So a few weeks ago a colleague pointed out Jimmy’s website about the pmsApp and seeing as we have a few underused blades in our development environment I offered my help to Jimmy.<\/p>\n
He’s already published my findings regarding failover testing of the pmsApp and today I thought I would post some performance metrics. The first set of tests will be using the pmsApp configured to use a RAID1 (software) array.<\/p>\n
In order to run the tests, I have created two guests:<\/p>\n
One running off the pmsApp, PMSTest, and the other running locally on the blade disk (It’s a single disk), PMSControl.<\/p>\n
I have installed CentOS 6.2 minimal install on both of them and installed the openssh-clients package to allow me to use scp.<\/p>\n
Each guest has 512 MB of RAM, a single NIC (dynamically configured (lease time is 36 hours)) and a 8 GB hard drive.<\/p>\n
Generally, speaking I ran three instances of the tests, unless there was a great disparity between the results, in which case I ran extra tests (normally two but sometimes three) and discarded the top and bottom results.<\/p>\n
Generally speaking, the results of the guest running off the pmsApp were considerably less stable.<\/p>\n
Reboot Time :\u00a0 This measures the time taken from typing init 6 and pressing enter to the logon screen appearing. I found this test to be more reliable that pressing reset on the vsphere client or even using powercli.<\/p>\n
PMSControl\u00a0\u00a0\u00a0 PMSTEST (RAID1)
\n34.66 s \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 30.44 s
\n33.02 s \u00a0\u00a0 \u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 27.75 s
\n34.07 s\u00a0 \u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 28.63 s<\/p>\n
This was a clear win for the pmsApp.<\/p>\n
The remaining tests are file copying tests. The source and destination server (depending on the test)\u00a0 was a third blade server running RHEL 6.0. In theory traffic bound for another blade never leaves the enclosure, but I’m not so sure. I ran these tests out of hours so there would have been very little traffic, if any, on the network. I did repeat some tests during the working day for good measure and results were comparable.<\/p>\n
SCP Write –\u00a0 Copy File VMware ESXi 5.0 iso (297 MB) from blade server to Guest<\/p>\n
PMSControl\u00a0\u00a0\u00a0 PMSTEST (RAID1)
\n24.675 s \u00a0 \u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 45.195 s
\n30.980 s\u00a0 \u00a0\u00a0\u00a0\u00a0\u00a0 \u00a0 45.197 s
\n28.505 s \u00a0 \u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 56.486 s<\/p>\n
The pmsApp is clearly slower.<\/p>\n
SCP Read –\u00a0 Copy File VMware ESXi 5.0 iso (297 MB) from Guest to blade server.<\/p>\n
PMSControl\u00a0\u00a0\u00a0 PMSTEST (RAID1)
\n7.764 s \u00a0 \u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 7.762 s
\n8.211 s \u00a0 \u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 7.711 s
\n7.674 s \u00a0\u00a0 \u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 8.017 s<\/p>\n
Reading is a tie.<\/p>\n
SCP Write – Copy Directory containing multiple files (total size 203 MB) from blade server to guest. There is an 87 MB file and a 16 MB file, but the rest are sub 1 MB files.<\/p>\n
PMSControl\u00a0\u00a0\u00a0 PMSTEST (RAID1)
\n12.717 s \u00a0\u00a0 \u00a0\u00a0\u00a0\u00a0 20.572 s
\n13.092 s\u00a0 \u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 18.772 s
\n11.752 s \u00a0\u00a0 \u00a0\u00a0\u00a0\u00a0\u00a0 23.380 s<\/p>\n
Another writing test and the pmsApp is slower again.<\/p>\n
SCP Read – Copy Directory containing multiple files (total size 203 MB) from guest to blade server. There is an 87 MB file and a 16 MB file, but the rest are sub 1 MB files.<\/p>\n
PMSControl\u00a0\u00a0\u00a0 PMSTEST (RAID1)
\n11.531 s \u00a0 \u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 11.623 s
\n10.972 s \u00a0 \u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 11.082 s
\n11.294 s\u00a0 \u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 11.245 s<\/p>\n
Both the pmsApp and the direct guest are faster copying multiple small files than one big one, which is odd as I would’ve expected one big file to be quicker, but the results are consistent on both guests so I’m not too worried. I’d be happy to hear an explanation though.<\/p>\n
A very small set of tests has shown that reading performance is comparable to hosting a guest directly on a disk. Unfortunately, write performance does suffer quite a bit, it’s ~ 40% slower and not very consistent.<\/p>\n
In my next post I intend to use filebench<\/a> to carry out some more tests using a more standardized approach.<\/p>\nShare this:<\/h3>