Re: [squid-users] Problem with HTTP Headers

Hello Amos,

I understand what you wrote to me but I really do not have any rule
that tells squid to cache wwww.facebook.com header ..

I only used refresh_pattern to match Pictures , Videos & certain
extensions by using ignore-must-revalidate , ignore-no-store ,
ignore-no-cache , store-stale .. etc

and howcome this rule doesnt work ?

refresh_pattern -i \.(htm|html|jhtml|mhtml|php)(\?.*|$) 0 0%

This rule tells squid not to cache these extensions if we had static
URL or dynamic URL.

As I noticed every time you open a website for example www.mtv.com.lb
then you try to open it again next day but you get the same news (
yesterday) which confused me and allow me to think that maybe Squid
ignore all headers related to website if you cached for example
pictures and multimedia objects thats why I was asking which rule
might be affecting websites?.

I cant spend my time on adding list to "cache deny" on websites that
were being cached so I thought of only removing the rule caused squid
to cached Websites .

How to ignore www.facebook.com not to cache but at the same time I
want to cache pictures , FLV Videos , CSS , JS but not the header of
the main page (HTML/PHP).

refresh_pattern ^http:\/\/www\.facebook\.com$ 0 0% 0

I tried to use $ after .com as I only wanted not to cache the main
page of Facebook but still I want to cache Pictures and Videos at
Facebook and so on at other websites .

Sorry If I didnt explain well .

Ghassan

On Sat, Nov 12, 2011 at 1:47 PM, Amos Jeffries <squid3_at_treenet.co.nz> wrote:
> On 12/11/2011 10:30 a.m., Ghassan Gharabli wrote:
>>
>> Hello,
>>
>> I am facing a trouble with Caching HTTP Headers.
>>
>> Everyday I see that www.facebook.com header is being cached and then I
>> try to remove it manually from Cache and so other websites ...
>
> ...other websites what?
>
>>
>> I tried to add these refresh_patterns before any rule but
>> unfortunately with no luck!
>
> Okay some basics. This is a bit complex so if I'm not clear please mention.
>
> There are several algorithms affecting caching.
>
> Firstly is absolute expiry.
>  This tells Squid exactly when to erase the object. Down to the second.
> Controlled by Expires: header, or a Cache-Control header with private,
> no-store, max-age= values.
>  As Squid HTTP/1.1 support increases Expires: (a HTTP/1.0 feature) is
> getting ignored more often.
>
> Secondly, there are freshness algorithm.
>  This tells Squid exactly when the object can be used immediately, or needs
> revalidation before use. It is an estimation only.
>  Controlled by the Date, Last-Modified headers, with Cache-Control
> max-stale, etc mixed in as well.
>  This is where refresh_pattern happens, its min/pct/max values are used to
> set boundaries in the decision about staleness. The wiki and refresh_pattern
> config docs cover exactly how it works, so I wont repeat it all here.
>
>
> Thirdly, there are the variant algorithm(s).
>  These tell Squid whether the object in cache is relevant to the request at
> all or needs to be skipped. Controlled by the ETag, Vary, Accept, etc.
>
> To complicate things refresh_pattern has ignore-* an doverride-* options
> which make Squid ignore the particular header. These are mostly HTTP
> violations and can prevent immediate expiry or extend the estimation well
> beyond anything that woudl otherwise be chosen.
> NOTE: all these options and refresh_pattern itself can only *extend* the
> time something is cached for. They cannot and do not prevent caching or
> remove things early. refresh_pattern can have the appearance of shortening
> cache times, *if* and only if, the object was caused to be cached that long
> by another refresh_pattern estimation later down the list (ie our default 1
> week storage time in the "." pattern line).
>
>  To prevent caching use "cache deny ...".
>
>
>>
>> refresh_pattern -i \.(htm|html|jhtml|mhtml|php)(\?.*|$)               0 0%
>> 0
>> refresh_pattern ^http:\/\/www\.facebook\.com$             0 0% 0
>>
>> REFRESH_PATTERN CONFIG :
>> ------------------------------------------------
>> # 1 year = 525600 mins, 1 month = 43800 mins
>> refresh_pattern
>> (get_video|videoplayback|videodownload|\.flv).*(begin|start)\=[1-9][0-9]*
>>       0
>> 0% 0
>> refresh_pattern -i \.(htm|html|jhtml|mhtml|php)(\?.*|$)               0 0%
>> 0
>> refresh_pattern ^http:\/\/www\.facebook\.com$             0 0% 0
>
> This rule above will never match. Squid uses absolute URLs to pass the
> refresh pattern.
> Absolute URL have a "/" in the path. *never* will  ".com" be the last four
> characters of the absolute URL.
>
> Amos
>
Received on Sat Nov 12 2011 - 23:15:33 MST