mela: monitoring and analyzing elasticity of cloud services -- cloudcom 2013
DESCRIPTION
Cloud computing has enabled a wide array of applications to be exposed as elastic cloud services. While the number of such services has rapidly increased, there is a lack of techniques for supporting cross-layered multi-level monitoring and analysis of elastic service behavior. In this paper we introduce novel concepts, namely elasticity space and elasticity pathway, for understanding elasticity of cloud services, and techniques for monitoring and evaluating them. We present MELA, a customizable framework that enables service providers and developers to analyze cross-layered, multi-level elasticity of cloud services, from the whole cloud service to service units, based on service structure dependencies. Besides support for real-time elasticity analysis of cloud service behavior, MELA provides several customizable features for extracting functions and patterns that characterize that behavior. To illustrate the usefulness of MELA, we conduct several experiments with a realistic data-as-a-service in an M2M cloud platform. Prototype and Demos at http://tuwiendsg.github.io/MELA/ Paper DOI: http://dx.doi.org/10.1109/CloudCom.2013.18TRANSCRIPT
Daniel Moldovan,Georgiana Copil, Hong-Linh Truong,
Schahram Dustdar
MELA: Monitoring and Analyzing Elasticity of Cloud Services
Work partially supported by the European Commission in terms of the CELAR FP7 project (http://www.celarcloud.eu/)
Distributed Systems Group (http://dsg.tuwien.ac.at/)
Vienna University of Technology (http://www.tuwien.ac.at/)
MotivationElastic Cloud Service
2
Data-as-a-Service for Machine to Machine platforms Load balancer distributes incoming requests to Event Processing instances Distributed Data Store: Controller and Nodes
Start with an initial lighter configuration
MotivationElastic Cloud Service
2
Data-as-a-Service for Machine to Machine platforms Load balancer distributes incoming requests to Event Processing instances Distributed Data Store: Controller and NodesAdd service unit instance when load
increases
MotivationElastic Cloud Service
2
Data-as-a-Service for Machine to Machine platforms Load balancer distributes incoming requests to Event Processing instances Distributed Data Store: Controller and NodesRemove service unit instance when load
decreases
MotivationElastic Cloud Service
2
Data-as-a-Service for Machine to Machine platforms Load balancer distributes incoming requests to Event Processing instances Distributed Data Store: Controller and Nodes
Add service unit instance and data node instance when load increases too much
Service Level Monitoring Response time Number of clients Other specific metrics
System Level Monitoring Ganglia, Nagios, etc. CPU usage Memory usage Network transfer
User-Defined Requirements violation: - Cost per client too highReasons: - Too much logging? Monitoring chatter? - Too expensive VMs? Which one can be downsized? - Not enough clients? Why?
Controlling the service’s elasticity
3
MotivationInsufficient Cloud Service Monitoring and Analysis Support
Approach and ChallengesStructure Monitoring Data
How to map system data to service level? How to derive higher level information?
4
Monitoring Data
Service Structure
Impose service structure over collected monitoring data
Multi-Level Monitoring Snapshot
5
Metrics composition and enrichment
Multi-Level Monitoring Snapshot
5
Multi-Level Monitoring Snapshot
5
Enrich metric with COST information
COST/VM * numberOfVMs
Multi-Level Monitoring Snapshot
5
Propagate activeConnections from LoadBalancer service unit
Multi-Level Monitoring Snapshot
5
Multi-Level Monitoring Snapshot
5
Multi-Level Monitoring Snapshot
5
Compute cost/client/h
Evaluate Service’s Elasticity How to characterize service elasticity? How to derive service‘s behavior limits? How to characterize and predict elasticity behavior?
Approach and Challenges
6
Runtime Properties of Elastic Cloud Services Background
Elastic process: cost, quality and resources elasticity Extend concept to cloud services
Elasticity Space Collection of monitoring snapshots I.e. the space in which an elastic service moves
Elasticity Boundary Elasticity Space boundaries in which service’s requirements are
respected
Elasticity Pathway Characterizes service evolution trough elasticity space
Elasticity Dimensions
16
Multi-Level Elasticity SpaceEvent Processing Topology
8
Elasticity Space Snapshot
Elasticity Space “Clients/h” Dimension
Elasticity Space “Response Time” Dimension
Service requirement COST<= 0.0034$/client/h 2.5$ monthly subscription for each
service client (sensor)
Multi-Level Elasticity SpaceEvent Processing Topology
Service requirement COST<= 0.0034$/client/h 2.5$ monthly subscription for each
service client (sensor)
8
Elasticity Space “Clients/h” Dimension
Elasticity Space “Response Time” Dimension
Determined Elasticity Space Boundaries Clients/h > 148 300ms ≤ ResponseTime ≤ 1100 ms
Multi-Level Elasticity Pathway
9
Service requirement COST<= 0.0034$/client/h 2.5$ monthly subscription for
each service client (sensor)
Multi-Level Elasticity Pathway
9
Cloud Service Elasticity Pathway
Service requirement COST<= 0.0034$/client/h 2.5$ monthly subscription for
each service client (sensor)
Multi-Level Elasticity Pathway
9
Event Processing service unit Elasticity Pathway
Cloud Service Elasticity Pathway
Service requirement COST<= 0.0034$/client/h 2.5$ monthly subscription for
each service client (sensor)
Conclusions
10
Concepts Elasticity Space and Elasticity Boundary Elasticity Pathway
Mechanisms Constructing cross-layer monitoring snapshots Determining elasticity space and boundary Determining elasticity pathway
MELA Customizable framework for monitoring and
analyzing elasticity of cloud services
MELA: Monitoring and Analyzing Elasticity of Cloud Services
Work partially supported by the European Commission in terms of the
CELAR FP7 project (http://www.celarcloud.eu/)
Distributed Systems Group(http://dsg.tuwien.ac.at/)
Vienna University of Technology (http://www.tuwien.ac.at/)
http://dsg.tuwien.ac.at/research/viecom/mela/