Re: Re: hard disk performance on Allnet 6500 (like Thecus N2100)

[Stefan Fritsch <sf@sfritsch.de>]

Lennart Sorensen wrote:
> I believe a bug was found at some point in hdparm that caused it to
> generate incorrect test values (of by a factor of 2 as far as I
> remember).  This would cause comparing the results between old
> (broken) and new (fixed) versions of hdparm to look as if things
> had suddenly gotten much worse.

The Thecus tarball I downloaded has hdparm 6.1, current is 7.7. I 
compiled 6.1 (on my desktop), and I get a factor two speed difference 
for hdparm -T (Timing cached reads), but no difference for hdparm -t 
(Timing buffered disk reads). Therefore I don't think it is only a 
hdparm problem. The factor 9 for cached reads is probably just a 
factor 4.5, but the factor 2.5 for buffered disk reads seems to be 
real.

Cheers,
Stefan