numbers don't lie ...

[Pieter de Goeje]

On Thursday 14 September 2006 19:28, Gary Corcoran wrote:
> The confusing thing is that I thought 'real' time should be >= 'user' +
> 'sys'. But here 'user' is much greater than 'real' for both machines!  The
> sense I got from the other messages in this thread is that 'user' time is
> somewhat meaningless (i.e. unreliable as a measure) in a multi-CPU and/or
> hyperthreading environment.  Can you clarify?

user time = time spent in userland on all logical processors combined.

The right equation is: real * ncpus > user + sys, where ncpus = number of 
active logical processors. 
In the optimal case (perfect parallelism): real * ncpus = user + sys


- Pieter