From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga02.intel.com (mga02.intel.com [134.134.136.20]) by dpdk.org (Postfix) with ESMTP id 1A0748E6A for ; Mon, 19 Oct 2015 07:22:43 +0200 (CEST) Received: from orsmga002.jf.intel.com ([10.7.209.21]) by orsmga101.jf.intel.com with ESMTP; 18 Oct 2015 22:22:43 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.17,700,1437462000"; d="scan'208";a="829728953" Received: from fmsmsx105.amr.corp.intel.com ([10.18.124.203]) by orsmga002.jf.intel.com with ESMTP; 18 Oct 2015 22:22:42 -0700 Received: from fmsmsx101.amr.corp.intel.com (10.18.124.199) by FMSMSX105.amr.corp.intel.com (10.18.124.203) with Microsoft SMTP Server (TLS) id 14.3.248.2; Sun, 18 Oct 2015 22:22:32 -0700 Received: from shsmsx104.ccr.corp.intel.com (10.239.4.70) by fmsmsx101.amr.corp.intel.com (10.18.124.199) with Microsoft SMTP Server (TLS) id 14.3.248.2; Sun, 18 Oct 2015 22:22:32 -0700 Received: from shsmsx101.ccr.corp.intel.com ([169.254.1.96]) by SHSMSX104.ccr.corp.intel.com ([169.254.5.194]) with mapi id 14.03.0248.002; Mon, 19 Oct 2015 13:22:13 +0800 From: "Xie, Huawei" To: Stephen Hemminger Thread-Topic: [dpdk-dev] [PATCH v2 6/7] virtio: simple tx routine Thread-Index: AdEKLhv/LM8Lwo+zRPm3Fwi44dKytA== Date: Mon, 19 Oct 2015 05:22:12 +0000 Message-ID: References: <1443537953-23917-1-git-send-email-huawei.xie@intel.com> <1445149744-3217-1-git-send-email-huawei.xie@intel.com> <1445149744-3217-7-git-send-email-huawei.xie@intel.com> <20151018211657.46cfe771@xeon-e3> Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [10.239.127.40] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Cc: "dev@dpdk.org" Subject: Re: [dpdk-dev] [PATCH v2 6/7] virtio: simple tx routine 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: Mon, 19 Oct 2015 05:22:44 -0000 On 10/19/2015 12:17 PM, Stephen Hemminger wrote:=0A= > On Sun, 18 Oct 2015 14:29:03 +0800=0A= > Huawei Xie wrote:=0A= >=0A= >> bulk free of mbufs when clean used ring.=0A= >> shift operation of idx could be further saved if vq_free_cnt means=0A= >> free slots rather than free descriptors.=0A= >>=0A= >> Signed-off-by: Huawei Xie =0A= > Did you measure this. I finished my transmit optimizations and gets 25% p= erformance improvement=0A= > without any of these restrictions.=0A= Which restriction do you mean? For the ring layout optimization, this=0A= is the core idea. For the single segment mbuf, this is what all other=0A= PMDs assume for fastest rx/tx path.=0A= With all vhost and virtio optimizations, it could achieve approximately=0A= 3~4 times performance improvement(depending on the workload).=0A= Do you mean the indirect feature support or additional optimization not=0A= submitted? Would review your patch this week.=0A= >=0A= =0A=