On 4/01/2012 5:32 p.m., Eliezer Croitoru wrote:
> i have couple of things things:
> i have made a long way of testing squid for a couple of days on
> various versions of linux distors such as centos 5.7\6.0\6.2 fedora
> 15\16 ubuntu 10.04.3\11.10 gentoo(on the last portage) using tproxy
> and forward proxy. (all i686 but ubuntu x64)
> i couldnt find any solid info on squid to work with these systems so i
> researched.
> i have used squid 3.1.18 3.2.0.8 3.2.0.13(latest daily source) 3.2.0.14.
> on centos and ubuntu squid 3.2.0.14 was unable to work smoothly on
> interception mode but on regular forward mode it was fine.
>
> on the centos 5 branch there is no tproxy support built-in the regular
> kernel so you must recompile the kernel to have tproxy support.
> on the centos 6 branch there is tproxy support built-in the basic
> kernel but nothing i did (disabling selinux, loading modules and some
> other stuff) didnt make the tproxy to work.
> because i started with centos i throughout that i'm doing something
> wrong but after checking ubuntu, fedora and gentoo i understood that
> the problem is with centos 6 tproxy or other things but not squid.
> also i didn't found any logic README or info about tproxy that can
> explain the logic of it so in a case of problem it can be debugged.
http://wiki.squid-cache.org/Feature/Tproxy4 has everything there is. The
"More Info" link to Balabit is a README that covers what the kernal
internals do. The internals of Squid is only is two trivial bits;
inverting the IPs on arrival, binding the spoofed on on exit, the rest
is generic intercepted traffic handling (parsing the URL in originserver
format, and doing IP security checks on Host header). These are well
tested now and work in 3.2.0.14.
I'd like to know what Ubuntu and Gentoo versions you tested with and
what you conclude the problems are there. Both to push for fixes and
update that feature page.
>
> after all this, what do you think about releasing a list of
> "supported" linux distors that seems to work fine on every squid release?
> i'm talking about the major releases and not about "puppy linux" or
> "dsl".
You mean as part of the release? that is kind of tricky because none of
the distros does run-testing until after the release package is
available. Sometimes months or even years after, as in the case of
certain RPM based distros having an 12-18 month round-trip between our
release and bug feedback. Naturally, its way too late to bother
announcing those problems and the faster moving distros appear to have
numerous unfixed bugs in a constantly changing set, a very fuzzy
situation in overview. If I'm aware of anything problematic to a
specific distro in advance I try to mention it in the release
announcement. http://wiki.squid-cache.org/BestOsForSquid has a list of
the major distros Squid works on, but not correlated to particular
releases or features. That could be updated to correlate with Squid
series for better documentation of what to expect.
I also get the impression that you want a feature-by-feature support
rundown on each distro. With an uncounted (literally) number of features
in Squid to be tested and very little automatiion coverage this is a lot
of work just to get a reasonably accurate idea. We try though as part of
the bug detection and removal work. Assistance is very welcome, our TODO
list has a few items anybody can help with:
* some help wanted documenting (even just a catalog list) all the
features in Squid. http://wiki.squid-cache.org/FeatureComparison and
http://wiki.squid-cache.org/Features need extending and correlating.
* resource donations wanted for automated tests. We run build tests on
major distros on multiple architectures. see
http://wiki.squid-cache.org/BuildFarm. But are limited by lack of some
hardware architectures and , CPU time available on the hardware we have,
and access to the distro itself in some cases (MacOS, Solaris, Windows,
AIX,...spot the trend). Donation details on how to help extend that are
outlined on the wiki page.
+ Given more CPU time we could start to look at run-time testing
features from the list above, but that is a bit problematic with the
present resources. Help would be very welcome.
* help wanted adding automated test coverage. The tests we have so far
are a bit sparse, many of the features are not distro specific and could
be tested as units during the existing build scans, but are not yet.
Interested persons carrying patches are very welcome. We use cppunit and
STUB frameworks which make test writing relatively easy, but it can be
time consuming.
+ even just a coverage list of classes versus what is/not tested so
far would be helpful to target future work.
* help wanted adding/updating Feature/* pages in the wiki as bugs are
discovered and analysed. Likewise KnowledgeBase/* pages for all the
major distros with distro-specific details as and when behaviour quirks
are found.
(Sorry its a bit of a long plea, but this is one area I'm keen to see
progress and all the dev have spent many hours unsponsored time slaving
away to get this far.)
>
> this is the place to rate the linux distro you would like squid to be
> tested on.
>
>
> another subject:
> what dynamic content or uncacheable sites by squid will you want to
> to be able to cache?
>
> let say youtube. ms updates and stuff like that.
> i know that cachevideo is available but i think that with some effort
> we can build some basic concept that will benefit all of us.
>
> votes for sites will be gladly accepted.
>
> (i will be glad to explain the reasons that makes these sites objects
> uncacheble in many cases to anyone that want to understand it.
> also how and why squid is doing such a great job.)
>
Facebook traffic is another FAQ (or at least was last year). Explaining
why so much of their traffic does not cache, and why we must suffer
instead of forcing it to, is in need of some good documentation.
Amos
Received on Wed Jan 04 2012 - 09:15:59 MST
This archive was generated by hypermail 2.2.0 : Wed Jan 04 2012 - 12:00:04 MST