Howdy,
Some ext2/3 benchmarks on a IBM-DPTA-372050 connected to k7 650MHz. The same
partition was used on all tests roughly with the same disk usage.
bonnie on ext2:
-------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 10458 99.5 35317 19.0 9870 13.3 6265 93.1 92609 31.7 24665.0
86.3
bonnie on ext3 0.0.2f:
-------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 5143 52.7 8137 12.8 5797 13.7 6517 96.9 117606 41.3 29756.8
96.7
bonnie on ext3 0.0.5b writeback
-------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 4820 90.5 21570 16.9 11273 11.8 4756 88.4 37523 14.3 29220.8
95.0
bonnie on ext3 0.0.5b ordered
-------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 5101 96.4 28041 21.4 10717 15.0 4909 91.8 52454 19.0 27812.5
97.3
The block reads on ext2 seem a bit exagerated.
Kudos Stephen!
--
Carlos Morgado - chbm(at)chbm(dot)nu - http://chbm.nu/ -- gpgkey: 0x1FC57F0A
http://wwwkeys.pgp.net/ FP:0A27 35D3 C448 3641 0573 6876 2A37 4BB2 1FC5 7F0A
On Mon, Dec 04, 2000 at 11:23:10PM +0000, Carlos Morgado wrote:> Howdy, > Some ext2/3 benchmarks on a IBM-DPTA-372050 connected to k7 650MHz. The same > partition was used on all tests roughly with the same disk usage....> The block reads on ext2 seem a bit exagerated.Could you try these with approx 5x your RAM? As you note, you are seeing effects of the disk cache. Even so, it is nice to see that the 0.0.5b code indicates little slowdown. Regards, Bill Rugolsky