1 / 7

USTH Presentation

USTH Presentation. Power-aware Scheduler for Virtualization TRAN Giang Son gtran@enseeiht.fr Prof. Daniel HAGIMONT Oct 19th, 2011. Energy saving. Data center: Large amount of Computers Network devices Air conditioners Almost no monitor, keyboard / mouse Wattage / computer: ~150W

maddoxa
Download Presentation

USTH Presentation

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. USTH Presentation • Power-aware Scheduler for • Virtualization • TRAN Giang Son • gtran@enseeiht.fr • Prof. Daniel HAGIMONT • Oct 19th, 2011

  2. Energy saving • Data center: Large amount of • Computers • Network devices • Air conditioners • Almost no monitor, keyboard / mouse • Wattage / computer: ~150W • Save power from computers

  3. Virtualization • Multiple operating systems on a same machine • Windows • Linux • Unix • Solaris • OS running in Virtual Machines • Maximize hardware utilization • Save power

  4. Virtualization • Customer • Needs hardware to run applications • Just enough hardware performance • Less $ • Hardware provider • Provides hardware platform • Guarantees performance • Less power

  5. Research work • Autonomic management in hypervisor • From grid scale to machine scale • Computers → Virtual machines • Analyzed Xen hypervisor • Most widely used • Open source • Credit scheduler

  6. Research work • Proposed an enhanced scheduler • Distributes CPU power to VMs • Performance impact (or better!) • Power-aware • Experiments • Comparison with existing solutions • Improvements in power saving • Papers

  7. How? • CPU frequency control • Monitor module • Decision making • Keep lowest frequency as possible • Dynamically changes VM's “cap” • Guarantees Service Level Agreement • Virtual machine performance

More Related