Re: [PATCH 2.6.13.1] Patch for invisible threads

[Sripathi Kodi <sripathik@in.ibm.com>]

Bill Davidsen wrote:
> 
> Let me say that this solution, and any other which loops through all 
> threads of a task, isn't going to scale well. I don't have a magic O(1) 
> solution, if it were easy someone would have done that instead of the 
> while loop, just noting that a clever solution would be a win on servers.

Bill,

We will only have to go through the while loop in rare cases where main 
thread has done pthread_exit() before other threads (and hence it's task->fs 
is null). Also, even in most such cases, the very first iteration through 
the while loop  will get us the 'fs' pointer, so we won't have to loop 
through all threads. So I think this won't have scalability problem. Am I right?

Thanks,
Sripathi.