Hao Yu
Commercial Scale Out
IBM T.J. Watson Research Center
1101 Kitchawan Rd/Route 134, Rm 36-019
Yorktown Heights, NY 10598-0218
914-945-1854, Email: yuh@xxxxxxxxxx
----- Forwarded by Hao Yu/Watson/IBM on 10/31/2006 09:52 AM -----
Jimi
Xenidis/Watson/IB
M To
Hao Yu/Watson/IBM@IBMUS
10/31/2006 09:36 cc
AM Dan E Poff/Watson/IBM@IBMUS, David
M Daly/Watson/IBM@IBMUS, Dilma M Da
silva/Watson/IBM@IBMUS, Doron
Shiloach/Watson/IBM@IBMUS, Edi
Shmueli/Watson/IBM@IBMUS, Jack
Kouloheris/Watson/IBM@IBMUS,
Jiuxing Liu/Watson/IBM@IBMUS,
Jonghyuk Choi/Watson/IBM@IBMUS
Subject
Re: domU network problem , 10/30
progress(Document link: Hao Yu)
PLEASE, post these to the mailing list, it is important that the community
sees these issues.
I'm happy you have some networking, I have some more network stability
fixes that I'll be pushing shortly.
-JX
Hao Yu/Watson/IBM
10/30/06 05:16 PM To
Jimi Xenidis/Watson/IBM@IBMUS
cc
David M Daly/Watson/IBM@IBMUS, Edi
Shmueli/Watson/IBM@IBMUS, Jonghyuk
Choi/Watson/IBM@IBMUS, Dan E
Poff/Watson/IBM@IBMUS, Jiuxing
Liu/Watson/IBM@IBMUS, Doron
Shiloach/Watson/IBM@IBMUS, Dilma M
Da silva/Watson/IBM@IBMUS, Jack
Kouloheris/Watson/IBM@IBMUS
Subject
domU network problem , 10/30
progress(Document link: Jimi
Xenidis)
Hi Jimi,
Dan, Jiuxing and I worked together on the problem. First we have following
summaries
1. the problem is now 'domU network not working properly' :
ping-to-outside runs into error after 30 seconds ; domU hangs in nc/netcat
test when receiving long stream (MB or so). For the pint-to-outside issue,
when domU runs into error, outside can still ping to the domU.
cso238:/ # ping 9.2.78.83
PING 9.2.78.83 (9.2.78.83) 56(84) bytes of data.
64 bytes from 9.2.78.83: icmp_seq=1 ttl=64 time=28.8 ms
64 bytes from 9.2.78.83: icmp_seq=2 ttl=64 time=4.24 ms
64 bytes from 9.2.78.83: icmp_seq=3 ttl=64 time=3.81 ms
64 bytes from 9.2.78.83: icmp_seq=4 ttl=64 time=10.0 ms
64 bytes from 9.2.78.83: icmp_seq=5 ttl=64 time=5.05 ms
64 bytes from 9.2.78.83: icmp_seq=6 ttl=64 time=9.65 ms
64 bytes from 9.2.78.83: icmp_seq=7 ttl=64 time=10.0 ms
64 bytes from 9.2.78.83: icmp_seq=8 ttl=64 time=10.0 ms
64 bytes from 9.2.78.83: icmp_seq=9 ttl=64 time=3.96 ms
64 bytes from 9.2.78.83: icmp_seq=10 ttl=64 time=10.0 ms
64 bytes from 9.2.78.83: icmp_seq=11 ttl=64 time=3.89 ms
64 bytes from 9.2.78.83: icmp_seq=12 ttl=64 time=2.73 ms
ping: sendmsg: No buffer space available
ping: sendmsg: No buffer space available
ping: sendmsg: No buffer space available
ping: sendmsg: No buffer space available
ping: sendmsg: No buffer space available
ping: sendmsg: No buffer space available
ping: sendmsg: No buffer space available
2. brctl does not work properly on our environment. 'strace brctl show'
indicates 'ioctl(3, SIOCGIFBR, 0xffc381d4) = -1 EINVAL (Invalid
argument)' . And on SLES 10 environment, brctl show works fine.
In addition, how the dhcp problem is gone ? Bulent reconfiged the dhcp
server to have more show-live IP available . Now, domU can get IP
cso238:/ # ifconfig
eth0 Link encap:Ethernet HWaddr 00:16:3E:F9:BB:B3
inet addr:9.2.78.238 Bcast:9.2.78.255 Mask:255.255.255.0
UP BROADCAST NOTRAILERS RUNNING MULTICAST MTU:1500 Metric:1
RX packets:39 errors:0 dropped:0 overruns:0 frame:0
TX packets:19 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:3884 (3.7 Kb) TX bytes:2508 (2.4 Kb)
lo Link encap:Local Loopback
inet addr:127.0.0.1 Mask:255.0.0.0
UP LOOPBACK RUNNING MTU:16436 Metric:1
RX packets:20 errors:0 dropped:0 overruns:0 frame:0
TX packets:20 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:0
RX bytes:1256 (1.2 Kb) TX bytes:1256 (1.2 Kb)
We thought the 'ping error' problem seemed non trivial.
Regards,
Hao
Hao Yu
Commercial Scale Out
IBM T.J. Watson Research Center
1101 Kitchawan Rd/Route 134, Rm 36-019
Yorktown Heights, NY 10598-0218
914-945-1854, Email: yuh@xxxxxxxxxx
_______________________________________________
Xen-users mailing list
Xen-users@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-users
|