Bug in calcru in he 6.2 and 6.3 kernels

[Jeremy Chadwick]

On Sun, Jul 20, 2008 at 06:51:22AM -0700, Murty, Ravi wrote:
> Has anyone identified the issue(s) that might be broken in the ULE
> scheduler in 6.2? I am running a rather simple test - creates 8 threads
> and runs it on an 8 CPU system (not a whole lot running on the system).
> When I run it with ULE, it runs slow, very slow sometimes - it's almost
> like the threads aren't picked to run. When I switch to 4BSD, things run
> fine. I was wondering if there is something I could look at? I realize
> it is broken, but I've added lots of stuff to the scheduler (for our
> project) which I'd have to migrate to ULE in 7.0. I'd like to figure out
> what might be going on in 6.2 before I spend the time to migrate to 7.0.

ULE in 7.0 is not the same as in 6.2 -- it was entirely re-written
before 7.0 was released.  The ULE scheduler in 7.0 is often called "ULE
2.0", to signify that it's not the same ULE scheduler in previous
FreeBSD releases.

See "New Scheduler: ULE 2.0 / 3.0" here:

http://ivoras.sharanet.org/freebsd/freebsd7.html

Technical details from the author:

http://jeffr-tech.livejournal.com/3729.html

The reason the ULE scheduler in 7.0 is not the default scheduler is
because the community felt more testing needed to be done.  I believe
the plan is to have ULE as the default scheduler in 7.1.

You should really be running 4BSD on 6.x, and ULE on 7.x (unless you
have reason to run 4BSD on 7.x -- and some people do.  And no, I don't
know the reasons why).

-- 
| Jeremy Chadwick                                jdc at parodius.com |
| Parodius Networking                       http://www.parodius.com/ |
| UNIX Systems Administrator                  Mountain View, CA, USA |
| Making life hard for others since 1977.              PGP: 4BD6C0CB |