Workload Characterization of SPECweb 2005 Presentation at SPECworkshop
Workload Characterization of SPECweb 2005 Presentation at SPECworkshop by Rema Hariharan Ning Sun Microsystems
SPECweb 2005 ● ● ● Banking workload – Heavy dynamic content and fully secure Ecommerce workload – Heavy dynamic content, some portion uses SSL Support workload – Heavy static download, no SSL
SPECweb 2005_Banking ● ● ● Users login, check account balance/transfer money/change profile, logout Includes GETs and POST Each dynamic request followed by request for image files (static) ● “ 304” responses ● 2 parallel TCP connections ● One SSL full handshake and one reuse
SPECweb 2005_Banking Stats ● Average number of SW 2005_Ops in a login session = 4. 6 ● Number of TCP connections made per login session = 2 ● ● ● Number of Page requests per TCP connection = 2. 3 Average number of HTTP requests per SW 2005_Op = 12 (average derived from design parameters) So, the average number of HTTP requests per TCP connection = 12*2. 3 = 27. 6 Think Time between SW 2005_Ops = 9. 98 sec Average number of SW 2005 Ops/sec per user session = 0. 149
SPECweb 2005_Banking – Network byte stats
Per 1000 user session stats Banking
SPECweb 2005_Ecommerce ● Based on traffic seen at one of the major Ecommerce sites selling computers ● Uses both http and https requests ● Redirects and “ 304” responses emulated ● Heavy on back-end communication ● ● Includes searches, general browsing, customization and checkout (11 distinct scripts) Product images scale with the benchmark
Some stats for Ecommerce workload ● ● ● Average number of SW 2005_Ops per incoming user session = 8. 8 Number of http ops per SW 2005_Op = 17 Number of SW 2005_Ops/s per user session supported = 0. 093 ● Fraction of sessions that enter the check-out stage = 2/3 ● TCP connections without check out = 2 ● TCP connections with check-out = 4 ● TCP connections/sec per user session supported = 0. 035
Network Characteristics Ecommerce
Per 1000 user session stats Ecommerce
Other bottlenecks for ECommerce ● Memory – more memory intensive than banking ● Performance difference between 8 GB memory configuration and 16 GB memory configuration can be substantial, 10 -20% ● Be. Sim Scaling
SPECweb 2005_Support ● Based on patch download/support site traffic characteristics ● User logs in, searches for the patch and then downloads it. ● Includes dynamic pages and embedded images ● “ 304” responses ● Download size can be as large as 35 MB – follows Zipf distribution for choice of directories and files. ● QOS defined separately for pages and downloads ● Designed to be intensive on Network and Disk IO.
Averages for Support workload ● Average number of SW 2005_Ops in a login session = 14. 5 ● Number of TCP connections made per login session = 2 ● ● ● Number of Page requests per TCP connection = 7. 25 Average number of HTTP requests per SW 2005_Op = 21 (average derived from design parameters) So, the average number of HTTP requests per TCP connection = 7. 25*21 = 152 Think Time between SW 2005_Ops = 4. 98 sec Average number of SW 2005 Ops/sec per user session = 0. 013
Summary Stats – Support Workload
Network Characteristics – Support workload
Zipf Parameter Analysis for Support workload
Questions to answer in the future ● Any other characteristic to represent? ● Do scripts represent real world scripts? ● ● ● How good is the representation of the composite score, currently a relative geometric mean? Is any characteristic represented incorrectly? Are the current workloads unfairly favoring any particular type of architecture, not representing reality?
- Slides: 18