From patchwork Wed Feb 12 09:24:54 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Joyce Kong X-Patchwork-Id: 65756 Return-Path: X-Original-To: patchwork@inbox.dpdk.org Delivered-To: patchwork@inbox.dpdk.org Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 8D671A0530; Wed, 12 Feb 2020 10:25:36 +0100 (CET) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id BD0811F28; Wed, 12 Feb 2020 10:25:35 +0100 (CET) Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by dpdk.org (Postfix) with ESMTP id 2E7891B53 for ; Wed, 12 Feb 2020 10:25:34 +0100 (CET) Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 6F2CD30E; Wed, 12 Feb 2020 01:25:33 -0800 (PST) Received: from net-arm-thunderx2-03.shanghai.arm.com (net-arm-thunderx2-03.shanghai.arm.com [10.169.41.185]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id D48C83F6CF; Wed, 12 Feb 2020 01:25:30 -0800 (PST) From: Joyce Kong To: dev@dpdk.org Cc: nd@arm.com, maxime.coquelin@redhat.com, tiwei.bie@intel.com, zhihong.wang@intel.com, thomas@monjalon.net, jerinj@marvell.com, yinan.wang@intel.com, honnappa.nagarahalli@arm.com, gavin.hu@arm.com Date: Wed, 12 Feb 2020 17:24:54 +0800 Message-Id: <20200212092456.29433-1-joyce.kong@arm.com> X-Mailer: git-send-email 2.17.1 Subject: [dpdk-dev] [PATCH v1 0/2] one way barrier for split vring idx 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" The similar changes for the packed ring were measured 10% performance lift and were merged. [1] In principle, less restrictive barriers generate better performance. However, no real performance lift was measured with the split ring on the limited number of existing HW implementations, the reason may be they are not in the critical path. To keep consistent with the barrier usage in the packed ring implementation and be future-proof, we still believe the patches make sense, we are looking forward to verify the performance when new HWs are available. [1] https://patchwork.dpdk.org/cover/59283/ Joyce Kong (2): virtio: one way barrier for split vring used idx virtio: one way barrier for split vring avail idx drivers/net/virtio/virtio_ethdev.c | 9 ++-- drivers/net/virtio/virtio_ring.h | 2 +- drivers/net/virtio/virtio_rxtx.c | 46 ++++++++-------- drivers/net/virtio/virtio_rxtx_simple_neon.c | 5 +- drivers/net/virtio/virtio_rxtx_simple_sse.c | 5 +- .../net/virtio/virtio_user/virtio_user_dev.c | 8 +-- drivers/net/virtio/virtqueue.c | 2 +- drivers/net/virtio/virtqueue.h | 53 ++++++++++++++++--- lib/librte_vhost/virtio_net.c | 19 +++---- 9 files changed, 90 insertions(+), 59 deletions(-)