>
> Hi Leonard!
>
> These reports are very interesting. I will try an explanation or just a
> speculation.
[explanation deleted]
> However, I dont think that normal system activity may be affected too
> much by this weird cache balancing behaviour.
I finally found the reason for such a strange behavior that for a long
time has bothered me. I allow myself to disagree with Gerald about
affectiveness. I just tried 2.1.20 and my boot time is significantly
shorter. I went into measuring IDE speed and hdparm -t consistently shows
over 30% improvements. (486/66, IDE PIO 3). I lost access to other, SCSI
system, however I do remember strange and *uncosistent* hdparm -t results
on it. (single user mode!)
Eugene.