 |
|
Features
key features
Advanced Affinity Map/Reduce
MapReduce paradigm is at core of what GridGain does. It defines the process of splitting initial task
into multiple sub-tasks, executing these sub-tasks in parallel and aggregating (reducing) results
back to one final result.
GridGain provides one of the most advanced implementation of MapReduce paradigm with the following features:
- direct API support for split and aggregation
- pluggable failover and topology resolution
- distributed task session
- annotation/AOP and direct, synchronous and asynchronous execution models
- redundant mapping
- partial asynchronous reduction
- support for weighted and adaptive split
- checkpoints for long running tasks
- early and late load balancing
- affinity co-location with data grids
 Top Wiki
Annotation-based grid-enabling with AOP
GridGain is the only grid computing infrastructure that allows to grid-enable existing code without any
modification. This is achieved by using Java annotations and AOP-style crosscutting effectively
forming a grid-enabling DSL. In some case, like for example with JBoss, you may not need to even
have the source code to grid-enable it as annotations and AOP-crosscutting can be applied via external file.
Top Wiki
SPI-based integration and customization
Service Provider Interface (SPI)-based architecture is at the core of configuration and customization
capabilities of GridGain. GridGain exposes all major functional areas of its infrastructure via SPI
allowing developers to customize practically every aspect of GridGain functionality from communication
between nodes, auto-discovery and topology management to deployment, load balancing and collision resolution.
Unified Spring-based configuration of SPIs enables LEGO-like approach to assembling your GridGain framework
with specific set of SPI implementations. In the same time grid task implementations (the actual business
logic that is running on the grid) are kept unaffected by different SPIs running underneath.
Top Wiki
Advanced load balancing and scheduling
GridGain provides both early and late load balancing that are defined by load balancing and
collision (scheduling) resolution SPIs - effectively enabling full customization of entire load balancing
process. Early and late load balancing allows adapting the grid task execution to non-deterministic
nature of execution on the grid.
In fact, grid environment is often heterogeneous and non-static,
tasks can change their complexity profiles dynamically at runtime and external resources can affect
execution of the task at any point. All these factors underscore the need for proactive load balancing
during initial mapping operation as well as on destination node where jobs can be in waiting queues.
Top Wiki
Pluggable Fault-Tolerance
Failover management and resulting fault tolerance is a key property of any grid computing infrastructure.
Based on its SPI-based architecture GridGain provides totally pluggable failover logic with several popular
implementations available out-of-the-box. Unlike other grid computing frameworks GridGain allows to failover
the logic and not only the data. With grid task being the atomic unit of execution on the grid the fully
customizable failover logic enables developer to choose specific policy much the same way as one would
choose concurrency policy in RDBMS transactions.
This allows to fine tune how grid task reacts to the failure, for example:
- fail entire task immediately upon failure of any of its jobs (fail-fast approach)
- failover any failed job to other nodes until all nodes are exhausted for this job (fail-slow approach)
Top Wiki
One compute grid - many data grids
GridGain gives you the freedom of choice of what caching/data grid solution you want to use
with compute grid infrastructure that GridGain provides. GridGain comes with native support for
Oracle Coherence and JBoss Cache providing true blend-in integration for both products.
Top Wiki
Zero deployment model
One of the characteristics of GridGain that has an immediate and dramatic effect on developers'
productivity is its deployment model. In GridGain you can start as multiple nodes on the same computer
or even in the same VM - all without any changes in configuration. Furthermore, with our unique peer-to-peer
class loading technology you don't have to run any Ant scripts, copy any files, start or re-start nodes - you
don't have to do any specific steps, you simply change code and lunch it as usually do. P2P class loading
will take care of loading all changed code on demand to remote nodes.
This feature of GridGain framework singlehandedly delivers the biggest productivity impact for the
developers using GridGain. The simple fact that you can develop, test and debug complex distributed
multi-node algorithms and applications on a single laptop without leaving your IDE's VM and without
any extra steps - saves you months and months of development time.
Top Wiki
JMX-based Management & Monitoring
GridGain comes with an extensive collection of JMX MBeans that exposes all major monitoring and statistical
information about all nodes in the grid. This information is available via programmatic interface as well
as through any JMX-compliant Web or standalone GUI viewer such as JConsole:
Top Wiki
future roadmap
Seamless integration with Amazon EC2
We are working on seamless integration between external clouds like Amazon EC2 for on-demand
discovery within GridGain. This feature will allow automatically or programmatically "boot-up"
external cloud when load picks up and "power it down" when pick subsides.
Top Wiki
RESTful/JSON grid access for Web 2.0 applications
Next major release of GridGain will include ability to execute grid task from any Ajax-based application via
REST/JSON combination providing native integration between server-side GridGain and Web 2.0 client side applications.
Top Wiki
Mobile Grid Computing with Android
GridGain is pioneering field of mobile grid computing and we are working on developing GridGain on
Google Android platform. This work is in early stages but we already have GridGain running on Android
in our tests!
Top Wiki
GridGain HQ - Advanced Web-Based Management
Next version of GridGain will feature improved management and monitoring for support subscription
subscribers based on Hyperc HQ features enterprise grade capabilities such as role-based access control,
global alerts, scheduling control, trend base-lining, reporting, external authentication, and distributed monitoring.
Top Wiki
|
|
|
PRODUCT
SERVICES
