How to get yarn job status from yarn client in scala

Question

I would like to poll submitted spark/yarn jobs status using scala.

Answer 1

Use yarn client:

Maven dependency:

    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-yarn-client</artifactId>
        <version>2.6.0-cdh5.16.2</version>
    </dependency>

Scala code:

import org.apache.hadoop.yarn.client.api.YarnClient
import org.apache.hadoop.yarn.conf.YarnConfiguration
import org.apache.hadoop.yarn.api.records.ApplicationId

val client  = YarnClient.createYarnClient()
val Yconf = new YarnConfiguration();
Yconf.addResource(hdfsCoreSiteXml)
Yconf.addResource(hdfsHDFSSiteXml)
Yconf.addResource(hdfsYarnSiteXml)
client.init(Yconf)

client.start

        val app_id = "application_1590803731996_57381"
        val app_id_parts = app_id.split("_")
        val app_time_part = app_id_parts(1).toLong
        val app_attempt_id_part = app_id_parts(2).toInt

        val applicationId = ApplicationId.newInstance(app_time_part, app_attempt_id_part)

        val applicationReport: ApplicationReport = client.getApplicationReport(applicationId)

        val yarnStatus: YarnApplicationState = applicationReport.getYarnApplicationState

        println("Yarn Status: "+yarnStatus.name)

      //Yarn status name enum values given below          
      /*    NEW,
            NEW_SAVING,
            SUBMITTED,
            ACCEPTED,
            RUNNING,
            FINISHED,
            FAILED,
            KILLED */