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

[Xen-devel] disk IO profiling in guest suing sar command

  • To: xen-users <xen-users@xxxxxxxxxxxxxxxxxxx>, xen-devel@xxxxxxxxxxxxxxxxxxx
  • From: Steven <wangwangkang@xxxxxxxxx>
  • Date: Wed, 18 May 2011 16:43:52 -0400
  • Cc:
  • Delivery-date: Wed, 18 May 2011 13:45:14 -0700
  • Domainkey-signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:date:message-id:subject:from:to:content-type; b=KxbEeQElyzvW0gFi8sOS1rYju1PHWOdMUlNmCI+//Mg1DQr56MHJ+FV429HHtbRPg5 ksruACIoxm5zHG+ZW2TdVYUwRRshXthF46GElz+Nl6BiBxJSo99KxnhsIPOA46Lo+RlQ JOxC2ek4x1nOQ9m0Vxbt399IA692loPk8J0ts=
  • List-id: Xen developer discussion <xen-devel.lists.xensource.com>

I am trying to profiling disk IO caused by page miss in memory inside
a guest OS. Both guest and host OS are Fedora 13.
I am using the linux command sar which provide such number of major faults like

                   Number of major faults the system has made per
second, those which have required loading a memory page from disk

Then I started a workloads on both the guest and host OS. As a result,
the guest reports about 1000 majfits, while the host reports only
around 80. So is 1000 majflt is the actual disk IO for that guest? Or
the number of host OS is what I want. Thanks.

- w

Xen-devel mailing list



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