https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=243392
--- Comment #7 from Andriy Gapon <a...@freebsd.org> ---
When I run tcpdump on the other end, there is no effect on the speed.
There are some potentially interesting snippets in the capture.
Here is one where 10.25.200.199 is the vmx side and 10.180.0.51 is the other
host that sends data to the vmx host:
115 02:16:28.787281 IP 10.180.0.51.17739 > 10.25.200.199.22: Flags [.], seq
81774:83160, ack 1, win 1026, options [nop,nop,TS val 3595053000 ecr
1184721692], length 1386
116 02:16:28.787284 IP 10.180.0.51.17739 > 10.25.200.199.22: Flags [.], seq
83160:84546, ack 1, win 1026, options [nop,nop,TS val 3595053000 ecr
1184721692], length 1386
117 02:16:28.787304 IP 10.180.0.51.17739 > 10.25.200.199.22: Flags [.], seq
84546:85932, ack 1, win 1026, options [nop,nop,TS val 3595053000 ecr
1184721692], length 1386
118 02:16:28.787307 IP 10.180.0.51.17739 > 10.25.200.199.22: Flags [.], seq
85932:87318, ack 1, win 1026, options [nop,nop,TS val 3595053000 ecr
1184721692], length 1386
119 02:16:28.883545 IP 10.25.200.199.22 > 10.180.0.51.17739: Flags [.], ack
83160, win 2192, options [nop,nop,TS val 1184721792 ecr 3595053000], length 0
120 02:16:28.883576 IP 10.180.0.51.17739 > 10.25.200.199.22: Flags [.], seq
87318:88704, ack 1, win 1026, options [nop,nop,TS val 3595053097 ecr
1184721792], length 1386
121 02:16:28.887035 IP 10.25.200.199.22 > 10.180.0.51.17739: Flags [.], ack
83160, win 2192, options [nop,nop,TS val 1184721792 ecr 3595053000,nop,nop,sack
1 {87318:88704}], length 0
122 02:16:29.336381 IP 10.180.0.51.17739 > 10.25.200.199.22: Flags [.], seq
83160:84546, ack 1, win 1026, options [nop,nop,TS val 3595053549 ecr
1184721792], length 1386
My reading of the above.
Packets 115-118: data packets
Packet 119: ack for packet 115
Packet 120: another data packet
Packet 121: appears to be exact duplicate of the packet 119 (ack)
Packet 122: looks like a retransmission of packet 116 after a noticeable delay
(0.44s)
Well, on another look, packets 119 and 121 are not exactly the same.
121 has this "sack 1 {87318:88704}" that 119 does not have.
And it seems like packet 121 is what "confuses" the sending side as the pause
and retransmission.
Not a TCP expert, so don't know if anything is wrong here.
--
You are receiving this mail because:
You are the assignee for the bug.
_______________________________________________
freebsd-net@freebsd.org mailing list
https://lists.freebsd.org/mailman/listinfo/freebsd-net
To unsubscribe, send any mail to "freebsd-net-unsubscr...@freebsd.org"
