On 5/2/2019 6:03 PM, Zhang, Jing C. (Nokia - CA/Ottawa) wrote:
We (our VNFs) continue to observe the same empty payload TCP (ACK)
packet drop with native firewall (see original post below) after
upgrading to Centos 7.6. This packet drop results in unacceptable TCP
performance, by that native firewall still can not be enabled in product.
_https://mail.openvswitch.org/pipermail/ovs-discuss/2018-August/047263.html_
<https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fmail.openvswitch.org%2Fpipermail%2Fovs-discuss%2F2018-August%2F047263.html&data=02%7C01%7Croseg%40vmware.com%7C99e374a533314ae804e308d6cf1e77bc%7Cb39138ca3cee4b4aa4d6cd83d9dd62f0%7C0%7C0%7C636924127135278159&sdata=CJwM1qEQ2vlVQh1Ko2wXQOtQpCLc2cVBkuSC5kB1H9k%3D&reserved=0>
$ uname -a
Linux overcloud-sriovperformancecompute-0 3.10.0-957.10.1.el7.x86_64
#1 SMP Mon Mar 18 15:06:45 UTC 2019 x86_64 x86_64 x86_64 GNU/Linux
$ ovs-vswitchd --version
ovs-vswitchd (Open vSwitch) 2.9.0
DPDK 17.11.0
The scenario: OVS provider VLAN network is used
1. in physical interface of ovs compute zero length tcp payload
packet arrives as padded to 64 bytes (and vlan tag is included in
ethernet header)
2. same packet does not appear anymore in the tcpdump taken from
tap-xyz interface (once vlan tag is removed and packet is cut by 4
bytes to 60 bytes)
Tcpdump on physical port:
00:25:24.468423 fa:16:3e:d7:bb:2c > fa:16:3e:ff:dd:29, ethertype
802.1Q (0x8100), length 2674: vlan 3837, p 0, ethertype IPv4, (tos
0x0, ttl 64, id 6893, offset 0, flags [DF], proto TCP (6), length 2656)
192.168.10.52.80 > 192.168.10.60.57576: Flags [P.], cksum 0xa013
(incorrect -> 0x772d), seq 8961:11577, ack 78, win 210, length 2616: HTTP
00:25:24.468593 fa:16:3e:ff:dd:29 > fa:16:3e:d7:bb:2c, ethertype
802.1Q (0x8100), length 60: vlan 3837, p 0, ethertype IPv4, (tos 0x0,
ttl 64, id 56318, offset 0, flags [DF], proto TCP (6), length 40)
192.168.10.60.57576 > 192.168.10.52.80: Flags [.], cksum 0x1d34
(correct), seq 78, ack 11577, win 391, length 0
00:25:24.475848 fa:16:3e:ff:dd:29 > fa:16:3e:d7:bb:2c, ethertype
802.1Q (0x8100), length 60: vlan 3837, p 0, ethertype IPv4, (tos 0x0,
ttl 64, id 56319, offset 0, flags [DF], proto TCP (6), length 40)
192.168.10.60.57576 > 192.168.10.52.80: Flags [F.], cksum 0x1d33
(correct), seq 78, ack 11577, win 391, length 0
00:25:24.480337 fa:16:3e:d7:bb:2c > fa:16:3e:ff:dd:29, ethertype
802.1Q (0x8100), length 2674: vlan 3837, p 0, ethertype IPv4, (tos
0x0, ttl 64, id 6894, offset 0, flags [DF], proto TCP (6), length 2656)
192.168.10.52.80 > 192.168.10.60.57576: Flags [P.], cksum 0xa013
(incorrect -> 0x772d), seq 8961:11577, ack 78, win 210, length 2616: HTTP
Tcpdump on vm tap interface:
00:25:24.468419 fa:16:3e:d7:bb:2c > fa:16:3e:ff:dd:29, ethertype IPv4
(0x0800), length 2670: (tos 0x0, ttl 64, id 6893, offset 0, flags
[DF], proto TCP (6), length 2656)
192.168.10.52.80 > 192.168.10.60.57576: Flags [P.], cksum 0xa013
(incorrect -> 0x772d), seq 8961:11577, ack 78, win 210, length 2616: HTTP
00:25:24.480331 fa:16:3e:d7:bb:2c > fa:16:3e:ff:dd:29, ethertype IPv4
(0x0800), length 2670: (tos 0x0, ttl 64, id 6894, offset 0, flags
[DF], proto TCP (6), length 2656)
192.168.10.52.80 > 192.168.10.60.57576: Flags [P.], cksum 0xa013
(incorrect -> 0x772d), seq 8961:11577, ack 78, win 210, length 2616: HTTP
Very straightforward to see the issue:
1. Configure neutron OVS agent to use native firewall
2. Create a pair of VMs on separate computes on provider vLAN
3. Disable TCP timestamp inside the VMs
4. Exchange TCP traffic between the VMs, e.g. http download.
5. Tcpdump on the physical and vm port, and compare.
I wonder why such obvious issue is not widely discussed?
I wonder that myself. I would indicate to me that there is some rare or
unique circumstance to your setup or
configuration.
In any case, we'll just focus on why you're seeing the issue and try to
determine the root cause. I'll probably want
to set up a remote debugging situation so I can interactively view and
troubleshoot the problem. Unfortunately,
that will probably not be doable until I return to work after May 27
because the next week and a half before I go
on PTO is pretty booked up for me.
Thanks,
- Greg
Jing
_______________________________________________
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss
_______________________________________________
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss
