trying
dpdk-2.2.0 or less.
As Ferruh replied earlier, refer to dpdk version what INSTALL.DPDK.md
suggests.
Thanks,
Gowrishankar
./configure --prefix=/usr --sysconfdir=/etc --localstatedir=/var
--with-dpdk=/home/ubuntu/raja1/dpdk-2.0.0/x86_64-native-linuxapp-gcc/
--enable-ssl
You can try turning on verbosity for related components within ovs. Run
vswitchd along with -v.
Use ovs-appct vlog/set to point where to redirect addn info. vlog/list
could help you to pick
what you want. netdev_vport, dpdk may give some hints.
Thanks,
Gowrishankar
On Thursday 07 April 2016
warning as I see 2.5.0 is to check out it from service
br (branch-2.5)
and continue your work. Recently, vhost user send path to guest is fixed
for min one txq.
Thanks,
Gowrishankar
Dpdk version: 2.2.0
Qemu verion : 2.2.1
vm ips are 192.168.0.93/24 and 192.168.0.91/24; os is Centos 6.7
igure: error: cannot link with dpdk*"
You need to have CONFIG_RTE_BUILD_COMBINE_LIBS=y while building dpdk.
Regards,
Gowrishankar
___
discuss mailing list
discuss@openvswitch.org
http://openvswitch.org/mailman/listinfo/discuss
capture packets.
--
Regards,
Gowrishankar M
___
discuss mailing list
discuss@openvswitch.org
http://openvswitch.org/mailman/listinfo/discuss
;
Interface "eth0"
etho type is not "dpdkvhostuser". Are you sure you have run
dpdk_nic_bind.py from dpdk build ?
--
Regards,
Gowrishankar M
___
discuss mailing list
discuss@openvswitch.org
http://openvswitch.org/mailman/listinfo/discuss
On Monday 24 August 2015 01:05 PM, gowrishankar wrote:
Hi,
I could get build done and dpdk 2.1.0 running along with ovs 2.4.0.
In case you wish to refer the changes I applied (including -ldpdk):
1. configure script to check libdpdk.a (not libintel_dpdk.a).
2. include
s checksum
issue here so that, if anyone have already fixed, could you please share
your finding.
Regards,
Gowrishankar
On Saturday 22 August 2015 10:17 PM, Gray, Mark D wrote:
Hello,
could you please tell me if OVS is already compatibile with recently released
DPDK 2.1.0? Or what sould I do to ma
ostforce: chardev
"char1" went up
Could you stop network manager in your OS and try again ?
Thanks,
Gowrishankar
I set the br0 10.0.0.2/24 and virtual machine eth0 10.0.0.1/24
But they can't ping each other
# ovs-ofctl dump-flows br0
NXST_FLOW reply (xid=0x4):
cookie=0x0, du
ifconfig br0 mtu 1600 works expectedly. Even ip link set command too.
You might need to check on why ifconfig fails to update br0. dmesg ?
Thanks,
Gowrishankar
On Friday 24 July 2015 09:26 PM, Dave Waters wrote:
Hi,
I am unable to increase the MTU of the bridge port (the internal port)
to
spewing out
packets. Any ideas, anybody?
Warm regards,
Dave
--
Regards,
Gowrishankar M
___
discuss mailing list
discuss@openvswitch.org
http://openvswitch.org/mailman/listinfo/discuss
ncase of virtio pmd driver case ?
Appreciating your help to more understand on this perf problem.
Regards,
Gowrishankar
___
discuss mailing list
discuss@openvswitch.org
http://openvswitch.org/mailman/listinfo/discuss
ith MTU.
https://www.mail-archive.com/discuss@openvswitch.org/msg13912.html
It may help. Then I thought of making use of upstream multiqueue support
in dpdk but
it seems not yet supported yet in ovs. I am also curious to find
ovs-dpdk tuned for more
perf than ovs.
Regards,
Gowrishankar
On
Hello list,
I would like to know if ovs today (master) is ready (or in plan to get
ready)
to support multiqueue for virtio-net driver with vhost-user backend.
There is
an upstream dpdk patch which leverages VMDq pool and RSS in NIC and creates
multiqueue per virtio port in guest.
http://d
On Thursday 25 June 2015 01:31 PM, Dongjun wrote:
As following topology, two VMs communicate via VXLAN tunnel.
TCP pkts may be droped for exceeding the MTU of host DPDK port in br2.
Now I can change the VMs' MTU from default to smaller to accommodate
the traffics, it works well.
The way I have
On Wednesday 17 June 2015 08:57 PM, Traynor, Kevin wrote:
Hi ,
We have brought up topology as below with OpenVSwitch 2.3.9 /DPDK enabled .
Sending 128 bytes of frame as bidirectional from Agilent N2X(traffic
generator) and observed that , in OVS we have found many errors(marked in red
colour
Checking code, I see -m helping me to see all fields wildcarded by flow.
Anyway, helpful to know if there is any other setting controlling it.
On Friday 12 June 2015 04:22 PM, gowrishankar wrote:
Hi,
Sometimes back, while checking datapath flows for my bridge br0, I had
noticed src and dst
recirc_id(0),in_port(2),eth_type(0x86dd),ipv6(frag=no), packets:245,
bytes:15190, used:6.644s, actions:3
Any help to get back same verbose level in dpif/dump-flows is appreciated.
--
Regards,
Gowrishankar M
___
discuss mailing list
discuss@openvswitch.org
so I'm not sure if the issue still exists, or if this
is relevant to your set up.
--
Regards,
Gowrishankar M
___
discuss mailing list
discuss@openvswitch.org
http://openvswitch.org/mailman/listinfo/discuss
-flows also report
0 packets).
I am looking for any one opinion on this if dpdkhost0 mac reported is
expected
(and to quickly debug any other problem there).
I am on qemu 2.1.0 as well.
Thank you,
Gowrishankar
On Friday 05 June 2015 10:32 PM, Andrey Korolyov wrote:
On Fri, Jun 5, 2015 at 11
90
Compiled May 19 2015 04:27:58
DB Schema 7.12.1
dpdk-2.0.0
Any help/pointer to further diagnose is greatly appreciated.
--
Regards,
Gowrishankar M
___
discuss mailing list
discuss@openvswitch.org
http://openvswitch.org/mailman/listinfo/discuss
tcpdump from host on guest's vnic could help ? See if 3way handshake
completes.
Also, check if csum correct on packets from guest (tcpdump -vvv).
Regards,
Gowrishankar
On Thursday 21 May 2015 10:37 AM, 钢锁0310 wrote:
ovs log:
2015-05-21T04:46:37.941Z|00023|connmgr|INFO|br0<-
"manager_options":["set",[]],"bridges":["uuid","d64a8e1a-0e69-4cbd-9081-332e5a4e04e6"],"statistics":["map",[]],"other_config":["map",[]],"cur_cfg":1,"next_cfg":2,"iface_types":[&qu
You would need tunnel endpoints to complete tunnel setup.
add-port br0 tep0 -- set interface tep0 type=internal (in each switch)
Assign a private subnet IP on tep0 (different than 192.168.1.x) and then
you would see GRE encapsulated packets
on pinging tep0.
Regards,
Gowrishankar
On
On Monday 27 April 2015 07:56 PM, Pyotr Bryzgalov wrote:
Thank you Gowrishankar,
I had MTU 1500. I set tap interfaces’ MTU to 1462 and it worked for
GRE tunnel!
Unfortunately, setting MTU to 1458 (1500 - 14 - 20 - 8) does’t work
for VXLAN. (8 bytes is vxlan header size)
In case of GRE
streams only the first packet reaches
destination and all subsequent packets get lost.
Make sure you have configured right MTU (1462) for docker bridge and
container interfaces.
Hope this one http://wiredcraft.com/blog/multi-host-docker-network/
helps you.
Thx,
Gowrishankar
For both
You may try "service openvswitch-switch start" and "service
openvswitch-controller start"
Regards,
Gowrishankar
On Monday 30 March 2015 03:53 PM, Amal KAMMOUN wrote:
Thank you for your response.
But when I try " /etc/init.d/ovsdb-server start ", I g
27 matches
Mail list logo
