energy efficiency in cloud data centers: energy efficient vm placement for cloud data centers...
TRANSCRIPT
Energy Efficiency in Cloud Data Centers: Energy Efficient VM Placement for Cloud Data Centers
Doctoral Student : Chaima Ghribi Advisor : Djamal ZeghlacheCo-Author : Makhlouf Hadji
Wireless Networks and Multimedia Services DepartmentCNRS UMR 5157-Samovar, Telecom SudParis
ICWS 2011, Washington DC, USA. Implementation of Communities of Web Service Registries
Summary
Objectives
Proposed Algorithms
Evaluation
Conclusion
page 2 Energy Efficient VM Placement for Cloud Data Centers
ICWS 2011, Washington DC, USA. Implementation of Communities of Web Service Registries
Objectives
page 3 direction ou services <pied de page> Energy Efficient VM Placement for Cloud Data Centers
Energy aware VM placement in cloud data centers.
Propose optimal algorithms for VM allocation and migration to reduce power consumption in cloud data centers
ICWS 2011, Washington DC, USA. Implementation of Communities of Web Service Registries
Framework
page 4 direction ou services <pied de page> Energy Efficient VM Placement for Cloud Data Centers
• Energy-aware VM placement o Responsible for the optimal energy
aware VM placement in the data center.
• Energy consomption estimatoro Relies on energy estimation tools that
use power models to infer power consumption of VMs or servers from resource usage
• Cloud Iaas managero OpenStack, OpenNebula, CloudStacko Control and manage cloud resources,
handle clients requests, schedule and provisioning of VMs
ICWS 2011, Washington DC, USA. Implementation of Communities of Web Service Registries
Proposed algoritms
page 5 direction ou services <pied de page> Energy Efficient VM Placement for Cloud Data Centers
Exact VM placement algorithmo selects where to deploy VMs
Exact VM Migration algorithmo migrates VMs to achieve consolidation
Adapted energy aware best fit algorithmo used for comparison purposes
ICWS 2011, Washington DC, USA. Implementation of Communities of Web Service Registries
VM placement algorithmObjective, conditions & constraints
page 6 direction ou services <pied de page> Energy Efficient VM Placement for Cloud Data Centers
Objectiveo initial VM placement leading to minimum number of used servers
(or containers)
Mathematical Programming Formulationo modelled as a bin packing problem with a minimum power
consumption objectiveVariable comment
m Number of servers
Pj,MaxServer power consumption limit
Pj, current Current power consumption
ej Boolean = 1 if j hosts VM
xij Boolean = 1 if VM I assigned to server j
n Number of requested VMs
ICWS 2011, Washington DC, USA. Implementation of Communities of Web Service Registries7/20
VM placement algorithmModel variables
ICWS 2011, Washington DC, USA. Implementation of Communities of Web Service Registriespage 8 direction ou services <pied de page> Energy Efficient VM Placement for Cloud Data Centers
Objective oOptimize data center power
consumption using dynamic VM consolidation
Mathematical Programming Formulationo Based on linear integer
programming formulation
• Zijk = 1 if VM k migrated from server i to j
• yi = 1 if server i idle and = 0 if at least one VM is active
• m’ = number of non idle servers m’< m
• P’k = power cost when migrating VM k• qi is the total number of VMs hosted on
server i and candidate for migration into destination servers, especially server j in equation
VM Migration algorithm
ICWS 2011, Washington DC, USA. Implementation of Communities of Web Service Registriespage 9 direction ou services <pied de page> Energy Efficient VM Placement for Cloud Data Centers
VM Migration algorithm
Maximize number of empty servers to shut them down by migrating VM to achieve consolidation
Destination VM power budget limit has to be respected
Ensuing migrations forbidden
if a VMk is migrated from a server i (source) to a server j (destination), it can not be migrated to any other server l (l j).
Non idle servers candidate for migration have to be entirely emptied
Equivalent total number of empty servers
Do not migrate a VM whose job is about to end….
ICWS 2011, Washington DC, USA. Implementation of Communities of Web Service Registries
VM Migration algorithm
page 10 direction ou services <pied de page> Energy Efficient VM Placement for Cloud Data Centers
A server candidate to a migration should not migrate its own VMs
A VM can not be migrated to many servers at the same time
ICWS 2011, Washington DC, USA. Implementation of Communities of Web Service Registries
Adapted energy aware best fit algorithm
page 11 direction ou services <pied de page> Energy Efficient VM Placement for Cloud Data Centers
Adaptation of the Best-Fit heuristic which consists of :
Sorting items (VMs) in a decreasing sequence of their power consumption.
Place all the sorted VMs by considering the first item (VM) in a server with a minimum remaining power budget
ICWS 2011, Washington DC, USA. Implementation of Communities of Web Service Registries
Evaluation
page 12 direction ou services <pied de page> Energy Efficient VM Placement for Cloud Data Centers
Proposed algorithms evaluated using the linear solver CPLEX
Estimate expected percentage of energy or power consumption savings when combining the exact allocation and migration algorithms
ICWS 2011, Washington DC, USA. Implementation of Communities of Web Service Registriespage 13 direction ou services <pied de page> Energy Efficient VM Placement for Cloud Data Centers
Evaluation
Comparison between Exact Placement and Best Fit algorithms
ICWS 2011, Washington DC, USA. Implementation of Communities of Web Service Registriespage 14 direction ou services <pied de page> Energy Efficient VM Placement for Cloud Data Centers
Evaluation
Performance comparison of the exact placement algorithm with and without migration
ICWS 2011, Washington DC, USA. Implementation of Communities of Web Service Registriespage 15 direction ou services <pied de page> Energy Efficient VM Placement for Cloud Data Centers
Evaluation
Convergence time of the Exact Placement Algorithm
ICWS 2011, Washington DC, USA. Implementation of Communities of Web Service Registriespage 16 direction ou services <pied de page> Energy Efficient VM Placement for Cloud Data Centers
Evaluation
Convergence time of the Exact Migration Algorithm (m’=5)
Convergence time of the Exact Migration
Algorithm (m’=10)
Convergence time of the Exact Migration
Algorithm (m’=20)
ICWS 2011, Washington DC, USA. Implementation of Communities of Web Service Registriespage 17 direction ou services <pied de page> Energy Efficient VM Placement for Cloud Data Centers
Evaluation
Percentage of gained energy when migration is used
ICWS 2011, Washington DC, USA. Implementation of Communities of Web Service Registriespage 18 direction ou services <pied de page> Energy Efficient VM Placement for Cloud Data Centers
Conclusion
Room for additional energy savings in data centers
through even more efficient algorithms – joint / one
shot scheduling and placement with reduced need for
consolidation
Pursue the quest for more efficient algorithms
Looking currently at scheduling and placement leading
to minimum power or energy consumption using graph
coloring techniques
Chaima Ghribi, Makhlouf Hadji, Djamal Zeghlache, "Energy Efficient VM Scheduling for Cloud Data Centers: Exact Allocation and Migration Algorithms," ccgrid, pp.671-678, 2013 13th IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing, 2013
Published Paper