Henrik Krohns wrote:
>>> I would *not* try to upgrade Perl. In doing so, you could cause you
>>> machine to laps in an error-log extravaganza.
>> Ya, that was my last resort, but I'd rather avoid it if I could. I'll
>> post back with my results if I do see an improvement.
>
> Why should you upgr
> What exactly do you mean by 'local loopback address'? I'm pretty sure I
> know what you're talking about, but I wanted to make sure I understood
> you correctly.
somehost:/var/log/spamassassin# ifconfig -a
eth0 Link encap:Ethernet HWaddr ***
inet addr:10.5.5.5 Bcast:*** Mask:25
Matthew Wilson wrote:
> Hmm. Maybe it is indeed a result of the additional local loopback address
> required for the IP load-balancers. I'm asking around various places if
> that's a supported situation.
What exactly do you mean by 'local loopback address'? I'm pretty sure I
know what you're ta
> I'm still seeing the same error happen even after making that change in
> /etc/hosts.
>
> If what you're saying above is true, then why am I am I only seeing
> these errors when there's a spike of incoming email. I'm graphing the
> number of mails coming in and every time I see these errors ther
Matthew Wilson wrote:
>> I had tried that as well, to no avail. I suspect that in our setup,
>> the
>> tcpcheck
>> from LVS/keepalived was closing the connection so quickly after
>> discovering
>> that
>> the port was open, the socket was closed even before ->peername was
>> called.
>>
>> -Matthew
> I had tried that as well, to no avail. I suspect that in our setup,
> the
> tcpcheck
> from LVS/keepalived was closing the connection so quickly after
> discovering
> that
> the port was open, the socket was closed even before ->peername was
> called.
>
> -Matthew
Yep, by the time the LVS' tcp
> > I was getting identical Socket.pm errors. See
> > http://issues.apache.org/SpamAssassin/show_bug.cgi?id=5388 for my
> diagnosis.
> > Let me know if you'd like me to explain further.
>
> Aha!
>
> We have a similar setup here with the BigIP having two addresses on the
> machine (a machine ip a
Matthew Wilson wrote:
>> Ya, that was my last resort, but I'd rather avoid it if I could. I'll
>> post back with my results if I do see an improvement.
>
> Lance-
>
> I was getting identical Socket.pm errors. See
> http://issues.apache.org/SpamAssassin/show_bug.cgi?id=5388 for my diagnosis.
> Le
> Ya, that was my last resort, but I'd rather avoid it if I could. I'll
> post back with my results if I do see an improvement.
Lance-
I was getting identical Socket.pm errors. See
http://issues.apache.org/SpamAssassin/show_bug.cgi?id=5388 for my diagnosis.
Let me know if you'd like me to explai
maillist wrote:
>
> I would see if you could maybe get a fresher version of IO::Socket The
> latest on CPAN is 1.2301
>
> (http://search.cpan.org/CPAN/authors/id/G/GB/GBARR/IO-1.2301.tar.gz)
Thanks, I'll give that a try. So far I haven't seen this error on the
machines that are running the new
Lance Albertson wrote:
I recently updated SA on our machines from 3.1.1 to 3.1.8 and I started
noticing a new issue crop up. I also noticed that someone else had a
similar problem and reported it on this last back in January [1], but it
never got an answer back about it. I've looked elsewhere onl
11 matches
Mail list logo
