| Steven L. Gaede. Perspectives on the SPEC SDET benchmark. Available from http://www. specbench.org/osg/sdm91/sdet/, January 1999. |
....Ousterhout et al. 53] According to Tang [77] the workload does not scale well and is not I O bound. Parallel le accesses do not occur since only one process is used. Chen and Patterson [15] found that IOStone spends less than 25 of the time doing I O, making it unsuitable for our use. SDET [21] simulates a time sharing system used in a software development environment. It simulates a software developer at a terminal typing and executing shell commands. Each user, simulated by a shell script, has an exclusive home directory and executes shell commands independent of other users. ....
Steven L. Gaede. Perspectives on the SPEC SDET Benchmark. Technical report, Lone Eagle Systems, Inc., January 1999.
....the NFS server through a UDP socket, rather than through le system related system calls that in turn trigger NFS requests and receive NFS responses. As a result, the SFS benchmark cannot capture the performance overhead of RFS due to client side logging. To address this issue, we use the SDET [15] benchmark to measure the client side logging overhead. SDET represents the workload typically seen in a software development environment. 5.1 Client Side Logging Overhead Client side logging records the system call parameters for le system related and process related system calls. The kernel ....
S. L. Gaede. Perspectives on the spec sdet benchmark. Jan 1999. http://www.specbench.org/osg/sdm91/sdet/SDETPerspectives.html.
....Our third workload is the deprecated SDET benchmark from SPEC. This benchmark was originally designed to emulate a typical timesharing workload, and was deprecated as the computing landscape shifted from being dominated by timesharing systems to being dominated by networked clients and servers [10]. Nonetheless, as SDET concurrently executes one or more scripts of user commands designed to emulate a typical software development environment (e.g. editing, compiling, and various UNIX utilities) it makes fairly extensive use of the file system. The scripts are generated from a predetermined ....
Gaede, S. "Perspectives on the SPEC SDET Benchmark," http://www.spec.org/osg/sdm91/sdet/
No context found.
Steven L. Gaede. Perspectives on the SPEC SDET benchmark. Available from http://www. specbench.org/osg/sdm91/sdet/, January 1999.
No context found.
Steven L. Gaede. Perspectives on the SPEC SDET benchmark. Available from http://www. specbench.org/osg/sdm91/sdet/, January 1999.
No context found.
S. L. Gaede. Perspectives on the spec sdet benchmark. Department of Computer Science, SUNY Stony Brook, Jan 1999. (http://www.specbench.- org/osg/sdm91/sdet/SDETPerspectives.html).
No context found.
Steven L. Gaede. Perspectives on the SPEC SDET Benchmark. Technical report, Lone Eagle Systems, Inc., January 1999.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC