Re: Benchmark oddities

2000-07-26 Thread Siobhan Patricia Lynch
heh, won;t happen if I can help it ;) -Trish __ Trish Lynch FreeBSD - The Power to Serve[EMAIL PROTECTED] Rush Networking [EMAIL PROTECTED] On Wed, 26 Jul 2000, Kris Kennaway wrote: > On Wed, 26 Jul 2000, [iso-8859-1] Tommy Hallgren wrote: > > > I'm readin

Re: Benchmark oddities

2000-07-26 Thread Kris Kennaway
On Wed, 26 Jul 2000, [iso-8859-1] Tommy Hallgren wrote: > I'm reading http://www-scf.usc.edu/~akhavans/Linux_vs_FreeBSD.pdf and have a > couple of questions I hope someone here could answer. I thought this paper was quite poorly written, in general - for example, the author is unable to stop gus

Re: Benchmark oddities

2000-07-26 Thread Robert Watson
Well, I tend to agree with your comments on the benchmark, but have observed that when starting a large number of forks from the same parent on 4.0-STABLE, the system sporadically hangs waiting in vm_wait for some processes to exit, despite not having hit max kernel processes permitted, or hittin

Benchmark oddities

2000-07-26 Thread Tommy Hallgren
Hi! I'm reading http://www-scf.usc.edu/~akhavans/Linux_vs_FreeBSD.pdf and have a couple of questions I hope someone here could answer. 1. Section 4.3 and 4.4 is about syscall overhead context switch time. "Figure 2 indicates that the FreeBSD context switch increases linearly with the number of