On Sun, 11 Jun 2000, Hans-Joachim Baader wrote:
> In article <Pine.LNX.4.10.10006110015130.1513-100000@pii.fast.net> you write:
> >Very impressive.
>
> And to get realistic numbers, use a file size of 3 or 4 times the
> memory size ;-)
Sure, how about 4x system memory:
$ iozone 1024 8192
IOZONE: Performance Test of Sequential File I/O -- V2.01 (10/21/94)
By Bill Norcott
Operating System: POSIX 1003.1-1990 -- using fsync()
Send comments to: b_norcott@xway.com
IOZONE writes a 1024 Megabyte sequential file consisting of
131072 records which are each 8192 bytes in length.
It then reads the file. It prints the bytes-per-second
rate at which the computer can read and write files.
Writing the 1024 Megabyte file, 'iozone.tmp'...39.000000 seconds
Reading the file...36.970000 seconds
IOZONE performance measurements:
27531841 bytes/second for writing the file
29043598 bytes/second for reading the file
$ Bonnie -s 1024
File './Bonnie.5693', size: 1073741824
Writing with putc()...done
Rewriting...done
Writing intelligently...done
Reading with getc()...done
Reading intelligently...done
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
1024 7520 99.7 30444 28.3 12277 25.3 8042 97.2 28768 16.4 113.7 0.8
Realistic enough?
> Anyway, IMO SCSI systems are much more responsive than IDE systems
> under load even if the IDE disks seem to be faster. In reality,
> SCSI is faster (and less braindamaged).
Until this week I would have unequivocably agreed. Now, I'm not so sure
that's a fair assessment.
Steve
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Thu Jun 15 2000 - 21:00:25 EST