[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] Impact of P/C-states on server power with xen-unstable


  • To: "Tian, Kevin" <kevin.tian@xxxxxxxxx>
  • From: Niraj Tolia <ntolia@xxxxxxxxx>
  • Date: Tue, 10 Feb 2009 21:15:26 -0800
  • Cc: xen-devel <xen-devel@xxxxxxxxxxxxxxxxxxx>
  • Delivery-date: Tue, 10 Feb 2009 21:16:16 -0800
  • Domainkey-signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; b=DVNTrBSIOU2Jh3JbNAt/KpGyx23416v9g7vuhgKK5BDgSUOlxuHeYfSL9OreUS3fMB 1MC93zA2N1awRheqnY9Xjeq6zV0UN0SpvK/AxPrWu9brDJ1+tLhNQqRnJd5nhhqeyMIg MZrZKO1C6C44P/cXB8LqHfl/Od2z5269Pnxuc=
  • List-id: Xen developer discussion <xen-devel.lists.xensource.com>



On Tue, Feb 10, 2009 at 6:40 PM, Tian, Kevin <kevin.tian@xxxxxxxxx> wrote:
Hi, Niraj
    C1, i.e 'hlt', is always enabled regardless of cpuidle cmdline option which is about other states deeper than C1. In your box, only C0 and C1 are available as reported and thus it's reasonable for you to observe no difference here. Try other box with more C-states available. :-)
 

Ah. I was working under the assumption that C1 not showing up in xenpm's output meant that hlt wasn't being used but your explanation makes sense. Let me see if I can find other machines to experiment with.

Cheers,
Niraj

 
Thanks,
Kevin


From: xen-devel-bounces@xxxxxxxxxxxxxxxxxxx [mailto:xen-devel-bounces@xxxxxxxxxxxxxxxxxxx] On Behalf Of Niraj Tolia
Sent: Wednesday, February 11, 2009 10:24 AM
To: xen-devel
Subject: [Xen-devel] Impact of P/C-states on server power with xen-unstable

Hi,

So, I was playing with C-states (with and without cpuidle on the xen command line) on Intel Xeons and I discovered that turning C-state support on/off makes no difference in terms of the power used by an idle server.

The processor in question is a Xeon X5355 and, when cpuidle is enabled, xenpm reports a C1 state and will show that the server is ~99.96% resident in C1 when idle. However, the power consumed by a idle server in C1 is virtually identical to that consumed by the server when C-state support is disabled and the idle server is in either P1 or even P0 (both set manually using the userspace governor and xenpm set-scaling-speed). Is the processor doing something that is not exposed to Xen/xenpm? For what it's worth, the power used by the server does show a significant difference between 100% busy CPUs at P0 and P1.

The relevant 'xm dmesg' output for the first core is included below. I am running xen-unstable changeset 19104/31983c30c460.

Cheers,
Niraj


(XEN) cpu0 cx acpi info:
(XEN)     count = 1
(XEN)     flags: bm_cntl[0], bm_chk[0], has_cst[0],
(XEN)            pwr_setup_done[1], bm_rld_set[0]
(XEN)     states[0]:
(XEN)         reg.space_id = 0x0
(XEN)         reg.bit_width = 0x0
(XEN)         reg.bit_offset = 0x0
(XEN)         reg.access_size = 0x0
(XEN)         reg.address = 0x0
(XEN)         type    = 1
(XEN)         latency = 0
(XEN)         power   = 0
(XEN)         dp(@0x00000000)
(XEN) ==cpu0==
(XEN) active state:        C-1
(XEN) max_cstate:        C7
(XEN) states:
(XEN)     C1:    type[C1] latency[000] usage[00000000] duration[0]
(XEN)     C0:    usage[00000000] duration[5708043748]
(XEN) xen_pminfo: @acpi_cpufreq_cpu_init,SYSTEM IO addr space
(XEN) CPU 0 initialization completed


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel

 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.