Re: Request for testing - top 3.8b1 in the base system

From: Oliver Fromme <olli_at_lurza.secnetix.de>
Date: Mon, 29 Sep 2008 09:23:25 +0200 (CEST)
Jeremy Chadwick wrote:
 > On Sun, Sep 28, 2008 at 03:46:45PM -0400, William LeFebvre wrote:
 > > Jeremy Chadwick wrote:
 > > > On Sun, Sep 28, 2008 at 02:24:09PM +0200, Nikola Le??i?? wrote:
 > > > > Is it normal to have 100.64% for cc1?
 > > > 
 > > > I would assume so, as your machine has more than one logical or
 > > > physical processor.
 > > > 
 > > 
 > > No, that was a per-thread display he posted.  Altho undesirable I can  
 > > come up with some plausible reasons why it is exceeding 100%, all  
 > > related to the uncertainty of trying to perform accurate measurements on  
 > > a moving target.  I suppose I could cap the percentage at 100 just for  
 > > aesthetic reasons, and to keep it from overflowing the column.
 > 
 > Ah ha.  That could also explain why gstat(8) has the same problem
 > (%busy column occasionally being >100, sometimes 102-103%).  A simple &
 > 100 on the displayed value should suffice, yep.

I think the reason why gstat(8) occasionally displays
values > 100% is that it doesn't know which value
exactly *is* 100%.

The %busy column should probably be regarded as a
relative measurement and not be taken to provide a
precise number.

Best regards
   Oliver

-- 
Oliver Fromme, secnetix GmbH & Co. KG, Marktplatz 29, 85567 Grafing b. M.
Handelsregister: Registergericht Muenchen, HRA 74606,  Geschäftsfuehrung:
secnetix Verwaltungsgesellsch. mbH, Handelsregister: Registergericht Mün-
chen, HRB 125758,  Geschäftsführer: Maik Bachmann, Olaf Erb, Ralf Gebhart

FreeBSD-Dienstleistungen, -Produkte und mehr:  http://www.secnetix.de/bsd

"One of the main causes of the fall of the Roman Empire was that,
lacking zero, they had no way to indicate successful termination
of their C programs."
        -- Robert Firth
Received on Mon Sep 29 2008 - 05:23:27 UTC

This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:39:35 UTC