Documentation Cluster Beat

HA Cluster Infrastructure

The Ha Cluster Infrastructure in F11 includes major changes and new features including hundreds of bug fixing and a major boost in peformance.

New Features from upstream

• The Corosync Cluster Engine
  • Provides a plug-in based cluster engine uing the virtual synchrony communications model.
    • Well considered plugin model and API.
    • Ultra high performance messaging, up to 300k messages/sec to a group of 32 nodes for ervice engine developers.
    • Provides most services for service engine developers.
    • Standard on many Linux distributions.
  • Default plug-in service engines and C APIs:
    • Closed Process Group Communication C API for cluster communications
    • Extended Virtual Synchrony passthrough C API for cluster communications at a lower level
    • Runtime Configuration Database C API for cluster configuration
    • Configuration C API for runtime cluster operations
    • Quorum engine C API for providing information related to quorum
  • Reusable C Libraries or headers tuned for high performance and quality
    • Totem Single Ring and Redundant Ring Multicast Protocol
    • Shared memory IPC system with sync and async communications models usable by other projects
    • logsys flight recorder which allows logging and tracing of complex applications and records state in core files or at user command
    • 64 bit handle to data block mapping with handle verification

• openais, that provides an implementation of the Service Availability Forum Application Interface Specification for application clustering:
  • Packaging and design changes
    • All core features from openais related to clustering merged into The Corosync Cluster Engine.
    • openais modified to work as plugins to the Corosync Cluster Engine
  • Provides implementation of various Service Availability Forum AIS Specifications as corosync service engines and C APIs:
    • Cluster Membership B.01.01
    • Checkpoint Service B.01.01
    • Event Service B.01.01
    • Message Service B.01.01
    • Distributed Lock Service B.01.01
    • Timer Service A.01.01
    • Experimental Availability Management Framework B.01.01

• cluster is now based on both corosync and openais and offers:
  • pluggable configuration mechanism:
    • xml (default)
    • ldap
    • corosync/openais file format
  • Cluster manager (cman):
    • CMAN FEATURES HERE
    • QDISK FEATURES HERE
  • DLM - Distributed Lock Manager:
    • DLM FEATURES HERE
  • fence / fence agents:
    • unfencing
    • FENCE FEATURES HERE
  • rgmanager:
    • RGMANAGER FEATURES HERE

Packaging changes

Lots of effort has been done to cleanup the packages and to make them as complete, intuitive and modular as possible, allowing also external entities to reuse most of the infrastructure without the requirement to pull the whole stack in.

With the new package reorganization, users will find easier to update their cluster. The introduction of fence-agents and resource-agents packages will avoid the pain for users to restarts cluster nodes for simple scripts updates.