Re: Load over 1000

From: Robert Watson <rwatson_at_FreeBSD.org>
Date: Mon, 21 Feb 2005 14:13:55 +0000 (GMT)
On Sun, 20 Feb 2005, Christian Jachmann wrote:

> so load over 1024 should not be usual, right?  it should't occur in
> ordinary practice.  I'm currently testing ULE-scheduler under high load
> works like a charme. 

Load is a property of the load on a system -- most people tend to avoid
high loads because it reflects high contention on system resources, and
usually means that there are more efficient (or effective) ways to get the
same work accomplished.  However, there are times when high loads make
sense -- i.e., if you have several CPU-bound tasks running at different
priorities, then several may be "runnable" at all times, and that some
aren't being serviced isn't a bug.  The reason the load on systems with
many processes is typically low is that most processes are blocked on I/O
-- either waiting for it to complete, waing for a network packet, or
waiting for the user, so they're idle the rest of the time.  The CPU sits
there waiting for the world to catch up...

Robert N M Watson
Received on Mon Feb 21 2005 - 13:15:32 UTC

This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:38:28 UTC