The metrics of the application workloads within each tile are computed and aggregated into a score for that tile. This aggregation is performed by first normalizing the different performance metrics (such as actions/minute and operations/minute) for a reference platform. Then, a geometric mean of the normalized scores is computed as the final score for the tile. The resulting per-tile scores are then summed to create the application-workload portion of the final metric.
The metrics for the infrastructure workloads are aggregated separately using the same mathematical technique of normalization for a reference platform followed by the computation of the geometric mean. Unlike the application workloads, the user does not explicitly scale infrastructure workloads. Therefore, the infrastructure workloads are compiled as a single group and no multitile sums are required.
The performance of each workload in every tile is combined with the performance of the infrastructure operations to determine the overall benchmark score. The final benchmark score is computed as a weighted average: 80 percent to the application workload component and 20 percent to the infrastructure workload component.
The three published results met all QoS thresholds and are compliant with VMmark 3.x run and reporting rules. The following table shows the submitted test results that include the infrastructure operations and associated statistics:
Table 10. Performance
vMotion (number of operations per hour) | 28.00 | 28.50 | 28.00 |
SvMotion (number of operations per hour) | 24.00 | 26.00 | 25.00 |
XvMotion (number of operations per hour) | 20.00 | 21.00 | 21.00 |
Deploy (number of operations per hour) | 6.5 | 6.5 | 6.5 |
Applications score | 11.18 | 13.90 | 14.81 |
Infrastructure score | 1.07 | 1.11 | 1.09 |
VMmark 3 performance score (80% of applications score + 20% of infrastructure score) | 9.16 @ 10 tiles | 11.34 @ 12 tiles | 12.06 @ 13 tiles |
The published results are available at:
