[squid-users] connections from particular users sometimes get stuck

[Eugene M. Zheganin]

Hi.

On 29.09.2016 08:38, Eugene M. Zheganin wrote:
> Hi.
>
> On 28.09.2016 21:21, Alex Rousskov wrote:
>>
>> Indeed! Fixing that exposes one HTTP request in the capture file.
>> Unfortunately,
>>
>> 1. Squid responded to that request (with a 407 message).
>>     Follow (tcp.stream eq 32) in Wireshark.
>>
>> 2. Squid did not receive this request when debugging was on:
>>     $ egrep -c 'www.ru|217.112.35.75' cache.log.debug
>>     0
> Yup, I noticed this too.
>> It may be important to know that the captured request was received at
>> minute 53 while Squid debugging starts at minute 58 (I assume the
>> difference in hours is due to time zone effects and such).
>>
> The thing is, the client machine is in the AD domain and it's time is
> NTP-synced, so is the time on the squid machine. I think I was
> accurate, but mey be I still wasn't. I will redo the captures, this
> time with squid-towards-the-LAN capture, and I will try to validate
> them myself. Luckily, I didn't restart squid yet and this machine
> still demonstrates the symptoms.
Okay, second try. Same IPs, same browser; this time user opens
http://turbodom.ru/index.html (www.ru/index.html got unstuck).
Time is NTP-synced on both machines.

This time turbodom.ru entries are present in the debug log (actually,
there's no /index.html at the turbodom.ru, so anyone requesting
http://turbodom.ru/index.html is me).

debug log:
http://zhegan.in/files/squid/cache.log.debug

tcpdump capture taken from a client machine:
http://zhegan.in/files/squid/squid-stuck-client.pcap

tcpdump capture taken from squid machine, on the interface the client
machine is connected via:
http://zhegan.in/files/squid/squid-stuck-server-to-client.pcap

Thanks.
Eugene.