On Thu 16 Jul 1998, Guenther Grau wrote:
> Hi Leo,
> 
> Leo Weppelman wrote:
> [...]
> > I'll look for it. Here at work, in my clipboard was the following piece of
> > Bonnie data (Note that this was on a 300Mb old MAXTOR, I had one on 1024 and
> > one on 512 byte sector size in my system at that time):
> > 
>>           -------Sequential Output-------- ---Sequential Input-- --Random--
>>           -Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
>> Mach   MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU  /sec %CPU
>> 1K    100   384 60.0   380 11.6   290 13.6   509 99.3   994 23.7  30.0  9.0
>> 
>> 512   100   583 99.0  1110 63.3   559 47.3   508 99.3  1005 46.6  31.5  8.8
>> 
>> 512O  100   583 99.1  1114 64.4   558 50.1   508 99.4  1005 46.6  31.6  8.9
> 
> How come that the 1K-sector is so much slower on output, but about
> the same on input???

Yes, weird isn't it... I have run multiple tests because I didn't believe
it at first, but they were pretty consistent. For completeness, I think
these tests should be repeated on more than 1 type of disk. It might have
been a problem with the maxtor firmware. When I started playing with bigger
sector sizes, I had the idea that 1K blocks should be slightly faster...

Leo.