论文标题
二重奏基准测试：提高云的测量精度
Duet Benchmarking: Improving Measurement Accuracy in the Cloud
论文作者
论文摘要
我们研究了二重奏测量程序，这有助于通过并行执行测量的工件并共同评估其相对性能，而不是单独评估其相对性能，从而有助于提高在共享机器上进行的性能比较实验的准确性。具体而言，我们分析了该过程在多个云环境中的行为，并使用实验证据回答了有关该过程基础假设的多个研究问题。我们证明，测试的Scalabench（和DACAPO）工作量的准确性范围从2.3倍到12.5倍（平均为5.03倍），而Spec CPU 2017年工作负载的准确性范围从23.8倍到82.4倍（平均为37.4倍）。
We investigate the duet measurement procedure, which helps improve the accuracy of performance comparison experiments conducted on shared machines by executing the measured artifacts in parallel and evaluating their relative performance together, rather than individually. Specifically, we analyze the behavior of the procedure in multiple cloud environments and use experimental evidence to answer multiple research questions concerning the assumption underlying the procedure. We demonstrate improvements in accuracy ranging from 2.3x to 12.5x (5.03x on average) for the tested ScalaBench (and DaCapo) workloads, and from 23.8x to 82.4x (37.4x on average) for the SPEC CPU 2017 workloads.
