TCP stalls, 2.6.12pre6

TCP stalls, 2.6.12pre6

[Krzysztof Halasa]

Hi,

I got this three times recently, with 2.6.12 pre6 and possibly pre5 (4?)
kernels on both sides:

intrepid is X11-server with ssh connection to defiant (X11-forwarding,
EPIC100 PCI NIC). defiant is an older notebook machine and it was running
XEmacs and Firefox with ssh/X11 (cardbus DEC 21143).
Both on the same Ethernet subnet. Both standard MTU etc.


intrepid# netstat -to

tcp 0 0 intrepid:3457 defiant:ssh  ESTABLISHED keepalive (5615.71/0/0)


defiant# netstat -to (not 100% sure about this data)

      Send-Q
tcp 0 32800 defiant:ssh intrepid:3457  ESTABLISHED keepalive (20.5/0/0)



Partial dump:

intrepid# tcpdump -r qwe -vve port not 4840

00:08:32.603003 len 1514: IP (tos 0x10, ttl  64, id 17467, offset 0,
   flags [DF], proto 6, length: 1500) defiant.ssh > intrepid.3457: .
   [bad tcp cksum 2fa (->8fbe)!] 2999401769:2999403217(1448)
   ack 1597770543 win 16022 <nop,nop,timestamp 131339306 29183805>

00:08:55.750326 len 158:  IP (tos 0x10, ttl  64, id 13187, offset 0,
   flags [DF], proto 6, length: 144) intrepid.3457 > defiant.ssh: P
   [tcp sum ok] 1:81(80) ack 0 win 18856 <nop,nop,timestamp 29224727
   131133680,nop,nop,sack sack 1 {1448:16816} >

00:08:55.750603 len 66:   IP (tos 0x10, ttl  64, id 17469, offset 0,
   flags [DF], proto 6, length: 52) defiant.ssh > intrepid.3457: .
   [tcp sum ok] 16816:16816(0) ack 81 win 16022 <nop,nop,timestamp
   131362456 29224727>

Send-Q is stuck at the fixed value. Other TCP connections (including
similar ones between the two hosts) are not affected.


Ideas?
-- 
Krzysztof Halasa

Re: TCP stalls - sack?, 2.6.12pre6

[Krzysztof Halasa]

Hi,

Another TCP stall (2.6.12pre6 on both ends):

> intrepid is X11-server with ssh connection to defiant (X11-forwarding,
> EPIC100 PCI NIC). defiant is an older notebook machine and it was running
> XEmacs and Firefox with ssh/X11 (cardbus DEC 21143).
> Both on the same Ethernet subnet. Both standard MTU etc.

[DEF] is TCP defiant:ssh
[INT] is TCP intrepid:4782

intrepid:~# netstat -to | grep 4782; tcpdump -w stall -s 1600 -i eth0
Sat Jun 11 15:55:51 CEST 2005
Recv-Q Send-Q
tcp  0      0 [INT] [DEF] ESTABLISHED keepalive (675.46/0/0)

tcpdump file basically shows (TCP already stalled):

15:56:27.1 [INT] > [DEF]: P 569644050:569644162(112) ack 3725119932 win 31164 <nop,nop,timestamp 6388700 274348581,nop,nop,sack sack 1 {1449:14985} >
15:56:27.1 [DEF] > [INT]: . ack 112 win 16022 <nop,nop,timestamp 274631570 6388700>
15:56:27.1 [INT] > [DEF]: P 112:256(144) ack 1 win 31164 <nop,nop,timestamp 6388701 274348581,nop,nop,sack sack 1 {1449:14985} >
15:56:27.1 [DEF] > [INT]: . ack 256 win 16022 <nop,nop,timestamp 274631571 6388701>
15:56:27.1 [INT] > [DEF]: P 256:336(80) ack 1 win 31164 <nop,nop,timestamp 6388710 274348581,nop,nop,sack sack 1 {1449:14985} >
15:56:27.1 [DEF] > [INT]: . ack 336 win 16022 <nop,nop,timestamp 274631579 6388710>

...


16:04:09.6 [DEF] > [INT]: . ack 35536 win 16022 <nop,nop,timestamp 275094166 6851304>
16:04:09.7 [INT] > [DEF]: P 35536:35616(80) ack 1 win 31164 <nop,nop,timestamp 6851394 274348581,nop,nop,sack sack 1 {1449:14985} >
16:04:09.7 [DEF] > [INT]: . ack 35616 win 16022 <nop,nop,timestamp 275094256 6851394>
16:05:12.7 [DEF] > [INT]: . 1:1449(1448) ack 35616 win 16022 <nop,nop,timestamp 275157275 6851394>
16:08:14.3 [INT] > [DEF]: P 35616:35760(144) ack 1 win 31164 <nop,nop,timestamp 7096034 274348581,nop,nop,sack sack 1 {1449:14985} >
16:08:14.3 [DEF] > [INT]: R 3725119932:3725119932(0) win 0


defiant:~# netstat -to | grep 4782
Recv-Q Send-Q
tcp  0  54512 [DEF] [INT] ESTABLISHED on (81.30/10/0)

and Send-Q is constant until TCP reset.

> Ideas?

-- 
Krzysztof Halasa