Hi Jesse,
Yeah that was the tcpdump for ingress port.
Kindly find the tcpdump for egress port in namespace as well-
[root@rhel7-23 ~]# ip netns exec
qrouter-223d91ae-3025-4070-83d0-63faa58d819b tcpdump -ennqi qg-ab10ec1d-2b
-c 30 host 1.1.1.34
tcpdump: verbose output suppressed, use -v or -vv for full protocol decode
listening on qg-ab10ec1d-2b, link-type EN10MB (Ethernet), capture size
65535 bytes
22:45:25.831965 fa:16:3e:86:37:b2 > 34:40:b5:c8:0a:3c, IPv4, length 74:
1.1.4.92.59169 > 1.1.1.34.5001: tcp 0
22:45:25.832307 34:40:b5:c8:0a:3c > fa:16:3e:86:37:b2, IPv4, length 60:
1.1.1.34.5001 > 1.1.4.92.59169: tcp 0
22:45:30.845157 fa:16:3e:86:37:b2 > 34:40:b5:c8:0a:3c, ARP, length 42:
Request who-has 1.1.1.34 tell 1.1.4.92, length 28
22:45:30.845542 34:40:b5:c8:0a:3c > fa:16:3e:86:37:b2, ARP, length 60:
Reply 1.1.1.34 is-at 34:40:b5:c8:0a:3c, length 46
22:45:42.941753 fa:16:3e:86:37:b2 > 34:40:b5:c8:0a:3c, IPv4, length 74:
1.1.4.92.59170 > 1.1.1.34.5001: tcp 0
22:45:42.942152 34:40:b5:c8:0a:3c > fa:16:3e:86:37:b2, IPv4, length 74:
1.1.1.34.5001 > 1.1.4.92.59170: tcp 0
22:45:42.942635 fa:16:3e:86:37:b2 > 34:40:b5:c8:0a:3c, IPv4, length 66:
1.1.4.92.59170 > 1.1.1.34.5001: tcp 0
22:45:42.942645 fa:16:3e:86:37:b2 > 34:40:b5:c8:0a:3c, IPv4, length 90:
1.1.4.92.59170 > 1.1.1.34.5001: tcp 24
22:45:42.942649 fa:16:3e:86:37:b2 > 34:40:b5:c8:0a:3c, IPv4, length 12648:
1.1.4.92.59170 > 1.1.1.34.5001: tcp 12582
22:45:42.942844 34:40:b5:c8:0a:3c > fa:16:3e:86:37:b2, IPv4, length 66:
1.1.1.34.5001 > 1.1.4.92.59170: tcp 0
22:45:42.942853 34:40:b5:c8:0a:3c > fa:16:3e:86:37:b2, IPv4, length 66:
1.1.1.34.5001 > 1.1.4.92.59170: tcp 0
22:45:42.943393 fa:16:3e:86:37:b2 > 34:40:b5:c8:0a:3c, IPv4, length 7056:
1.1.4.92.59170 > 1.1.1.34.5001: tcp 6990
22:45:42.943404 fa:16:3e:86:37:b2 > 34:40:b5:c8:0a:3c, IPv4, length 8454:
1.1.4.92.59170 > 1.1.1.34.5001: tcp 8388
22:45:42.943583 34:40:b5:c8:0a:3c > fa:16:3e:86:37:b2, IPv4, length 66:
1.1.1.34.5001 > 1.1.4.92.59170: tcp 0
22:45:42.943592 34:40:b5:c8:0a:3c > fa:16:3e:86:37:b2, IPv4, length 66:
1.1.1.34.5001 > 1.1.4.92.59170: tcp 0
22:45:42.943961 fa:16:3e:86:37:b2 > 34:40:b5:c8:0a:3c, IPv4, length 8454:
1.1.4.92.59170 > 1.1.1.34.5001: tcp 8388
22:45:42.943975 fa:16:3e:86:37:b2 > 34:40:b5:c8:0a:3c, IPv4, length 8454:
1.1.4.92.59170 > 1.1.1.34.5001: tcp 8388
22:45:42.944146 34:40:b5:c8:0a:3c > fa:16:3e:86:37:b2, IPv4, length 66:
1.1.1.34.5001 > 1.1.4.92.59170: tcp 0
22:45:42.944151 34:40:b5:c8:0a:3c > fa:16:3e:86:37:b2, IPv4, length 66:
1.1.1.34.5001 > 1.1.4.92.59170: tcp 0
22:45:42.944462 fa:16:3e:86:37:b2 > 34:40:b5:c8:0a:3c, IPv4, length 8454:
1.1.4.92.59170 > 1.1.1.34.5001: tcp 8388
22:45:42.944475 fa:16:3e:86:37:b2 > 34:40:b5:c8:0a:3c, IPv4, length 9852:
1.1.4.92.59170 > 1.1.1.34.5001: tcp 9786
22:45:42.944637 34:40:b5:c8:0a:3c > fa:16:3e:86:37:b2, IPv4, length 66:
1.1.1.34.5001 > 1.1.4.92.59170: tcp 0
22:45:42.944647 34:40:b5:c8:0a:3c > fa:16:3e:86:37:b2, IPv4, length 66:
1.1.1.34.5001 > 1.1.4.92.59170: tcp 0
22:45:42.944917 fa:16:3e:86:37:b2 > 34:40:b5:c8:0a:3c, IPv4, length 21036:
1.1.4.92.59170 > 1.1.1.34.5001: tcp 20970
22:45:42.945089 34:40:b5:c8:0a:3c > fa:16:3e:86:37:b2, IPv4, length 66:
1.1.1.34.5001 > 1.1.4.92.59170: tcp 0
22:45:42.945420 fa:16:3e:86:37:b2 > 34:40:b5:c8:0a:3c, IPv4, length 22434:
1.1.4.92.59170 > 1.1.1.34.5001: tcp 22368
22:45:42.945441 fa:16:3e:86:37:b2 > 34:40:b5:c8:0a:3c, IPv4, length 1464:
1.1.4.92.59170 > 1.1.1.34.5001: tcp 1398
22:45:42.945943 34:40:b5:c8:0a:3c > fa:16:3e:86:37:b2, IPv4, length 66:
1.1.1.34.5001 > 1.1.4.92.59170: tcp 0
22:45:42.945947 34:40:b5:c8:0a:3c > fa:16:3e:86:37:b2, IPv4, length 66:
1.1.1.34.5001 > 1.1.4.92.59170: tcp 0
22:45:42.946234 fa:16:3e:86:37:b2 > 34:40:b5:c8:0a:3c, IPv4, length 22434:
1.1.4.92.59170 > 1.1.1.34.5001: tcp 22368
30 packets captured
39 packets received by filter
0 packets dropped by kernel
The packets are STILL OFFLOADED at egress port within namespace.
[root@rhel7-23 ~]# ip netns exec
qrouter-223d91ae-3025-4070-83d0-63faa58d819b ethtool -k qg-ab10ec1d-2b
Features for qg-ab10ec1d-2b:
rx-checksumming: off [fixed]
tx-checksumming: on
tx-checksum-ipv4: off [fixed]
tx-checksum-ip-generic: on
tx-checksum-ipv6: off [fixed]
tx-checksum-fcoe-crc: off [fixed]
tx-checksum-sctp: off [fixed]
scatter-gather: on
tx-scatter-gather: on
tx-scatter-gather-fraglist: on
tcp-segmentation-offload: on
tx-tcp-segmentation: on
tx-tcp-ecn-segmentation: on
tx-tcp6-segmentation: on
udp-fragmentation-offload: on
generic-segmentation-offload: on
generic-receive-offload: on
large-receive-offload: off [fixed]
rx-vlan-offload: off [fixed]
tx-vlan-offload: on
ntuple-filters: off [fixed]
receive-hashing: off [fixed]
[root@rhel7-23 ~]# ip netns exec
qrouter-223d91ae-3025-4070-83d0-63faa58d819b ifconfig qg-ab10ec1d-2b
qg-ab10ec1d-2b: flags=4163<UP,BROADCAST,RUNNING,MULTICAST> mtu 1500
inet 1.1.4.92 netmask 255.255.0.0 broadcast 1.1.255.255
inet6 fe80::f816:3eff:fe86:37b2 prefixlen 64 scopeid 0x20<link>
inet6 2002:976:2c08:200:f816:3eff:fe86:37b2 prefixlen 64 scopeid
0x0<global>
ether fa:16:3e:86:37:b2 txqueuelen 0 (Ethernet)
RX packets 6548056 bytes 436574568 (416.3 MiB)
RX errors 0 dropped 6101 overruns 0 frame 0
TX packets 6565538 bytes 218968595312 (203.9 GiB)
TX errors 0 dropped 0 overruns 0 carrier 0 collisions 0
Details of External Bridge
[root@rhel7-23 ~]# ifconfig br-ex
br-ex: flags=4163<UP,BROADCAST,RUNNING,MULTICAST> mtu 1500
inet 1.1.1.23 netmask 255.255.0.0 broadcast 1.1.255.255
inet6 2002:976:2c08:200:a236:9fff:fe07:2381 prefixlen 64 scopeid
0x0<global>
inet6 fe80::a236:9fff:fe07:2381 prefixlen 64 scopeid 0x20<link>
ether a0:36:9f:07:23:81 txqueuelen 0 (Ethernet)
RX packets 5304862 bytes 569468446 (543.0 MiB)
RX errors 0 dropped 6108 overruns 0 frame 0
TX packets 1086769 bytes 70618710682 (65.7 GiB)
TX errors 0 dropped 0 overruns 0 carrier 0 collisions 0
[root@rhel7-23 ~]# ovs-vsctl show
7f2dc796-5e5c-4e73-b976-43b953b7255c
Bridge br-ex
Port br-ex
Interface br-ex
type: internal
Port "eth1"
Interface "eth1"
Port "qg-ab10ec1d-2b"
Interface "qg-ab10ec1d-2b"
type: internal
Bridge br-tun
fail_mode: secure
Port patch-int
Interface patch-int
type: patch
options: {peer=patch-tun}
Port br-tun
Interface br-tun
type: internal
Port "vxlan-0a0a0a1e"
Interface "vxlan-0a0a0a1e"
type: vxlan
options: {csum="true", df_default="true", in_key=flow,
local_ip="10.10.10.23", out_key=flow, remote_ip="10.10.10.30"}
Port "vxlan-0a0a0a15"
Interface "vxlan-0a0a0a15"
type: vxlan
options: {csum="true", df_default="true", in_key=flow,
local_ip="10.10.10.23", out_key=flow, remote_ip="10.10.10.21"}
Port "vxlan-0a0a0a19"
Interface "vxlan-0a0a0a19"
type: vxlan
options: {csum="true", df_default="true", in_key=flow,
local_ip="10.10.10.23", out_key=flow, remote_ip="10.10.10.25"}
Bridge br-int
fail_mode: secure
Port "tap5ba622a6-f5"
tag: 1
Interface "tap5ba622a6-f5"
type: internal
Port int-br-ex
Interface int-br-ex
type: patch
options: {peer=phy-br-ex}
Port "qr-85495bc6-fe"
tag: 85
Interface "qr-85495bc6-fe"
type: internal
Port "tape2373e56-80"
tag: 85
Interface "tape2373e56-80"
type: internal
Port br-int
Interface br-int
type: internal
Port patch-tun
Interface patch-tun
type: patch
options: {peer=patch-int}
ovs_version: "2.3.0"
Both the egress port of Namespace and physical NIC for external network
(eth1) are mapped to BR-EX, however, BR-EX has 1500 MTU.
Do you think that is affecting, even with TSO ON for eth1?
Thanks and regards,
Piyush Raman
Mail: [email protected]
From: Jesse Gross <[email protected]>
To: Piyush R Srivastava1/India/IBM@IBMIN
Cc: [email protected], Gowtham Narasimhaiah/India/IBM@IBMIN,
Mala Anand <[email protected]>
Date: 12/18/2015 10:36 PM
Subject: Re: [ovs-discuss] TSO not working for VM iperf data packets.
On Fri, Dec 18, 2015 at 11:17 AM, Piyush R Srivastava1
<[email protected]> wrote:
> Hi,
>
> Problem-
>
> We have a testbed OpenStack setup which uses VXLAN Tunneling for
connecting
> the network and compute nodes.
> On doing an iperf (TCP stream) from VM (client) to external network node
> (server), we see that the TCP packets
> ( which are encapsulated by VTEP on compute node and decapsulated by VTEP
on
> network node ) are NOT getting segment offloaded (TSO)
> by the external network NIC on Network Node.
> However, TCP stream iperf packets are getting offloaded when doing iperf
> between the Network Node (client) and External Node (server)
>
> Any help on what is causing this anomaly?
I'm guessing that the tcpdump for the device inside the network
namespace is on the ingress port. I would look at the ethtool settings
for the egress since that seems to be the point at which packets are
no longer larger than MTU size.
_______________________________________________
discuss mailing list
[email protected]
http://openvswitch.org/mailman/listinfo/discuss
