From mboxrd@z Thu Jan 1 00:00:00 1970 From: Bruce Richardson Subject: Re: [PATCH] net/i40e: add packet prefetch Date: Thu, 6 Apr 2017 10:54:54 +0100 Message-ID: <20170406095454.GB3564@bricha3-MOBL3.ger.corp.intel.com> References: <1488365813-12442-1-git-send-email-vladyslav.buslov@harmonicinc.com> <188971FCDA171749BED5DA74ABF3E6F03B6ACF0D@shsmsx102.ccr.corp.intel.com> <2c220d4f-b8c5-1824-c8cd-69f20c6ce04f@intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Ferruh Yigit , "Pei, Yulong" , "Zhang, Helin" , "Wu, Jingjing" , "dev@dpdk.org" , Nitin Kumar To: Vladyslav Buslov Return-path: Received: from mga14.intel.com (mga14.intel.com [192.55.52.115]) by dpdk.org (Postfix) with ESMTP id 1975E201 for ; Thu, 6 Apr 2017 11:54:58 +0200 (CEST) Content-Disposition: inline In-Reply-To: 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 Thu, Apr 06, 2017 at 09:29:12AM +0000, Vladyslav Buslov wrote: > Ferruh, > > In our case patch significantly improves application performance. (~40% more PPS on load balancer core) > Using DPDK examples I can only reproduce perf improvements with similar design apps like load_balancer. > With applications that send on free packets on same core where they are received performance is not improved. > > It seems that this patch doesn't do anything(or even actually slightly degrades performance) for run-to-completion apps so we will have to continue maintaining it as part part of our internal branch. > > Regards, > Vlad > Is it possible to get the same performance boost in your app, while avoiding the perf hit in run-to-completion apps, by using a runtime, rather than compile-time option? /Bruce