In two recent blogs I described test I performed to validate a Citrix VDI-in-a-Box and the HP ProLiant reference architecture. The solution goes a long way to simplify VDI deployment task because it defines a low cost approach punch to rapidly deploy VDI. Previously, I ran a series of single-server scalability tests to validate 50- and 100 configurations users based on the reference architecture and a series of stress tests.
During this test, I was thinking about how to expand performance measures beyond the parameters for the infrastructure components - I wanted to incorporate client / user and capture the overall experience of the user. For this reason, I have developed a method of recording the user experience (UX) data at runtime scalability tests. This blog sharing my results and recent testing data samples VDI-in-a-Box UX. If you want to understand the testing methodology UX I used, I have written a separate blog on this topic.
Capturing VDI-in-a-Box User Experience
As in previous scalability testing, I ran a series of tests using single server a Login VSI average with flash workload, test the user capacity of 75 to 100 users. In short, my test harness UX uses a dedicated launcher and a physical client system to create a baseline that acts as a "canary in the coal mine." The baseline provides a point for workloads of remaining users of comparison. The testbed then captured metrics since the start of the test through the entire run Login VSI. Furthermore, I recorded videos to illustrate the user experience and to corroborate the data collected.
The results of the test 100-user
This is a comparison between baseline and VSI workload loops in the 100- VDI-in-a-Box user test. graphs below the data show for the baseline and four consecutive years Login VSI workload loops:
- Baseline Test (1 user)
- 100 user test
o 1 VSI loop (25 users)
o 2nd VSI loop (50 users)
o 3rd VSI loop (75 users)
o 4th VSI loop (100 users, with 0 seconds of steady state activity)
(to understand what constitutes a VSI loop please see the test video, discussed below.)
in the tables above, you can compare the baseline Log VSI test loop for the following loops to evaluate the user experience during the two connection / rise and phase equilibrium state of the test. You can see clearly corresponding to models with only a small amount of gap between the loops, indicating that the user experience in the subsequent test loops closely approximates that of the baseline.
The table below the graph and ICART FPS average metric for the base line of the following user and test loops. Again, the data indicate that the tested configuration VDI-in-a-Box maintains near baseline levels of performance. 
Support Video Test
During test execution, I record videos to validate the collected UX parameters. I created this short video comparing the composite core experience VDI-in-a-Box user to the last section of the test 100 users, which is when the server is at its peak. Video corroborate the data collected, illustrating how the UX of the fourth loop closely approximates that of the recorded baseline.
The video UX and associated metrics form one leg of a three-legged stool that represents my overall VDI tests in-a-Box scalability test-Login VSI (the measure application response time ) and PerfMon scripts (the railway infrastructure performance data) are the other two legs. The UX test is used to validate the results I have seen in other series of scalability tests. For example, during a phase of the 100-user test, I observed spikes in certain storage parameters, including average length of the disk queue (as shown below). However, video and UX parameters confirmed that maintained satisfactory usability configuration, even during these peaks storage performance.
length of the average disk queue (100-user test with eight 10,000 RPM SAS)
Summary
the purpose of the UX test was to examine how the VDI-in-a-Box solution scaling the view point of a user. Even with higher than expected storage statistics, the video provided a visual reference qualitative and quantitative data UX, confirming a consistent quality to the overall user experience.
References
- Virtualization HP SMB client reference architecture for Citrix VDI-in-a-Box (PDF)
- User Experience test video
- measurement of user experience (Blog)
- HP and Citrix VDI-in-a-Box: Part 1 - reference architecture scaling (Blog)
- HP and Citrix VDI-in-a-Box: Part 2 - Pushing the limits (Blog)
0 Komentar