xen-devel.lists.xenproject.org archive mirror
 help / color / mirror / Atom feed
From: Priya <pbhat@acis.ufl.edu>
To: xen-devel@lists.xensource.com, xen-users@lists.xensource.com
Subject: Xen Domains scheduling parameters do not take effect before rebooting
Date: Mon, 19 Jul 2010 12:17:36 -0400	[thread overview]
Message-ID: <AANLkTiloi9wXeFP0blKBZu6xEcCDlyEfQVq9smGWzAEt@mail.gmail.com> (raw)


[-- Attachment #1.1: Type: text/plain, Size: 1284 bytes --]

Dear all,

I am not observing a change in the performance of my hardware-assisted
virtual machines (HVMs) when I change the scheduling parameters (weight and
cap) associated with the HVMs unless they are rebooted.

I am testing using 2 HVMs running Linux kernels (2.6.24-26-generic) in the
guest operating system. My hardware is 1 x Intel(R) Core(TM)2 Duo CPU
E8400 @ 3.00GHz. I have pinned my Domain-0 to physical CPU-0 and the 2 HVMs
to physical CPU-1. In order create a load on my HVMs I run the "glxgears"
API and monitor the performance using "xentop" (and from the movement of the
gears, on the pop-up screen). I use the "xe" CLI to set and check the
scheduling parameters.

I have experimented with setting the cap and weight of one domains to the
least  possible value (1, 1 respectively) and that of the other to the
maximum possible value (0 and 65536 respectively), the initial cap and
weight of both domains being at the default setting of 0 and 256, but the
processor utilization remains unchanged (at 50% for both domains) unless I
reboot my HVMs. Once I do that, I can see the expected (enormous) difference
in the performance.

Is it not possible to change processor utilization without having to reboot
the HVMs? What am I missing here?
Please help!


-- 
Priya Bhat

[-- Attachment #1.2: Type: text/html, Size: 1477 bytes --]

[-- Attachment #2: Type: text/plain, Size: 138 bytes --]

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

                 reply	other threads:[~2010-07-19 16:17 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=AANLkTiloi9wXeFP0blKBZu6xEcCDlyEfQVq9smGWzAEt@mail.gmail.com \
    --to=pbhat@acis.ufl.edu \
    --cc=xen-devel@lists.xensource.com \
    --cc=xen-users@lists.xensource.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).