1 / 19

Studying Hardware and Software Trade-Offs for a Real-Life Web 2.0 Workload

Studying Hardware and Software Trade-Offs for a Real-Life Web 2.0 Workload. Authors: Stijn Polfliet et. al. By: Ali Nikravesh. Agenda. Introduction - What is the research question? What is authors’ approach to address the problem? Results. Introduction. Online Social Networking

arnold
Télécharger la présentation

Studying Hardware and Software Trade-Offs for a Real-Life Web 2.0 Workload

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Studying Hardware and Software Trade-Offs for a Real-Life Web 2.0 Workload Authors: StijnPolfliet et. al. By: Ali Nikravesh

  2. Agenda • Introduction - What is the research question? • What is authors’ approach to address the problem? • Results

  3. Introduction • Online Social Networking • Facebook • Twitter • LinkedIn • Netlog • Large number of users  designing the servers and data centres to support social networking is challenging • Large scale data centres  very much cost driven

  4. Introduction (contd.) • Factors that affect the cost of data centre: • Hardware infrastructure • Power and cooling infrastructure • Operating expenditure • Real estate • Increase performance increase cost  • Reduce cost   reduce performance  • RESULT  optimize performance per dollar

  5. Introduction (contd.) • So, which server should be bought? • Depends on workload (interactive, batch, memory intensive,…) • Idea: different workloads run on different hardware • Correct hardware for correct task 

  6. Introduction (contd.) • Research Question: • Scope: Social networking Can we come up with a way of guiding service operators and owners of data centre to what hardware to purchase for a given workload?

  7. Analysis • Social networking workload • Multiple services run on multiple servers in a distributed way in a data center • Fundamental difficulty  performance of the ensemble can only be measured by modeling and evaluating the ensemble  • Authors’ approach: A case study to evaluate how hardware choices affect end-user experience

  8. Case study • Netlog • Is a social network available in 40 languages • Architecture • WS 54% • MC 16% • DB 30%

  9. Experimental Setup • 10 dual AMD Opteron 6168 servers • 12 cores per CPU • 64 GB of main memory • HDD & SSD

  10. Web Server Results • Three CPU frequency • 1.9 GHz • 1.3 GHz • 800 Mhz • Frequency has a significant impact on response time.

  11. Web Server Results (contd.) • Number of cores per node • Four-socket system is typically more than twice as expensive as a two-socket system. • As long as the total number of cores is constant, CPU node is not affected much by node and core count

  12. Database Server • Database server: HDD versus SDD • Although this is a significant reduction in the longest response times observed, it may not justify the significantly higher cost of SSD versus HDD

  13. Memcached Server • Average CPU load for memcached server is typically below 5%

  14. Usecase • Hardware Purchasing • Hardware vendor suggestion: • Web server: Intel Xeon X3480, 8 GB RAM, typical HDD ($1795) • Memcached server: Intel Xeon X3480, 16GB RAM, typical HDD ($2015) • Database server: Intel Xeon X3480, 16GB RAM, SSD ($2915) • Total: $18615 • Suggestion • Web server the same as above. Memcached the same as Web server but lower CPU frequency. DB the same as memcached but not SSD (Total: $15015 – 18.9% reduction) • Performance Evaluation: • 50% of all requests will not experience any extra latency • For other 50%, increase from 11% to 39%

  15. Thanks Questions?

  16. Les important diagrams 1 • Comparing simulation response with actual response packets

  17. Les important diagrams 2 • Sampling in time • Traffic classified by its type

  18. Les important diagrams 3 • Warm-up

  19. Les important diagrams 4 • CPU load as a function of clock frequency • CPU load as a func of cores

More Related