1 / 18

DENS: Data Center Energy-Efficient Network-Aware Scheduling

This study focuses on the importance of energy efficiency in data centers and proposes a methodology called DENS to achieve a balance between energy consumption, job performance, and data center traffic demands.

salberto
Download Presentation

DENS: Data Center Energy-Efficient Network-Aware Scheduling

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. Dec 20, 2010 DENS: Data Center Energy-EfficientNetwork-Aware Scheduling Dzmitry KliazovichUniversity of Luxembourg Pascal BouvryUniversity of Luxembourg Samee Ullah Khan North Dakota State University

  2. 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 Pascal Bouvry (pascal.bouvry@uni.lu)

  3. Distribution of data center energy consumption Pascal Bouvry (pascal.bouvry@uni.lu)

  4. Data center architectures • Three-tier data center architecture • Most Widely Used Nowadays • Access, Aggregation, and Core layers • Scales to over 10,000 servers Pascal Bouvry (pascal.bouvry@uni.lu)

  5. Data center components memory modules, disks, I/O resources CPU Idle server consumes about 66% of the peak load for all CPU frequencies • Servers’ Energy Model Pascal Bouvry (pascal.bouvry@uni.lu)

  6. Data center 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 consume 0.4W for 100 meter transmissions over twisted pair • 10 GE links consume 1W for 300 meter transmission over optical fiber • Supported power management modes • DVFS, DNS, or both Pascal Bouvry (pascal.bouvry@uni.lu)

  7. Simulator components Chassis ~ 36% Linecards ~ 53% Port transceivers ~ 11% • Switches’ Energy Model Pascal Bouvry (pascal.bouvry@uni.lu)

  8. DENS methodology Data Center Architecture • DENS achieves balance between • Energy consumed by the data center • Individual job performances • Job QoS requirements • Data center traffic demands • DENS is architecture specific Pascal Bouvry (pascal.bouvry@uni.lu)

  9. DENS methodology Avoid Overloading Penalize Under-loaded Servers Favor High Server Utilization Computing server selection Pascal Bouvry (pascal.bouvry@uni.lu)

  10. DENS methodology Favor Low Congestion Levels Penalize Congested Queues Computing server selection Pascal Bouvry (pascal.bouvry@uni.lu)

  11. DENS methodology Maximize Server Load, Minimizing Network Congestion Computing server selection Pascal Bouvry (pascal.bouvry@uni.lu)

  12. Performance Evaluation • GreenCloud simulator is developed • Three-tier data center topology • 1536 nodes, 32 racks, 4 core and 8 aggregation switches Pascal Bouvry (pascal.bouvry@uni.lu)

  13. Performance Evaluation Green scheduler Redistributing Computing Load DENS scheduler Round-robin scheduler Server workload distribution Pascal Bouvry (pascal.bouvry@uni.lu)

  14. Performance Evaluation Network congestion Green scheduler Redistributing Load to Satisfy QoS DENS scheduler Round-robin scheduler Network workload distribution Pascal Bouvry (pascal.bouvry@uni.lu)

  15. Performance Evaluation Network congestion Green scheduler Green scheduler DENS scheduler DENS scheduler Top-of-Rack (ToR) switch load Pascal Bouvry (pascal.bouvry@uni.lu)

  16. Performance Evaluation QoS Energy Data center energy consumption Pascal Bouvry (pascal.bouvry@uni.lu)

  17. Conclusions GreenCloud • We acknowledge • Funding form Luxembourg FNR in the framework of GreenIT project • Research fellowship provided by the European Research Consortium for Informatics and Mathematics (ERCIM) • Related publications • "GreenCloud: A Packet-level Simulator of Energy-aware Cloud Computing Data Centers," in Journal of Supercomputing, special issue on Green Networks, 2011. • “GreenCloud: A Packet-level Simulator of Energy-aware Cloud Computing Data Centers,” IEEE Global Communications Conference (GLOBECOM), Miami, FL, USA, December 2010. Pascal Bouvry (pascal.bouvry@uni.lu)

  18. Thank you! Pascal Bouvry (pascal.bouvry@uni.lu)

More Related