My environment is in VMware
OS: CentOS 7ovs: compiled by git masterDPDK: 2.0.0qemu:2.3.0
qemu conecting ovs by vhost-userOne NIC bind to ovs 
When I send pkts from qemu to VMware`s NIC by using iperf3, Segmentation falt 
occurs
Do you need to see the backtrace?  I forget to save it, if need, I will repeat 
it


*********************RTFSC*********************------------------------------------------------------------------发件人:Gray,
 Mark D <mark.d.g...@intel.com>发送时间:2015年6月5日(星期五) 20:27收件人:钢锁0310 
<l...@dtdream.com>,d...@openvswitch.com <d...@openvswitch.com>主 题:RE: [ovs-dev] 
[PATCH] netdev-dpdk: Do not flush tx queue which is        shared among CPUs 
since it is always flushed> > When tx queue is shared among CPUS,the pkts 
always be flush in> 'netdev_dpdk_eth_send'> So it is unnecessarily for flushing 
in netdev_dpdk_rxq_recv Otherwise tx will> be accessed without lockingAre you 
seeing a specific bug or is this just to account for a device withless queues 
than pmds?> > Signed-off-by: Wei li <l...@dtdream.com>> --->  lib/netdev-dpdk.c 
| 7 +++++-->  1 file changed, 5 insertions(+), 2 deletions(-)> > diff --git 
a/lib/netdev-dpdk.c b/lib/netdev-dpdk.c index 63243d8..25e3a73> 100644> --- 
a/lib/netdev-dpdk.c> +++ b/lib/netdev-dpdk.c> @@ -892,8 +892,11 @@ 
netdev_dpdk_rxq_recv(struct netdev_rxq *rxq_,> struct dp_packet **packets,>     
 int nb_rx;> >      /* There is only one tx queue for this core.  Do not flush 
other> -     * queueus. */> -    if (rxq_->queue_id == rte_lcore_id()) {> +     
* queueus.s/queueus/queues> +     * Do not flush tx queue which is shared among 
CPUs> +     * since it is always flushed */> +    if (rxq_->queue_id == 
rte_lcore_id() &&> +  OVS_LIKELY(!dev->txq_needs_locking)) {>          
dpdk_queue_flush(dev, rxq_->queue_id);Do you see any drop in performance in a 
simple phy-phy case beforeand after this patch?>      }> > --> 1.9.5.msysgit.1> 
> > _______________________________________________> dev mailing list> 
dev@openvswitch.org> http://openvswitch.org/mailman/listinfo/dev
_______________________________________________
dev mailing list
dev@openvswitch.org
http://openvswitch.org/mailman/listinfo/dev

Reply via email to