I don't trust bonnie, or any other benchmark at all. The drasitic changes you
saw don't make sense. Could you TELL it was that much of a change? NO? Then it
wasn't. Observe my results below...first thing to notice is it's make a
difference where on the disks the program is benching because of the change in
rotational speed. Next the numbers below are just plain wrong and inconsistent
at that. Two days ago I ran bonnie and it told me my max seq in block was 4999.
I have 5 Ultra FastWIDE Atlas II drive in RAID 0. Actual performace of the RAID
should be around 11-12MB. On the linux RAID list there was a guy with 4 Cheetahs
in RAID5, and his reads were LESS then your single cheetah. You buy that? I
don't...
I also have some mail here from Joshua Snyder <josh@ims1.imagestream.com>
who has a single cheetah. His numbers are:
-------Sequential Output-------- ---Sequential Input-- --Random--
-Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec %CPU
256 7488 91.5 10369 42.5 4041 28.2 7865 77.9 10208 23.6 225.1 4.2
Compare those to yours. Bonnie lies! All disk benchmarks are the spawn of Satan!
My RAID:
Zen-Machine# [~] cd tmp
-------Sequential Output-------- ---Sequential Input-- --Random--
-Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec %CPU
100 2361 77.4 6008 35.3 2490 27.3 2669 77.9 7068 20.6 553.3 12.6
Zen-Machine# [/tmp] cd /mnt/sda12/
-------Sequential Output-------- ---Sequential Input-- --Random--
-Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec %CPU
100 2559 83.6 6674 40.2 2482 27.7 2714 79.4 8025 26.2 583.5 18.4
Zen-Machine# [/mnt/sda12] cd /mnt/mnt
-------Sequential Output-------- ---Sequential Input-- --Random--
-Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec %CPU
100 2774 91.2 6865 41.0 2493 28.1 2741 80.0 8639 26.5 593.6 20.3
-- http://www.psychosis.com/emc/ Elite MicroComputers 908-541-4214 http://www.psychosis.com/linux-router/ Linux Router Project "The only way to remain cutting edge, is to design for things that do not yet exist." -- Me : )- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu