Autonomic Resource Provisioning for
Cloud-Based Software
Pooyan Jamshidi
Supervisor: Dr. Claus Pahl
In collaboration with: Aakash Ahmad
IC4- Irish Centre for Cloud Computing and Commerce
School of Computing, Dublin City UniversityDepartment of Computer Engineering
Shahid Beheshti University, Tehran, Iran
30th Dec, 2013
Elasticity
Measured
Service
Self
Service
Ubiquitous
Network
Access
Resource
Pooling
~50% = wasted hardware
Actual traffic
~75% = wasted hardwareActual traffic
Really like this??
Capacity we can provision with RobusT2Scale
scale-up =bigger VMs
scale-out = more VMs
SUT Criteria Big spike Dual phaseLarge
variations
Quickly
varying
Slowly
varying
Steep tri
phase
with
RobusT2Scale
饾憻饾憽95% 973ms 537ms 509ms 451ms 423ms 498ms
饾懀饾憵 3.2 3.8 5.1 5.3 3.7 3.9
with
overprovisioning
饾憻饾憽95% 354ms 411ms 395ms 446ms 371ms 491ms
饾懀饾憵 6 6 6 6 6 6
with under
provisioning
饾憻饾憽95% 1465ms 1832ms 1789ms 1594ms 1898ms 2194ms
饾懀饾憵 2 2 2 2 2 2
SLA with 饾挀饾挄饾煑饾煋 = 饾煍饾煄饾煄饾拵饾挃
0
0.02
0.04
0.06
0.08
0.1
alpha=0.1 alpha=0.5 alpha=0.9 alpha=1.0
Benefits
Limitations, open issues
& future directions
~75% = wasted hardwareActual traffic
0
0.02
0.04
0.06
0.08
0.1
alpha=0.1 alpha=0.5 alpha=0.9 alpha=1.0
Top Related