[PATCH]: additional futex operations

[Alexander Leidinger]

Quoting Roman Divacky <rdivacky at FreeBSD.org> (from Thu, 20 Mar 2008  
17:50:24 +0100):

>> The thought behind this is, that we can go from "should be" to "are".
>> Doing a rate limited logging (print the message once) in -current (not
>> in a MFC) should be enough to get a better idea.
>>
>> >Also.. if anyone is willing/able to implement the FD backing I think such
>> >person is skilled enough to see what is the problem even without the
>> >printf.
>>
>> It's not about finding some to implement it, it's about getting _hard_
>> facts in our userbase.
>
> what is the point in getting to know that we dont implement FD backed
> futexes? I already know that :)

That's not the point. The point is to know which programs use this. If  
we see that only a little tiny tools which nearly nobody uses wants to  
use FD futexes, we don't care. But if some big software like Oracle,  
DB2, Websphere (I don't say they use it and I don't say I think they  
use it, that are just examples of the class of applications) or  
something like this, then we should really have a look at implementing  
them.

> in a case of problems people should be running -DDEBUG linuxulator anyway.

So far we told the users about stuff we don't implement without any  
need to recompile. We should not change that. Specially as there are a  
lot of users out there, which don't recompile a kernel at all.

> I dont honestly think that anyone will ever implement the FD backed futexes
> (too much work for basically null gain).

I don't say the opposite, I just want to get hard facts to proof that  
it is not necessary.

Bye,
Alexander.

-- 
The meat is rotten, but the booze is holding out.
Computer translation of "The spirit is willing, but the flesh is weak."

http://www.Leidinger.net    Alexander @ Leidinger.net: PGP ID = B0063FE7
http://www.FreeBSD.org       netchild @ FreeBSD.org  : PGP ID = 72077137