Messages in this thread | | | From | "Sean Hunter" <> | Date | Fri, 21 Jan 2000 08:51:27 +0000 | Subject | Re: Interesting analysis of linux kernel threading by IBM |
| |
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@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |