424f919cd0175ab1624439@napatech.com>","User-Agent":"Mutt/1.5.24 (2015-08-30)","X-Spam-Status":"No, score=0.0 required=5.0 tests=DKIM_SIGNED,DKIM_VALID,\n\tRCVD_IN_DNSWL_NONE autolearn=disabled version=3.3.1","X-Spam-Checker-Version":"SpamAssassin 3.3.1 (2010-03-16) on\n\tsmtp1.linux-foundation.org","Cc":"\"dev@openvswitch.org\" ,\n\tSimon Horman ","Subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","X-BeenThere":"ovs-dev@openvswitch.org","X-Mailman-Version":"2.1.12","Precedence":"list","List-Id":"","List-Unsubscribe":",\n\t","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n\t","Content-Type":"text/plain; charset=\"us-ascii\"","Content-Transfer-Encoding":"7bit","Sender":"ovs-dev-bounces@openvswitch.org","Errors-To":"ovs-dev-bounces@openvswitch.org"}},{"id":1776237,"web_url":"http://patchwork.ozlabs.org/comment/1776237/","msgid":"","list_archive_url":null,"date":"2017-09-27T10:41:32","subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","submitter":{"id":72305,"url":"http://patchwork.ozlabs.org/api/people/72305/","name":"Finn Christensen","email":"fc@napatech.com"},"content":"-----Original Message-----\n From: Yuanhan Liu [mailto:yliu@fridaylinux.org]\n Sent: 27. september 2017 11:47\n To: Finn Christensen \n Cc: Darrell Ball ; dev@openvswitch.org; Chandran\n Sugesh ; Simon Horman\n \n Subject: Re: [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow\n \n On Wed, Sep 27, 2017 at 09:12:49AM +0000, Finn Christensen wrote:\n >\n > [Darrell] It looks fine; of course, if we could drop dependencies on cap\n > probe, it would be ideal (.\n >\n >\n > [Finn]\n > From a Napatech point of view, we would definitely want to use the\n > RTE_FLOW_ACTION_TYPE_RSS if it were implement. It definitely makes\n > good sense to me. I have 2 reasons for this:\n > 1. It would fit nicely into the way Napatech does flow programming in\n > nic 2. We would be fully RSS controlled through OVS Furthermore,\n > Future RSS splitting on a per megaflow basis will be possible.\n > IMO the \"pure_mark_cap_probed\" function is a temp work-around to\n make it work.\n > The RSS seems to be a solution to the queue problem.\n \n Finn, that's really good to know! I do agree without this probe, it makes the\n code simpler and cleaner.\n \n Few questions though. Have Napatech already implemented rss action? If\n not, what's the plan? \n\n[Finn]\nOur nic handles rss on a per flow basis, but we have not yet used rte rss action \nfor OVS. In OVS we simply handles RSS config outside it.\nThe full control of rss through OVS is better though.\n\n And are you okay with following code?\n \n \tadd_mark_action();\n \tadd_rss_action_unconditionally();\n \n \tflow = rte_create_flow(...);\n \tif (!flow)\n \t\treturn -1;\n \n That is, no probes, no feedbacks. If it failed, it just failed (flow offload then\n is just skipped).\n \n[Finn]\nYes, we can easily make this work. Good suggestion!\n\n\n But I do think some feedbacks are necessary. If we know the rte_flow cap\n in the begnning, we could simply disable the flow offload for a specific port\n if we know it doesn't have offload ability. This would avoid the repeat\n effort of trying to do hw offload completely.\n \n[Finn]\nThis seems to be a good idea.\n\n\n \t--yliu","headers":{"Return-Path":"","X-Original-To":["incoming@patchwork.ozlabs.org","dev@openvswitch.org"],"Delivered-To":["patchwork-incoming@bilbo.ozlabs.org","ovs-dev@mail.linuxfoundation.org"],"Authentication-Results":["ozlabs.org;\n\tspf=pass (mailfrom) smtp.mailfrom=openvswitch.org\n\t(client-ip=140.211.169.12; helo=mail.linuxfoundation.org;\n\tenvelope-from=ovs-dev-bounces@openvswitch.org;\n\treceiver=)","ozlabs.org;\n\tdkim=fail reason=\"signature verification failed\" (2048-bit key;\n\tunprotected) header.d=napatech.com header.i=@napatech.com\n\theader.b=\"miW5OrrP\"; dkim-atps=neutral"],"Received":["from mail.linuxfoundation.org (mail.linuxfoundation.org\n\t[140.211.169.12])\n\t(using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256\n\tbits)) (No client certificate requested)\n\tby ozlabs.org (Postfix) with ESMTPS id 3y2Ds26kV1z9tXf\n\tfor ;\n\tWed, 27 Sep 2017 20:41:42 +1000 (AEST)","from mail.linux-foundation.org (localhost [127.0.0.1])\n\tby mail.linuxfoundation.org (Postfix) with ESMTP id DFB9F949;\n\tWed, 27 Sep 2017 10:41:38 +0000 (UTC)","from smtp1.linuxfoundation.org (smtp1.linux-foundation.org\n\t[172.17.192.35])\n\tby mail.linuxfoundation.org (Postfix) with ESMTPS id 774296C\n\tfor ; Wed, 27 Sep 2017 10:41:37 +0000 (UTC)","from mail02.napatech.com (mail02.napatech.com [188.120.77.119])\n\tby smtp1.linuxfoundation.org (Postfix) with ESMTPS id 8ACE3204\n\tfor ; Wed, 27 Sep 2017 10:41:35 +0000 (UTC)","from cph-gen-exch02.napatech.com (10.240.1.84) by\n\tcph-gen-exch02.napatech.com (10.240.1.84) with Microsoft SMTP Server\n\t(version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA256_P256) id\n\t15.1.1034.26; Wed, 27 Sep 2017 12:41:32 +0200","from cph-gen-exch02.napatech.com ([fe80::581:51a1:ac3f:84e]) by\n\tcph-gen-exch02.napatech.com ([fe80::581:51a1:ac3f:84e%12]) with mapi\n\tid 15.01.1034.026; Wed, 27 Sep 2017 12:41:32 +0200"],"X-Greylist":"domain auto-whitelisted by SQLgrey-1.7.6","DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=napatech.com; i=@napatech.com; q=dns/txt; s=mar2017;\n\tt=1506508895; x=1538044895;\n\th=from:to:cc:subject:date:message-id:references:\n\tin-reply-to:content-transfer-encoding:mime-version;\n\tbh=2L3hlzkENLHllqVuRrB+ANmf5yI/IjYS3YmPfIuespY=;\n\tb=miW5OrrPmvkVAe0Idr7Zeu0Aqz2rqtOcvUvQEcB3mT4Bia+Maq2LKgF3\n\tA+80g7vWl9e89j4ZnapUZ0DGSdX9YYpaKYlH/mVeTqA4n0fMrMBN9zfgu\n\tW8Er0vTx/dKhRhMsx77tXAfr/bTRFAPSfFg+uHEpN7xqGDMZrsR2w4Wtd\n\tZHSsX2ghHJt6+9vBgobEMIjvEkwBFivCvidPFvqRysNzuHJ5Fv//qZuW/\n\t4/W6gpqHnApD0rlbzuGXSGomO1STH1aEXK//e1D9rosOD8KuJqzGUX5wr\n\t3AAKE7xukgA6ZpAlT2orB7y6llaJbbN92YYsj2YY0KjLymNgWUy7iAU8Q g==;","IronPort-PHdr":"9a23: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","X-IronPort-Anti-Spam-Filtered":"true","X-IronPort-Anti-Spam-Result":"A2FuAAAef8tZ/1QB8ApcGQEBAQEBAQEBAQEBBwEBAQEBFAEBAQEBAQEBAQEBBwEBAQEBhSoHjg6RbJYrghIKhTsChRcYAQEBAQEBAQEBAQECgRCCMyQBgkABAQEBAzo/DAQCAQgOAwQBAQEeCQcyFAkIAgQOBQgTtH2LAgEBAQEBAQEDAQEBAQEBASGDK4NTgWqDKIp3BYoLiRiNfZRUkw5IlFICAgICCQIagTkfgUd4FYdmdocbgRABAQE","X-IPAS-Result":"A2FuAAAef8tZ/1QB8ApcGQEBAQEBAQEBAQEBBwEBAQEBFAEBAQEBAQEBAQEBBwEBAQEBhSoHjg6RbJYrghIKhTsChRcYAQEBAQEBAQEBAQECgRCCMyQBgkABAQEBAzo/DAQCAQgOAwQBAQEeCQcyFAkIAgQOBQgTtH2LAgEBAQEBAQEDAQEBAQEBASGDK4NTgWqDKIp3BYoLiRiNfZRUkw5IlFICAgICCQIagTkfgUd4FYdmdocbgRABAQE","From":"Finn Christensen ","To":"Yuanhan Liu ","Thread-Topic":"[PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","Thread-Index":"AQHTNomWAirl91DsckS9/4ffz8FOzqLHloIAgAA5uwCAAB5cgIAAA7yAgAAHkwCAAHK5MP//7/QAgAAsdtA=","Date":"Wed, 27 Sep 2017 10:41:32 +0000","Message-ID":"","References":"<1506404199-23579-1-git-send-email-yliu@fridaylinux.org>\n\t<48EB9B23-48D4-4417-B6E9-0D332295BF54@vmware.com>\n\t<20170927012454.GF2251@yliu-home>\n\t\n\t<20170927032655.GH2251@yliu-home>\n\t<86D9E1E3-DBF7-4CD8-B472-C6CDD156929A@vmware.com>\n\t<10fc4027ed424f919cd0175ab1624439@napatech.com>\n\t<20170927094712.GK2251@yliu-home>","In-Reply-To":"<20170927094712.GK2251@yliu-home>","Accept-Language":"da-DK, en-US","Content-Language":"en-US","X-MS-Has-Attach":"","X-MS-TNEF-Correlator":"","x-originating-ip":"[10.240.10.239]","MIME-Version":"1.0","X-Spam-Status":"No, score=-0.1 required=5.0 tests=DKIM_SIGNED,DKIM_VALID,\n\tDKIM_VALID_AU,RP_MATCHES_RCVD autolearn=disabled version=3.3.1","X-Spam-Checker-Version":"SpamAssassin 3.3.1 (2010-03-16) on\n\tsmtp1.linux-foundation.org","Cc":"\"dev@openvswitch.org\" , Simon\n\tHorman ","Subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","X-BeenThere":"ovs-dev@openvswitch.org","X-Mailman-Version":"2.1.12","Precedence":"list","List-Id":"","List-Unsubscribe":",\n\t","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n\t","Content-Type":"text/plain; charset=\"us-ascii\"","Content-Transfer-Encoding":"7bit","Sender":"ovs-dev-bounces@openvswitch.org","Errors-To":"ovs-dev-bounces@openvswitch.org"}},{"id":1776539,"web_url":"http://patchwork.ozlabs.org/comment/1776539/","msgid":"<1673FE6D-3515-437A-819C-2940BFFFA320@vmware.com>","list_archive_url":null,"date":"2017-09-27T18:54:41","subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","submitter":{"id":68212,"url":"http://patchwork.ozlabs.org/api/people/68212/","name":"Darrell Ball","email":"dball@vmware.com"},"content":"On 9/27/17, 3:41 AM, \"Finn Christensen\" wrote:\r\n\r\n -----Original Message-----\r\n From: Yuanhan Liu [mailto:yliu@fridaylinux.org]\r\n Sent: 27. september 2017 11:47\r\n To: Finn Christensen \r\n Cc: Darrell Ball ; dev@openvswitch.org; Chandran\r\n Sugesh ; Simon Horman\r\n \r\n Subject: Re: [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow\r\n \r\n On Wed, Sep 27, 2017 at 09:12:49AM +0000, Finn Christensen wrote:\r\n >\r\n > [Darrell] It looks fine; of course, if we could drop dependencies on cap\r\n > probe, it would be ideal (.\r\n >\r\n >\r\n > [Finn]\r\n > From a Napatech point of view, we would definitely want to use the\r\n > RTE_FLOW_ACTION_TYPE_RSS if it were implement. It definitely makes\r\n > good sense to me. I have 2 reasons for this:\r\n > 1. It would fit nicely into the way Napatech does flow programming in\r\n > nic 2. We would be fully RSS controlled through OVS Furthermore,\r\n > Future RSS splitting on a per megaflow basis will be possible.\r\n > IMO the \"pure_mark_cap_probed\" function is a temp work-around to\r\n make it work.\r\n > The RSS seems to be a solution to the queue problem.\r\n \r\n Finn, that's really good to know! I do agree without this probe, it makes the\r\n code simpler and cleaner.\r\n \r\n Few questions though. Have Napatech already implemented rss action? If\r\n not, what's the plan?\r\n \r\n [Finn]\r\n Our nic handles rss on a per flow basis, but we have not yet used rte rss action\r\n for OVS. In OVS we simply handles RSS config outside it.\r\n The full control of rss through OVS is better though.\r\n \r\n And are you okay with following code?\r\n \r\n add_mark_action();\r\n add_rss_action_unconditionally();\r\n \r\n flow = rte_create_flow(...);\r\n if (!flow)\r\n return -1;\r\n \r\n That is, no probes, no feedbacks. If it failed, it just failed (flow offload then\r\n is just skipped).\r\n \r\n [Finn]\r\n Yes, we can easily make this work. Good suggestion!\r\n \r\n \r\n But I do think some feedbacks are necessary. If we know the rte_flow cap\r\n in the begnning, we could simply disable the flow offload for a specific port\r\n if we know it doesn't have offload ability. This would avoid the repeat\r\n effort of trying to do hw offload completely.\r\n \r\n [Finn]\r\n This seems to be a good idea.\r\n\r\n[Darrell] Regarding the general question of capability checking, it is fine to have this support\r\n in general and we already identified some cases where it would be best to use this\r\n if we can (the question mostly comes down to support by RTE and drivers).\r\n\r\n Probing is different and we usually use the term for some try and error checking to configure\r\n something during initialization and see if works and then mark the associated capability as enabled\r\n or disabled. We could also use a different kind of probing here in a dynamic fashion, where we try to do\r\n HWOL and if it fails X times we don’t try again unless we detect the port has been reconfigured,\r\n for example, in case the capability check is not possible or not implemented yet.\r\n\r\n\r\n \r\n \r\n --yliu\r\n Disclaimer: This email and any files transmitted with it may contain confidential information intended for the addressee(s) only. The information is not to be surrendered or copied to unauthorized persons. If you have received this communication in error, please notify the sender immediately and delete this e-mail from your system.","headers":{"Return-Path":"","X-Original-To":["incoming@patchwork.ozlabs.org","dev@openvswitch.org"],"Delivered-To":["patchwork-incoming@bilbo.ozlabs.org","ovs-dev@mail.linuxfoundation.org"],"Authentication-Results":["ozlabs.org;\n\tspf=pass (mailfrom) smtp.mailfrom=openvswitch.org\n\t(client-ip=140.211.169.12; helo=mail.linuxfoundation.org;\n\tenvelope-from=ovs-dev-bounces@openvswitch.org;\n\treceiver=)","ozlabs.org;\n\tdkim=fail reason=\"signature verification failed\" (1024-bit key;\n\tunprotected) header.d=onevmw.onmicrosoft.com\n\theader.i=@onevmw.onmicrosoft.com header.b=\"lMiQdKEn\"; \n\tdkim-atps=neutral","spf=none (sender IP is )\n\tsmtp.mailfrom=dball@vmware.com; "],"Received":["from mail.linuxfoundation.org (mail.linuxfoundation.org\n\t[140.211.169.12])\n\t(using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256\n\tbits)) (No client certificate requested)\n\tby ozlabs.org (Postfix) with ESMTPS id 3y2Rp363cPz9t6B\n\tfor ;\n\tThu, 28 Sep 2017 04:54:50 +1000 (AEST)","from mail.linux-foundation.org (localhost [127.0.0.1])\n\tby mail.linuxfoundation.org (Postfix) with ESMTP id 4D1BAACC;\n\tWed, 27 Sep 2017 18:54:46 +0000 (UTC)","from smtp1.linuxfoundation.org (smtp1.linux-foundation.org\n\t[172.17.192.35])\n\tby mail.linuxfoundation.org (Postfix) with ESMTPS id 5558EAB9\n\tfor ; Wed, 27 Sep 2017 18:54:45 +0000 (UTC)","from NAM02-SN1-obe.outbound.protection.outlook.com\n\t(mail-sn1nam02on0085.outbound.protection.outlook.com [104.47.36.85])\n\tby smtp1.linuxfoundation.org (Postfix) with ESMTPS id 634C34BE\n\tfor ; Wed, 27 Sep 2017 18:54:44 +0000 (UTC)","from MWHPR05MB3406.namprd05.prod.outlook.com (10.174.175.155) by\n\tMWHPR05MB3405.namprd05.prod.outlook.com (10.174.175.154) with\n\tMicrosoft SMTP Server (version=TLS1_2,\n\tcipher=TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA384_P256) id\n\t15.20.77.5; Wed, 27 Sep 2017 18:54:41 +0000","from MWHPR05MB3406.namprd05.prod.outlook.com ([10.174.175.155]) by\n\tMWHPR05MB3406.namprd05.prod.outlook.com ([10.174.175.155]) with\n\tmapi id 15.20.0077.007; Wed, 27 Sep 2017 18:54:41 +0000"],"X-Greylist":"whitelisted by SQLgrey-1.7.6","DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=onevmw.onmicrosoft.com; s=selector1-vmware-com;\n\th=From:Date:Subject:Message-ID:Content-Type:MIME-Version;\n\tbh=5JwNRolpX9xfVp4Rtl+ZnxSVwl2tCA+NDHTCcCa3xDo=;\n\tb=lMiQdKEnA5GdzfY6WuDHLfqJWktkiEAOFqOdaRhL+Pf7/UM9ytPv+y8GCyjsQSBAZIM3A/OGRDxHjaSmOj20NpRhFW3pAi8tjIX1+35L/R4CqL7LrCbXGa4smQrW7ySF7ew2u/B4m/n1g79DPgydSECrQX+sokBe6aK58OC9LQ8=","From":"Darrell Ball ","To":"Finn Christensen , Yuanhan Liu ","Thread-Topic":"[PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","Thread-Index":"AQHTNomLA1xYF2/wCU28LyYMHmmNz6LHuAiAgAA5vQCAAB5aAIAAA72AgAAHkoCAAFkTgIAACZsAgAAPLgCAAInIAA==","Date":"Wed, 27 Sep 2017 18:54:41 +0000","Message-ID":"<1673FE6D-3515-437A-819C-2940BFFFA320@vmware.com>","References":"<1506404199-23579-1-git-send-email-yliu@fridaylinux.org>\n\t<48EB9B23-48D4-4417-B6E9-0D332295BF54@vmware.com>\n\t<20170927012454.GF2251@yliu-home>\n\t\n\t<20170927032655.GH2251@yliu-home>\n\t<86D9E1E3-DBF7-4CD8-B472-C6CDD156929A@vmware.com>\n\t<10fc4027ed424f919cd0175ab1624439@napatech.com>\n\t<20170927094712.GK2251@yliu-home>\n\t","In-Reply-To":"","Accept-Language":"en-US","Content-Language":"en-US","X-MS-Has-Attach":"","X-MS-TNEF-Correlator":"","user-agent":"Microsoft-MacOutlook/f.26.0.170902","authentication-results":["ozlabs.org;\n\tspf=pass (mailfrom) smtp.mailfrom=openvswitch.org\n\t(client-ip=140.211.169.12; helo=mail.linuxfoundation.org;\n\tenvelope-from=ovs-dev-bounces@openvswitch.org;\n\treceiver=)","ozlabs.org;\n\tdkim=fail reason=\"signature verification failed\" (1024-bit key;\n\tunprotected) header.d=onevmw.onmicrosoft.com\n\theader.i=@onevmw.onmicrosoft.com header.b=\"lMiQdKEn\"; \n\tdkim-atps=neutral","spf=none (sender IP is )\n\tsmtp.mailfrom=dball@vmware.com; "],"x-originating-ip":"[73.162.236.45]","x-ms-publictraffictype":"Email","x-microsoft-exchange-diagnostics":"1; MWHPR05MB3405;\n\t20:4JO4rjpkUlCRHRWA7tpV39i+SNOakSuPoMVipiu4OC+1yk8eSjBUqzqj9NKH/7SC6lEWea/cYvUeBvppJUEKSpV4MgJxq89rLJfKhcSANaadsJyXIlQJ8DNYeOc47CYjVcRDoZM58bJufmtc9XeqxYZ2BQayEXRWwXGfhaRbwz0=","x-ms-exchange-antispam-srfa-diagnostics":"SSOS;","x-ms-office365-filtering-correlation-id":"d5f8c47c-895d-458f-5746-08d505d93627","x-microsoft-antispam":"UriScan:; BCL:0; PCL:0;\n\tRULEID:(22001)(2017030254152)(2017052603199)(201703131423075)(201703031133081)(201702281549075);\n\tSRVR:MWHPR05MB3405; ","x-ms-traffictypediagnostic":"MWHPR05MB3405:","x-exchange-antispam-report-test":"UriScan:(61668805478150)(216315784871565)(228905959029699); ","x-microsoft-antispam-prvs":"","x-exchange-antispam-report-cfa-test":"BCL:0; PCL:0;\n\tRULEID:(100000700101)(100105000095)(100000701101)(100105300095)(100000702101)(100105100095)(6040450)(2401047)(8121501046)(5005006)(100000703101)(100105400095)(10201501046)(3002001)(93006095)(93001095)(6041248)(20161123564025)(20161123560025)(20161123558100)(20161123555025)(201703131423075)(201702281528075)(201703061421075)(201703061406153)(20161123562025)(6072148)(201708071742011)(100000704101)(100105200095)(100000705101)(100105500095);\n\tSRVR:MWHPR05MB3405; BCL:0; PCL:0;\n\tRULEID:(100000800101)(100110000095)(100000801101)(100110300095)(100000802101)(100110100095)(100000803101)(100110400095)(100000804101)(100110200095)(100000805101)(100110500095);\n\tSRVR:MWHPR05MB3405; ","x-forefront-prvs":"04433051BF","x-forefront-antispam-report":"SFV:NSPM;\n\tSFS:(10009020)(6009001)(376002)(346002)(189002)(377454003)(24454002)(199003)(13464003)(77096006)(83506001)(478600001)(81166006)(3660700001)(97736004)(6486002)(105586002)(66066001)(33656002)(3846002)(8676002)(6436002)(86362001)(76176999)(54906003)(83716003)(3280700002)(82746002)(2906002)(6506006)(68736007)(102836003)(81156014)(6116002)(229853002)(2900100001)(25786009)(4326008)(54356999)(36756003)(53936002)(5660300001)(6246003)(39060400002)(14454004)(101416001)(58126008)(53546010)(316002)(6512007)(99286003)(8936002)(305945005)(93886005)(189998001)(106356001)(7736002)(2950100002)(50986999)(110136005);\n\tDIR:OUT; SFP:1101; SCL:1; SRVR:MWHPR05MB3405;\n\tH:MWHPR05MB3406.namprd05.prod.outlook.com; FPR:; SPF:None;\n\tPTR:InfoNoRecords; MX:1; A:1; LANG:en; ","received-spf":"None (protection.outlook.com: vmware.com does not designate\n\tpermitted sender hosts)","spamdiagnosticoutput":"1:99","spamdiagnosticmetadata":"NSPM","Content-ID":"<4A08D9C78454BD4F8A1A8B5CE1A2F0E1@namprd05.prod.outlook.com>","MIME-Version":"1.0","X-OriginatorOrg":"vmware.com","X-MS-Exchange-CrossTenant-originalarrivaltime":"27 Sep 2017 18:54:41.5195\n\t(UTC)","X-MS-Exchange-CrossTenant-fromentityheader":"Hosted","X-MS-Exchange-CrossTenant-id":"b39138ca-3cee-4b4a-a4d6-cd83d9dd62f0","X-MS-Exchange-Transport-CrossTenantHeadersStamped":"MWHPR05MB3405","X-Spam-Status":"No, score=0.0 required=5.0 tests=DKIM_SIGNED,DKIM_VALID,\n\tRCVD_IN_DNSWL_NONE autolearn=disabled version=3.3.1","X-Spam-Checker-Version":"SpamAssassin 3.3.1 (2010-03-16) on\n\tsmtp1.linux-foundation.org","Cc":"\"dev@openvswitch.org\" ,\n\tSimon Horman ","Subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","X-BeenThere":"ovs-dev@openvswitch.org","X-Mailman-Version":"2.1.12","Precedence":"list","List-Id":"","List-Unsubscribe":",\n\t","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n\t","Content-Type":"text/plain; charset=\"utf-8\"","Content-Transfer-Encoding":"base64","Sender":"ovs-dev-bounces@openvswitch.org","Errors-To":"ovs-dev-bounces@openvswitch.org"}},{"id":1778442,"web_url":"http://patchwork.ozlabs.org/comment/1778442/","msgid":"<2EF2F5C0CC56984AA024D0B180335FCB5256907A@IRSMSX102.ger.corp.intel.com>","list_archive_url":null,"date":"2017-10-02T16:22:29","subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","submitter":{"id":67440,"url":"http://patchwork.ozlabs.org/api/people/67440/","name":"Chandran, Sugesh","email":"sugesh.chandran@intel.com"},"content":"Regards\r\n_Sugesh\r\n\r\n\r\n> -----Original Message-----\r\n> From: Darrell Ball [mailto:dball@vmware.com]\r\n> Sent: Wednesday, September 27, 2017 7:55 PM\r\n> To: Finn Christensen ; Yuanhan Liu \r\n> Cc: dev@openvswitch.org; Chandran, Sugesh ;\r\n> Simon Horman \r\n> Subject: Re: [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow\r\n> \r\n> \r\n> \r\n> On 9/27/17, 3:41 AM, \"Finn Christensen\" wrote:\r\n> \r\n> -----Original Message-----\r\n> From: Yuanhan Liu [mailto:yliu@fridaylinux.org]\r\n> Sent: 27. september 2017 11:47\r\n> To: Finn Christensen \r\n> Cc: Darrell Ball ; dev@openvswitch.org; Chandran\r\n> Sugesh ; Simon Horman\r\n> \r\n> Subject: Re: [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow\r\n> \r\n> On Wed, Sep 27, 2017 at 09:12:49AM +0000, Finn Christensen wrote:\r\n> >\r\n> > [Darrell] It looks fine; of course, if we could drop dependencies on cap\r\n> > probe, it would be ideal (.\r\n> >\r\n> >\r\n> > [Finn]\r\n> > From a Napatech point of view, we would definitely want to use the\r\n> > RTE_FLOW_ACTION_TYPE_RSS if it were implement. It definitely makes\r\n> > good sense to me. I have 2 reasons for this:\r\n> > 1. It would fit nicely into the way Napatech does flow programming in\r\n> > nic 2. We would be fully RSS controlled through OVS Furthermore,\r\n> > Future RSS splitting on a per megaflow basis will be possible.\r\n> > IMO the \"pure_mark_cap_probed\" function is a temp work-around to\r\n> make it work.\r\n> > The RSS seems to be a solution to the queue problem.\r\n> \r\n> Finn, that's really good to know! I do agree without this probe, it makes the\r\n> code simpler and cleaner.\r\n> \r\n> Few questions though. Have Napatech already implemented rss action? If\r\n> not, what's the plan?\r\n> \r\n> [Finn]\r\n> Our nic handles rss on a per flow basis, but we have not yet used rte rss action\r\n> for OVS. In OVS we simply handles RSS config outside it.\r\n> The full control of rss through OVS is better though.\r\n> \r\n> And are you okay with following code?\r\n> \r\n> add_mark_action();\r\n> add_rss_action_unconditionally();\r\n> \r\n> flow = rte_create_flow(...);\r\n> if (!flow)\r\n> return -1;\r\n> \r\n> That is, no probes, no feedbacks. If it failed, it just failed (flow offload then\r\n> is just skipped).\r\n> \r\n> [Finn]\r\n> Yes, we can easily make this work. Good suggestion!\r\n> \r\n> \r\n> But I do think some feedbacks are necessary. If we know the rte_flow cap\r\n> in the begnning, we could simply disable the flow offload for a specific port\r\n> if we know it doesn't have offload ability. This would avoid the repeat\r\n> effort of trying to do hw offload completely.\r\n> \r\n> [Finn]\r\n> This seems to be a good idea.\r\n> \r\n> [Darrell] Regarding the general question of capability checking, it is fine to have\r\n> this support\r\n> in general and we already identified some cases where it would be best\r\n> to use this\r\n> if we can (the question mostly comes down to support by RTE and\r\n> drivers).\r\n> \r\n> Probing is different and we usually use the term for some try and error\r\n> checking to configure\r\n> something during initialization and see if works and then mark the\r\n> associated capability as enabled\r\n> or disabled. We could also use a different kind of probing here in a\r\n> dynamic fashion, where we try to do\r\n> HWOL and if it fails X times we don’t try again unless we detect the port\r\n> has been reconfigured,\r\n> for example, in case the capability check is not possible or not\r\n> implemented yet.\r\n[Sugesh] I agree with Darrel here and we are also looking at implementing a capability APIs\r\nto expose the device feature sets. I will check with our DPDK team and will post the update.\r\n> \r\n> \r\n> \r\n> \r\n> --yliu\r\n> Disclaimer: This email and any files transmitted with it may contain\r\n> confidential information intended for the addressee(s) only. The information is\r\n> not to be surrendered or copied to unauthorized persons. If you have received\r\n> this communication in error, please notify the sender immediately and delete\r\n> this e-mail from your system.\r\n>","headers":{"Return-Path":"","X-Original-To":["incoming@patchwork.ozlabs.org","dev@openvswitch.org"],"Delivered-To":["patchwork-incoming@bilbo.ozlabs.org","ovs-dev@mail.linuxfoundation.org"],"Authentication-Results":"ozlabs.org;\n\tspf=pass (mailfrom) smtp.mailfrom=openvswitch.org\n\t(client-ip=140.211.169.12; helo=mail.linuxfoundation.org;\n\tenvelope-from=ovs-dev-bounces@openvswitch.org;\n\treceiver=)","Received":["from mail.linuxfoundation.org (mail.linuxfoundation.org\n\t[140.211.169.12])\n\t(using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256\n\tbits)) (No client certificate requested)\n\tby ozlabs.org (Postfix) with ESMTPS id 3y5SB52jx7z9t5s\n\tfor ;\n\tTue, 3 Oct 2017 03:22:37 +1100 (AEDT)","from mail.linux-foundation.org (localhost [127.0.0.1])\n\tby mail.linuxfoundation.org (Postfix) with ESMTP id 95CE3AAC;\n\tMon, 2 Oct 2017 16:22:35 +0000 (UTC)","from smtp1.linuxfoundation.org (smtp1.linux-foundation.org\n\t[172.17.192.35])\n\tby mail.linuxfoundation.org (Postfix) with ESMTPS id C7932A80\n\tfor ; Mon, 2 Oct 2017 16:22:34 +0000 (UTC)","from mga09.intel.com (mga09.intel.com [134.134.136.24])\n\tby smtp1.linuxfoundation.org (Postfix) with ESMTPS id 1482BFC\n\tfor ; Mon, 2 Oct 2017 16:22:32 +0000 (UTC)","from orsmga003.jf.intel.com ([10.7.209.27])\n\tby orsmga102.jf.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384;\n\t02 Oct 2017 09:22:31 -0700","from irsmsx109.ger.corp.intel.com ([163.33.3.23])\n\tby orsmga003.jf.intel.com with ESMTP; 02 Oct 2017 09:22:31 -0700","from irsmsx102.ger.corp.intel.com ([169.254.2.180]) by\n\tIRSMSX109.ger.corp.intel.com ([169.254.13.28]) with mapi id\n\t14.03.0319.002; Mon, 2 Oct 2017 17:22:30 +0100"],"X-Greylist":"domain auto-whitelisted by SQLgrey-1.7.6","X-ExtLoop1":"1","X-IronPort-AV":"E=Sophos; i=\"5.42,470,1500966000\"; d=\"scan'208\";\n\ta=\"1020708475\"","From":"\"Chandran, Sugesh\" ","To":"Darrell Ball , Finn Christensen ,\n\tYuanhan Liu ","Thread-Topic":"[PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","Thread-Index":"AQHTNomNn8GWLvTaX0qmBg0CYuwtTqLHp0UAgAA5vACAAB5bgIAAA7yAgAAHlACAAFkRgIAACZsAgAAPLwCAAInIgIAHqb1A","Date":"Mon, 2 Oct 2017 16:22:29 +0000","Message-ID":"<2EF2F5C0CC56984AA024D0B180335FCB5256907A@IRSMSX102.ger.corp.intel.com>","References":"<1506404199-23579-1-git-send-email-yliu@fridaylinux.org>\n\t<48EB9B23-48D4-4417-B6E9-0D332295BF54@vmware.com>\n\t<20170927012454.GF2251@yliu-home>\n\t\n\t<20170927032655.GH2251@yliu-home>\n\t<86D9E1E3-DBF7-4CD8-B472-C6CDD156929A@vmware.com>\n\t<10fc4027ed424f919cd0175ab1624439@napatech.com>\n\t<20170927094712.GK2251@yliu-home>\n\t\n\t<1673FE6D-3515-437A-819C-2940BFFFA320@vmware.com>","In-Reply-To":"<1673FE6D-3515-437A-819C-2940BFFFA320@vmware.com>","Accept-Language":"en-US","Content-Language":"en-US","X-MS-Has-Attach":"","X-MS-TNEF-Correlator":"","dlp-product":"dlpe-windows","dlp-version":"11.0.0.116","dlp-reaction":"no-action","x-originating-ip":"[163.33.239.182]","MIME-Version":"1.0","X-Spam-Status":"No, score=-5.0 required=5.0 tests=RCVD_IN_DNSWL_HI,\n\tRP_MATCHES_RCVD autolearn=disabled version=3.3.1","X-Spam-Checker-Version":"SpamAssassin 3.3.1 (2010-03-16) on\n\tsmtp1.linux-foundation.org","Cc":"\"dev@openvswitch.org\" ,\n\tSimon Horman ","Subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","X-BeenThere":"ovs-dev@openvswitch.org","X-Mailman-Version":"2.1.12","Precedence":"list","List-Id":"","List-Unsubscribe":",\n\t","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n\t","Content-Type":"text/plain; charset=\"utf-8\"","Content-Transfer-Encoding":"base64","Sender":"ovs-dev-bounces@openvswitch.org","Errors-To":"ovs-dev-bounces@openvswitch.org"}},{"id":1778775,"web_url":"http://patchwork.ozlabs.org/comment/1778775/","msgid":"","list_archive_url":null,"date":"2017-10-03T08:44:47","subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","submitter":{"id":72305,"url":"http://patchwork.ozlabs.org/api/people/72305/","name":"Finn Christensen","email":"fc@napatech.com"},"content":"-----Original Message-----\r\n From: Chandran, Sugesh [mailto:sugesh.chandran@intel.com]\r\n Sent: 2. oktober 2017 18:22\r\n To: Darrell Ball ; Finn Christensen\r\n ; Yuanhan Liu \r\n Cc: dev@openvswitch.org; Simon Horman\r\n \r\n Subject: RE: [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow\r\n \r\n \r\n \r\n Regards\r\n _Sugesh\r\n \r\n \r\n > -----Original Message-----\r\n > From: Darrell Ball [mailto:dball@vmware.com]\r\n > Sent: Wednesday, September 27, 2017 7:55 PM\r\n > To: Finn Christensen ; Yuanhan Liu\r\n > \r\n > Cc: dev@openvswitch.org; Chandran, Sugesh\r\n ;\r\n > Simon Horman \r\n > Subject: Re: [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow\r\n >\r\n >\r\n >\r\n > On 9/27/17, 3:41 AM, \"Finn Christensen\" wrote:\r\n >\r\n > -----Original Message-----\r\n > From: Yuanhan Liu [mailto:yliu@fridaylinux.org]\r\n > Sent: 27. september 2017 11:47\r\n > To: Finn Christensen \r\n > Cc: Darrell Ball ; dev@openvswitch.org;\r\n Chandran\r\n > Sugesh ; Simon Horman\r\n > \r\n > Subject: Re: [PATCH v3 0/9] OVS-DPDK flow offload with\r\n > rte_flow\r\n >\r\n > On Wed, Sep 27, 2017 at 09:12:49AM +0000, Finn Christensen wrote:\r\n > >\r\n > > [Darrell] It looks fine; of course, if we could drop dependencies\r\n on cap\r\n > > probe, it would be ideal (.\r\n > >\r\n > >\r\n > > [Finn]\r\n > > From a Napatech point of view, we would definitely want to use\r\n the\r\n > > RTE_FLOW_ACTION_TYPE_RSS if it were implement. It definitely\r\n makes\r\n > > good sense to me. I have 2 reasons for this:\r\n > > 1. It would fit nicely into the way Napatech does flow programming\r\n in\r\n > > nic 2. We would be fully RSS controlled through OVS Furthermore,\r\n > > Future RSS splitting on a per megaflow basis will be possible.\r\n > > IMO the \"pure_mark_cap_probed\" function is a temp work-around\r\n to\r\n > make it work.\r\n > > The RSS seems to be a solution to the queue problem.\r\n >\r\n > Finn, that's really good to know! I do agree without this probe, it\r\n makes the\r\n > code simpler and cleaner.\r\n >\r\n > Few questions though. Have Napatech already implemented rss\r\n action? If\r\n > not, what's the plan?\r\n >\r\n > [Finn]\r\n > Our nic handles rss on a per flow basis, but we have not yet used rte rss\r\n action\r\n > for OVS. In OVS we simply handles RSS config outside it.\r\n > The full control of rss through OVS is better though.\r\n >\r\n > And are you okay with following code?\r\n >\r\n > add_mark_action();\r\n > add_rss_action_unconditionally();\r\n >\r\n > flow = rte_create_flow(...);\r\n > if (!flow)\r\n > return -1;\r\n >\r\n > That is, no probes, no feedbacks. If it failed, it just failed (flow offload\r\n then\r\n > is just skipped).\r\n >\r\n > [Finn]\r\n > Yes, we can easily make this work. Good suggestion!\r\n >\r\n >\r\n > But I do think some feedbacks are necessary. If we know the\r\n rte_flow cap\r\n > in the begnning, we could simply disable the flow offload for a\r\n specific port\r\n > if we know it doesn't have offload ability. This would avoid the repeat\r\n > effort of trying to do hw offload completely.\r\n >\r\n > [Finn]\r\n > This seems to be a good idea.\r\n >\r\n > [Darrell] Regarding the general question of capability checking, it is\r\n > fine to have this support\r\n > in general and we already identified some cases where\r\n > it would be best to use this\r\n > if we can (the question mostly comes down to support by\r\n > RTE and drivers).\r\n >\r\n > Probing is different and we usually use the term for\r\n > some try and error checking to configure\r\n > something during initialization and see if works and\r\n > then mark the associated capability as enabled\r\n > or disabled. We could also use a different kind of\r\n > probing here in a dynamic fashion, where we try to do\r\n > HWOL and if it fails X times we don’t try again unless we\r\n > detect the port has been reconfigured,\r\n > for example, in case the capability check is not possible\r\n > or not implemented yet.\r\n [Sugesh] I agree with Darrel here and we are also looking at implementing\r\n a capability APIs to expose the device feature sets. I will check with our\r\n DPDK team and will post the update.\r\n\r\n[Finn]\r\nI also agree here, however, the \"X times failed and then mark port as HWOL \r\ndisabled\", should only be done initially, where no successfully offloads has \r\nyet occurred.\r\n\r\n >\r\n >\r\n >\r\n >\r\n > --yliu\r\n > Disclaimer: This email and any files transmitted with it may\r\n > contain confidential information intended for the addressee(s) only.\r\n > The information is not to be surrendered or copied to unauthorized\r\n > persons. If you have received this communication in error, please\r\n > notify the sender immediately and delete this e-mail from your system.\r\n >","headers":{"Return-Path":"","X-Original-To":["incoming@patchwork.ozlabs.org","dev@openvswitch.org"],"Delivered-To":["patchwork-incoming@bilbo.ozlabs.org","ovs-dev@mail.linuxfoundation.org"],"Authentication-Results":["ozlabs.org;\n\tspf=pass (mailfrom) smtp.mailfrom=openvswitch.org\n\t(client-ip=140.211.169.12; helo=mail.linuxfoundation.org;\n\tenvelope-from=ovs-dev-bounces@openvswitch.org;\n\treceiver=)","ozlabs.org;\n\tdkim=fail reason=\"signature verification failed\" (2048-bit key;\n\tunprotected) header.d=napatech.com header.i=@napatech.com\n\theader.b=\"GbT9p6cG\"; dkim-atps=neutral"],"Received":["from mail.linuxfoundation.org (mail.linuxfoundation.org\n\t[140.211.169.12])\n\t(using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256\n\tbits)) (No client certificate requested)\n\tby ozlabs.org (Postfix) with ESMTPS id 3y5szc2vK6z9sRq\n\tfor ;\n\tTue, 3 Oct 2017 19:44:59 +1100 (AEDT)","from mail.linux-foundation.org (localhost [127.0.0.1])\n\tby mail.linuxfoundation.org (Postfix) with ESMTP id 040F64A6;\n\tTue, 3 Oct 2017 08:44:55 +0000 (UTC)","from smtp1.linuxfoundation.org (smtp1.linux-foundation.org\n\t[172.17.192.35])\n\tby mail.linuxfoundation.org (Postfix) with ESMTPS id 82F44305\n\tfor ; Tue, 3 Oct 2017 08:44:53 +0000 (UTC)","from mail01.napatech.com (mail01.napatech.com [188.120.77.121])\n\tby smtp1.linuxfoundation.org (Postfix) with ESMTPS id 962833D5\n\tfor ; Tue, 3 Oct 2017 08:44:51 +0000 (UTC)","from cph-gen-exch02.napatech.com (10.240.1.84) by\n\tcph-gen-exch02.napatech.com (10.240.1.84) with Microsoft SMTP Server\n\t(version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA256_P256) id\n\t15.1.1034.26; Tue, 3 Oct 2017 10:44:47 +0200","from cph-gen-exch02.napatech.com ([fe80::581:51a1:ac3f:84e]) by\n\tcph-gen-exch02.napatech.com ([fe80::581:51a1:ac3f:84e%12]) with mapi\n\tid 15.01.1034.026; Tue, 3 Oct 2017 10:44:47 +0200"],"X-Greylist":"domain auto-whitelisted by SQLgrey-1.7.6","DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=napatech.com; i=@napatech.com; q=dns/txt; s=mar2017;\n\tt=1507020291; x=1538556291;\n\th=from:to:cc:subject:date:message-id:references:\n\tin-reply-to:content-transfer-encoding:mime-version;\n\tbh=coVYPeHRtu4UwTL16uh5ntp3HhVpkPVyR0hrCFSg4D4=;\n\tb=GbT9p6cGqFpPgeFRsep0FkHUlGrO4SplDj+xpn7e1LhDeCH8Oi6MdO/l\n\tRmWzXW4/paLW9c8FR4ufBHzzSfz/VCRL2wvSltvSXUbsuUdt4bH9ljKqo\n\tj3fALf2eJFtEP+mHXpjsDS+KAiLj9hAymcbS9ZWYqYkiKQuh5KFlvPG+9\n\tH9e03GLr/9U71uUMwYN9wMei3HwXUbTr2XCQtQRB37I06s3hSG7VMzlR4\n\tEWaAnQwaAerQJkOj50H3mSgFGH5akM7yuiMUcMxTTwksjKdkrrPcyBL6x\n\tI63KMc8fgcqUyGqcl5fOa9wL/XdbCR2SRk89b65JxBN2D+wNqewbdBR/R g==;","IronPort-PHdr":"9a23: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","X-IronPort-Anti-Spam-Filtered":"true","X-IronPort-Anti-Spam-Result":"A2FuAADeTNNZ/1QB8ApdGQEBAQEBAQEBAQEBBwEBAQEBFAEBAQEBAQEBAQEBBwEBAQEBhSsHg3KKH5FaliwOggQKhTsCGoRsGAEBAQEBAQEBAQEBAoEQgjMkAYJAAQEBAQMjEUUMBAIBCBEEAQEBAgIjAwICAjAUAQgIAgQBDQUIE69JgieLMgEBAQEBAQEDAQEBAQEBAQEggQ6CH4ExgiKBaoIbgQ2ESAkBEgGDMoJhBYoLiR6OCZRcgh2Fb4sGSIlLixQCAgICCQIagTkfgTwLeBWHZnaHIIEkgRABAQE","X-IPAS-Result":"A2FuAADeTNNZ/1QB8ApdGQEBAQEBAQEBAQEBBwEBAQEBFAEBAQEBAQEBAQEBBwEBAQEBhSsHg3KKH5FaliwOggQKhTsCGoRsGAEBAQEBAQEBAQEBAoEQgjMkAYJAAQEBAQMjEUUMBAIBCBEEAQEBAgIjAwICAjAUAQgIAgQBDQUIE69JgieLMgEBAQEBAQEDAQEBAQEBAQEggQ6CH4ExgiKBaoIbgQ2ESAkBEgGDMoJhBYoLiR6OCZRcgh2Fb4sGSIlLixQCAgICCQIagTkfgTwLeBWHZnaHIIEkgRABAQE","From":"Finn Christensen ","To":"\"Chandran, Sugesh\" , Darrell Ball\n\t, Yuanhan Liu ","Thread-Topic":"[PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","Thread-Index":"AQHTNomWAirl91DsckS9/4ffz8FOzqLHloIAgAA5uwCAAB5cgIAAA7yAgAAHkwCAAHK5MP//7/QAgAAsdtCAAGyBgIAHsSKAgAEliXA=","Date":"Tue, 3 Oct 2017 08:44:47 +0000","Message-ID":"","References":"<1506404199-23579-1-git-send-email-yliu@fridaylinux.org>\n\t<48EB9B23-48D4-4417-B6E9-0D332295BF54@vmware.com>\n\t<20170927012454.GF2251@yliu-home>\n\t\n\t<20170927032655.GH2251@yliu-home>\n\t<86D9E1E3-DBF7-4CD8-B472-C6CDD156929A@vmware.com>\n\t<10fc4027ed424f919cd0175ab1624439@napatech.com>\n\t<20170927094712.GK2251@yliu-home>\n\t\n\t<1673FE6D-3515-437A-819C-2940BFFFA320@vmware.com>\n\t<2EF2F5C0CC56984AA024D0B180335FCB5256907A@IRSMSX102.ger.corp.intel.com>","In-Reply-To":"<2EF2F5C0CC56984AA024D0B180335FCB5256907A@IRSMSX102.ger.corp.intel.com>","Accept-Language":"da-DK, en-US","Content-Language":"en-US","X-MS-Has-Attach":"","X-MS-TNEF-Correlator":"","x-originating-ip":"[10.240.10.239]","MIME-Version":"1.0","X-Spam-Status":"No, score=-2.4 required=5.0 tests=DKIM_SIGNED,DKIM_VALID,\n\tDKIM_VALID_AU,RCVD_IN_DNSWL_MED,RP_MATCHES_RCVD autolearn=disabled\n\tversion=3.3.1","X-Spam-Checker-Version":"SpamAssassin 3.3.1 (2010-03-16) on\n\tsmtp1.linux-foundation.org","Cc":"\"dev@openvswitch.org\" ,\n\tSimon Horman ","Subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","X-BeenThere":"ovs-dev@openvswitch.org","X-Mailman-Version":"2.1.12","Precedence":"list","List-Id":"","List-Unsubscribe":",\n\t","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n\t","Content-Type":"text/plain; charset=\"utf-8\"","Content-Transfer-Encoding":"base64","Sender":"ovs-dev-bounces@openvswitch.org","Errors-To":"ovs-dev-bounces@openvswitch.org"}},{"id":1789608,"web_url":"http://patchwork.ozlabs.org/comment/1789608/","msgid":"<20171018135318.GZ1545@yliu-home>","list_archive_url":null,"date":"2017-10-18T13:53:18","subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","submitter":{"id":72215,"url":"http://patchwork.ozlabs.org/api/people/72215/","name":"Yuanhan Liu","email":"yliu@fridaylinux.org"},"content":"On Wed, Sep 27, 2017 at 10:09:20AM +0800, Yuanhan Liu wrote:\n> On Wed, Sep 27, 2017 at 09:24:54AM +0800, Yuanhan Liu wrote:\n> > > The support needed would be in some drivers and seems reasonably doable. \n> > > Moreover, this was discussed in the last dpdk meeting and the support was\n> > > indicated as existing?, although I only verified the MLX code, myself.\n> > \n> > >From the code point of view, yes, the code was there months ago.\n> > \n> > > I had seen the MLX code supporting _RSS action and there are some checks for\n> > > supported cases; when you say “it didn't work”, what was the issue ?\n> > \n> > I actually have met the error months ago, I even debugged it. IIRC,\n> > the error is from libibverbs, when trying to create the hw flow. I\n> > think I need double-confirm it with our colleague who developed this\n> > feature.\n> \n> Hmm, I think I was wrong, and apparenetly, I think I have did something\n> stupid in the last try. I double confirmed it just now, at least the\n> flow creation now works. I just need take some time to intergrate it\n> to OVS-DPDK, to see how it goes. I will get it back to you when I have\n> done that. Currently, I was occupied by something else.\n\nHere is a short update I should have done in last week (apologize for\nbeing late).\n\nThe RSS action should work. I also have intergated it to ovs-dpdk. I\nintended to send v4 in last week. Later, I noticed a fatal bug (regarding\nto MQ).\n\nI was still heavily occupied by something else, that I don't have time\nto fix that. I have tried to figure out a solution at spare time though.\nI might have found a solution. I just don't know the results yet without\nreally trying it.\n\nI will update progress when I have made some. Please also note that\nit's very likely I won't have time on that before the end of this month :/\n\n\t--yliu","headers":{"Return-Path":"","X-Original-To":["incoming@patchwork.ozlabs.org","dev@openvswitch.org"],"Delivered-To":["patchwork-incoming@bilbo.ozlabs.org","ovs-dev@mail.linuxfoundation.org"],"Authentication-Results":["ozlabs.org;\n\tspf=pass (mailfrom) smtp.mailfrom=openvswitch.org\n\t(client-ip=140.211.169.12; helo=mail.linuxfoundation.org;\n\tenvelope-from=ovs-dev-bounces@openvswitch.org;\n\treceiver=)","ozlabs.org;\n\tdkim=fail reason=\"signature verification failed\" (2048-bit key;\n\tunprotected) header.d=fridaylinux.org header.i=@fridaylinux.org\n\theader.b=\"aDoO7e/x\"; \n\tdkim=fail reason=\"signature verification failed\" (2048-bit key;\n\tunprotected) header.d=messagingengine.com\n\theader.i=@messagingengine.com header.b=\"Am3dQgLd\"; \n\tdkim-atps=neutral"],"Received":["from mail.linuxfoundation.org (mail.linuxfoundation.org\n\t[140.211.169.12])\n\t(using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256\n\tbits)) (No client certificate requested)\n\tby ozlabs.org (Postfix) with ESMTPS id 3yHDL61Lwdz9t3l\n\tfor ;\n\tThu, 19 Oct 2017 01:03:25 +1100 (AEDT)","from mail.linux-foundation.org (localhost [127.0.0.1])\n\tby mail.linuxfoundation.org (Postfix) with ESMTP id C97E59BA;\n\tWed, 18 Oct 2017 14:03:21 +0000 (UTC)","from smtp1.linuxfoundation.org (smtp1.linux-foundation.org\n\t[172.17.192.35])\n\tby mail.linuxfoundation.org (Postfix) with ESMTPS id F21349BA\n\tfor ; Wed, 18 Oct 2017 14:03:19 +0000 (UTC)","from new2-smtp.messagingengine.com (new2-smtp.messagingengine.com\n\t[66.111.4.224])\n\tby smtp1.linuxfoundation.org (Postfix) with ESMTPS id 2A80F140\n\tfor ; Wed, 18 Oct 2017 14:03:19 +0000 (UTC)","from compute1.internal (compute1.nyi.internal [10.202.2.41])\n\tby mailnew.nyi.internal (Postfix) with ESMTP id 695DBF63;\n\tWed, 18 Oct 2017 09:53:26 -0400 (EDT)","from frontend1 ([10.202.2.160])\n\tby compute1.internal (MEProxy); Wed, 18 Oct 2017 09:53:26 -0400","from yliu-home (unknown [124.79.168.36])\n\tby mail.messagingengine.com (Postfix) with ESMTPA id D7C1F7FA80;\n\tWed, 18 Oct 2017 09:53:24 -0400 (EDT)"],"X-Greylist":"delayed 00:09:51 by SQLgrey-1.7.6","DKIM-Signature":["v=1; a=rsa-sha256; c=relaxed/relaxed; d=fridaylinux.org;\n\th=cc:content-transfer-encoding:content-type:date:from\n\t:in-reply-to:message-id:mime-version:references:subject:to\n\t:x-me-sender:x-me-sender:x-sasl-enc; s=fm1; bh=0YHvxXAOn3SR86GQ5\n\t3fMFkValmrashTe1MXzMNj3QVM=; b=aDoO7e/xucfFof6xaq8OpcVkL43VUlG85\n\txaOKqlrPKZ2Ysn04CeqYi2kKFfIW2mVOUOkBxRs1Ds2+pOuP4QZmwYvQiTQb1tuN\n\tkAnHFV25Eol3j40mdWeucGA16ryEg54K4/8VKH2tU0sTQUPzq2FdMPdPLeHw1RN4\n\t4wLZb9wljfY7JCcrbXTLJ94O0BeEDslLWYddDtIIwSHuM0poL5ItyiStXt2uPJ8O\n\t2oLoofYzFLEYS3nHkBDYsVr4V3+X09l1WhVG7K4svxB6ZhbTQt8pnllugQ2GN+No\n\tdV7hiqT0dw+Qt2pGDPVe+SeA+syd4/LGYApsj3y8QkD/tp5Fmx+dg==","v=1; a=rsa-sha256; c=relaxed/relaxed; d=\n\tmessagingengine.com; h=cc:content-transfer-encoding:content-type\n\t:date:from:in-reply-to:message-id:mime-version:references\n\t:subject:to:x-me-sender:x-me-sender:x-sasl-enc; s=fm1; bh=0YHvxX\n\tAOn3SR86GQ53fMFkValmrashTe1MXzMNj3QVM=; b=Am3dQgLd9aiaXDBPlJNMdN\n\t78I4MreIX2YUrAeLhs9oXZvNra7vJIKfPOpqKgLzGShA1pW4DsiGdVVYeJqekwH7\n\tgKVTEMrUg9X5i8IQNTUbN/yYSI8rmX7A8t43nTEC9Na8U2HJeOvs+xvoNacLzWAZ\n\tz7XIsXBzFOeyJ3XOgRkIMD1eJpsERABG14uo4wz1wucedoXqnGab0XuiSpA8zfat\n\tQokf1NNHUBA7uc9o1FeJ2ZP15wftGVCZrkGFbxkFcId/9GmcyP011eDd/042OT2N\n\tRq8Fs4eKfac6F+3Ap5uMi/yWPRxfEQldPdIqs3ELoqsvy6Sl2ePPDnaI7UM9fwJA\n\t=="],"X-ME-Sender":"","Date":"Wed, 18 Oct 2017 21:53:18 +0800","From":"Yuanhan Liu ","To":"Darrell Ball ","Message-ID":"<20171018135318.GZ1545@yliu-home>","References":"<1506404199-23579-1-git-send-email-yliu@fridaylinux.org>\n\t<48EB9B23-48D4-4417-B6E9-0D332295BF54@vmware.com>\n\t<20170927012454.GF2251@yliu-home> <20170927020920.GG2251@yliu-home>","MIME-Version":"1.0","Content-Disposition":"inline","In-Reply-To":"<20170927020920.GG2251@yliu-home>","User-Agent":"Mutt/1.5.24 (2015-08-30)","X-Spam-Status":"No, score=-0.8 required=5.0 tests=DKIM_SIGNED,DKIM_VALID,\n\tDKIM_VALID_AU,RCVD_IN_DNSWL_LOW autolearn=disabled version=3.3.1","X-Spam-Checker-Version":"SpamAssassin 3.3.1 (2010-03-16) on\n\tsmtp1.linux-foundation.org","Cc":"\"dev@openvswitch.org\" ,\n\tSimon Horman ","Subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","X-BeenThere":"ovs-dev@openvswitch.org","X-Mailman-Version":"2.1.12","Precedence":"list","List-Id":"","List-Unsubscribe":",\n\t","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n\t","Content-Type":"text/plain; charset=\"utf-8\"","Content-Transfer-Encoding":"base64","Sender":"ovs-dev-bounces@openvswitch.org","Errors-To":"ovs-dev-bounces@openvswitch.org"}},{"id":1796941,"web_url":"http://patchwork.ozlabs.org/comment/1796941/","msgid":"<20171031211920.GH27530@ovn.org>","list_archive_url":null,"date":"2017-10-31T21:19:20","subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","submitter":{"id":67603,"url":"http://patchwork.ozlabs.org/api/people/67603/","name":"Ben Pfaff","email":"blp@ovn.org"},"content":"I see that this series appears to have stalled. Should we expect a new\nversion sometime soon? Do you need more reviews on the current version?","headers":{"Return-Path":"","X-Original-To":["incoming@patchwork.ozlabs.org","dev@openvswitch.org"],"Delivered-To":["patchwork-incoming@bilbo.ozlabs.org","ovs-dev@mail.linuxfoundation.org"],"Authentication-Results":"ozlabs.org;\n\tspf=pass (mailfrom) smtp.mailfrom=openvswitch.org\n\t(client-ip=140.211.169.12; helo=mail.linuxfoundation.org;\n\tenvelope-from=ovs-dev-bounces@openvswitch.org;\n\treceiver=)","Received":["from mail.linuxfoundation.org (mail.linuxfoundation.org\n\t[140.211.169.12])\n\t(using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256\n\tbits)) (No client certificate requested)\n\tby ozlabs.org (Postfix) with ESMTPS id 3yRPPL5F6Sz9t3x\n\tfor ;\n\tWed, 1 Nov 2017 08:19:34 +1100 (AEDT)","from mail.linux-foundation.org (localhost [127.0.0.1])\n\tby mail.linuxfoundation.org (Postfix) with ESMTP id C7B55C04;\n\tTue, 31 Oct 2017 21:19:30 +0000 (UTC)","from smtp1.linuxfoundation.org (smtp1.linux-foundation.org\n\t[172.17.192.35])\n\tby mail.linuxfoundation.org (Postfix) with ESMTPS id E818ABF1\n\tfor ; Tue, 31 Oct 2017 21:19:28 +0000 (UTC)","from relay4-d.mail.gandi.net (relay4-d.mail.gandi.net\n\t[217.70.183.196])\n\tby smtp1.linuxfoundation.org (Postfix) with ESMTPS id 0D761F8\n\tfor ; Tue, 31 Oct 2017 21:19:26 +0000 (UTC)","from ovn.org (unknown [208.91.3.26])\n\t(Authenticated sender: blp@ovn.org)\n\tby relay4-d.mail.gandi.net (Postfix) with ESMTPSA id A7DFB17209A;\n\tTue, 31 Oct 2017 22:19:23 +0100 (CET)"],"X-Greylist":"domain auto-whitelisted by SQLgrey-1.7.6","X-Originating-IP":"208.91.3.26","Date":"Tue, 31 Oct 2017 14:19:20 -0700","From":"Ben Pfaff ","To":"Yuanhan Liu ","Message-ID":"<20171031211920.GH27530@ovn.org>","References":"<1506404199-23579-1-git-send-email-yliu@fridaylinux.org>","MIME-Version":"1.0","Content-Disposition":"inline","In-Reply-To":"<1506404199-23579-1-git-send-email-yliu@fridaylinux.org>","User-Agent":"Mutt/1.5.23 (2014-03-12)","X-Spam-Status":"No, score=-0.7 required=5.0 tests=RCVD_IN_DNSWL_LOW\n\tautolearn=disabled version=3.3.1","X-Spam-Checker-Version":"SpamAssassin 3.3.1 (2010-03-16) on\n\tsmtp1.linux-foundation.org","Cc":"dev@openvswitch.org, Simon Horman ","Subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","X-BeenThere":"ovs-dev@openvswitch.org","X-Mailman-Version":"2.1.12","Precedence":"list","List-Id":"","List-Unsubscribe":",\n\t","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n\t","Content-Type":"text/plain; charset=\"us-ascii\"","Content-Transfer-Encoding":"7bit","Sender":"ovs-dev-bounces@openvswitch.org","Errors-To":"ovs-dev-bounces@openvswitch.org"}},{"id":1797317,"web_url":"http://patchwork.ozlabs.org/comment/1797317/","msgid":"<20171101152430.GR1545@yliu-home>","list_archive_url":null,"date":"2017-11-01T15:24:30","subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","submitter":{"id":72215,"url":"http://patchwork.ozlabs.org/api/people/72215/","name":"Yuanhan Liu","email":"yliu@fridaylinux.org"},"content":"On Tue, Oct 31, 2017 at 02:19:20PM -0700, Ben Pfaff wrote:\n> I see that this series appears to have stalled. Should we expect a new\n> version sometime soon? Do you need more reviews on the current version?\n\nMy bad. As I have stated in another email, I meant to send v4 earlier, but\nI found a bug. Meanwhile, I was heavily occupied by something else, that I\ndon't have time to shape it.\n\nLikely, I could be able to start working on v4 at mid of this month.\n\n\t--yliu","headers":{"Return-Path":"","X-Original-To":["incoming@patchwork.ozlabs.org","dev@openvswitch.org"],"Delivered-To":["patchwork-incoming@bilbo.ozlabs.org","ovs-dev@mail.linuxfoundation.org"],"Authentication-Results":["ozlabs.org;\n\tspf=pass (mailfrom) smtp.mailfrom=openvswitch.org\n\t(client-ip=140.211.169.12; helo=mail.linuxfoundation.org;\n\tenvelope-from=ovs-dev-bounces@openvswitch.org;\n\treceiver=)","ozlabs.org;\n\tdkim=fail reason=\"signature verification failed\" (2048-bit key;\n\tunprotected) header.d=fridaylinux.org header.i=@fridaylinux.org\n\theader.b=\"LCOuSora\"; \n\tdkim=fail reason=\"signature verification failed\" (2048-bit key;\n\tunprotected) header.d=messagingengine.com\n\theader.i=@messagingengine.com header.b=\"n82A7XFF\"; \n\tdkim-atps=neutral"],"Received":["from mail.linuxfoundation.org (mail.linuxfoundation.org\n\t[140.211.169.12])\n\t(using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256\n\tbits)) (No client certificate requested)\n\tby ozlabs.org (Postfix) with ESMTPS id 3yRsTN4TdZz9sNc\n\tfor ;\n\tThu, 2 Nov 2017 02:24:40 +1100 (AEDT)","from mail.linux-foundation.org (localhost [127.0.0.1])\n\tby mail.linuxfoundation.org (Postfix) with ESMTP id 3C161A7C;\n\tWed, 1 Nov 2017 15:24:38 +0000 (UTC)","from smtp1.linuxfoundation.org (smtp1.linux-foundation.org\n\t[172.17.192.35])\n\tby mail.linuxfoundation.org (Postfix) with ESMTPS id 8A936978\n\tfor ; Wed, 1 Nov 2017 15:24:37 +0000 (UTC)","from new2-smtp.messagingengine.com (new2-smtp.messagingengine.com\n\t[66.111.4.224])\n\tby smtp1.linuxfoundation.org (Postfix) with ESMTPS id 182F0F8\n\tfor ; Wed, 1 Nov 2017 15:24:37 +0000 (UTC)","from compute1.internal (compute1.nyi.internal [10.202.2.41])\n\tby mailnew.nyi.internal (Postfix) with ESMTP id 40DFAF97;\n\tWed, 1 Nov 2017 11:24:36 -0400 (EDT)","from frontend2 ([10.202.2.161])\n\tby compute1.internal (MEProxy); Wed, 01 Nov 2017 11:24:36 -0400","from yliu-home (unknown [124.79.168.36])\n\tby mail.messagingengine.com (Postfix) with ESMTPA id 30D0C24724;\n\tWed, 1 Nov 2017 11:24:34 -0400 (EDT)"],"X-Greylist":"from auto-whitelisted by SQLgrey-1.7.6","DKIM-Signature":["v=1; a=rsa-sha256; c=relaxed/relaxed; d=fridaylinux.org;\n\th=cc:content-type:date:from:in-reply-to:message-id:mime-version\n\t:references:subject:to:x-me-sender:x-me-sender:x-sasl-enc; s=\n\tfm1; bh=POF7pa11I6vzR+wUQsEXiNizO+d9RhrH6gAYx9lZI1M=; b=LCOuSora\n\tvdQqabnvlqIJwrTFeAcBTYDz/qD1SNjbjvZcNTmyQ+bPDu0LFmMOqFYjdYq0mN/R\n\t9rcpoW/z8co8ULO5AW1ArmzhQgY/YW2vSDQwY/BMPZHrN9zIgp9kw7X2Jf5H4495\n\tC82HfHvhEEJ9grWToN5afoKH4t1v/dKVQ/7vXCCLxDbvkFNEWNCJxLytx+5kd4rQ\n\tu7VDEn9ZcSa3zGtnkDhxcDWpqWTfCXHVmBy9u5PqfhWnKBG43dBhSSwRHZmiDxKa\n\tUezibrT3C//9WEU9FRdJW54tWcZsccQnXlorXqRvO+BCmYkqDhxpjTiQW2yuTD1M\n\tw+4jztZewtfwJw==","v=1; a=rsa-sha256; c=relaxed/relaxed; d=\n\tmessagingengine.com; h=cc:content-type:date:from:in-reply-to\n\t:message-id:mime-version:references:subject:to:x-me-sender\n\t:x-me-sender:x-sasl-enc; s=fm1; bh=POF7pa11I6vzR+wUQsEXiNizO+d9R\n\thrH6gAYx9lZI1M=; b=n82A7XFFvGsQ7F3Z2fZyT/jgBxiNWcye49ApP7tJB9/oJ\n\t5MOBP0kigt2RfW4AaaVcWEtr+FtfCW9Mlnla7VirGaFL1pi2oM+6n3lSgvHobpiu\n\twZmcOgi2gYJGFyV+FScyJFneQGgCVEYf3YhvseHZ+sm3Qsbc6XvNp7JGNhx4yB6t\n\tP7SWZwhM86nr654nVzUB9/9wtHI3fzXHhEQ8Ot0aKElAmauUhA56yuxCfgfaES19\n\ttDyU+X48BrYLB3bCa+f7xIIXpu8xWpxGZ3gfLld8uW57zuLl0mEE3fh/zcKEBBJK\n\twnNa8tgpMwOiJ5edKkfjevXZCSj5bkqAxr2UIt+Xg=="],"X-ME-Sender":"","Date":"Wed, 1 Nov 2017 23:24:30 +0800","From":"Yuanhan Liu ","To":"Ben Pfaff ","Message-ID":"<20171101152430.GR1545@yliu-home>","References":"<1506404199-23579-1-git-send-email-yliu@fridaylinux.org>\n\t<20171031211920.GH27530@ovn.org>","MIME-Version":"1.0","Content-Disposition":"inline","In-Reply-To":"<20171031211920.GH27530@ovn.org>","User-Agent":"Mutt/1.5.24 (2015-08-30)","X-Spam-Status":"No, score=-0.8 required=5.0 tests=DKIM_SIGNED,DKIM_VALID,\n\tDKIM_VALID_AU,RCVD_IN_DNSWL_LOW autolearn=disabled version=3.3.1","X-Spam-Checker-Version":"SpamAssassin 3.3.1 (2010-03-16) on\n\tsmtp1.linux-foundation.org","Cc":"dev@openvswitch.org, Simon Horman ","Subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","X-BeenThere":"ovs-dev@openvswitch.org","X-Mailman-Version":"2.1.12","Precedence":"list","List-Id":"","List-Unsubscribe":",\n\t","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n\t","Content-Type":"text/plain; charset=\"us-ascii\"","Content-Transfer-Encoding":"7bit","Sender":"ovs-dev-bounces@openvswitch.org","Errors-To":"ovs-dev-bounces@openvswitch.org"}},{"id":1797325,"web_url":"http://patchwork.ozlabs.org/comment/1797325/","msgid":"<20171101153129.GZ27530@ovn.org>","list_archive_url":null,"date":"2017-11-01T15:31:29","subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","submitter":{"id":67603,"url":"http://patchwork.ozlabs.org/api/people/67603/","name":"Ben Pfaff","email":"blp@ovn.org"},"content":"On Wed, Nov 01, 2017 at 11:24:30PM +0800, Yuanhan Liu wrote:\n> On Tue, Oct 31, 2017 at 02:19:20PM -0700, Ben Pfaff wrote:\n> > I see that this series appears to have stalled. Should we expect a new\n> > version sometime soon? Do you need more reviews on the current version?\n> \n> My bad. As I have stated in another email, I meant to send v4 earlier, but\n> I found a bug. Meanwhile, I was heavily occupied by something else, that I\n> don't have time to shape it.\n> \n> Likely, I could be able to start working on v4 at mid of this month.\n\nThere's no hurry from my perspective, my main goal was to make sure that\nI/we hadn't dropped the ball. I'll look forward to the next version.","headers":{"Return-Path":"","X-Original-To":["incoming@patchwork.ozlabs.org","dev@openvswitch.org"],"Delivered-To":["patchwork-incoming@bilbo.ozlabs.org","ovs-dev@mail.linuxfoundation.org"],"Authentication-Results":"ozlabs.org;\n\tspf=pass (mailfrom) smtp.mailfrom=openvswitch.org\n\t(client-ip=140.211.169.12; helo=mail.linuxfoundation.org;\n\tenvelope-from=ovs-dev-bounces@openvswitch.org;\n\treceiver=)","Received":["from mail.linuxfoundation.org (mail.linuxfoundation.org\n\t[140.211.169.12])\n\t(using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256\n\tbits)) (No client certificate requested)\n\tby ozlabs.org (Postfix) with ESMTPS id 3yRsdV0CHbz9sNw\n\tfor ;\n\tThu, 2 Nov 2017 02:31:41 +1100 (AEDT)","from mail.linux-foundation.org (localhost [127.0.0.1])\n\tby mail.linuxfoundation.org (Postfix) with ESMTP id 44994BC7;\n\tWed, 1 Nov 2017 15:31:40 +0000 (UTC)","from smtp1.linuxfoundation.org (smtp1.linux-foundation.org\n\t[172.17.192.35])\n\tby mail.linuxfoundation.org (Postfix) with ESMTPS id 378A2ACA\n\tfor ; Wed, 1 Nov 2017 15:31:38 +0000 (UTC)","from relay6-d.mail.gandi.net (relay6-d.mail.gandi.net\n\t[217.70.183.198])\n\tby smtp1.linuxfoundation.org (Postfix) with ESMTPS id D207616A\n\tfor ; Wed, 1 Nov 2017 15:31:37 +0000 (UTC)","from ovn.org (173-228-112-34.dsl.dynamic.fusionbroadband.com\n\t[173.228.112.34]) (Authenticated sender: blp@ovn.org)\n\tby relay6-d.mail.gandi.net (Postfix) with ESMTPSA id 8D9F7FB882;\n\tWed, 1 Nov 2017 16:31:33 +0100 (CET)"],"X-Greylist":"domain auto-whitelisted by SQLgrey-1.7.6","X-Originating-IP":"173.228.112.34","Date":"Wed, 1 Nov 2017 08:31:29 -0700","From":"Ben Pfaff ","To":"Yuanhan Liu ","Message-ID":"<20171101153129.GZ27530@ovn.org>","References":"<1506404199-23579-1-git-send-email-yliu@fridaylinux.org>\n\t<20171031211920.GH27530@ovn.org> <20171101152430.GR1545@yliu-home>","MIME-Version":"1.0","Content-Disposition":"inline","In-Reply-To":"<20171101152430.GR1545@yliu-home>","User-Agent":"Mutt/1.5.23 (2014-03-12)","X-Spam-Status":"No, score=-0.7 required=5.0 tests=RCVD_IN_DNSWL_LOW\n\tautolearn=disabled version=3.3.1","X-Spam-Checker-Version":"SpamAssassin 3.3.1 (2010-03-16) on\n\tsmtp1.linux-foundation.org","Cc":"dev@openvswitch.org, Simon Horman ","Subject":"Re: [ovs-dev] [PATCH v3 0/9] OVS-DPDK flow offload with rte_flow","X-BeenThere":"ovs-dev@openvswitch.org","X-Mailman-Version":"2.1.12","Precedence":"list","List-Id":"","List-Unsubscribe":",\n\t","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n\t","Content-Type":"text/plain; charset=\"us-ascii\"","Content-Transfer-Encoding":"7bit","Sender":"ovs-dev-bounces@openvswitch.org","Errors-To":"ovs-dev-bounces@openvswitch.org"}}]