Re: (disk/cpu) kernel performance problem

Mark Lord (mlord@pobox.com)
Mon, 26 Jul 1999 23:02:18 -0400

Gerald Aigner wrote:
..
> Looking into the problem I found that reading large data blocks from
> two IDE disks with the read(2) library/system call consumes about 45%
> of the available CPU time when reading roughly 30 Mbytes/sec.
...

Percentage of CPU time is not a useful measurement.
Think about it.. if I/O were infinitely fast, then CPU usage
would be 100%, since the CPU would never have to wait.

If disk I/O were infinitely slow, CPU usage would be 0%,
but that's not a Good Thing, is it..

Cycle/instruction counts would be useful, if available.

-- 
mlord@pobox.com


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/