libkse and SMP (was Re: USB bulk read & pthreads)

[Daniel Eischen]

On Thu, 22 May 2003, Julian Elischer wrote:
> 
> On Thu, 22 May 2003, Dan Nelson wrote:
> 
> > In the last episode (May 22), Terry Lambert said:
> > > Make sure you use SCHED_4BSD, rather than SCHED_ULE, if you are using
> > > one of the kernel threads libraries, for now.
> > > 
> > > You really should read the -current archives before attempting any of
> > > this, if you don't follow -current closely enough to have caught
> > > Jeff's message on this, or which kernel threading libraries are
> > > available.
> > 
> > I do read -current, and I'm definitely not going anywhere near
> > SCHED_ULE.  I just tested both libraries with today's kernel and
> > libraries, and was able to get a hard lockup with both libthr and
> > libkse.  Mysql seems to run okay.  Starting a threaded pike process
> > seems to be the killer.  Unfortunately, pike's a pretty large app so
> > it's not easy to get a stripped-down testcase.
> 
> Ok so we need to get a description of this 'lockup'.

In my experience with the ACE test MT_SOCK_Test:

> 1/ does teh whole system lock up?

Yes.

> 2/ is this SMP?  (how many cpus)?

No.

> 3/ does the system respond to pings?

No.

> 4/ do you have teh kernel dbugger installed, and if you do, does it
> respond on the console to <CTL><ALT><ESC>. You may have to start you
> app from outside X11 on a console to be able to see the console once it
> has frozen if it si an X app.

Haven't been able to do this.

> 5/ if it DOES go into ddb, what does 'ps' show?
> 6/ got a serial console?

No :(

You can repeat it by downloading and building the ACE tests.
David and I can tell you how.  It doesn't happen all the time,
so it is not easily repeatable.  Though, it's only been the
last few weeks that I've had the problem.

-- 
Dan Eischen