Dynamic Resource Allocation in
Clouds: Smart Placement with Live
Migration
Makhlouf Hadji
Ingénieur de Recherche
[email protected]
FONDATION DE COOPERATION SCIENTIFIQUE
2
NOS VALEURS
❶
Excellence
❷ Souplesse
- Talents
- Résultats
- Echanges
- Fonctionnement
- Partenariat
- Projets
❸
Rigueur
- Propriété Intellectuelle
- Confidentialité
- Exécution
3
PROGRAMMES DE R&D
Ingénierie numérique des Systèmes et Composants
4
PROJETS R&D
Projets opérationnels depuis le lancement
9
15,5
Projets Opérationnels
M€ Financement Industriel
29
ETP/an sur 3 ans
110
42 Partenaires Industriels
12 Partenaires Académiques
Thèses
5
I- Smart Placement in Clouds
Smart Placement in Clouds
VM Placement problem
Problem: Based on allocating and hosting N VMs on a physical
infrastructure of X Serveurs, what is the best manner to optimally place
workloads to minimize different infrastructure costs ?
Non optimal
placement
ESX 1
ESX 2…
ESX N
VMs demand
management
VMs placement
strategy
Cloud End-Users
???
Optimal
placement
ESX 1
ESX 2…
ESX N
ESX 1
Benefits

Resources optimization,

Minimization of infrastructure costs,

Energy consumption optimization.
Challenges of the problem:
Exponential number of cases to enumerate.

7
ESX 2…
ESX N
Infrastructure servers
Define the best strategy to place VMs workloads
leading to optimally reduce infrastructure costs.
Smart Placement in Clouds

French Providers Point of View
8
Smart Placement in Clouds
Due to fluctuations in
users’ demands, we
use Auto-Regressive
(AR(k)) process, to
handle with future
demands:
Gestion de la
demande de
VM
Utilisateurs des
services Cloud
Forcasting &
Scheduling
k
d t    i d t i   t
large
small
i 1
ESX 1
Problem Complexity :
NP-Hard Problem: One can construct
easily a plynomial reduction from the
NP-Hard notary problem of the BinPacking.
ESX 2…
ESX N
Infrastructure serveurs
9
Smart Placement in Clouds
Mathematical formulation:
N
Formulation as ILP:
The corresponding mathematical
model is an Integer Linear
Programming:
difficulties
to
characterize the convex hull of the
considered problem and the optimal
solution.
I
N
I
min Z    ij yij   Pj xij
i 1 j 1
i 1 j 1
Subject To :
xij  Cij yij , j  I , i  1, N
N
x
i 1
ij
 d j , j  I
xij  N , i, j
1 if VM j is hosted in server i
yij  
 0 else.
10
Smart Placement in Clouds
Minimum Cost Maximum Flow Algorithm
Instance i
(2; 0,23)
S
T
Legend: (capacity; cost)
11
Smart Placement in Clouds
Small Instance
Minimum Cost Maximum Flow Algorithm
(2; 0,23)
Medium Instance
S
T
(2; 0,23)
12
Smart Placement in Clouds
Simulation Tests: Case of (0;1) Random Costs
Random Hosting Costs Scenario
We consider (0; 1) Random hosting costs between each couple of vertices (a, b), where a is a fictif
node, and b is a physical machine (server).
13
Smart Placement in Clouds
Simulations Tests: Case of Inverse Hosting Costs:
Inverse Hosting Costs Scenario
We consider inversed hosting costs function between each couple of vertices (a, b), where a is a fictif
node, and b is a physical machine:
Where
1
g ab 
if Cab  0, otherwise g ab  
f (Cab )
Cab represents the available capacity on the considered arc. f est une fonction non nulle.
14
II- Live Migration of VMs
Live Migration of VMs

Migration process:
Xen
ESX
KVM
Hyper-V
16
Live Migration of VMs
Polyhedral Approachs
Polytops, faces and facets
Min  c j x j
Subject To constraints:
 1x 1
aij x jbi , i1,...,m
xi  0,1 , i  1,..., n
x*
facets
face
 2x 2
20
Live Migration of VMs
Polyhedral Approachs
Some Valid Inequalities of our Problem:

Decision Variables:

Z ijk  1 if A VM k is migrated from i to j (0 else).
Prevent backword migration of a VM:

Z ijk  Z jlk '  1
Server’s destination uniqueness of a VM migration:
m'
Z
j 1, j  i

1
Servers’ power consumption limitation constraints:
m'
qi


ijk
Etc…
i 1 k 1
pk zijk   p j ,max  p j ,current 1  y j 
18
Live Migration of VMs
max M 
m'
P
i 1
i ,idl
qi
m'
m'
i 1
j 1 k 1
yi     p 'k zijk
Polyhedral Approachs
Subject To :
zijk  z jlk '  1, i  1, m, j  i , m', k  1, qi , k '  1, q j , l  1, m', l  j , k  k '
m'
z
j 1, j  i
m'
1
ijk
qi
 p
i 1 k 1
m'
k
zijk  Pj , max  Pj ,current 1  y j 
qi
 z
j 1 k 1
ijk 
qi yi
 m'
  Pj ,current
m'
j 1
yi  m' 

Pj , max

i 1


zijk t k  T0






1 if VM k is migrated from i to j,
zijk  
0 otherwise
1 if server i is idle
yi  
0 otherwise
19
Live Migration of VMs
Polyhedral Approachs
Number of used servers when taking into account Migrations
20
Convergence Time (in seconds) of Migration Algorithm:
21
Live Migration of VMs
Polyhedral Approachs
Percentage of Gained Energy when Migration is Used
5
10
15
20
25
30
10
35,55
36,59
00
00
00
00
20
27,29
34,00
35,23
38,50
00
00
30
17,48
27,39
35,21
40,32
41,89
36,65
40
16,77
18,85
22,02
32,31
39,90
40,50
50
10,86
16,17
19,85
22,30
39,20
36,52
60
08,63
14,29
18,01
22,13
25,15
30,68
70
08,10
14,00
14,86
15,90
22,91
23,20
80
07,01
10,20
10,91
15,34
17,02
21,60
90
06,80
09,32
10,31
14,70
16,97
19,20
100
05,90
07,50
08,40
12,90
16,00
14,97
22
Thank you

浮き輪 浮輪 フロート 大人 子供 プール グッズ 海水浴 水遊び チューブ

NP-hard problems