<html>
<head>
<meta content="text/html; charset=windows-1252"
http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
On 4/14/2015 3:52 PM, Jatin Davey wrote:<br>
<blockquote cite="mid:552CEA79.2050002@cisco.com" type="cite">
<meta http-equiv="Content-Type" content="text/html;
charset=windows-1252">
<font face="Times New Roman">Hi All<br>
<br>
We are currently testing our product using KVM as the
hypervisor. We are not using KVM as a bare-metal hypervisor. We
use it on top of a RHEL installation. So basically RHEL acts as
our host and using KVM we deploy guests on this system.<br>
<br>
We have all along tested and shipped our application image for
VMware ESXi installations , So this it the first time we are
trying our application image on a KVM hypervisor.<br>
<br>
On this front i have done some tests to find out how our
application's response time is when deployed on KVM and then
compare it with a VM deployed on VMware ESXi. We have a
benchmark test that basically loads the application simulating a
load of 100 parallel users logging into the system and
downloading reports. These tests basically use a HTTP GET query
to load the application VM. In addition to that i have taken
care to use the same hardware for both the tests , one with
RHEL(Host)+KVM and another with VMware ESXi. All the hardware
specifications for both the servers remain the same. The load
test also remains the same for testing with both the servers.<br>
<br>
First observation is that the average response time on the
VMware ESXi is : 500 milli-seconds while the application's
average response time when deployed using RHEL(Host)+ KVM is :
1050 milli-seconds. The response time of the application when
deployed on KVM is twice as much as when it is deployed using
VMware ESXi.<br>
<br>
I did few more tests to find which sub-system on these servers
shows varying metrics.<br>
<br>
First i started with IOZone to find out if there is any mismatch
in the speed with which data is read / written to the local disk
on the two VMs and found that "Read" speed in the VM that was
deployed using RHEL(Host)+KVM was twice as slow as the VM which
was deployed using VMware ESXi.<br>
<br>
For more on IoZone , Please refer : <a moz-do-not-send="true"
class="moz-txt-link-freetext" href="http://www.iozone.org/">http://www.iozone.org/</a><br>
<br>
more specifically the following IoZone metrics were twice as
less when compared to the server running with VMware ESXi:<br>
<br>
</font><font face="Times New Roman"> </font>
<table style="border-collapse: collapse;width:150pt" border="0"
cellpadding="0" cellspacing="0" width="199">
<colgroup><col
style="mso-width-source:userset;mso-width-alt:6958;width:150pt"
width="199"> </colgroup><tbody>
<tr style="height:14.5pt" height="19">
<td style="height:14.5pt;width:150pt" height="19"
width="199">Read</td>
</tr>
<tr style="height:14.5pt" height="19">
<td style="height:14.5pt" height="19">Re-read</td>
</tr>
<tr style="height:14.5pt" height="19">
<td style="height:14.5pt" height="19">Reverse-Read</td>
</tr>
<tr style="height:14.5pt" height="19">
<td style="height:14.5pt" height="19">Stride Read</td>
</tr>
</tbody>
</table>
<table style="border-collapse: collapse;width:150pt" border="0"
cellpadding="0" cellspacing="0" width="199">
<colgroup><col
style="mso-width-source:userset;mso-width-alt:6958;width:150pt"
width="199"></colgroup><tbody>
<tr style="height:14.5pt" height="19">
<td style="height:14.5pt;width:150pt" height="19"
width="199">Pread</td>
</tr>
</tbody>
</table>
<font face="Times New Roman"> <br>
Note: I had run the IoZone tests on the VMs on both the servers.<br>
<br>
Second observation to be made was the output from the "top"
command. I could see that the VM deployed on RHEL(Host)+KVM was
showing high numbers for the following metrics when compared
with the VM deployed on VMware ESXi:<br>
<br>
load averages<br>
%sy for all the logical processors<br>
%si for all the logical processors<br>
<br>
i debugged further to find out which device is causing more
interrupts and found it to be "ide0" , See the output from the
/proc/interrupts file below:<br>
The other interrupts apart from ide0 are pretty much similar to
the VM deployed using VMware ESXi.<br>
<br>
************/proc/interrupts *******************<br>
[root@localhost ~]# cat /proc/interrupts<br>
CPU0 CPU1 CPU2 CPU3
CPU4 CPU5 CPU6 CPU7<br>
0: 795827 0 0 0
0 0 0 0 IO-APIC-edge timer<br>
1: 65 0 0 0
0 0 0 0 IO-APIC-edge i8042<br>
6: 2 0 0 0
0 0 0 0 IO-APIC-edge floppy<br>
8: 0 0 0 0
0 0 0 0 IO-APIC-edge rtc<br>
9: 0 0 0 0
0 0 0 0 IO-APIC-level acpi<br>
10: 425785 0 0 0
0 0 0 0 IO-APIC-level virtio0,
eth0<br>
11: 47 0 0 0
0 0 0 0 IO-APIC-level
uhci_hcd:usb1, HDA Intel<br>
12: 730 0 0 0
0 0 0 0 IO-APIC-edge i8042<br>
14: 188086 0 0 0
0 0 0 0 IO-APIC-edge ide0<br>
NMI: 0 0 0 0
0 0 0 0<br>
LOC: 795813 795798 795783 795767 795752
795737 795723 795709<br>
ERR: 0<br>
MIS: 0<br>
*********************************************<br>
<br>
Any pointers to improving the response time for the VM for
RHEL(Host)+KVM installation would be greatly appreciated.<br>
<br>
Thanks<br>
Jatin<br>
<br>
</font> <br>
<fieldset class="mimeAttachmentHeader"></fieldset>
<br>
<pre wrap="">_______________________________________________
libvirt-users mailing list
<a class="moz-txt-link-abbreviated" href="mailto:libvirt-users@redhat.com">libvirt-users@redhat.com</a>
<a class="moz-txt-link-freetext" href="https://www.redhat.com/mailman/listinfo/libvirt-users">https://www.redhat.com/mailman/listinfo/libvirt-users</a></pre>
</blockquote>
Forgot to provide this information.<br>
<br>
We are using RHEL(Host):<br>
<br>
[root@localhost ~]# cat /etc/*release<br>
LSB_VERSION=base-4.0-amd64:base-4.0-noarch:core-4.0-amd64:core-4.0-noarch:graphics-4.0-amd64:graphics-4.0-noarch:printing-4.0-amd64:printing-4.0-noarch<br>
Red Hat Enterprise Linux Server release 6.5 (Santiago)<br>
Red Hat Enterprise Linux Server release 6.5 (Santiago)<br>
<br>
and the Qemu being used is: <br>
<br>
virsh # version<br>
Compiled against library: libvirt 0.10.2<br>
Using library: libvirt 0.10.2<br>
Using API: QEMU 0.10.2<br>
Running hypervisor: QEMU 0.12.1<br>
<br>
Thanks<br>
Jatin<br>
</body>
</html>