org.jppf.server.scheduler.bundle.impl
Class AutoTunedBundler

java.lang.Object
  org.jppf.server.scheduler.bundle.AbstractBundler
      org.jppf.server.scheduler.bundle.impl.AbstractAutoTunedBundler
          org.jppf.server.scheduler.bundle.impl.AutoTunedBundler

All Implemented Interfaces:

Bundler

public class AutoTunedBundler
extends AbstractAutoTunedBundler

This class implements a self tuned bundle size algorithm. It starts using the bundle size defined in property file and starts changing it to find a better performance. The algorithm starts making The algorithm waits for some execution to get a mean execution time, and them make a change in bundle size Each time the change is done, it is done over a smaller range randomly selected (like Monte Carlo algorithm).

Author:

Domingos Creado, Laurent Cohen

Field Summary

Fields inherited from class org.jppf.server.scheduler.bundle.impl.AbstractAutoTunedBundler

currentSize, rnd, samplesMap

Fields inherited from class org.jppf.server.scheduler.bundle.AbstractBundler

bundlerNumber, profile, timestamp

Constructor Summary

AutoTunedBundler(LoadBalancingProfile profile)
Creates a new instance with the initial size of bundle as the start size.

Method Summary

Bundler	copy() Make a copy of this bundler.
void	feedback(int bundleSize, double time) This method performs the actual bundle size computation, based on current and past performance data.
int	getBundleSize() Get the latest bundle size computed by this bundler.
protected int	maxSize() Get the max bundle size that can be used for this bundler.

Methods inherited from class org.jppf.server.scheduler.bundle.AbstractBundler

dispose, getBundlerNumber, getProfile, getTimestamp, setup

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

AutoTunedBundler

public AutoTunedBundler(LoadBalancingProfile profile)

Creates a new instance with the initial size of bundle as the start size.

Parameters:

profile - the parameters of the auto-tuning algorithm, grouped as a performance analysis profile.

Method Detail

getBundleSize

public int getBundleSize()

Get the latest bundle size computed by this bundler.

Specified by:

getBundleSize in interface Bundler

Overrides:

getBundleSize in class AbstractAutoTunedBundler

Returns:

the bundle size as an int.

See Also:

Bundler.getBundleSize()

feedback

public void feedback(int bundleSize,
                     double time)

This method performs the actual bundle size computation, based on current and past performance data.
Depending on the the performance samples and profile parameters, the following actions may be triggered in this method:

• samples collection (unconditional)
• detection of performance profile changes, if not currently being done
• when a performance profile change is detected, recompute the bundle size.

Specified by:

feedback in interface Bundler

Overrides:

feedback in class AbstractAutoTunedBundler

Parameters:

bundleSize - bundle size of the new performance sample.

time - total execution time of the new sample.

See Also:

Bundler.feedback(int, double)

copy

public Bundler copy()

Make a copy of this bundler.

Returns:

a new AutoTunedBundler instance.

See Also:

Bundler.copy()

maxSize

protected int maxSize()

Get the max bundle size that can be used for this bundler.

Specified by:

maxSize in class AbstractBundler

Returns:

the bundle size as an int.

See Also:

AbstractBundler.maxSize()