Re: [ovs-discuss] Efficiency of OVN packet forwarding

2016-08-03 Thread Justin Pettit
> On Aug 3, 2016, at 6:48 PM, Wilence Yao wrote: > > Hi, > I'm studying OVN these days. I found that ovn-controller issue too match flow > table to br-int in compute node. Number of flows it too large。 > > The question is that those flow tables may reduce efficiency of flow match in > packet

[ovs-discuss] Efficiency of OVN packet forwarding

2016-08-03 Thread Wilence Yao
Hi, I'm studying OVN these days. I found that ovn-controller issue too match flow table to br-int in compute node. Number of flows it too large。 The question is that those flow tables may reduce efficiency of flow match in packet forwarding. I have heard that efficiency reduce heavily when num

Re: [ovs-discuss] vSwitch simple config - no ping between same br ports

2016-08-03 Thread Justin Pettit
> On Aug 2, 2016, at 10:21 AM, José Tomás@Home wrote: > > So far I search I always do find > "master ovs-system state UP" > > at ip addr show where I get > "master ovs-system state DOWN" > > help needed to understand why this... > > By the way I'm working with fresh installs for Ubuntu 14.04

Re: [ovs-discuss] OpenvSwitch/KVM/Cisco-ASAv issue

2016-08-03 Thread Ben Pfaff
On Wed, Aug 03, 2016 at 11:09:41AM -0400, Carl Wilkerson wrote: > Two identical Cisco UCS 240 servers. OpenvSwitch (version 2.4.0) and KVM > running on CentOS 6.8. We've recently received a number of reports related to LACP and interoperation with Cisco equipment. These may be a regression since

Re: [ovs-discuss] ovs-vswitchd tcp:openvswitch-db:6640

2016-08-03 Thread Justin Pettit
> On Aug 3, 2016, at 7:19 AM, Serguei Bezverkhi (sbezverk) > wrote: > > Hello, > > I need to run openvswitch in the environment where there is no way to use > fixed ip addresses and dns names must be used to discover the actual location > (ip address) of database process. Here is the command

[ovs-discuss] OpenvSwitch/KVM/Cisco-ASAv issue

2016-08-03 Thread Carl Wilkerson
I have an interesting issue. My current setup is as follows: Two identical Cisco UCS 240 servers. OpenvSwitch (version 2.4.0) and KVM running on CentOS 6.8. *OVS setup:* Linux created bond0 (physical eth0 and eth1 LACP pair) connected to ovs bridge (br0) configured as a trunk allowing all confi

[ovs-discuss] ovs-vswitchd tcp:openvswitch-db:6640

2016-08-03 Thread Serguei Bezverkhi (sbezverk)
Hello, I need to run openvswitch in the environment where there is no way to use fixed ip addresses and dns names must be used to discover the actual location (ip address) of database process. Here is the command line I used: ovs-vswitchd tcp:openvswitch-db:6640 where openvswitch-db is the dns

[ovs-discuss] 答复: help - ovs 2.5 flow statistics issues

2016-08-03 Thread awan...@masonlive.gmu.edu
Hi, Bhanu, In my case, I don't think it is the rate issue. I sent the traffic at a very low rate (~0.7 Mbps) and the statistics are still not correct. Also, in my trace for the test, traffic belonging 10.0.0.0/8 -> 81.0.0.0/8 only serves a small portion. The total statistics combined together

Re: [ovs-discuss] unable to map backing store for hugepages: Cannot allocate memory

2016-08-03 Thread Charlie Li
Thanks Mark - I get VM console working now. Charlie On Wed, Aug 3, 2016 at 11:06 AM, Kavanagh, Mark B wrote: > > > >Thanks Mark, > > > >That is a very good point. > > > >Just found out I forgot to add "--socket-mem 1024,0" after increasing the > page number from 1 > >to 4. > > > >With "sudo ./o

Re: [ovs-discuss] unable to map backing store for hugepages: Cannot allocate memory

2016-08-03 Thread Kavanagh, Mark B
> >Thanks Mark, > >That is a very good point. > >Just found out I forgot to add "--socket-mem 1024,0" after increasing the page >number from 1 >to 4. > >With "sudo ./ovs-vswitchd --dpdk -c 0x1 -n 4 --socket-mem 1024,0 -- >unix:$DB_SOCK --pidfile - >-detach", the problem is gone. > >Now I got: > >

Re: [ovs-discuss] unable to map backing store for hugepages: Cannot allocate memory

2016-08-03 Thread Charlie Li
Thanks Mark, That is a very good point. Just found out I forgot to add "--socket-mem 1024,0" after increasing the page number from 1 to 4. With "sudo ./ovs-vswitchd --dpdk -c 0x1 -n 4 --socket-mem 1024,0 -- unix:$DB_SOCK --pidfile --detach", the problem is gone. Now I got: qemu-system-x86_64:

[ovs-discuss] ovs-vswitchd tcp:openvswitch-db:6640

2016-08-03 Thread Serguei Bezverkhi (sbezverk)
Hello, I need to run openvswitch in the environment where there is no way to use fixed ip addresses and dns names must be used to discover the actual location (ip address) of database process. Here is the command line I used: ovs-vswitchd tcp:openvswitch-db:6640 where openvswitch-db is the dns

Re: [ovs-discuss] unable to map backing store for hugepages: Cannot allocate memory

2016-08-03 Thread Kavanagh, Mark B
> >Thanks Sugesh for your response. > >I have 4 1G hugepages allocated and the VM is requesting 3G memory. > >$ cat /proc/cmdline >BOOT_IMAGE=/vmlinuz-4.5.7-200.fc23.x86_64 >root=/dev/mapper/fedora--desktop-root ro >rd.lvm.lv=fedora-desktop/root rd.lvm.lv=fedora-desktop/swap >default_hugepagesz=1

Re: [ovs-discuss] unable to map backing store for hugepages: Cannot allocate memory

2016-08-03 Thread Charlie Li
Thanks Sugesh for your response. I have 4 1G hugepages allocated and the VM is requesting 3G memory. $ cat /proc/cmdline BOOT_IMAGE=/vmlinuz-4.5.7-200.fc23.x86_64 root=/dev/mapper/fedora--desktop-root ro rd.lvm.lv=fedora-desktop/root rd.lvm.lv=fedora-desktop/swap default_hugepagesz=1G hugepagesz=

Re: [ovs-discuss] help - ovs 2.5 flow statistics issues

2016-08-03 Thread Bodireddy, Bhanuprakash
>-Original Message- >From: awan...@masonlive.gmu.edu [mailto:awan...@masonlive.gmu.edu] >Sent: Monday, August 1, 2016 3:49 PM >To: Bodireddy, Bhanuprakash ; >discuss@openvswitch.org >Subject: 答复: help - ovs 2.5 flow statistics issues > >Thank you, Bhanu, for your verification. I really appr