GreenCloud: A Packet-level Simulator of Energy-aware Cloud Computing Data Centers

1. Apr 16, 2010 GreenCloud:A Packet-level Simulator of Energy-aware Cloud Computing Data Centers Dzmitry Kliazovich ERCIM Fellow UniversityofLuxembourg

2. Outline • Data center architectures • Two-tier, three-tier, and three-tier high-speed • Structure of data center simulator • Energy efficiency, simulator components • Case study data center simulations Dzmitry Kliazovich (dzmitry.kliazovich@uni.lu)

3. Why energy is important? • Increased computing demand • Data centers are rapidly growing • Consume 10 to 100 times more energy per square foot than a typical office building • Energy cost dynamics • Energy accounts for 10% of data center operational expenses (OPEX) and can rise to 50% in the next few years • Accompanying cooling system costs $2-$5 million per year Dzmitry Kliazovich (dzmitry.kliazovich@uni.lu)

4. Distribution of data center energy consumption Dzmitry Kliazovich (dzmitry.kliazovich@uni.lu)

5. Data center architectures • Two-tier data center architecture • Access and Core layers • 1 GE and 10 GE links • Full mesh core network • Load balancing using ICMP Dzmitry Kliazovich (dzmitry.kliazovich@uni.lu)

6. Data center architectures • Three-tier data center architecture • Access, Aggregation, and Core layers • Scales to over 10,000 servers • 8-way ECMP load balancing Dzmitry Kliazovich (dzmitry.kliazovich@uni.lu)

7. Data center architectures • Three-tier High-Speed data center architecture • Increased core network bandwidth • 2-way ECMP load balancing • 100 GE standard (IEEE 802.3ba) still in works since Nov 2007 Dzmitry Kliazovich (dzmitry.kliazovich@uni.lu)

8. Data center simulator Greencloud is an extension of NS-2 network simulator for energy-aware cloud computing simulations Provides packet-level simulation dynamics Focused on workload distribution strategies and energy consumption models of simulator components (servers, switches, links, etc.) Dzmitry Kliazovich (dzmitry.kliazovich@uni.lu)

9. Data center simulator Dzmitry Kliazovich (dzmitry.kliazovich@uni.lu)

10. Simulator components • Servers • Responsible for task execution • Single-core nodes • Preset processing limit in MIPS or FLOPS • Supported power management modes • DVFS: Dynamic Voltage/Frequency Scaling • DNS: Dynamic Shutdown • Both: DNS if server is idle, DVFS otherwise Dzmitry Kliazovich (dzmitry.kliazovich@uni.lu)

11. Simulator components memory modules, disks, I/O resources CPU Idle server consumes about 66% of the peak load for all CPU frequencies • Servers’ Energy Model Dzmitry Kliazovich (dzmitry.kliazovich@uni.lu)

12. Simulator components • Switches • Most common Top-of-Rack (ToR) switches typically operate at Layer-2 interconnecting gigabit links in the access network • Aggregation and core networks host Layer-3 switches operating at 10 GE (or 100 GE) • Links • Transceivers’ power consumption depends on the quality of signal transmission in cables and is proportional to their cost • 1 GE links: 0.4W is consumed for 100 meter transmissions over twisted pair • 10 GE links: 1W is consumed for 300 meter transmission over optical fiber • Supported power management modes • DVFS, DNS, or both Dzmitry Kliazovich (dzmitry.kliazovich@uni.lu)

13. Simulator components Chassis ~ 36% Linecards ~ 53% Port transceivers ~ 11% • Switches’ Energy Model Dzmitry Kliazovich (dzmitry.kliazovich@uni.lu)

14. Simulator components • Workloads • Model cloud user applications (social networking, instant messaging, content distribution, etc.) • Workload properties • Computational: MIPS, duration • Communicational: workload size, its internal and external transfers • Generation • Trace-driven • Using random distribution (Exp, Pareto, etc.) Dzmitry Kliazovich (dzmitry.kliazovich@uni.lu)

15. Simulation Setup • Data center architectures • Two-tier (2T), three-tier (3T), and three-tier high-speed (3Ths) • Simulation parameters • Average data center load is 30% • 1536 computing servers • 1, 10, and 100 GE links with 10 ns delay • 4500 bytes workloads (3 Ethernet packets) • 60 minutes of simulation time Dzmitry Kliazovich (dzmitry.kliazovich@uni.lu)

16. Simulation Setup Under-loaded servers, DVFS can be applied Servers at the peak load Idle servers, DNS can be applied Energy-aware “green” scheduler Dzmitry Kliazovich (dzmitry.kliazovich@uni.lu)

17. Evaluation results Distribution of energy consumption in data center Dzmitry Kliazovich (dzmitry.kliazovich@uni.lu)

18. Evaluation results Comparison of energy-efficiency schemes Dzmitry Kliazovich (dzmitry.kliazovich@uni.lu)

19. Conclusions Energy consumption is becoming a concern in cloud computing data centers Developed a packet-level simulator for energy-aware data centers Obtained results compare the performance of dynamic voltage/frequency scaling (DVFS) and dynamic server/network shutdown (DNS) schemes Future work will focus on adding storage area network as well as on the development of novel workload consolidation and traffic aggregation techniques Dzmitry Kliazovich (dzmitry.kliazovich@uni.lu)

20. Thank you! Dzmitry Kliazovich (dzmitry.kliazovich@uni.lu)