On Thu, 11 Mar 2010 02:18:40 +0100, Henrik Nordstrom
<henrik_at_henriknordstrom.net> wrote:
> tor 2010-03-11 klockan 11:42 +1300 skrev Amos Jeffries:
>
>> His trace earlier showed squid receiving the whole list of AAAA and A,
>> then running through them in the proper order marking each bad as it
>> went.
>> Reporting error after the last IPv4 had been tried.
>
> Are you sure?
>
> while there was lots of ipcacheCycleAddr calls, there was just 3
> forwarding attempts with 3 addresses getting marked as bad.
>
Um, I only did a quick read, but the cycle only happens during a connect
failure I thought.
There are two levels which do cycling. The comm internal on it's own array
of DNS results for the connected-to host, and the forwarding loop over
connection attempts to its own copy of whatever the current cycled-to
address is.
You may have just uncovered the bug. If it's not even trying most of the
addresses that could account for the v4 ones being skipped.
Amos
Received on Thu Mar 11 2010 - 01:33:46 MST
This archive was generated by hypermail 2.2.0 : Thu Mar 11 2010 - 12:00:06 MST