Re: Problems with ICP on 2.0-RELEASE

"David Darville" writes:

>I have a machine configured with 2 instances of squid running. Each
>squid has it's outgoing addresses bound to a different interface, and
>the caches are configured as each others siblings (with the proxy-only
>option enabled), and I have it running with V1.1.22. But now I want to
>upgrade to 2.0-RELEASE, and I have been able to get each squid to work
>separately, but I have not been able to get the sibling relationship to
>work. When I request an URL from one of the squid's, which I know is
>cached on the other, it still fetches the URL direct, to try to clear
>up the situation, I have run it with some debugging enabled
>(debug_options ALL,1 12,9 15,9 44,9 seemed OK), I get the following
>log:
>
>1998/10/11 13:40:29| peerSelect: http://www.internic.net/
>1998/10/11 13:40:29| peerSelectFoo: 'GET www.internic.net'
>1998/10/11 13:40:29| peerSelectFoo: direct = DIRECT_MAYBE
>1998/10/11 13:40:29| peerSelectIcpPing: http://www.internic.net/
>1998/10/11 13:40:29| neighborsCount: 1
>1998/10/11 13:40:29| peerSelectIcpPing: counted 1 neighbors
>1998/10/11 13:40:29| peerSelect: Doing ICP pings
>1998/10/11 13:40:29| neighborsUdpPing: Peer 130.225.71.227
>1998/10/11 13:40:29| neighborsUdpPing: pinging peer 130.225.71.227 for
>'http://www.internic.net/'
>1998/10/11 13:40:29| neighborsUdpPing: key =
>'91BAE14A0EF398EF90B9B47E8F4265B9'
>1998/10/11 13:40:29| neighborsUdpPing: reqnum = 1
>1998/10/11 13:40:29| icpUdpSend: FD 48 sending ICP_QUERY, 49 bytes to
>130.225.71.227:10004
>1998/10/11 13:40:29| peerSelectFoo: 0 ICP replies expected, RTT 2000
>msec

That line is the key. Squid-2 does not expect to get a reply
from squid-1. what does 'server_list' from the cachemgr
say?

Duane W.
Received on Mon Oct 12 1998 - 15:15:11 MDT