processes not getting fair share of available disk I/O (was: Re: TCP parameters and interpreting tcpdump output )

[Dieter]

> I'm surprised that you're seeing that much of a "hang".  Even if the disks
> are busy, the system should slow down all disk processes equally, so no
> one process "blocks", but they're all a little slower.

I collected a bit of data:

While copying a large file from disk1 to disk2,

time ls on a small directory on disk3 (not cached in memory)

real    0m0.032s
user    0m0.000s
sys     0m0.003s

time ls on a small directory on disk2

real    4m51.911s
user    0m0.000s
sys     0m0.002s

I expect access to a busy disk to take longer, but 5 minutes is
a bit much.  And that's the root directory of the filesystem,
it didn't have to follow a long chain of directories to get there.

Sometimes I see long delays when accessing disk3, but it is
behaving at the moment.