Interesting analysis of linux kernel threading by IBM

[Sean Hunter]

On Thu, Jan 20, 2000 at 11:20:35AM -0800, Larry McVoy wrote:
> There are a number of unsubstantiated statements in this message and
> I'd like to request that the various people who are claiming that these
> statements are true, please back them up.  All we need is vmstat/ps/top
> output on machines with these sorts of loads.  Benchmark machines do
> not count, only real workloads, please.
> 
> : > Hondreds of tasks is just not a typical (perhaps even realistic)
> : > workload.
> : 
> : Yes it is.  
> : 
> : If you are running a webserver. 
> 
> ps -ax outout please.

Our webservers hit a load average of 80+ for about four hours twice a
week.  However, I don't want anyone to optimise the scheduler.  I want
us to fix our _dumb_ cgis.  And we are working hard at doing that.

As it is, I agree totally with Larry. If your load is this high in
normal use its probably a sign you're being dumb.  I know we are.

I don't think linux should optimise for the "I'm being dumb and I want 
the kernel to solve my problems" case.

Sean

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo en vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/