From mboxrd@z Thu Jan 1 00:00:00 1970 From: Diwaker Gupta Subject: Re: monitoring domain resource usage Date: Tue, 19 Oct 2004 16:53:19 -0700 Sender: xen-devel-admin@lists.sourceforge.net Message-ID: <1b0b455704101916535c636b00@mail.gmail.com> References: <39CC97884CA19A4D8D6296FE94357BCBAD4FB4@swsmsx404> Reply-To: Diwaker Gupta Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <39CC97884CA19A4D8D6296FE94357BCBAD4FB4@swsmsx404> Errors-To: xen-devel-admin@lists.sourceforge.net List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , List-Archive: To: "Neugebauer, Rolf" Cc: xen-devel@lists.sourceforge.net List-Id: xen-devel@lists.xenproject.org On Tue, 19 Oct 2004 21:52:59 +0100, Neugebauer, Rolf wrote: > There currently is no such tool, however xen exports via the control > interface to dom0 the relevant information. E.g. 'xm list' reports cpu > time consumed per VM. It should be straight forward to implement a tool > periodically calling this interface and compute CPU percentages. This > could either be done via the 'xm' interface or the xen.lowlevel.xc > interface. The latter should have less overhead. I played around with 'xm list' but soon ran into problems. I'm not sure if this is specific to a particular CPU scheduler, or a general problem that others have noticed too. Right now I have xen (booted using sched=atropos) running two VMs, each running a CPU intensive job. However, the cpu-time (as reported by xm list -l) does not seem to be changing *at all*, even across runs lasting for minutes. The uptime gets updated properly, though. Is this a known issue? -- Diwaker Gupta http://resolute.ucsd.edu/diwaker ------------------------------------------------------- This SF.net email is sponsored by: IT Product Guide on ITManagersJournal Use IT products in your business? Tell us what you think of them. Give us Your Opinions, Get Free ThinkGeek Gift Certificates! Click to find out more http://productguide.itmanagersjournal.com/guidepromo.tmpl