Benchmarking MOL

Subject: Benchmarking MOL
From: Sean Mahrt (bigmouth@pionet.net)
Date: Thu May 10 2001 - 19:11:53 MDT

• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
• Next message: Quentin Mason: "Re: Benchmarking MOL"
• Previous message: Fridolfs, Michael S.: "RE: unsuscribe"
• In reply to: Samuel Rydh: "Re: Multiple instances of mol"
• Next in thread: Quentin Mason: "Re: Benchmarking MOL"
• Reply: Sean Mahrt: "Benchmarking MOL"

OK, being an engineer and a 10 year mac user it's time for some benchmarks
of MOL. Maybe we can assemble a database (I plan to as soon as I get my
static IP).

Here's the scoop using MacBench 5.0 (if anybody has the full cd I'd love a
copy!)

I'm comparing my stock G3/233 (speed demon) using macbench's included
benchmark.

A little about my machine

320MB ram
2-45 GB ide drives (macos volume on stripe as a 2 gb file)
standard video set at 800x600xthousands (for comparison)

Here's the scoop

Processor

MacBench rating on stock machine on os 8.1 (no linux) 100%
MOL 0.9.58 in X with -20 niceness %64
MOL 0.9.58 console standard priority %62
MOL 0.9.58 in X with standard pri %59

Floating Point

MacBench rating on stock machine on os 8.1 (no linux) 100%
MOL 0.9.58 in X with -20 niceness %68
MOL 0.9.58 console standard priority %72
MOL 0.9.58 in X with standard pri %72

Disk

MacBench rating on stock machine on os 8.1 (no linux) 100%
MOL 0.9.58 in X with -20 niceness %168
MOL 0.9.58 console standard priority %154
MOL 0.9.58 in X with standard pri %156

Publishing tests

MacBench rating on stock machine on os 8.1 (no linux) 100%
MOL 0.9.58 in X with -20 niceness %141
MOL 0.9.58 console standard priority %137
MOL 0.9.58 in X with standard pri %141

Processor

MacBench rating on stock machine on os 8.1 (no linux) 100%
MOL 0.9.58 in X with -20 niceness %64
MOL 0.9.58 console standard priority %62
MOL 0.9.58 in X with standard pri %59

You don't want to even see the graphics test. If anybody wants, I can send
them the macbench and my testing files. WHen I get closer to building the
web site, I'll ask for people to submit tests to me...

I was under the impression that the linux disk handling would be better
(which it is), but I really was suprised by the processor efficiency. Is
this all overhead? Mabye not an appropriate area for this discussion.

Samuel, if you want any more testing, let me know. Maybe we'll deploy a
fleet on a cross section for your own information!

Sean

• Next message: Quentin Mason: "Re: Benchmarking MOL"
• Previous message: Fridolfs, Michael S.: "RE: unsuscribe"
• In reply to: Samuel Rydh: "Re: Multiple instances of mol"
• Next in thread: Quentin Mason: "Re: Benchmarking MOL"
• Reply: Sean Mahrt: "Benchmarking MOL"

This archive was generated by hypermail 2a24 : Thu May 10 2001 - 18:20:48 MDT