Check out the new USENIX Web site. next up previous
Next: Trace-based experiments Up: Performance Evaluation Previous: Performance Evaluation

Synthetic Workload

In the first experiment, a set of clients repeatedly request the same file, where the file size is varied in each test. The simplicity of the workload in this test allows the servers to perform at their highest capacity, since the requested file is cached in the server's main memory. The results are shown in Figures 6 (Solaris) and 7 (FreeBSD). The left-hand side graphs plot the servers' total output bandwidth against the requested file size. The connection rate for small files is shown separately on the right.


  
Figure 6: Solaris single file test -- On this trivial test, server architecture seems to have little impact on performance. The aggressive optimizations in Flash and Zeus cause them to outperform Apache.
\begin{figure*}
\centering
\centerline{\psfig{figure=graph_sol_filetest.ps,width=5.0in}}
\end{figure*}


  
Figure 7: FreeBSD single file test -- The higher network performance of FreeBSD magnifies the difference between Apache and the rest when compared to Solaris. The shape of the Zeus curve between 10 kBytes and 100 kBytes is likely due to the byte alignment problem mentioned in Section 5.5
\begin{figure*}
\centering
\centerline{\psfig{figure=graph_bsd_filetest.ps,width=5.0in}}
.\end{figure*}

Results indicate that the choice of architecture has little impact on a server's performance on a trivial, cached workload. In addition, the Flash variants compare favorably to Zeus, affirming the absolute performance of the Flash-based implementation. The Apache server achieves significantly lower performance on both operating systems and over the entire range of file sizes, most likely the result of the more aggressive optimizations employed in the Flash versions and presumably also in Zeus.

Flash-SPED slightly outperforms Flash because the AMPED model tests the memory-residency of files before sending them. Slight lags in the performance of Flash-MT and Flash-MP are likely due to the extra kernel overhead (context switching, etc.) in these architectures. Zeus' anomalous behavior on FreeBSD for file sizes between 10 and 100 KB appears to stem from the byte alignment problem mentioned in Section 5.5.

All servers enjoy substantially higher performance when run under FreeBSD as opposed to Solaris. The relative performance of the servers is not strongly affected by the operating system.


next up previous
Next: Trace-based experiments Up: Performance Evaluation Previous: Performance Evaluation
Peter Druschel
1999-04-27