RE: heavyweight OS monitoring as standard

  • From: "Tanel Poder" <tanel@xxxxxxxxxx>
  • To: <greg@xxxxxxxxxxxxxxxxxx>, <jeremy.schneider@xxxxxxxxxxxxxx>
  • Date: Wed, 6 May 2009 14:31:04 +0300

Hi Greg,

I may be missing something, but it looks like even collectl --all does not
report the CPU runqueue lengths?!

That's the first thing I look at in vmstat when determining system health -
I must be missing some option there, it's hard to believe that it's not
reported at all?

Tanel Poder

> -----Original Message-----
> From: oracle-l-bounce@xxxxxxxxxxxxx 
> [mailto:oracle-l-bounce@xxxxxxxxxxxxx] On Behalf Of Greg Rahn
> Sent: 06 May 2009 07:29
> To: jeremy.schneider@xxxxxxxxxxxxxx
> Cc: oracle-l@xxxxxxxxxxxxx
> Subject: Re: heavyweight OS monitoring as standard
> I'm a huge fan of collectl for Linux, although I would not 
> consider it heavy weight though it captures quite a bit of 
> different system metrics.


Other related posts: