[squid-users] time based range_offset_limit

[Heiler Bemerguy]

1468423415.143 160645 10.1.4.7 TCP_MISS_ABORTED/206 510 GET 
http://au.v4.download.windowsupdate.com/d/msdownload/update/software/secu/2016/06/word-x-none_48e3c2f2bb14dd57321ae5a53cf8de2ca0fe6114.cab 
- HIER_DIRECT/201.48.38.146 application/octet-stream
1468423415.146 160651 10.1.4.7 TCP_MISS_ABORTED/206 510 GET 
http://au.v4.download.windowsupdate.com/d/msdownload/update/software/secu/2016/06/word-x-none_48e3c2f2bb14dd57321ae5a53cf8de2ca0fe6114.cab 
- HIER_DIRECT/201.48.38.146 application/octet-stream
1468423415.146 160509 10.1.4.7 TCP_MISS_ABORTED/206 510 GET 
http://au.v4.download.windowsupdate.com/d/msdownload/update/software/secu/2016/06/word-x-none_48e3c2f2bb14dd57321ae5a53cf8de2ca0fe6114.cab 
- HIER_DIRECT/201.48.38.146 application/octet-stream
1468423415.147 160579 10.1.4.7 TCP_MISS_ABORTED/206 510 GET 
http://au.v4.download.windowsupdate.com/d/msdownload/update/software/secu/2016/06/word-x-none_48e3c2f2bb14dd57321ae5a53cf8de2ca0fe6114.cab 
- HIER_DIRECT/201.48.38.146 application/octet-stream
1468423415.643 251033 10.1.4.7 TCP_MISS/206 103141 GET 
http://au.v4.download.windowsupdate.com/d/msdownload/update/software/secu/2016/06/excel-x-none_2acf846b28d580d20f1d5973c9697cb54dc1ad21.cab 
- HIER_DIRECT/201.48.38.146 application/octet-stream


For some reason, it seems the client is aborting the range connection.. 
and squid keeps downloading it all simultaneously because it triggers 
range_offset_limit. But why would BITS (background intelligent transfer 
services - microsoft) cancel these downloads?

It really seems to use some no-cache headers:

Cache-Control: no-cache
Pragma: no-cache


How to ignore it?


-- 
Best Regards,

Heiler Bemerguy
Network Manager - CINBESA
55 91 98151-4894/3184-1751


Em 13/07/2016 10:26, Amos Jeffries escreveu:
> On 14/07/2016 12:43 a.m., Heiler Bemerguy wrote:
>> Em 12/07/2016 23:43, Alex Rousskov escreveu:
>>>> (without using Range: header).
>>> That's your squid.conf customization, I presume.
>>>
>> The squid won't send a Range: header to the server because the request
>> is matching the range_offset_limit -1 ACL. I presume. So squid will try
>> to fetch the file from the beginning, faking a full request, right?
> No faking. Is making.
>
>>>> That's why I don't understand why it does not work on a REAL
>>>> enviroment.
>>> Many things can go wrong -- the real requests may require collapsed
>>> forwarding that you do not test, the real requests may have no-cache,
>>> the real response may not be cachable, or there is some Range handling
>>> bug that your test scripts do not tickle (e.g., they request ranges that
>>> are always close to each other and are always available at the same
>>> time).
>> Well, if I turn off collapsed_forwarding and try to GET the same file on
>> the same server in a row (only changing the Range), it will create *two
>> *connections to the server instead of only *one*.
>> I use "override-expire ignore-private ignore-no-store ignore-reload
>> ignore-must-revalidate store-stale" for this particular request, won't
>> it override the no-cache or whatever?
> No. Those refresh_pattern options are overriding the response
> requirements mandated by the server.
>
> The "no-cache" Alex speaks of is a client requirement that no cached
> data be sent. Which also means that client request cannot be collapsed
> with others, since collapsing is essentially just using 'cached' data
> before it gets stored to the cache.
>
> Amos
>
> _______________________________________________
> squid-users mailing list
> squid-users at lists.squid-cache.org
> http://lists.squid-cache.org/listinfo/squid-users