Re: [PATCH] Fix session helper "crashing too rapidly"

From: Amos Jeffries <squid3_at_treenet.co.nz>
Date: Thu, 22 Sep 2011 11:10:50 +1200

On 22/09/11 10:09, Andrew Beverley wrote:
> On Wed, 2011-09-21 at 11:01 +1200, Amos Jeffries wrote:
>> On Tue, 20 Sep 2011 22:26:20 +0100, Andrew Beverley wrote:
>>> On Tue, 2011-09-20 at 12:09 +1200, Amos Jeffries wrote:
>>>>> Do you mean the -d option to the Squid binary? If so, this doesn't
>>>>> seem
>>>>> to make any difference; it just prints all the log messages to the
>>>>> display as well as the log file.
>>>>
>>>> -d parameter of the helper binary. stderr is piped to cache.log at
>>>> level-0. Thus the need for a separate switch to enable lots of
>>>> debug
>>>> from the helper.
>>>
>>> Sorry if I'm being stupid, but do you mean the actual session helper
>>> binary or something else? If it's the former, then that obviously
>>> just
>>> causes an exit due to an invalid option.
>>>
>>
>> Yes I did. Sorry, being unbelievably stupid this week it seems :(.
>> Completely overlooked the fact the 'd' parameter and debugs do not
>> exist there.
>
> No problem!
>
> However, it still leaves the question: what is the best way to log
> errors from the helper. At the moment, even with the patch applied, a
> user will still get "The helpers are crashing too rapidly, need help" if
> they don't specify a concurrency value. I was trying to fix this, as I
> spent hours locating the problem!
>

The correct way is with ERROR: or in this case "FATAL:" messages sent to
stderr from the helper. The user will get N of that message over a 30
seconds period, then Squids helpers dying message and abort.

Why the message is not showing up in your cache.log is a mystery.
Perhapse it was buffered and discarded by the segfault? something like that?

Amos

-- 
Please be using
   Current Stable Squid 2.7.STABLE9 or 3.1.15
   Beta testers wanted for 3.2.0.12
Received on Wed Sep 21 2011 - 23:10:57 MDT

This archive was generated by hypermail 2.2.0 : Thu Sep 22 2011 - 12:00:05 MDT