Re: [squid-users] Squid 3.0.STABLE17 is available

Amos Jeffries wrote:
> Thomas Meier wrote:
>> im also have this error:
>>
>> 2009/07/30 09:48:16| HttpMsg.cc(157) first line of HTTP message is
>> invalid
>> 2009/07/30 09:48:16| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:48:19| Starting Squid Cache version 3.0.STABLE17 for
>> sparc-sun-sol
>> aris2.9...
>> 2009/07/30 09:48:19| Process ID 17345
>> 2009/07/30 09:48:19| With 32768 file descriptors available
>> 2009/07/30 09:48:19| Performing DNS Tests...
>> 2009/07/30 09:48:19| Successful DNS name lookup tests...
>>
>>
>> ####
>>
>> 2009/07/30 09:47:38| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:48:16| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:48:46| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:48:58| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:49:44| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:49:53| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:50:02| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:51:33| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:51:39| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:51:45| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:52:26| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:53:02| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:53:12| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:53:22| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:53:30| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:54:32| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:55:35| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:57:04| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:57:41| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:57:57| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:58:22| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:59:31| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:59:44| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 09:59:59| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 10:01:13| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 10:01:48| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 10:02:29| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 10:02:34| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 10:02:41| assertion failed: http.cc:738: "!eof"
>> 2009/07/30 10:03:51| assertion failed: http.cc:738: "!eof"
>>
>> back to stable 13 the good old unfixed Problem is back:
>>
>> 2009/07/30 11:05:05| tunnelReadServer: FD 377: read failure: (0) Error 0
>> 2009/07/30 11:05:16| tunnelReadServer: FD 211: read failure: (0) Error 0
>> 2009/07/30 11:05:20| tunnelReadServer: FD 462: read failure: (0) Error 0
>> 2009/07/30 11:05:32| tunnelReadServer: FD 437: read failure: (0) Error 0
>> 2009/07/30 11:05:36| tunnelReadServer: FD 340: read failure: (0) Error 0
>> 2009/07/30 11:05:41| tunnelReadServer: FD 432: read failure: (0) Error 0
>> 2009/07/30 11:06:13| assertion failed: store_client.cc:430:
>> "STORE_DISK_CLIENT =
>> = getType()"
>> 2009/07/30 11:06:18| Starting Squid Cache version 3.0.STABLE13 for
>> sparc-sun-sol
>> aris2.9...
>>
>>
>>
>>> > On Tuesday 28 July 2009 23:22:56 Amos Jeffries wrote:
>>>
>>>> >> The next formally bundled will be STABLE18. However the daily
>>>> snapshots
>>>> >> serve as intermediate updates on STABLE
>>>> >> (http://www.squid-cache.org/Versions/v3/3.0/).
>>>> >>
>>>> >> I just have not yet had time to apply these fixes to the branch yet.
>>>>
>>> > > > 3.0.STABLE17-20090729 still crashing here (x86_64)...
>>> > > 2009/07/29 16:07:45| ctx: enter level 0: >
>>> 'http://images.windowsmedia.com/svcswitch/MG_pt-
>>> > br.xml?locale=416&geoid=20&version=1
>>> >
>>> 1.0.6001.7004&userlocale=416'
>>>
>>
>>> > > 2009/07/29 16:07:45| assertion failed: http.cc:738: "!eof" > > I
>>> also applied (the patch from previous e-mail) against this version:
>>> > > patching file src/HttpMsg.cc
>>> > patching file src/HttpReply.cc
>>> > patching file src/HttpRequest.cc
>>> > patching file src/pconn.cc
>>> > > The only solution here was downgrade to previous release...
>>> > > Any clue?
>>>
>>
>> It seems to be a fread() issue between Squid and x86_64. Disappears on
>> i386/i686.
>>
>> Maybe *BSD specific as well, but there are a few reports without OS info
>> fuzzing my info there.
>> I plan on spending more time over the weekend adding good tracing info to
>> find it.
>>
>
> Okay. This gets rid of the assert and adds some debug instead.
> The reason for sending eof=1 when not at true EOF is not yet clear, so
> use carefully, but additional debugs are added when the flag is set.
> debug_options ... 11,9 for these.
>
> Amos
>

   -p0 for Squid-3 patches.

Anyway, in the interim the case appears to have been found.

I've kicked the snapshots to get one that _should_ work properly and
have all the polish patches included as well. Will be built in a few hours.

Give that a try first off, if any problems are found in it we go after
those.

Amos

-- 
Please be using
   Current Stable Squid 2.7.STABLE6 or 3.0.STABLE17
   Current Beta Squid 3.1.0.12