23
vGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

Embed Size (px)

Citation preview

Page 1: VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

vGreen: A System for Energy Efficient Manager in Virtualized Environments

G. Dhiman, G Marchetti, T Rosing ISLPED 2009

Page 2: VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

vGreen

• Multi-tiered software system for energy efficient computing and management in virtualized environments.

• Captures power and performance characteristics of virtual machines and develops policies for energy efficient VM scheduling.

• Performance and system level energy savings of 20% and 15%

Page 3: VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

Importance

• Power Consumption critical– because it impacts deployment (peak power delivery)– Affects operational costs (power supply, cooling)

• Current work treats overall CPU utilization of PM and its VM as indicator for power consumption and resource utilization

• Characteristics of co located VMs causes variation in power consumption at similar CPU utilization levels.

Page 4: VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

Solution technique

• vGreen– Understand and exploit relationship between

architectural characteristics of VM and its performance and power consumption.

– Architectural characteristics comprise of instructions per cycle, memory access

– Based on client server model– Vgserv and vgnodes

Page 5: VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

vgserv and vgnodes

• Vgserv– Centralized server– Performs management decisions like scheduling and

DVFS of VMs across PMs– Places VMs across vgnodes to improve overall

performance• Vgnodes– Physical Machines where VMs located– Perform online characterization of the VMs running

on them and updates vgserv

Page 6: VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

Principle and methodology

• Nature of workload executed in each VM determines the power profile and performance of the VM, and thereby its energy consumption.

• VMs with different or same characteristics co-located in same VM

• Characteristics refer to CPU and memory utilization• Two contrasting benchmarks mcf and perl used to

implement heterogeneous characteristics

Page 7: VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

eon and mcf

• mcf– High Memory Accesses per cycle (MPC)– Results in increased cache conflict rate for

multiple instances– Increased execution time

• eon– Has high Instructions per cycle but low MPC– Results in higher utilization of CPU resource

Page 8: VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

Comparison of mcf and eon

Page 9: VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

Conclusion from results

• Co-scheduling VMs with similar characteristics not beneficial from energy efficiency and power consumption point of view.

• mcf contributes to higher system energy consumption because of its longer running time.

• eon contributes to power imbalance as it consumes more power

• Running VMs with mcf and eon on both PMs result in high performance improvement and energy savings upto 20%

Page 10: VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

Power Management in Virtualized

Page 11: VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

Hierarchical Metrics

Page 12: VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

Explanation

• vgpolicy decisions based on value of different metrics, namely MPC, IPC and utilization of different VMs

• These metrics received as updates from vgnodes.• Metrics evaluated and updated dynamically

Page 13: VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

Continued…

• vgxen estimates aggregate metrics (vMPC, vIPC, vutil) for each VM by adding up metrics of constituent VCPU and stores it and exports it to vgpolicy through vgdom vgnode.

• vgdom acts as interface for vgnode to vgserv and registers vgnode with vgserv.

Page 14: VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

MPC balance algorithm

Page 15: VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

Explanation

• Checks if nMPC of n1 greater than threshold MPC.• Return if small otherwise find VM with minimum

vMPC in n1 and migrate it to vgnode with lower nMPC for better balance.

• But migration should not result in the nMPC of new node exceeding threshold MPC.

• Same procedure for IPC.• Utilization is balanced to ensure no overcommitted

or underutilized node exists.• VM consolidation of low utilization VM to idle VM

Page 16: VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

DVFS

• Vgpolicy issues command to scale v-f setting if it is more energy efficient than VM migration.

• Can be required if heterogeneous VMs are absent.

• Exploit characteristics of workload to find v-f setting that is best suited.

• mcf and eon run at 90% CPU utilization levels

Page 17: VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

Different frequency levels

Page 18: VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

MPC, IPC, DVFS

• MPC highest priority– Memory bottleneck impacts performance and

energy efficiency• IPC next– Balanced power consumption, results in uniform

thermal profile and decreases cooling cost.• Utilization for fair distribution of workload.• DVFS when no benefits obtained from VM

scheduling

Page 19: VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

Average Weighted Speedup

• Average Weighted speedup

• Te+i = time of execution of VMi with E+• Tvgreeni = time of execution of VMi with vGreen• Talonei = time of execution of VMi running

alone on VMi

Page 20: VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

Mixed vs Same VM placement

Page 21: VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

Weighted Speedup and Energy Savings

Page 22: VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

Power Consumption

Page 23: VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009

Conclusion• vGreen has negligible runtime overhead• Workload characterization achieves better

performance and energy efficiency• Reduces power consumption variance between two

vgnodes by 80%