On Sun, 14 Apr 1996, J Wunsch wrote:
> As Gerard Roudier wrote:
>
> Many things have already been written...
>
> > File Read (10 seconds) 209771.0 KBps (10 secs, 1 samples)
> > File Read (30 seconds) 212303.0 KBps (30 secs, 1 samples)
>
> Of course, in case this should read as ``kilobytes per second'', it is
> a good indication for the poor benchmark. It measures (if anything)
> just the buffer cache. Must have been a rather small file.
>
> Real disks are < 10 MB/s these days, at least those that are in common
> use, so it's obvious that the figures are off by at least factor 30.
>
> Well, perhaps the file performance tests were run on a memory file
> system though... :-))
Whole Linux seems to be a memory file system ;-) They are caching
like hell. Only benchmarks like bonnie on files of about 3xRAMSIZE
address the fact that we want to bench the disk and not the RAM.
Gerard compares chicken with eggs. This Byte Bench is really
questionable.
Another thing he is certainly missing is, that he has to use
128 HZ, to get the correct results with the times function.
- --
andreas@knobel.gun.de /\/\___ Wiechers & Partner Datentechnik GmbH
Andreas Klemm ___/\/\/ $$ Support Unix - aklemm@wup.de $$
pgp p-key http://www-swiss.ai.mit.edu/~bal/pks-toplev.html >>> powered by <<<
ftp://sunsite.unc.edu/pub/Linux/system/Printing/aps-491.tgz >>> FreeBSD <<<
-----BEGIN PGP SIGNATURE-----
Version: 2.6.2
iQCVAwUBMXFqRvMLpmkD/U+FAQF/CgP/YfRpQ0ypheunmjgjxkdyOkaGUKVRRmF5
l00BqSuh1+fitOXhhBApD50guUk+uBDZkIuyKmrA4OcRALskxzUGFzKcYfibn9QV
3tFPGW5EXcTA6gm2BtyRK715GTQBkAC+jVlKFmx9xL8lQ6+9ql6W9AbZEwwDEUco
5H9tMoLLVsk=
=TwMd
-----END PGP SIGNATURE-----