Work Package 6 Innovative Cloud-like Management of

Transcript:Work Package 6 Innovative Cloud-like Management of:
Work Package 6 Innovative Cloud-like Management of Grid Services and Resources StratusLab First Periodic Review Brussels, Belgium 4 July 2011 Introduction Description of Work Package WP6 develops advanced technology/features for deployment on existing Cloud infrastructures through automatic deployment and dynamic provision of grid services as well as scalable cloud-like management of grid site resources Objectives The extension of currently available service-level open-source elasticity frameworks on top of cloud infrastructures, The invention of new techniques for the efficient management of virtualized resources for grid services The inclusion of novel resource provisioning models based on cloud-like interfaces Tasks Task 6.1: Dynamic Provision of Grid Services (TID, GRNET) Task 6.2: Scalable and Elastic Management of Grid Site Infrastructure (UCM, TID) Task 6.3: Cloud-like Interfaces Specific for the Scientific Community (UCM, TID) Relationship with others WPs Interactions with WP4 WP4 detected a set of gaps in the architecture that are being filled in WP6 WP4 integrates the developments done in WP6 as part of StratusLab distributions Interactions with users WP5 and WP2 provides requirements to take into account in the functionalities to be developed in WP6 Achievements (Task 6.1) Grid site deployment by using a service manager Grid site specification as a whole in a OVF (images, networks, certificates…) Claudia manages and configure the grid site as a whole Grid site configuration by OVF contextualization Grid site monitoring Infrastructure monitoring by Ganglia Key Performance Indicator (KPI) values by probes Feeding Claudia and OpenNebula from Ganglia information Grid site scalability Introduction of an elasticity framework for scaling up and down the WNs in the grid site Load balancer support Achievements (Task 6.2) Virtual resource placement heuristics Evaluation of placement policies in OpenNebula, using its RANK expression. Improved fault tolerance in OpenNebula, which automatically triggers recovery actions when a physical host or VM fails. Cloud-aware image management techniques Development of a Image Repository in OpenNebula for image management. Support for multiple storage backends to access persistent images, including external catalogues. Cloud-aware virtual network management techniques Dynamic modification of “fixed” virtual networks, which will potentially support an elastic management of public IPs. Automatic setup of simple TCP/UDP firewall rules for VMs. Achievements (Task 6.3) Specification of Cloud services TCloud (OVF) as the Claudia API for service management OCCI (OVF) as OpenNebula API for virtual machine management CDMI as storage service API Authentication and authorization in interaction with OpenNebula Authentication in OpenNebula based on LDAP Authentication based on