Thread Scheduling

[Gardner Bell]

On Thu, Jan 20, 2005 at 09:48:59PM -0800 stheg olloydson wrote:
> it was said:
> 
> <snip>
> 
> >My question is, will I notice any performance improvement by using the
> >new scheduler opposed to the 4.4BSD scheduler on an SMP system and can
> >the new scheduler be utilized on a single processor system?  The
> >intended use of the SMP system is for MySQL databases only.
> 
> <snip>
> 
> Hello,
> 
> I asked about the new scheduler on the performance list. Below is
> (posted on list) reply:
> 
> >FWIW, one of the reasons that there hasn't been as much 
> >interest in SCHED_ULE lately is likely that several of the 
> >features previously only present in SCHED_ULE are now also 
> >present in SCHED_4BSD -- for example, making more effective 
> >uses of IPIs in reducing latency during inter-process 
> >communication across processors.  While SCHED_ULE does contain 
> >a number of interesting things not present in SCHED_4BSD, the 
> >4BSD scheduler has hardly gone un-improved in that time.  
> >However, Jeff Robserson does seem to have picked up recently 
> >on both VFS SMP locking and ULE.  The scheduler tracing and 
> >visualization tools he committed a couple of weeks ago are 
> >really quite neat tools.
> >
> >Robert N M Watson
> 
> So we'll just have to wait until ULE is fully baked to see which
> scheduler is best for a given application. For a more definitive
> answer, you may want to ask directly on the performance list.
> 
Thanks for your reply, I do have more questions regarding this so I'll
ask away on the performance list.

Gardner