From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-wi0-f176.google.com (mail-wi0-f176.google.com [209.85.212.176]) by dpdk.org (Postfix) with ESMTP id 622E28D96 for ; Thu, 24 Sep 2015 23:29:22 +0200 (CEST) Received: by wicge5 with SMTP id ge5so1664495wic.0 for ; Thu, 24 Sep 2015 14:29:22 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:from:to:cc:subject:date:message-id:organization :user-agent:in-reply-to:references:mime-version :content-transfer-encoding:content-type; bh=QOVIGDI54xg0VmIidQ3J8zB8BJpfRNmCyrDIeipgAOQ=; b=Z3RSg1a1EnzNaX4wqphCLFXkZV0N1Fzgj37Gy+EqzAuU/qADdSLdGUVPUU+V9Bkoqp C7HGz2E6acb4JszEToVcPqy8DzN5lA6mAAiR+uGG1QxcFGXhPGmGiFTlcgnOGd2uwJL6 I01TmgBSbQMq/YL6MTBJaxEdC+euLBKWQ7AeBgCyRT8CvqmDZtfLjHb+fPbi6DWtqism d2BNTLOzHkyKU89NyKZOdrs851hN610rZYkBb6RbljMWHt/iqa0w/orBm2/StLBMCU7X 26slFhFX0ezCbi0PYE/9WfujO9qNLqMlmLGP8VEy37StPXOqFpqpT/l6YmuWK2LW3Zq5 0WNQ== X-Gm-Message-State: ALoCoQl+x93ATbDKzQxm0WI6Kad52CRFj5W3ZXBJTFtKBVwIhuN8BpO1qPtRRhLF3E9jBMStRN+c X-Received: by 10.180.88.37 with SMTP id bd5mr13271222wib.82.1443130162178; Thu, 24 Sep 2015 14:29:22 -0700 (PDT) Received: from xps13.localnet (136-92-190-109.dsl.ovh.fr. [109.190.92.136]) by smtp.gmail.com with ESMTPSA id p1sm136655wif.7.2015.09.24.14.29.21 (version=TLSv1.2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Thu, 24 Sep 2015 14:29:21 -0700 (PDT) From: Thomas Monjalon To: Arnon Warshavsky Date: Thu, 24 Sep 2015 23:28:15 +0200 Message-ID: <1510891.FFAirmlrxl@xps13> Organization: 6WIND User-Agent: KMail/4.14.10 (Linux/4.1.6-1-ARCH; KDE/4.14.11; x86_64; ; ) In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: 7Bit Content-Type: text/plain; charset="us-ascii" Cc: dev@dpdk.org Subject: Re: [dpdk-dev] Missing prefetch in non-vector rx function X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 24 Sep 2015 21:29:22 -0000 Hi, 2015-09-24 22:10, Arnon Warshavsky: > Moving from dpdk 1.5 to 2.0 we observed a PPS performance degradation of > ~30%. > After chasing this one for a while we found the problem: > > A) Between the 2 versions rte_mbuf was increased in size from 1 to 2 cache > lines. > B) The standard (non-vector) rx function does not perform a prefetch for > the 2nd cache line of the mbuf (I see this bug exists in 2.1 as well) and > it touches it setting the next pointer to NULL. > I tested it in ixgbe, but it looks like it exists in all drivers in the > *_rx_recv_pkts() and *_rx_recv_scattered_pkts() functions. > Once added the prefetch for the 2nd line, we were back in our previous > numbers. > > I believe this one slipped under the radar as the vector mode is now the > default. > We stumbled into it because we work in non-vector mode due to a different > mempool bug in 2.0 which sometimes crashes the application upon port stop. Big thanks for this double bug report! > I have 2 questions > 1) > Could anyone tell if the regression tests are comparing performance while > building DPDK with the default set of flags alone, or are multiple options > examined? There is no official regression test of performance. Though Intel is probably monitoring it for their hardware. By the way, it would be a good improvement to have such standard benchmark in DTS or elsewhere. > 2) > How are issues like that being tracked and later associated to a patch? In general, it is followed by discussion and a patch on this mailing list. The patch must track the fixed issue in the release notes. In order to give better exposure of current bugs we could instantiate a bug tracker. I think it's time to think about it seriously. Let's discuss about the possible solutions in another thread. Thanks again to you and all the Qwilt team. PS: it would be nice to hear about your DPDK deployment and results