edu.isi.pegasus.planner.code.gridstart
Class NoGridStart

java.lang.Object
  edu.isi.pegasus.planner.code.gridstart.NoGridStart

All Implemented Interfaces:

GridStart

public class NoGridStart
extends Object
implements GridStart

This class ends up running the job directly on the grid, without wrapping it in any other launcher executable. It ends up connecting the jobs stdio and stderr to condor commands to ensure they are sent back to the submit host.

Version:

$Revision: 4731 $

Author:

Karan Vahi vahi@isi.edu

Field Summary

static String	CLASSNAME The basename of the class that is implmenting this.
private PegasusBag	mBag
private ADag	mDAG
protected boolean	mEnablingPartOfAggregatedJob An instance variable to track if enabling is happening as part of a clustered job.
protected String	mExitParserArguments The argument string containing the arguments with which the exitcode is invoked on kickstart output.
protected boolean	mGenerateLOF A boolean indicating whether to generate lof files or not.
protected LogManager	mLogger The LogManager object which is used to log all the messages.
protected PlannerOptions	mPOptions The options passed to the planner.
protected PegasusProperties	mProps The object holding all the properties pertaining to Pegasus.
protected SiteStore	mSiteStore Handle to the site catalog store.
protected SLS	mSLS The handle to the SLS implementor
protected String	mSubmitDir The submit directory where the submit files are being generated for the workflow.
protected boolean	mWorkerPackageStagingEnabled Boolean indicating whether worker package staging is enabled or not.
static String	SHORT_NAME The SHORTNAME for this implementation.

Fields inherited from interface edu.isi.pegasus.planner.code.GridStart

mSeparator, VERSION

Constructor Summary

NoGridStart()

Method Summary

private void	addToFile(File src, OutputStream out) Adds contents to an output stream.
boolean	canSetXBit() Indicates whether the enabling mechanism can set the X bit on the executable on the remote grid site, in addition to launching it on the remote grid stie
private void	construct(Job job, String key, String value) Constructs a condor variable in the condor profile namespace associated with the job.
String	defaultPOSTScript() Returns the SHORT_NAME for the POSTScript implementation that is used to be as default with this GridStart implementation.
boolean	enable(AggregatedJob job, boolean isGlobusJob) Enables a job to run on the grid.
AggregatedJob	enable(AggregatedJob aggJob, Collection jobs) Enables a collection of jobs and puts them into an AggregatedJob.
boolean	enable(Job job, boolean isGlobusJob) Enables a job to run on the grid by launching it directly.
String	generateListofFilenamesFile(Set files, String basename) Writes out the list of filenames file for the job.
protected String	getDirectory(Job job) Returns the directory in which the job should run.
private String	getDirectoryKey(Job job) Returns the directory that is associated with the job to specify the directory in which the job needs to run
String	getVDSKeyValue() Returns the value of the vds profile with key as Pegasus.GRIDSTART_KEY, that would result in the loading of this particular implementation.
String	getWorkerNodeDirectory(Job job) Returns the directory in which the job executes on the worker node.
protected String	handleTransferOfExecutable(Job job) It changes the paths to the executable depending on whether we want to transfer the executable or not.
void	initialize(PegasusBag bag, ADag dag) Initializes the GridStart implementation.
private boolean	removeDirectoryKey(Job job) Returns a boolean indicating whether to remove remote directory information or not from the job.
protected boolean	requiresToSetDirectory(Job job) Returns a boolean indicating whether we need to set the directory for the job or not.
String	shortDescribe() Returns a short textual description in the form of the name of the class.
void	useFullPathToGridStarts(boolean fullPath) Setter method to control whether a full path to Gridstart should be returned while wrapping a job or not.

Methods inherited from class java.lang.Object

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

Field Detail

mBag

private PegasusBag mBag

mDAG

private ADag mDAG

CLASSNAME

public static final String CLASSNAME

The basename of the class that is implmenting this. Could have been determined by reflection.

See Also:

Constant Field Values

SHORT_NAME

public static final String SHORT_NAME

The SHORTNAME for this implementation.

See Also:

Constant Field Values

mLogger

protected LogManager mLogger

The LogManager object which is used to log all the messages.

mProps

protected PegasusProperties mProps

The object holding all the properties pertaining to Pegasus.

mSubmitDir

protected String mSubmitDir

The submit directory where the submit files are being generated for the workflow.

mExitParserArguments

protected String mExitParserArguments

The argument string containing the arguments with which the exitcode is invoked on kickstart output.

mGenerateLOF

protected boolean mGenerateLOF

A boolean indicating whether to generate lof files or not.

mSLS

protected SLS mSLS

The handle to the SLS implementor

mPOptions

protected PlannerOptions mPOptions

The options passed to the planner.

mSiteStore

protected SiteStore mSiteStore

Handle to the site catalog store.

mEnablingPartOfAggregatedJob

protected boolean mEnablingPartOfAggregatedJob

An instance variable to track if enabling is happening as part of a clustered job. See Bug 21 comments on Pegasus Bugzilla

mWorkerPackageStagingEnabled

protected boolean mWorkerPackageStagingEnabled

Boolean indicating whether worker package staging is enabled or not.

Constructor Detail

NoGridStart

public NoGridStart()

Method Detail

initialize

public void initialize(PegasusBag bag,
                       ADag dag)

Initializes the GridStart implementation.

Specified by:

initialize in interface GridStart

Parameters:

bag - the bag of objects that is used for initialization.

dag - the concrete dag so far.

enable

public AggregatedJob enable(AggregatedJob aggJob,
                            Collection jobs)

Enables a collection of jobs and puts them into an AggregatedJob. The assumption here is that all the jobs are being enabled by the same implementation. It enables the jobs and puts them into the AggregatedJob that is passed to it.

Parameters:

aggJob - the AggregatedJob into which the collection has to be integrated.

jobs - the collection of jobs (Job) that need to be enabled.

Returns:

the AggregatedJob containing the enabled jobs.

See Also:

enable(Job,boolean)

enable

public boolean enable(AggregatedJob job,
                      boolean isGlobusJob)

Enables a job to run on the grid. This also determines how the stdin,stderr and stdout of the job are to be propogated. To grid enable a job, the job may need to be wrapped into another job, that actually launches the job. It usually results in the job description passed being modified modified.

Specified by:

enable in interface GridStart

Parameters:

job - the Job object containing the job description of the job that has to be enabled on the grid.

isGlobusJob - is true, if the job generated a line universe = globus, and thus runs remotely. Set to false, if the job runs on the submit host in any way.

Returns:

boolean true if enabling was successful,else false.

enable

public boolean enable(Job job,
                      boolean isGlobusJob)

Enables a job to run on the grid by launching it directly. It ends up running the executable directly without going through any intermediate launcher executable. It connects the stdio, and stderr to underlying condor mechanisms so that they are transported back to the submit host.

Specified by:

enable in interface GridStart

Parameters:

job - the Job object containing the job description of the job that has to be enabled on the grid.

isGlobusJob - is true, if the job generated a line universe = globus, and thus runs remotely. Set to false, if the job runs on the submit host in any way.

Returns:

boolean true if enabling was successful,else false in case when the path to kickstart could not be determined on the site where the job is scheduled.

handleTransferOfExecutable

protected String handleTransferOfExecutable(Job job)

It changes the paths to the executable depending on whether we want to transfer the executable or not. Currently, the transfer_executable is only handled for staged compute jobs, where Pegasus is staging the binaries to the remote site.

Parameters:

job - the Job containing the job description.

Returns:

the path that needs to be set as the executable key. If transfer_executable is not set the path to the executable is returned as is.

canSetXBit

public boolean canSetXBit()

Indicates whether the enabling mechanism can set the X bit on the executable on the remote grid site, in addition to launching it on the remote grid stie

Specified by:

canSetXBit in interface GridStart

Returns:

false, as no wrapper executable is being used.

getVDSKeyValue

public String getVDSKeyValue()

Returns the value of the vds profile with key as Pegasus.GRIDSTART_KEY, that would result in the loading of this particular implementation. It is usually the name of the implementing class without the package name.

Specified by:

getVDSKeyValue in interface GridStart

Returns:

the value of the profile key.

See Also:

org.griphyn.cPlanner.namespace.Pegasus#GRIDSTART_KEY

shortDescribe

public String shortDescribe()

Returns a short textual description in the form of the name of the class.

Specified by:

shortDescribe in interface GridStart

Returns:

short textual description.

defaultPOSTScript

public String defaultPOSTScript()

Returns the SHORT_NAME for the POSTScript implementation that is used to be as default with this GridStart implementation.

Specified by:

defaultPOSTScript in interface GridStart

Returns:

the identifier for the NoPOSTScript POSTScript implementation.

See Also:

POSTScript.shortDescribe()

requiresToSetDirectory

protected boolean requiresToSetDirectory(Job job)

Returns a boolean indicating whether we need to set the directory for the job or not.

Parameters:

job - the job for which to set directory.

Returns:

getDirectory

protected String getDirectory(Job job)

Returns the directory in which the job should run.

Parameters:

job - the job in which the directory has to run.

Returns:

getDirectoryKey

private String getDirectoryKey(Job job)

Returns the directory that is associated with the job to specify the directory in which the job needs to run

Parameters:

job - the job

Returns:

the condor key . can be initialdir or remote_initialdir

removeDirectoryKey

private boolean removeDirectoryKey(Job job)

Returns a boolean indicating whether to remove remote directory information or not from the job. This is determined on the basis of the style key that is associated with the job.

Parameters:

job - the job in question.

Returns:

boolean

construct

private void construct(Job job,
                       String key,
                       String value)

Constructs a condor variable in the condor profile namespace associated with the job. Overrides any preexisting key values.

Parameters:

job - contains the job description.

key - the key of the profile.

value - the associated value.

generateListofFilenamesFile

public String generateListofFilenamesFile(Set files,
                                          String basename)

Writes out the list of filenames file for the job.

Parameters:

files - the list of PegasusFile objects contains the files whose stat information is required.

basename - the basename of the file that is to be created

Returns:

the full path to lof file created, else null if no file is written out.

addToFile

private void addToFile(File src,
                       OutputStream out)
                throws IOException

Adds contents to an output stream.

Parameters:

src -

out -

Throws:

IOException

getWorkerNodeDirectory

public String getWorkerNodeDirectory(Job job)

Returns the directory in which the job executes on the worker node.

Specified by:

getWorkerNodeDirectory in interface GridStart

Parameters:

job -

Returns:

the full path to the directory where the job executes

useFullPathToGridStarts

public void useFullPathToGridStarts(boolean fullPath)

Description copied from interface: GridStart

Setter method to control whether a full path to Gridstart should be returned while wrapping a job or not.

Specified by:

useFullPathToGridStarts in interface GridStart

Parameters:

fullPath - if set to true, indicates that full path would be used.