Recent changes to news

JPPF 3.3.2 Maintenance Release

Laurent Cohen — Thu, 23 May 2013 22:49:56 -0000

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

What's new in JPPF 3.3.2

This maintenance release brings important bug fixes and enhancements.

Bugs fixes:

JPPF-140 Node class loader's resource cache should perform proper cleanup
JPPF-145 Node execution manager does not clean up the data provider after job execution
JPPF-147 Deadlock in the driver
JPPF-148 Deadlock in the admin console at startup

Enhancements

JPPF-118 Improvements in NodeExecutionManagerImpl
JPPF-149 Enable on-demand cleanup of class loader resource cache

JPPF Links: Web Site - Downloads - Documentation - User forums - Issue tracker - SF.net project page

JPPF 3.3.1 maintenance release

Laurent Cohen — Fri, 26 Apr 2013 05:45:51 -0000

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

What's new in JPPF 3.3.1

This maintenance release brings important bug fixes and performance improvements.

Bugs fixes:

JPPF-138 JCA client does not reconnect to the driver when discovery is disabled
JPPF-139 JVM crash in IdleSystem sample on Ubuntu 12.04
JPPF-142 Erroneous property names for discovery filters

Enhancements

JPPF-141 Deserialization performance improvement

JPPF Links: Web Site - Downloads - Documentation - User forums - Issue tracker - SF.net project page

JPPF 3.3 Released

Laurent Cohen — Mon, 08 Apr 2013 08:17:30 -0000

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

What's new in JPPF 3.3

JPPF 3.3 brings grid health monitoring, flexible network management, GPU computing and a lot more

Forwarding of node management requests through the server

This feature resolves a long-standing issue which prevented management and monitoring of the nodes not directly reachable by the clients and administration console.
It also opens up new possibilities that make monitoring and management of a JPPF grid easier, more flexible and more powerful by an order of magnitude:

it dynamically adapts to the grid topology: new nodes are automatically enrolled in the forwarding mechanism, while terminated nodes are automatically unsubscribed
a very flexible node selection mechanism provides users with a fine-grained control of which nodes are involved
JMX notifications from the nodes are also forwarded with the same benefits
the JPPF administration console was entirely refactored to make the best use of this feature
resources usage for management and monitoring has dropped dramatically: the clients do not connect to the nodes anymore, which removes the need for additional network connections, along with the resources they consume

JVM monitoring and diagnostics help

A new JVM diagnostic MBean allows users to monitor the JVM health of remote servers and nodes.
Both management APIs and administration console now provide a set of JVM telemetry and diagnostics features:

memory usage and CPU load with configurable alert thresholds
thread deadlock detection and number of live threads
export thread dumps from remote JVMs
trigger remote heap dumps
trigger remote garbage collections

GPU computing

A new GPU computing demo was added to the JPPF samples pack,
which demonstrates how JPPF tasks can submit work to OpenCL-compatible devices with the APARAPI library.

Class loading improvements

The nodes now have the ability to reset a client-linked class loader without the need to restart. This allows complete control over the class loader's classpath with minimal performance impact.
The Extended class loading demo was updated to use this feature.

New node customization: class loading events

This new extension point enables users to receive notifications when a JPPF class loader loads a class or fails to load it.

JPPF artifacts published to Maven Central

As of JPPF 3.3, the JPPF jar files and associated sources and javadoc are available on Maven Central.

All changes JPPF 3.3

New Features

JPPF-24 Ability to deactivate a node
JPPF-26 Enable node management via the driver connection
JPPF-34 Inefficient load balancing with peer servers
JPPF-38 Use SplashScreen support from Java
JPPF-109 Pluggable error handler for NodeLifeCycleListener
JPPF-112 Refactor the admin console for management and monitoring via the driver
JPPF-119 Add JVM state monitoring and diagnostics for JPPF components
JPPF-12 Using GPU performance
JPPF-121 Provide class loader hooks for reporting and analysis of loaded classes and resources
JPPF-133 Publish JPPF artifacts to maven central

Enhancements

JPPF-68 Node: separation of class loader instances and driver connection
JPPF-69 Minimize usage of static fields/instances in JPPF
JPPF-104 Inconsistent naming of the load-balancing properties
JPPF-118 Improvements in NodeExecutionManagerImpl
JPPF-124 Refactor the \"Extended Class Loading\" sample to use class loader reset ability
JPPF-128 Provide version information in the JPPFSystemInformation properties
JPPF-129 Enhancements to the node connection listener

Bug fixes

JPPF-102 Ongoing issues with the administration and monitoring console
JPPF-107 Missing exception handling upon invocation of NodeLifeCycleListener methods
JPPF-110 Proportional algorithm results in uneven load with small number of long-lived tasks
JPPF-113 NullPointerException in the console upon connection to first driver
JPPF-114 Missing unit tests for node management and monitoring APIs
JPPF-116 NPE in AbstractJPPFClassLoader.findResources()
JPPF-117 Task timeout is not working as expected
JPPF-120 [Regression] Impossible to make an SSL connection to the server
JPPF-122 JMX connection threads leak in the driver
JPPF-123 NPE at driver startup when jppf.ssl.server.port = -1
JPPF-125 Selection in job data panel does not update the buttons state
JPPF-126 Job cancelled from the admin console may get stuck in the server queue
JPPF-131 JPPF client does not release JMX thread upon connection failure
JPPF-132 The documentation on the JPPFClient API is incomplete
JPPF-134 Frequent driver reconnections cause job to hang in the client

JPPF Links: Web Site - Downloads - Documentation - User forums - Issue tracker - SF.net project page

JPPF 3.3-RC1 Released

Laurent Cohen — Thu, 28 Mar 2013 06:58:11 -0000

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

What's new in JPPF 3.3-RC1

Bug fixes

Enhancements

New Features

JPPF-12 Using GPU performance
JPPF-24 Ability to deactivate a node
JPPF-26 Enable node management via the driver connection
JPPF-34 Inefficient load balancing with peer servers
JPPF-38 Use SplashScreen support from Java
JPPF-109 Pluggable error handler for NodeLifeCycleListener
JPPF-112 Refactor the admin console for management and monitoring via the driver
JPPF-119 Add JVM state monitoring and diagnostics for JPPF components

JPPF Links: Web Site - Downloads - Documentation - User forums - Issue tracker - SF.net project page

JPPF 3.2.3 Released

Laurent Cohen — Tue, 12 Mar 2013 22:01:36 -0000

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

What's new in JPPF 3.2.3

This maintenance release brings important bug fixes.

Bugs fixes:

JPPF-122 JMX connection threads leak in the driver
JPPF-123 NPE at driver startup when jppf.ssl.server.port = -1
JPPF-125 Selection in job data panel does not update the buttons state
JPPF-126 Job cancelled from the admin console may get stuck in the server queue
JPPF-130 Job hang when loading a large number of classes with multiple nodes
JPPF-131 JPPF client does not release JMX thread upon connection failure

Enhancements

JPPF-118 Improvements in NodeExecutionManagerImpl

JPPF Links: Web Site - Downloads - Documentation - User forums - Issue tracker - SF.net project page

JPPF 3.3-beta Released

Laurent Cohen — Mon, 18 Feb 2013 07:42:26 -0000

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

What's new in JPPF 3.3-beta

Bug fixes

JPPF-107 Missing exception handling upon invocation of NodeLifeCycleListener methods
JPPF-110 Proportional algorithm results in uneven load with small number of long-lived tasks
JPPF-113 NullPointerException in the console upon connection to first driver
JPPF-114 Missing unit tests for node management and monitoring APIs
JPPF-116 NPE in AbstractJPPFClassLoader.findResources()
JPPF-117 Task timeout is not working as expected
JPPF-120 [Regression] Impossible to make an SSL connection to the server
JPPF-122 JMX connection threads leak in the driver
JPPF-123 NPE at driver startup when jppf.ssl.server.port = -1
JPPF-125 Selection in job data panel does not update the buttons state
JPPF-126 Job cancelled from the admin console may get stuck in the server queue

Enhancements

JPPF-68 Node: separation of class loader instances and driver connection
JPPF-69 Minimize usage of static fields/instances in JPPF
JPPF-104 Inconsistent naming of the load-balancing properties
JPPF-118 Improvements in NodeExecutionManagerImpl
JPPF-124 Refactor the "Extended Class Loading" sample to use class loader reset ability

Feature requests

JPPF-24 Ability to deactivate a node
JPPF-26 Enable node management via the driver connection
JPPF-38 Use SplashScreen support from Java
JPPF-109 Pluggable error handler for NodeLifeCycleListener
JPPF-112 Refactor the admin console for management and monitoring via the driver

JPPF Links: Web Site - Downloads - Documentation - User forums - Issue tracker - SF.net project page

JPPF 3.2.2 Released

Laurent Cohen — Sun, 27 Jan 2013 07:03:34 -0000

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

What's new in JPPF 3.2.2

This maintenance release brings important bug fixes, including a critical issue preventing secure connections to the server.

Bugs fixes:

JPPF-110 Proportional algorithm results in uneven load with small number of long-lived tasks
JPPF-116 NPE in AbstractJPPFClassLoader.findResources()
JPPF-117 Task timeout is not working as expected
JPPF-120 (Regression) Impossible to make an SSL connection to the server (Critical)

JPPF Links: Web Site - Downloads - Documentation - User forums - Issue tracker - SF.net project page

JPPF 3.2.1 Released

Laurent Cohen — Tue, 08 Jan 2013 08:10:17 -0000

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

What's new in JPPF 3.2.1

This maintenance release brings important bug fixes.

Bugs fixes:

JPPF-105 Temporary files disappear when setting a large MemoryMapDataProvider as data provider in a JPPFJob
JPPF-107 Missing exception handling upon invocation of NodeLifeCycleListener methods
JPPF-108 Deadlock in the server upon client disconnection
JPPF-113 NullPointerException in the console upon connection to first driver
JPPF-114 Missing unit tests for node management and monitoring APIs

JPPF Links: Web Site - Downloads - Documentation - User forums - Issue tracker - SF.net project page

JPPF 3.2 Released

Laurent Cohen — Tue, 18 Dec 2012 10:32:45 -0000

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/

JPPF 3.1.4 Released

Laurent Cohen — Tue, 13 Nov 2012 06:58:36 -0000

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

What's new in JPPF 3.1.4

This maintenance release brings important bug fixes.

Bugs fixes:

JPPF-58 JPPFResultCollector.setStatus(COMPLETE) is called twice for each job
JPPF-59 Cannot submit multiple jobs concurrently with JCA adaptor
JPPF-62 Jobs with timeout expire in the client instead of the server
JPPF-65 Some threads are still alive when the client is closed
JPPF-78 Generic serializer throws a ClassFormatError
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-96 Deadlock in the client: RemoteChannelWrapper / TaskQueueChecker
JPPF-97 OutOfMemoryError in the driver when using multiple client connections

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

JPPF Links: