公开(公告)号：US5303166A

公开(公告)日：1994-04-12

申请号：US868744

申请日：1992-04-14

申请人： Eugenie A. Amalfitano ,  Gregory J. McKnight

发明人： Eugenie A. Amalfitano ,  Gregory J. McKnight

IPC分类号： G06F11/34

CPC分类号： G06F11/3428

摘要： A method and system for automated network benchmark performance analysis which providing a highly realistic benchmark test representative of actual operation of specific software applications, without requiring installation and/or operation of the software applications during testing. Selected software applications generally utilized within a specific network are identified and representative transactions within those applications are executed while tracing the operation of the software application to identify and record input/output operations which occur during those transactions. The recorded list of input/output operations is then utilized to create a benchmark script for utilization in testing which has a high degree of verisimilitude when compared with actual software application operations. Benchmark testing is then performed utilizing the scripted input/output operations and highly accurate performance parameters such as throughput, transactions per second and absolute minimum, maximum and average response times may be determined. Additionally, performance parameter statistics for performance of a selected sequence of input/output operations characteristic of representative transactions may be determined and utilized as a more accurate benchmark for performance than individual response times.

摘要翻译： 一种用于自动化网络基准性能分析的方法和系统，其提供了高度现实的基准测试代表特定软件应用的实际操作，而不需要在测试期间安装和/或操作软件应用。 在特定网络中通常使用的选定的软件应用程序被识别，并且在跟踪软件应用程序的操作以识别和记录在这些事务期间发生的输入/输出操作时，执行那些应用程序内的代表性事务。 然后利用记录的输入/输出操作列表创建一个用于测试的基准脚本，与实际的软件应用程序操作相比，它具有很高的验证性。 然后使用脚本输入/输出操作执行基准测试，并且可以确定诸如吞吐量，每秒事务和绝对最小值，最大和平均响应时间等高精度的性能参数。 此外，可以确定和利用代表性交易特征的所选择的输入/输出操作序列的性能参数统计量作为比单个响应时间更准确的性能基准。