Re: [Linux-streams] LiS-2.18 performance ?

[Dave Grothe]

I don't remember any more.  I was probably concerned with multiple executions of queue processing on the same CPU.  One thread calls lis_runqueues on the way out of a system call and then another thread wakes up the queue runner thread for that CPU.  Now you have two instances running on the same CPU.  Don't know if that causes problems or not.
-- Dave

At 08:32 PM 12/10/2005, [EMAIL PROTECTED] wrote:

> I suppose the only problem might be that some semaphore gets held  while
> queue are being run.  Perhaps Dave could comment why it was removed in
> the first place. 
 
Dave, sorry to bother you, can you comment on why the 'can_call'
processing was removed from lis_setqsched() function in LiS-2.18 ?
 
I.e. in 2.16 lis_setqsched() could call lis_runqueues() directly if 'can_call'
parameter was set.   In 2.18 everything is passed on to LiS threads.
 
Since performance is so much better with direct lis_runqueues() call
can I add it back?  I.e. is it safe to add it back or there is something to consider
before doing this?
 
I'll really appreciate your comments.
 
Thanks,
--
Eugene
 

---

Try the New Netscape Mail Today!
Virtually Spam-Free | More Storage | Import Your Contact List
http://mail.netscape.com