From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from NAM03-DM3-obe.outbound.protection.outlook.com (mail-dm3nam03on0064.outbound.protection.outlook.com [104.47.41.64]) by dpdk.org (Postfix) with ESMTP id 8D2504C92 for ; Thu, 15 Mar 2018 05:11:45 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=CAVIUMNETWORKS.onmicrosoft.com; s=selector1-cavium-com; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version; bh=AcrSZOHFQGhewOO0hqc84Fc6yVC263KLUyge0gfANdY=; b=IpwD2zFtFDavm8P2LRhJclnvMZJFQVMs4bSTydrYtGXtjjtpdMRiutkAFN/T924Ip8+y24FV2k417u+a8QpQ1yQpgYlK/aSvRRa8Ty1w8WvtwFO6C7kaen1PptuRqT4QogZJEFVcQcdJWgKwXJM3onHAJGWJSZE911Kxvjh4hnA= Received: from CY4PR0701MB3634.namprd07.prod.outlook.com (52.132.101.164) by CY4PR0701MB3635.namprd07.prod.outlook.com (52.132.102.10) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA384_P256) id 15.20.588.14; Thu, 15 Mar 2018 04:11:41 +0000 Received: from CY4PR0701MB3634.namprd07.prod.outlook.com ([fe80::f040:5777:9f62:17b9]) by CY4PR0701MB3634.namprd07.prod.outlook.com ([fe80::f040:5777:9f62:17b9%13]) with mapi id 15.20.0588.013; Thu, 15 Mar 2018 04:11:39 +0000 From: "Verma, Shally" To: Ahmed Mansour , "Trahe, Fiona" , "dev@dpdk.org" CC: "De Lara Guarch, Pablo" , "Athreya, Narayana Prasad" , "Gupta, Ashish" , "Sahu, Sunila" , "Challa, Mahipal" , "Jain, Deepak K" , Hemant Agrawal , Roy Pledge , Youri Querry , "Daly, Lee" , "Jozwiak, TomaszX" , Alok Makhariya , Shreyansh Jain Thread-Topic: [dpdk-dev] [PATCH] compressdev: implement API - mbuf alternative Thread-Index: AdO6FqZGVQESVGJPRLukdFdKpdlnigB+2tOQ Date: Thu, 15 Mar 2018 04:11:39 +0000 Message-ID: References: <348A99DA5F5B7549AA880327E580B435893478BA@IRSMSX101.ger.corp.intel.com> <348A99DA5F5B7549AA880327E580B4358934A600@IRSMSX101.ger.corp.intel.com> <348A99DA5F5B7549AA880327E580B4358934B32C@IRSMSX101.ger.corp.intel.com> In-Reply-To: Accept-Language: en-US Content-Language: en-US X-Mentions: ahmed.mansour@nxp.com,fiona.trahe@intel.com X-MS-Has-Attach: X-MS-TNEF-Correlator: authentication-results: spf=none (sender IP is ) smtp.mailfrom=Shally.Verma@cavium.com; x-originating-ip: [117.98.156.46] x-ms-publictraffictype: Email x-microsoft-exchange-diagnostics: 1; CY4PR0701MB3635; 7:zauV2RlvhulhFJwjutgbNk3MH35SzrsHYWFtCNAoLap7OiQY3Id3vWYOhyYj+4eLIOosrDUtquMimst7OhjUgTBObDLymIebzsOIVkCPJBbLrhFifh0ML/GwDze7T1d6fGfEl1nlhE0/bNApLpfzePwyDNz/PiNB6Ydv/U+aSaRoX7v5R3VkRgtUNUyoTDflKY/3ZUBj7mdqvv1kKnD/7f7vSjitHpJ/vjMJF28dIbz7zQotsqtvDHGshGZ3Wvfw x-ms-exchange-antispam-srfa-diagnostics: SSOS;SSOR; x-forefront-antispam-report: SFV:SKI; SCL:-1; SFV:NSPM; SFS:(10009020)(396003)(346002)(376002)(39860400002)(366004)(39380400002)(53754006)(13464003)(199004)(189003)(8656006)(86362001)(76176011)(6306002)(5250100002)(59450400001)(74316002)(9686003)(478600001)(7696005)(7416002)(2501003)(99286004)(45080400002)(55016002)(102836004)(186003)(53546011)(6506007)(14454004)(93886005)(26005)(316002)(5660300001)(2950100002)(54906003)(106356001)(110136005)(25786009)(72206003)(966005)(4326008)(2900100001)(3660700001)(3280700002)(6246003)(68736007)(8676002)(6116002)(3846002)(105586002)(81156014)(8936002)(81166006)(561944003)(2906002)(229853002)(66066001)(53936002)(305945005)(7736002)(6436002)(97736004)(33656002); DIR:OUT; SFP:1101; SCL:1; SRVR:CY4PR0701MB3635; H:CY4PR0701MB3634.namprd07.prod.outlook.com; FPR:; SPF:None; PTR:InfoNoRecords; A:1; MX:1; LANG:en; x-ms-office365-filtering-correlation-id: 892676e9-56ab-423d-67bc-08d58a2ada3f x-microsoft-antispam: UriScan:; BCL:0; PCL:0; RULEID:(7020095)(4652020)(5600026)(4604075)(3008032)(4534165)(4627221)(201703031133081)(201702281549075)(2017052603328)(7153060)(7193020); SRVR:CY4PR0701MB3635; x-ms-traffictypediagnostic: CY4PR0701MB3635: x-microsoft-antispam-prvs: x-exchange-antispam-report-test: UriScan:(278428928389397)(189930954265078)(185117386973197)(85827821059158)(788757137089)(45079756050767)(228905959029699); x-exchange-antispam-report-cfa-test: BCL:0; PCL:0; RULEID:(8211001083)(6040522)(2401047)(8121501046)(5005006)(93006095)(93001095)(3231221)(944501244)(52105095)(3002001)(10201501046)(6041310)(20161123562045)(20161123564045)(20161123558120)(201703131423095)(201702281528075)(20161123555045)(201703061421075)(201703061406153)(20161123560045)(6072148)(201708071742011); SRVR:CY4PR0701MB3635; BCL:0; PCL:0; RULEID:; SRVR:CY4PR0701MB3635; x-forefront-prvs: 0612E553B4 received-spf: None (protection.outlook.com: cavium.com does not designate permitted sender hosts) x-microsoft-antispam-message-info: y+DsBuVjS2dhvHyoIPhLZWoKlkHJdI8WmhS3FSl81jqenIborY4vnbGWuaOMGQ05vl1Vxopd4eVat8h3YDfy6iH3O897if+U/ChMR9kIG7lk6sEZuG4WlgX2uVYYGytERaN71q3Tm1e9zztgO2/8H9JLRMYN/RlnjQt0dCnilKuxWp+OQLayaejLO4P8N1lY5yvMUgaRWn8lRHdNH2FxU+1yvHJuLIzOvhwIzZSjScOGLTvzVdKSwizI+FbNcIh393so1oYMUYFDgP/Q8aUldT3wPL2OhutRwAkLaRi8YJ90i4piRhrG/U8/2rSGB4a/53g1U9k6kPhOFXfAP9UZKQ== spamdiagnosticoutput: 1:99 spamdiagnosticmetadata: NSPM Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 X-OriginatorOrg: cavium.com X-MS-Exchange-CrossTenant-Network-Message-Id: 892676e9-56ab-423d-67bc-08d58a2ada3f X-MS-Exchange-CrossTenant-originalarrivaltime: 15 Mar 2018 04:11:39.6078 (UTC) X-MS-Exchange-CrossTenant-fromentityheader: Hosted X-MS-Exchange-CrossTenant-id: 711e4ccf-2e9b-4bcf-a551-4094005b6194 X-MS-Exchange-Transport-CrossTenantHeadersStamped: CY4PR0701MB3635 Subject: Re: [dpdk-dev] [PATCH] compressdev: implement API - mbuf alternative X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 15 Mar 2018 04:11:46 -0000 @Trahe, Fiona>> We're proposing, in the interest of getting the API out in = 18.05, to stick with mbufs - acknowledging >> that they're not optimal for storage and we may propose changes in 18.08= . [Shally] Sounds good to us too. @Ahmed Mansour . I am assuming that transferring from mbuf to regular buffe= rs and back does >not involve some time consuming work like data copying and such. [Shally] I too assume copying shouldn't be a need and a big no-no. We norma= lly extract and pass buf_addr from mbuf as it is to HW. So implicit assumption is data memory is dma-able to device. Thanks Shally >-----Original Message----- >From: Ahmed Mansour [mailto:ahmed.mansour@nxp.com] >Sent: 15 March 2018 00:32 >To: Trahe, Fiona ; Verma, Shally ; dev@dpdk.org >Cc: De Lara Guarch, Pablo ; Athreya, Naray= ana Prasad ; >Gupta, Ashish ; Sahu, Sunila ; Challa, Mahipal >; Jain, Deepak K ; Hem= ant Agrawal ; Roy >Pledge ; Youri Querry ; Daly, = Lee ; Jozwiak, TomaszX >; Alok Makhariya ; Shre= yansh Jain >Subject: Re: [dpdk-dev] [PATCH] compressdev: implement API - mbuf alternat= ive > >Hi All, > >Sticking with mbufs until at least 1805 works for us. We also see >storage as the main use case, but ipcomp maybe an important customer use >case in the future. Nonetheless, I see the mbuf formatting as inherently >external to the compressdev APIs. An application doing ipcomp should >just do the mbuf packaging outside of compressdev. At least that is what >current software implementation of ipcomp do when using zlib.net. I am >assuming that transferring from mbuf to regular buffers and back does >not involve some time consuming work like data copying and such. > >Thanks, > >Ahmed > >On 3/14/2018 2:39 PM, Trahe, Fiona wrote: >> Hi Shally, Ahmed, et al, >> >> Following internal and community feedback we've decided that there's sti= ll too much churn in this. >> We're proposing, in the interest of getting the API out in 18.05, to sti= ck with mbufs - acknowledging >> that they're not optimal for storage and we may propose changes in 18.08= . >> Compressdev will start as an experimental API in 18.05 - we'll POC and b= enchmark alternatives >> or API extensions once we get time to do so. >> >> Regards, >> Fiona >> >>> -----Original Message----- >>> From: Verma, Shally [mailto:Shally.Verma@cavium.com] >>> Sent: Wednesday, March 14, 2018 12:51 PM >>> To: Trahe, Fiona ; Ahmed Mansour ; dev@dpdk.org >>> Cc: De Lara Guarch, Pablo ; Athreya, Na= rayana Prasad >>> ; Gupta, Ashish ; Sahu, Sunila >>> ; Challa, Mahipal ; = Jain, Deepak K >>> ; Hemant Agrawal ; Roy= Pledge >>> ; Youri Querry ; Daly, Lee = ; >>> Jozwiak, TomaszX >>> Subject: RE: [dpdk-dev] [PATCH] compressdev: implement API - mbuf alter= native >>> >>> >>> >>>> -----Original Message----- >>>> From: Trahe, Fiona [mailto:fiona.trahe@intel.com] >>>> Sent: 13 March 2018 21:22 >>>> To: Verma, Shally ; Ahmed Mansour ; >>> dev@dpdk.org >>>> Cc: De Lara Guarch, Pablo ; Athreya, N= arayana Prasad >>> ; >>>> Gupta, Ashish ; Sahu, Sunila ; Challa, Mahipal >>>> ; Jain, Deepak K ;= Hemant Agrawal >>> ; Roy >>>> Pledge ; Youri Querry ; Da= ly, Lee >>> ; Jozwiak, TomaszX >>>> ; Trahe, Fiona >>>> Subject: RE: [dpdk-dev] [PATCH] compressdev: implement API - mbuf alte= rnative >>>> >>>> Hi Shally, >>>> >>>>> -----Original Message----- >>>>> From: Verma, Shally [mailto:Shally.Verma@cavium.com] >>>>> Sent: Tuesday, March 13, 2018 8:15 AM >>>>> To: Trahe, Fiona ; Ahmed Mansour ; >>> dev@dpdk.org >>>>> Cc: De Lara Guarch, Pablo ; Athreya, = Narayana Prasad >>>>> ; Gupta, Ashish ; Sahu, Sunila >>>>> ; Challa, Mahipal = ; Jain, Deepak K >>>>> ; Hemant Agrawal ; R= oy Pledge >>>>> ; Youri Querry ; fiona.tr= ahe@gmail.com; Daly, Lee >>>>> ; Jozwiak, TomaszX >>>>> Subject: RE: [dpdk-dev] [PATCH] compressdev: implement API - mbuf alt= ernative >>>>> >>>>> HI Fiona >>>>> >>>>> So I understand we're moving away from mbufs because of its size limi= tation (64k) and cacheline >>> overhead >>>>> and their more suitability to n/w applications. Given that, I underst= and benefit of having another >>> structure >>>>> to input data but then what is proposal for ipcomp like application w= here mbuf usage may be a better >>>>> option? Should we keep support for both (mbuf and this structure) so = that apps can use appropriate >>> data >>>>> structure depending on their requirement. >>>> [Fiona] An application can use pass buffers from an mbuf or mbuf chain= to compressdev by filling in the >>>> compressdev struct fields with the mbuf meta-data, using rte_pktmbuf_d= ata_len(), >>>> rte_pktmbuf_mtod(), rte_pktmbuf_mtophys(), etc >>>> For simplicity I'd prefer to offer only 1 rather than 2 data formats o= n the API. >>>> We see storage applications rather than IPComp as the main use-case fo= r compressdev, so would prefer >>>> to optimise for that. >>>> Do you think otherwise? >>> [Shally] Yea. We plan to use it for ipcomp and other such possible n/w = apps. So, we envision mbuf support >>> as necessary. So, I think we can add two APIs one which process on rte_= comp_op and other on rte_mbufs >>> to make it simpler. >>> >>>>> Further comments, on github. >>>>> >>>>> Thanks >>>>> Shally >>>>> >>>>>> -----Original Message----- >>>>>> From: Trahe, Fiona [mailto:fiona.trahe@intel.com] >>>>>> Sent: 12 March 2018 21:31 >>>>>> To: Ahmed Mansour ; Verma, Shally ; >>>>> dev@dpdk.org >>>>>> Cc: De Lara Guarch, Pablo ; Athreya,= Narayana Prasad >>>>> ; >>>>>> Gupta, Ashish ; Sahu, Sunila ; Challa, >>> Mahipal >>>>>> ; Jain, Deepak K ; Hemant Agrawal >>>>> ; Roy >>>>>> Pledge ; Youri Querry ; = fiona.trahe@gmail.com; >>> Daly, >>>>> Lee ; >>>>>> Jozwiak, TomaszX >>>>>> Subject: RE: [dpdk-dev] [PATCH] compressdev: implement API - mbuf al= ternative >>>>>> >>>>>> Hi Shally, Ahmed, and anyone else interested in compressdev, >>>>>> >>>>>> I mentioned last week that we've been exploring using something othe= r than mbufs to pass src/dst >>>>> buffers to compressdev PMDs. >>>>>> Reasons: >>>>>> - mbuf data is limited to 64k-1 in each segment of a chained mbuf. D= ata for compression >>>>>> can be greater and it would add cycles to have to break up into s= maller segments. >>>>>> - data may originate in mbufs, but is more likely, particularly for = storage use-cases, to >>>>>> originate in other data structures. >>>>>> - There's a 2 cache-line overhead for every segment in a chain, most= of this data >>>>>> is network-related, not needed by compressdev >>>>>> So moving to a custom structure would minimise memory overhead, remo= ve restriction on 64k-1 size >>> and >>>>> give more flexibility if >>>>>> compressdev ever needs any comp-specific meta-data. >>>>>> >>>>>> We've come up with a compressdev-specific structure using the struct= iovec from sys/uio.h, which is >>>>> commonly used by storage >>>>>> applications. This would replace the src and dest mbufs in the op. >>>>>> I'll not include the code here - Pablo will push that to github shor= tly and we'd appreciate review >>>>> comments there. >>>>>> https://emea01.safelinks.protection.outlook.com/?url=3Dhttps%3A%2F%2= Fgithub.com%2Fpablodelara%2Fdpdk-draft- >compressdev&data=3D02%7C01%7Cahmed.mansour%40nxp.com%7C6a8977f9b3714d58621= 708d589dae567%7C686ea1d3bc2b4c6fa92cd >99c5c301635%7C0%7C0%7C636566495639618830&sdata=3DwmFrxeUNyXdxI5%2Fp5gCmyIR= feDnbHebBJXbztqdsMrc%3D&reserved=3D0 >>>>>> Just posting on the mailing list to give a heads-up and ensure this = reaches a wider audience than may >>> see >>>>> it on github. >>>>>> Note : We also considered having no data structures in the op, inste= ad the application >>>>>> would supply a callback which the PMD would use to retrieve meta-dat= a (virt address, iova, length) >>>>>> for each next segment as needed. While this is quite flexible and al= low the application >>>>>> to keep its data in its native structures, it's likely to cost more = cycles. >>>>>> So we're not proposing this at the moment, but hope to benchmark it = later while the API is still >>>>> experimental. >>>>>> General feedback on direction is welcome here on the mailing list. >>>>>> For feedback on the details of implementation we would appreciate co= mments on github. >>>>>> >>>>>> Regards, >>>>>> Fiona. >