org.apache.hudi.cli.commands

Class ClusteringCommand

java.lang.Object

org.apache.hudi.cli.commands.ClusteringCommand

@ShellComponent
public class ClusteringCommand
extends Object

Constructor Summary

Constructors

Constructor and Description
ClusteringCommand()

Method Summary

Modifier and Type	Method and Description
String	runClustering(String master, String sparkMemory, String parallelism, String retry, String propsFilePath, String[] configs) Run clustering table service.
String	runClustering(String master, String sparkMemory, String parallelism, String retry, String clusteringInstantTime, String propsFilePath, String[] configs) Run clustering table service.
String	scheduleClustering(String master, String sparkMemory, String propsFilePath, String[] configs) Schedule clustering table service.

Methods inherited from class java.lang.Object

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

Constructor Detail

ClusteringCommand

public ClusteringCommand()

Method Detail

scheduleClustering

@ShellMethod(key="clustering schedule",
             value="Schedule Clustering")
public String scheduleClustering(@ShellOption(value="--sparkMaster",defaultValue="yarn",help="Spark master")
                                                                                                                   String master,
                                                                                                                   @ShellOption(value="--sparkMemory",defaultValue="1g",help="Spark executor memory")
                                                                                                                   String sparkMemory,
                                                                                                                   @ShellOption(value="--propsFilePath",help="path to properties file on localfs or dfs with configurations for hoodie client for clustering",defaultValue="")
                                                                                                                   String propsFilePath,
                                                                                                                   @ShellOption(value="--hoodieConfigs",help="Any configuration that can be set in the properties file can be passed here in the form of an array",defaultValue="")
                                                                                                                   String[] configs)
                                                                                                            throws Exception

Schedule clustering table service.

Example: > connect --path {path to hudi table} > clustering schedule --sparkMaster local --sparkMemory 2g

Throws:

Exception

runClustering

@ShellMethod(key="clustering run",
             value="Run Clustering")
public String runClustering(@ShellOption(value="--sparkMaster",defaultValue="yarn",help="Spark master")
                                                                                                    String master,
                                                                                                    @ShellOption(value="--sparkMemory",help="Spark executor memory",defaultValue="4g")
                                                                                                    String sparkMemory,
                                                                                                    @ShellOption(value="--parallelism",help="Parallelism for hoodie clustering",defaultValue="1")
                                                                                                    String parallelism,
                                                                                                    @ShellOption(value="--retry",help="Number of retries",defaultValue="1")
                                                                                                    String retry,
                                                                                                    @ShellOption(value="--clusteringInstant",help="Clustering instant time",defaultValue="__NULL__")
                                                                                                    String clusteringInstantTime,
                                                                                                    @ShellOption(value="--propsFilePath",help="path to properties file on localfs or dfs with configurations for hoodie client for compacting",defaultValue="")
                                                                                                    String propsFilePath,
                                                                                                    @ShellOption(value="--hoodieConfigs",help="Any configuration that can be set in the properties file can be passed here in the form of an array",defaultValue="")
                                                                                                    String[] configs)
                                                                                             throws Exception

Run clustering table service.

Example: > connect --path {path to hudi table} > clustering schedule --sparkMaster local --sparkMemory 2g > clustering run --sparkMaster local --sparkMemory 2g --clusteringInstant 20211124005208

Throws:

Exception

runClustering

@ShellMethod(key="clustering scheduleAndExecute",
             value="Run Clustering. Make a cluster plan first and execute that plan immediately")
public String runClustering(@ShellOption(value="--sparkMaster",defaultValue="yarn",help="Spark master")
                                                                                                                                                                                String master,
                                                                                                                                                                                @ShellOption(value="--sparkMemory",help="Spark executor memory",defaultValue="4g")
                                                                                                                                                                                String sparkMemory,
                                                                                                                                                                                @ShellOption(value="--parallelism",help="Parallelism for hoodie clustering",defaultValue="1")
                                                                                                                                                                                String parallelism,
                                                                                                                                                                                @ShellOption(value="--retry",help="Number of retries",defaultValue="1")
                                                                                                                                                                                String retry,
                                                                                                                                                                                @ShellOption(value="--propsFilePath",help="path to properties file on localfs or dfs with configurations for hoodie client for compacting",defaultValue="")
                                                                                                                                                                                String propsFilePath,
                                                                                                                                                                                @ShellOption(value="--hoodieConfigs",help="Any configuration that can be set in the properties file can be passed here in the form of an array",defaultValue="")
                                                                                                                                                                                String[] configs)
                                                                                                                                                                         throws Exception

Run clustering table service.

Example: > connect --path {path to hudi table} > clustering scheduleAndExecute --sparkMaster local --sparkMemory 2g

Throws:

Exception