Re: [PATCH] log error details

On 10/14/2010 12:46 PM, Amos Jeffries wrote:
> On 14/10/10 22:04, Tsantilas Christos wrote:
>> On 10/14/2010 12:58 AM, Amos Jeffries wrote:
>>> On Wed, 13 Oct 2010 16:25:34 +0300, Tsantilas Christos
>>> <chtsanti_at_users.sourceforge.net> wrote:
>>> .....
>>>>
>>>>>
>>>>> * Can FileNameHashCached() be made a private static method of
>>>>> TextException and work with the file and line details passed in to
>>>>> cnstructor please?
>>>> Will not work Amos.
>>>
>>> Ah I overlooked the static local.
>>>
>>> FileNameHash() could still be a member, but protected with friend
>>> function
>>> FileNameHashCached().
>>>
>>>>> The singleton hack making local copies in almost every file .o is
>>> likely
>>>>> to symbol clash on the more picky compilers like MacOSX.
>>>>
>>>> We need a copy of the FileNameHashCached in each .o file, which will
>>>> compute and cache once the hash of its filename. Alternatively we can
>>>> compute the hash when the Must exception called (direct use of the
>>>> FileNameHash).
>>>
>>> IMO that would be better. A system throwing and failing a lot of Must()
>>> requirements has worse problems than a few cycles of hashing.
>> Probably you are right here. In the other hand some thousands of
>> transactions aborted the same time for the same reason, will cause squid
>> to compute the same hash value some thousand times.
>>
>> If we decide to not cache the hash value and there is not any objection
>> from others developers I will do the followings:
>> - remove the FileNaneHashCached and the FileNameHashCached class.
>> - make FilenameHash a private method of the TextException class.
>> - Compute the hash only in TextException::id() method. This will compute
>> the hash value only if it is requested, not for all Must()
>>
>>>
>>> * NP: if performance is _that_ much of a problem we had best look into
>>> pre-calculating FileNameHash() results as a const parameter to the
>>> Must/TextcHere macros during build.
>> I can not find any simple way for this one. Any hint? But if we decide
>> to not cache the hash value of the file name we do not need it.
>
> A separate script that runs and does the filename hashing. It might be
> run by configure, top level Makefile, or if it was useful enough we
> could add it to source-maitenance.sh for permanent embedding.
>
> Easiest would be for it to add/update a "#define FILENAMEHASH abf0" at
> the top of each file which is used by the Must() macro later on.
> If the hash bits were split 16/16 then the hash need only be two bytes
> and easily identified by us humans as the first two of the EXCEPTION id.
> The __LINE__ bit would still need to be masked on later to avoid
> problems with patchings.

It will not be so easy. We should add a "#undef FILENAMEHASH/#define
FILENAMEHASH" after the last "#include" in each file.
Also should be added in "*.h" files too, because a Must may used in
include files. The current solution looks much simpler and better...

Also using a 16bit hash can produce the same hash value for two files,
but it is not a real problem because it is unusual to have two files
with the same hash value and a Must expression in the same line.

>
>
> Amos
Received on Thu Oct 14 2010 - 10:28:25 MDT