From mboxrd@z Thu Jan 1 00:00:00 1970 From: Huawei Xie Subject: [PATCH v2 0/2] vhost: numa aware allocation of vhost device and queues Date: Fri, 19 Jun 2015 00:59:54 +0800 Message-ID: <1434646796-23101-1-git-send-email-huawei.xie@intel.com> References: <1433474005-597-1-git-send-email-huawei.xie@intel.com> To: dev@dpdk.org Return-path: Received: from mga09.intel.com (mga09.intel.com [134.134.136.24]) by dpdk.org (Postfix) with ESMTP id B86C4C762 for ; Thu, 18 Jun 2015 19:00:06 +0200 (CEST) In-Reply-To: <1433474005-597-1-git-send-email-huawei.xie@intel.com> List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" The vhost device and queues should be allocated on the same numa node as vring descriptor table. When we firstly allocate the vhost device and queues, we don't know the numa node of vring descriptor table. When we receive the VHOST_SET_VRING_ADDR message, we get the numa node of vring descriptor table, we will try to reallocate vhost device and queues to the same numa node. Huawei Xie (2): use rte_malloc to allocate vhost device and queues reallocate vhost device and queues when we get the address of vring descriptor table config/common_linuxapp | 1 + lib/librte_vhost/Makefile | 4 ++ lib/librte_vhost/virtio-net.c | 112 ++++++++++++++++++++++++++++++++++++++---- mk/rte.app.mk | 4 ++ 4 files changed, 112 insertions(+), 9 deletions(-) -- 1.8.1.4