More Related Content Similar to Selfxl Project Solutions Linux Ow2 (20) More from Catherine Nuel (9) Selfxl Project Solutions Linux Ow21. SelfXL project
Autonomic management of PaaS
cloud infrastructure with JASMINe
Jean-Marc Menaud, Ecole des Mines de Nantes
Benoit Pelletier, Bull
Frédéric Dang Tran, Orange Labs
This research is supported by the french Agence Nationale de la
Recherche with the ANR-08-SEGI-017
18 Mars 2010
2. SelfXL
Self-management of compleX and Large scale
systems
Acquire new processes in the field of the
autonomic computing
© OW2 Consortium 2010 http://selfxl.gforge.inria.fr 2
3. Partners
Bull
Open Source Java EE Middleware R&D
Virtualization system expertise
France Telecom / Orange Labs
R&D expertise in distributed systems architecture,
management of virtual IT infrastructures
Mines de Nantes
Virtualization and constraint programming
expertise.
IRIT
Meta-modelisation expertise.
LIG
Data mediation
ScalAgent
Mediation system
© OW2 Consortium 2010 http://selfxl.gforge.inria.fr 3
4. Cloud Computing at France
Telecom
Context:
Large-scale datacenters (+40,000 x86 servers)
JavaEE JOnAS middleware stack: +250 applications,
+1000 application server instances
Static server consolidation (12/1) through virtualization:
• Utilization level increased from 20% to 75%
Next step: migration to a Cloud model
On-demand JavaEE server provisioning according to
demand fluctuations
Automation of the management of virtualized JavaEE
clusters: deployment, update, auto-scaling etc.
Open (source) cloud management stacks alternatives
to proprietary solutions (IaaS/PaaS)
© OW2 Consortium 2010 http://selfxl.gforge.inria.fr 4
5. Self-sizing for Java EE PaaS
Goal : improve the platform efficiency
(performance, energy cost)
Challenges
Cluster growth/shrink capabilities according to
the load
Datacenter multi-tenancy with limited
capacities requires arbitration policies
Datacenter placement for minimizing the
energy consumption
© OW2 Consortium 2010 http://selfxl.gforge.inria.fr 5
7. JASMINe
Management tools for SOA platform
OW2 Open Source project (license LGPL,
Leadership Bull)
Cross-platform (JOnAS AS prime target)
Four main features (Design, Deploy,
Monitoring, Self-*)
© OW2 Consortium 2010 http://selfxl.gforge.inria.fr 7
8. JASMINe & MAPE loop
Monitor
JMX probes (JavaEE,
Hypervisor)
Mediation bus
Graphs console
Analyse/Plan
Rules engine
Execute
Reconfiguration load-balancer
API
JASMINe Virtual Machine
Management (VMM) for VM
provisioning & deployment
© OW2 Consortium 2010 http://selfxl.gforge.inria.fr 8
9. CLIF is a load injection
framework
CLIF is a software framework for load testing
load injectors (workload generation and response time
measurement) and probes (resources usage monitoring)
open, adaptable/extensible, independent from:
• System Under Test (protocols, probes/observed resources)
• workload definition mode
• user interfaces (Java/Swing, Eclipse, command line...)
distributed infrastructure designed for high level workloads
100% Java (+ specific or native code for system probes)
based on OW2's Fractal component model (fractal.ow2.org)
© OW2 Consortium 2010 http://selfxl.gforge.inria.fr 9
10. CLIF: Self-benchmarking of
JavaEE applications
feedback load injector 1
probes
automatic load injector 2
control
probes
load injector n
measures
Performance
Response 1 JOnAS VM prediction
time
2 JOnAS VM
saturation 3 JOnAS VM
criteria
definition/choice workload
© OW2 Consortium 2010 http://selfxl.gforge.inria.fr 10
11. JASMINe Virtual Machine
Management (VMM)
Support for the following
hypervisors:
Open-source Xen and
KVM
Citrix XenServer
VMware virtualCenter 2.x
Microsoft Hyper-V
© OW2 Consortium 2010 http://selfxl.gforge.inria.fr 11
12. Entropy: Architecture
Entropy is a virtual
machine (VM) manager for
clusters and acts as an
infinite control loop, which
performs a globally
optimized dynamic VM
placement without
downtime according to
cluster resource usage and
scheduler objectives
© OW2 Consortium 2010 http://selfxl.gforge.inria.fr 12
13. Entropy: Dynamic consolidation
Our first result focuses on the dynamic consolidation issue.
Entropy observes the current CPU and memory requirements
of each VM and computes a globally optimized placement of
them that satisfy all their requirements while using a minimum
number of hosts.
© OW2 Consortium 2010 http://selfxl.gforge.inria.fr 13
14. Entropy in Action
Consumption is reduced by 25%
4 Tasks, 3 or 4 servers
4 tasks
4 servers
© OW2 Consortium 2010
Without Entropy
http://selfxl.gforge.inria.fr With Entropy 14
15. To conclude
Conclusion
Self-management of compleX and Large scale
systems
Toward an Open Cloud platform
Future Work
Domain Specific Langage
• Shell Console adminstration
Coordination between levels
Pointers:
ANR SelfXL project: selfxl.gforge.inria.fr
JASMINe: jasmine.ow2.org
Entropy: entropy.gforge.inria.fr
CLIF: clif.ow2.org
© OW2 Consortium 2010 http://selfxl.gforge.inria.fr 15