Just FYI, a run on a Netfinity 5000 with a ServeRAID card and two IBM 8G
LVD disks plugged into a backplane. I can dig up the model if it makes
things more meaningful. mem=16M, runlevel 1, numruns 5.. you know the
drill. AFAICS to me the ServeRAID is LVD as well, which should give us
80Mb/s max theoretical throughput.
Nice low CPU usage, but sad numbers, I'm afraid - about half the
throughput on the 40Mb/s Ultra I have on the box I performed last weeks
marks. I guess the nice chassis and backplane are a plus :-) Plus the
huge 7-inch fans.
I see from the flat progression in read throughput that it does no read
balancing - a pity, isn't it? ;-)
Size is MB, BlkSz is Bytes, Read and Write are MB/sec, Seeks are Seeks/sec
Dir Size BlkSz Thr# Read (CPU%) Write (CPU%) Seeks (CPU%)
----- ------ ------- ---- ------------- -------------- --------------
/usr/ 512 4096 1 11.3997 4.96% 6.99304 4.27% 149.242 0.77%
/usr/ 512 4096 2 11.8671 5.47% 6.95879 4.25% 195.759 0.97%
/usr/ 512 4096 4 12.2617 5.69% 6.94252 4.27% 223.820 1.14%
/usr/ 512 4096 8 12.3979 5.78% 6.93575 4.29% 250.433 1.41%
/usr/ 512 4096 16 12.3850 5.82% 6.93202 4.32% 277.247 1.44%
/usr/ 512 4096 32 12.1949 5.82% 6.92113 4.34% 297.975 1.50%
/usr/ 512 4096 64 11.7323 5.81% 6.87402 4.37% 314.251 1.59%
Seeker 1...Seeker 2...Seeker 3...start 'em...done...done...done...
-------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
512 7457 77.8 7367 4.4 4346 7.0 8566 83.0 12819 6.9 235.9 2.4
Cheers,
--
_/\ Christian Reis is sometimes [EMAIL PROTECTED]
\/~ suicide architect | free software advocate | mountain biker
