From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 9C689A04DD; Wed, 28 Oct 2020 19:07:47 +0100 (CET) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 192A14C73; Wed, 28 Oct 2020 19:07:46 +0100 (CET) Received: from new2-smtp.messagingengine.com (new2-smtp.messagingengine.com [66.111.4.224]) by dpdk.org (Postfix) with ESMTP id 0369C378B for ; Wed, 28 Oct 2020 19:07:43 +0100 (CET) Received: from compute2.internal (compute2.nyi.internal [10.202.2.42]) by mailnew.nyi.internal (Postfix) with ESMTP id 6BC765803B2; Wed, 28 Oct 2020 14:07:42 -0400 (EDT) Received: from mailfrontend1 ([10.202.2.162]) by compute2.internal (MEProxy); Wed, 28 Oct 2020 14:07:42 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=monjalon.net; h= from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding:content-type; s=fm2; bh= SvpWyO1UnNB0HdcEz/VCFS0YeCjbqOTF+OPBuhyZnCc=; b=RlwdnevuZkVdl0T/ zJclnYKPxi1i5gYjD3iwfL/uhUlF4nChdNdEkKukPkj1W8ZQhkwgcKDymvtevuGL RYHEitsYN23zC1Z3DnHrrqWARe1u3cZSeSa358S5WPOs4gxcW4FGPlc2mx4380wp /YLjkmwaSL1zfEnTj94sXKS6j5o37w/SZZ1pZBh9ufqgU0C7K4VVFdBs1le2IrRd Kt6bg4mYBRNUQBQuElCfqm5n4cIkxmz3XMBaHTM4qc7f4I9Gaf5aTeCnGAhoNXf3 WFFPVVzNqSn2tHoqZNa2dTSXwpH8Y+zdYA+e2VWHT79/IKbi/6amEVl4YyQvPW2U RF1gXA== DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:content-transfer-encoding:content-type :date:from:in-reply-to:message-id:mime-version:references :subject:to:x-me-proxy:x-me-proxy:x-me-sender:x-me-sender :x-sasl-enc; s=fm1; bh=SvpWyO1UnNB0HdcEz/VCFS0YeCjbqOTF+OPBuhyZn Cc=; b=RWv+sZFgWIMUpBVIYsUh1KemckWlAOn+7GRa1TIJ0CuYtp6vsfli3POBq cF5muglH0nPNNWP2Kd8dPWA63dpTR1yipVXLGMTOnVWGpB8y+EyRQIyzJyJAfEXO /3+GDyCqN+Ci1UO7mNWic30d3RPUWK3CFVojyZj83goR2EAU43Ds0KXy/kZYExHf du2+IMPeKYxdDSXqeoUOWvg+iYWiWdy61YWdiGwuzjzkbuQP45RiuD3VYTAkRyvK BHLz9rFZuhcoeqirn3+ruRI+yAIJ4+u623KQ4RU1OXObUv60wMPg7pRguBYz68vr 8+ZcGJUgiLehSv/i7C8IuOkCh+eDA== X-ME-Sender: X-ME-Proxy-Cause: gggruggvucftvghtrhhoucdtuddrgedujedrledugddutdejucetufdoteggodetrfdotf fvucfrrhhofhhilhgvmecuhfgrshhtofgrihhlpdfqfgfvpdfurfetoffkrfgpnffqhgen uceurghilhhouhhtmecufedttdenucesvcftvggtihhpihgvnhhtshculddquddttddmne cujfgurhephffvufffkfgjfhgggfgtsehtufertddttddvnecuhfhrohhmpefvhhhomhgr shcuofhonhhjrghlohhnuceothhhohhmrghssehmohhnjhgrlhhonhdrnhgvtheqnecugg ftrfgrthhtvghrnhepudeggfdvfeduffdtfeeglefghfeukefgfffhueejtdetuedtjeeu ieeivdffgeehnecukfhppeejjedrudefgedrvddtfedrudekgeenucevlhhushhtvghruf hiiigvpedtnecurfgrrhgrmhepmhgrihhlfhhrohhmpehthhhomhgrshesmhhonhhjrghl ohhnrdhnvght X-ME-Proxy: Received: from xps.localnet (184.203.134.77.rev.sfr.net [77.134.203.184]) by mail.messagingengine.com (Postfix) with ESMTPA id 0D891328005E; Wed, 28 Oct 2020 14:07:39 -0400 (EDT) From: Thomas Monjalon To: Nithin Dabilpuram , "Van Haaren, Harry" Cc: dev@dpdk.org, Pavan Nikhilesh , Jerin Jacob , Ruifeng Wang , "Richardson, Bruce" , "Ananyev, Konstantin" , "kirankumark@marvell.com" , "dev@dpdk.org" , "david.marchand@redhat.com" , "olivier.matz@6wind.com" Date: Wed, 28 Oct 2020 19:07:38 +0100 Message-ID: <32079303.me3necsKF1@thomas> In-Reply-To: References: <3705096.qAGAdPRMt2@thomas> <2153992.0QQoBXgI6F@thomas> MIME-Version: 1.0 Content-Transfer-Encoding: 7Bit Content-Type: text/plain; charset="us-ascii" Subject: Re: [dpdk-dev] [PATCH v4] node: switch IPv4 metadata to dynamic mbuf field 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: , Errors-To: dev-bounces@dpdk.org Sender: "dev" 28/10/2020 11:24, Van Haaren, Harry: > From: Thomas Monjalon > > > + IP4_LOOKUP_NODE_PRIV1_OFF(node->ctx) = node_mbuf_priv1_dynfield_offset; > > > > That's interesting. > > You copy the offset in the node context for better performance. > > How much is it better than with global offset variable? > > How much it decreases compared to a static mbuf field? > > Also interested in this topic, I'll offer the logical/theory point of view; > > With a static field, the offset into the mbuf can be encoded in the instruction > stream, meaning there are no d-cache loads to identify particular dynamic field. > > With a static/global variable, the cache line where the value resides is presumably > not hot in cache per burst (assuming an application that does significant work, so not > in cache since last burst). Hence overhead estimate could be 1x cache line load per burst. Would it help to group all dynfields and dynflags offsets in the same cache line?