JPPF Files

JPPF makes it easy to parallelize computationally intensive tasks and execute them on a Grid

What's new in JPPF 3.2


Load balancing in the client:

As for the server with the nodes, the client can now distribute jobs over multiple server channels and the local execution channel.
This opens up a broad variety of distribution capabilities, including:
- distribution through connections to multiple servers
- distribution through multiple connections to the same server
- distribution to the client-local execution channel
- any combination of the above

Load-balancing / scheduling is applied in exactly the same way as within the server, with the same APIs and configuration properties and the ability to implement custom class loaders.


Client-side SLA:

All jobs now have a distinct <a href="/doc/v3/index.php?title=Job_Service_Level_Agreement">service level agreement</a> for the client-side dispatching of their tasks. This  provides the ability for each job to specifiy:
- a start and expiration schedule on the client side
- an execution policy to determine through which channels a job can be dispatched (channel filtering)
- the maximum number of channels to dispatch to
- as a result, the ability to specifiy local vs. remote execution on a per job basis


Executor services enhancements:

- a data provider</a> can now be sent along with the jobs
- ability to register a listener to receive notfications of each job's execution status
- a <a href="/doc/v3/index.php?title=JPPF_Executor_Services#JPPFCompletionService">JPPF-specific CompletionListener</a> is now available


Class loading improvements:

- Parallel class loading requests from the same node are now batched and sent together to the server, providing a sigificant speed-up of the nodes performance
- Nodes maintain a cache of classes and resources not found in the remote classpath, avoiding costly network requests and improving class loading performance overall
- Local cache of resources found in remote classpaths can now be switched from file system to memory storage with automatic fallback strategy.
	This addresses environments where disk space available to the node is minimal or inexistant.


New JPPF task APIs:

Two very useful methods were added to JPPFTask:
- isInNode() determines whether the task is executing within a node or in the client's local executor
- compute(JPPFCallable) enables the execution of a callback in the client. This replaces the ClientDataProvider API which is now deprecated.


IPv6 ready:

All areas of JPPF networking have been updated to handle IPv6 addresses properly and transparently:
- discovery information broadcast by the server
- connectivity from the nodes and clients
- JMX-based connections for management and monitoring of the Grid


Automated testing:

A major effort has taken place to provide automated testing of the JPPF features, to ensure that the quality of each release meets the expectations.
This results in a large and growing set of tests based on JUnit and integrated into our development process.<br/>
An additional module was created to perform stress testing of JPPF grids and improve its stability and resilience under high-throughput and highly unstable networking conditions.


List of enhancements in JPPF 3.2

JPPF-50 Add data provider to the JPPFExecutor service job configuration
JPPF-55 Extensions to NodeLifeCycleListener
JPPF-45 Class loader enhancements
JPPF-66 Additional notifications needed for JobListener
JPPF-63 Add a separate job SLA for processing on the client side
JPPF-53 Enhancements to JPPFExecutorService
JPPF-76 Make sure JPPF is IPv6-ready
JPPF-79 Stability, stress and load testing for v3.2
JPPF-80 Improve exception handling

Feature Requests 

JPPF-3 API to provide information of client connections
JPPF-46 Missing public API to determine which and how many nodes are idle
JPPF-47 Add a management API to determine how many nodes are attached to a driver
JPPF-40 Provide ClientDataProvider functionality in the tasks
JPPF-36 Toggle Local execution per Job
JPPF-44 Restrict server broadcast to specific interfaces for discovery
JPPF-34 Inefficient load balancing with peer servers
JPPF-35 Job submission through multiple channels
JPPF-84 Add isLocal() to JPPFManagementInfo
JPPF-83 Add systemInformation() to JPPFClient, JPPFNode, JPPFDriver
JPPF-77 Extend Client, JPPFManagementInfo with identifiaction for local, remove node and peer driver
JPPF-101 Ability to provide dynamic binding for the driver
JPPF-30 Broadcast job: execute on ALL nodes (currently only ACTIVE)

Bug Fixes 

JPPF-5 NoSuchFieldException: target for ForkJoinWorkerThread
JPPF-43 MemLeak: ResourceCache (minor)
JPPF-60 NPE: AbstractJPPFClassLoader.findResources(284)
JPPF-67 NPE: periodic task
JPPF-71 Regression: administration console is broken
JPPF-54 LocalNode: long init when network is broken
JPPF-74 Reg: Failing test on slow single core machine
JPPF-73 Peer nodes - infinite reconnection
JPPF-75 NPE: display information about peer node in admin
JPPF-72 Server deadlock in TaskQueueChecker / NodeNioServer
JPPF-78 Generic serializer throws a ClassFormatError
JPPF-81 FAIL: TestExecutorServiceConfiguration.testSubmitWithClientExecutionPolicy
JPPF-82 FAIL: TestJobPersistence.testJobRecovery
JPPF-41 BarChart: queue size sometimes negative
JPPF-42 ServerStats/Latest number of jobs show negative value
JPPF-70 IllegalStateException: Job xxx already enqueued when job is submitted via multiple channels
JPPF-64 Deadlock: state transition in NodeClass and ClientClass
JPPF-85 P2P connection failure: IllegalArgumentException: bundle is null
JPPF-87 Memory leak in the driver: ServerJob instances fill the heap
JPPF-88 Nodes and drivers running as services cannot be restarted via JMX
JPPF-94 JPPF source distribution is missing 'jdk7-addons' and 'application-template' modules
JPPF-95 ConcurrentModificationException in DriverJobManagement.getAllJobIds()
JPPF-91 NPE: in class loaders when AbstractJPPFClassLoaderLifeCycle:loadRemoteData return NULL
JPPF-96 Deadlock in the client: RemoteChannelWrapper / TaskQUeueChecker
JPPF-90 Job never ends after reconnection 
JPPF-89 ConnectException during performTransition
JPPF-98 Server discovery threads are duplicated int he client
JPPF-92 Regression: results returned by the driver should depend on the driver load-balancer
JPPF-100 Missing deployment instructions for custom execution policies
JPPF-103 Node local resources cache may lead to grid hang in some environments

To browse an issue, use the URL http://www.jppf.org/tracker/tbg/jppf/issues/JPPF-<issue_number>

JPPF Links:

Web Site: http://www.jppf.org
Downloads: http://www.jppf.org/downloads.php
Documentation: http://www.jppf.org/wiki
User forums: http://www.jppf.org/forums
Issue tracker: http://www.jppf.org/tracker/tbg/jppf
SF.net project page: http://sourceforge.net/projects/jppf-project/