| 摘要 |
During a technique for estimating a scalability breakpoint of a software product, performance load tests of the software product are performed with different numbers of simulated concurrent users. For a given number of simulated concurrent users, a performance load test may include an associated set of transactions that are executed by the software product. Furthermore, during the performance load tests performance metrics for the transactions in the associated sets of transactions are measured. Then estimated total performance metrics for the transactions in the associated sets of transactions for the different numbers of simulated concurrent users are determined based on the measured performance metrics and the associated sets of transactions. Next, using the determined estimated total performance metrics, the estimated scalability breakpoint is calculated. |
