Highlights of validation test findings include:
- TPM remained consistent as load increased. The SQL Server databases remained within 6 percent of the baseline TPM performance, even with all workloads running in parallel.
The Oracle database displayed the same TPM performance during the baseline test and during testing with all the workloads running. No performance loss resulted from the increased workload.
- NOPM for the SQL Server databases remained within 6 percent of the baseline NOPM performance with all the workloads running.
The Oracle NOPM baseline value was the same as the NOPM value with all workloads running in parallel, meaning that no performance loss occurred, even with the increased workload.
- Throughput and IOPS were directly correlated: When the IOPS or the workload increases, the throughput also increases. In our findings, we observed that throughput improved with the scaled complexity of the mixed workloads. For example, when the IOPS (OLTP + DSS) was 6,720, the throughput was 625 MB/s, and when the IOPS (OLTP + DSS + SNAP) was 7,587, the throughput was 714 MB/s.
- Increasing workloads did not affect Oracle database throughput.