From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 225F4A0548; Wed, 21 Apr 2021 10:58:16 +0200 (CEST) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id DDAA0419EC; Wed, 21 Apr 2021 10:58:15 +0200 (CEST) Received: from mga05.intel.com (mga05.intel.com [192.55.52.43]) by mails.dpdk.org (Postfix) with ESMTP id E7D68419D3 for ; Wed, 21 Apr 2021 10:58:13 +0200 (CEST) IronPort-SDR: DKM5lVxXnG25sgB3uSzdpjHGUrrqU2mPu30JR5G8g9B9LJuYXZfLfEitAp1oAqrYg829ogW+A0 yY9EQ12B1Sfw== X-IronPort-AV: E=McAfee;i="6200,9189,9960"; a="280994622" X-IronPort-AV: E=Sophos;i="5.82,238,1613462400"; d="scan'208";a="280994622" Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga105.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 21 Apr 2021 01:58:13 -0700 IronPort-SDR: TBjZnJOwaVYXTJNOxGiJOkuorCXXmN4h5RXG5rnHWNEkxNMD8Uxxzz5beCLoUWGfUHmDjxWFTs toMNK/v6Z/yw== X-IronPort-AV: E=Sophos;i="5.82,238,1613462400"; d="scan'208";a="455254485" Received: from fyigit-mobl1.ger.corp.intel.com (HELO [10.213.206.218]) ([10.213.206.218]) by fmsmga002-auth.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 21 Apr 2021 01:58:11 -0700 To: Asaf Penso , "Jiawei(Jonny) Wang" , Matan Azrad , Ori Kam , Slava Ovsiienko , NBU-Contact-Thomas Monjalon Cc: "dev@dpdk.org" , Raslan Darawsheh References: <20210331073632.1443011-1-lizh@nvidia.com> <1618916122-181792-1-git-send-email-jiaweiw@nvidia.com> <2783b22f-aff2-28d6-71dd-8e0725bf499f@intel.com> From: Ferruh Yigit X-User: ferruhy Message-ID: Date: Wed, 21 Apr 2021 09:58:06 +0100 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset=utf-8; format=flowed Content-Language: en-US Content-Transfer-Encoding: 8bit Subject: Re: [dpdk-dev] [PATCH v6 00/15] Add ASO meter support in MLX5 PMD X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" On 4/21/2021 9:33 AM, Asaf Penso wrote: >> -----Original Message----- >> From: Ferruh Yigit >> Sent: Wednesday, April 21, 2021 11:32 AM >> To: Jiawei(Jonny) Wang ; Matan Azrad >> ; Ori Kam ; Slava Ovsiienko >> ; NBU-Contact-Thomas Monjalon >> >> Cc: dev@dpdk.org; Raslan Darawsheh ; Asaf Penso >> >> Subject: Re: [PATCH v6 00/15] Add ASO meter support in MLX5 PMD >> >> On 4/20/2021 11:55 AM, Jiawei Wang wrote: >>> To support more meters and better performance, MLX HW provides ASO >>> (Advanced Steering Operation) flow meter. >>> It can expose millions of ASO flow meter context's in HW. >>> This ASO object can allocate the large bulk meter objects. >>> This patch set implement the ASO flow meter for mlx5 driver. >>> MLX5 PMD driver will be responsible for ASO flow meter manage to HW. >>> >>> V2: Fix compile error issue (mlx5_glue->destroy_flow_action) >>> V3: Fix comments. >>> V4: Fix comments and add Acked. >>> V5: Fix unused log_obj_size issue. >>> V6: Fix comments and update release notes. >>> >>> Jiawei Wang (1): >>> doc: update release notes for ASO meter >>> >>> Li Zhang (10): >>> net/mlx5: optimize meter statistics >>> common/mlx5: add definitions for ASO flow meter >>> common/mlx5: add read ASO flow meter HCA capability >>> common/mlx5: add DevX API to create ASO flow meter object >>> net/mlx5: flow meter pool to manage meter object >>> net/mlx5: initialize the flow meter ASO SQ >>> net/mlx5: add meter ASO queue management >>> net/mlx5: add support of ASO meter action >>> net/mlx5: make ASO meter queue thread-safe >>> net/mlx5: allow multiple flow tables on the same level >>> >>> Shun Hao (3): >>> common/mlx5: add color register idle bits definition >>> net/mlx5: fix meter statistics >>> net/mlx5: use mask for meter register setting >>> >>> Suanming Mou (1): >>> net/mlx5: support three level table walk >>> >> >> Hi Li, >> >> The request in previous patch was to add some documentation on the new >> feature in driver documentation, plus some design documentation if needed, >> not just release notes update. >> >> But this patch become on the critical path for -rc1, since an mlx ethdev patch >> depends on this patch, I want to block them for the release, instead does it >> make sense the have the documentation update for the -rc2, what do you >> think? >> >> Thanks, >> ferruh > > Hello Ferruh, > The ASO is not a new concept, and is already used by other features like shared RSS and sharing Aging. > Regardless, I agree we can improve documention of the driver, as always 😊 +1 > We'll take it as part of -rc2, and would appreciate the integration of this patchset in the meanwhile. > A correction from above, "I _don't_ want to block them for the release" and already working on it, the documentation update can be merged on -rc2. Thanks.