From mboxrd@z Thu Jan 1 00:00:00 1970 From: Shahaf Shuler Subject: Re: Survey for final decision about per-port offload API Date: Sun, 1 Apr 2018 04:44:20 +0000 Message-ID: References: <2759953.P7QpFFSjiU@xps> Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Cc: Ajit Khaparde , Jerin Jacob , Shijith Thotton , Santosh Shukla , Rahul Lakkireddy , John Daley , Wenzhuo Lu , Konstantin Ananyev , Beilei Xing , Qi Zhang , Jingjing Wu , Adrien Mazarguil , =?iso-8859-1?Q?N=E9lio_Laranjeiro?= , Yongseok Koh , "Tomasz Duszynski" , Jianbo Liu , "Alejandro Lucero" , Hemant Agrawal , Shreyansh Jain , "Harish Patil" , Rasesh Mody , "dev@dpdk.org" Return-path: Received: from EUR02-VE1-obe.outbound.protection.outlook.com (mail-eopbgr20064.outbound.protection.outlook.com [40.107.2.64]) by dpdk.org (Postfix) with ESMTP id 2C4FA1F28 for ; Sun, 1 Apr 2018 06:44:26 +0200 (CEST) In-Reply-To: <2759953.P7QpFFSjiU@xps> Content-Language: en-US List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" Friday, March 30, 2018 4:48 PM, Thomas Monjalon: > Subject: Survey for final decision about per-port offload API >=20 > There are some discussions about a specific part of the offload API: > "To enable per-port offload, the offload should be set on both > device configuration and queue setup." >=20 > It means the application must repeat the port offload flags in > rte_eth_conf.[rt]xmode.offloads and rte_eth_[rt]xconf.offloads, when > calling respectively rte_eth_dev_configure() and > rte_eth_[rt]x_queue_setup for each queue. >=20 > The PMD must check if there is mismatch, i.e. a port offload not repeated= in > queue setup. > There is a proposal to do this check at ethdev level: > https://emea01.safelinks.protection.outlook.com/?url=3Dhttp%3A%2F > %2Fdpdk.org%2Fml%2Farchives%2Fdev%2F2018- > March%2F094023.html&data=3D02%7C01%7Cshahafs%40mellanox.com%7Cb2a > e36d768424c9e616308d59644e2a7%7Ca652971c7d2e4d9ba6a4d149256f461b > %7C0%7C0%7C636580144980414466&sdata=3DRe2xM9u5jJr4M1PDTn5gE9mp22 > NmBI%2Bwa2GFPmUzq38%3D&reserved=3D0 >=20 > It was also proposed to relax the API and allow "forgetting" port offload= s in > queue offloads: > https://emea01.safelinks.protection.outlook.com/?url=3Dhttp%3A%2F > %2Fdpdk.org%2Fml%2Farchives%2Fdev%2F2018- > March%2F092978.html&data=3D02%7C01%7Cshahafs%40mellanox.com%7Cb2a > e36d768424c9e616308d59644e2a7%7Ca652971c7d2e4d9ba6a4d149256f461b > %7C0%7C0%7C636580144980414466&sdata=3DxaUM8jcVl9gf3e%2By9geZDPpO > 1RJ5%2FXWJwA%2BpGp54pNs%3D&reserved=3D0 >=20 > It would mean the offloads applied to a queue result of OR operation: > rte_eth_conf.[rt]xmode.offloads | rte_eth_[rt]xconf.offloads >=20 > 1/ Do you agree with above API change? Yes. >=20 >=20 > If we agree with this change, we need to update the documentation and > remove the checks in PMDs. And to update applications and examples in the tree to set the offloads acc= ording to above change.=20 > Note: no matter what is decided here, 18.05-rc1 should have all PMDs > switched to the API which was defined in 17.11. > Given that API is new and not yet adopted by the applications, the sonner= it > is fixed, the better. >=20 > 2/ Should we do this change in 18.05-rc2? >=20 >=20 > At the same time, we want to make clear that an offload enabled at port > level, cannot be disabled at queue level. >=20 > 3/ Do you agree with above statement (to be added in the doc)? Yes=20 >=20 >=20 > There is the same kind of confusion in the offload capabilities: > rte_eth_dev_info.[rt]x_offload_capa > rte_eth_dev_info.[rt]x_queue_offload_capa > The queue capabilities must be a subset of port capabilities, i.e. every = queue > capabilities must be reported as port capabilities. > But the port capabilities should be reported at queue level only if it ca= n be > applied to a specific queue. >=20 > 4/ Do you agree with above statement (to be added in the doc)? No.=20 The documentation should describe the API from the application side, and no= t provide guidelines for the PMDs implementation.=20 If missing, we should clarify more about what queue and port offload means.= Something like: "When port offload is enabled, the offload applies on the port along with a= ll of its associated queues" and "When queue offload is enabled the offload, the offload applies only on the= specific queue." The PMDs then will decide how they report the different offloads they offer= .=20 >=20 >=20 > Please give your opinion on questions 1, 2, 3 and 4. > Answering by yes/no may be sufficient in most cases :) Thank you >=20