[FIXED] Spring Batch restart persistent jobs after abnormal termination

Issue

I have a following Spring Batch Job config:

@Configuration
@EnableBatchProcessing
public class JobConfig {

    @Autowired
    private JobBuilderFactory jobBuilderFactory;

    @Autowired
    private StepBuilderFactory stepBuilderFactory;

    @Bean
    public Job job() {
        return jobBuilderFactory.get("job")
                .flow(stepA()).on("FAILED").to(stepC())
                .from(stepA()).on("*").to(stepB()).next(stepC())
                .end().build();
    }

    @Bean
    public Step stepA() {
        return stepBuilderFactory.get("stepA").tasklet(new RandomFailTasket("stepA")).build();
    }

    @Bean
    public Step stepB() {
        return stepBuilderFactory.get("stepB").tasklet(new PrintTextTasklet("stepB")).build();
    }

    @Bean
    public Step stepC() {
        return stepBuilderFactory.get("stepC").tasklet(new PrintTextTasklet("stepC")).build();
    }

}

I'm starting the job with a following code:

    try {
        Map<String,JobParameter> parameters = new HashMap<>();
        JobParameter ccReportIdParameter = new JobParameter("03061980");
        parameters.put("ccReportId", ccReportIdParameter);

        jobLauncher.run(job, new JobParameters(parameters));
    } catch (JobExecutionAlreadyRunningException | JobRestartException | JobInstanceAlreadyCompleteException
            | JobParametersInvalidException e) {
        e.printStackTrace();
    }

This is my test tasklet:

public class PrintTextTasklet implements Tasklet {

    public PrintTextTasklet() {
    }

    public RepeatStatus execute(StepContribution stepContribution, ChunkContext chunkContext) throws Exception {

        String ccReportId = chunkContext.getStepContext().getStepExecution().getJobParameters().getString("ccReportId");
        System.out.println("ccReportId: " + ccReportId);
        Thread.sleep(60 * 1000);
        return RepeatStatus.FINISHED;
    }

}

I use H2 database as a persistent storage for my jobs.

During the jobs execution I'm terminating my application. Right after application restart I expect that all uncompleted jobs will continue execution from terminated steps but nothing happens.

Also, in my application.properties file I added a following property:

spring.batch.job.enabled=false

because I don't want to allow Spring Batch automatically start new(not terminated) job. I need to start all new jobs manually(on user request) and restart all completed jobs after next application run.

How to configure Spring Batch in this case ?

UPDATED

Right now I'm trying to restart jobs with a following method:

public void restartUncompletedJobs() {
        List<String> jobs = jobExplorer.getJobNames();
        for (String job : jobs) {
            Set<JobExecution> runningJobs = jobExplorer.findRunningJobExecutions(job);

            for (JobExecution runningJob : runningJobs) {
                try {
                    jobOperator.restart(runningJob.getId());
                    logger.info("Restarted: " + runningJob);
                } catch (Exception e) {
                    logger.error(e.getMessage(), e);
                }
            }
        }
    }

but failing with a following exception:

org.springframework.batch.core.launch.NoSuchJobException: No job configuration with the name [job] was registered
    at org.springframework.batch.core.configuration.support.MapJobRegistry.getJob(MapJobRegistry.java:66) ~[spring-batch-core-3.0.5.RELEASE.jar:3.0.5.RELEASE]
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) ~[na:1.8.0_60]
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) ~[na:1.8.0_60]
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) ~[na:1.8.0_60]
    at java.lang.reflect.Method.invoke(Method.java:497) ~[na:1.8.0_60]
    at org.springframework.aop.support.AopUtils.invokeJoinpointUsingReflection(AopUtils.java:302) ~[spring-aop-4.2.0.RELEASE.jar:4.2.0.RELEASE]
    at org.springframework.aop.framework.ReflectiveMethodInvocation.invokeJoinpoint(ReflectiveMethodInvocation.java:190) ~[spring-aop-4.2.0.RELEASE.jar:4.2.0.RELEASE]
    at org.springframework.aop.framework.ReflectiveMethodInvocation.proceed(ReflectiveMethodInvocation.java:157) ~[spring-aop-4.2.0.RELEASE.jar:4.2.0.RELEASE]
    at org.springframework.batch.core.configuration.annotation.SimpleBatchConfiguration$PassthruAdvice.invoke(SimpleBatchConfiguration.java:127) ~[spring-batch-core-3.0.5.RELEASE.jar:3.0.5.RELEASE]
    at org.springframework.aop.framework.ReflectiveMethodInvocation.proceed(ReflectiveMethodInvocation.java:179) ~[spring-aop-4.2.0.RELEASE.jar:4.2.0.RELEASE]
    at org.springframework.aop.framework.JdkDynamicAopProxy.invoke(JdkDynamicAopProxy.java:207) ~[spring-aop-4.2.0.RELEASE.jar:4.2.0.RELEASE]
    at com.sun.proxy.$Proxy94.getJob(Unknown Source) ~[na:na]
    at org.springframework.batch.core.launch.support.SimpleJobOperator.restart(SimpleJobOperator.java:275) ~[spring-batch-core-3.0.5.RELEASE.jar:3.0.5.RELEASE]
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) ~[na:1.8.0_60]
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) ~[na:1.8.0_60]
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) ~[na:1.8.0_60]
    at java.lang.reflect.Method.invoke(Method.java:497) ~[na:1.8.0_60]
    at org.springframework.aop.support.AopUtils.invokeJoinpointUsingReflection(AopUtils.java:302) ~[spring-aop-4.2.0.RELEASE.jar:4.2.0.RELEASE]
    at org.springframework.aop.framework.JdkDynamicAopProxy.invoke(JdkDynamicAopProxy.java:201) ~[spring-aop-4.2.0.RELEASE.jar:4.2.0.RELEASE]
    at com.sun.proxy.$Proxy96.restart(Unknown Source) ~[na:na]
    at com.example.domain.api.batch.job.ReportJobServiceImpl.restartUncompletedJobs(ReportJobServiceImpl.java:72) ~[classes/:na]
    at com.example.domain.api.Application.lambda$0(Application.java:46) [classes/:na]
    at org.springframework.boot.SpringApplication.runCommandLineRunners(SpringApplication.java:672) ~[spring-boot-1.2.5.RELEASE.jar:1.2.5.RELEASE]
    at org.springframework.boot.SpringApplication.afterRefresh(SpringApplication.java:690) ~[spring-boot-1.2.5.RELEASE.jar:1.2.5.RELEASE]
    at org.springframework.boot.SpringApplication.run(SpringApplication.java:321) ~[spring-boot-1.2.5.RELEASE.jar:1.2.5.RELEASE]
    at org.springframework.boot.SpringApplication.run(SpringApplication.java:957) ~[spring-boot-1.2.5.RELEASE.jar:1.2.5.RELEASE]
    at org.springframework.boot.SpringApplication.run(SpringApplication.java:946) ~[spring-boot-1.2.5.RELEASE.jar:1.2.5.RELEASE]
    at com.example.domain.api.Application.main(Application.java:53) [classes/:na]

Solution

I got it working by adding following line

jobRegistry.register(new ReferenceJobFactory(job));

into the restartUncompletedJobs method

public void restartUncompletedJobs() {
    try {
        jobRegistry.register(new ReferenceJobFactory(job));

        List<String> jobs = jobExplorer.getJobNames();
        for (String job : jobs) {
            Set<JobExecution> runningJobs = jobExplorer.findRunningJobExecutions(job);

            for (JobExecution runningJob : runningJobs) {
                runningJob.setStatus(BatchStatus.FAILED);
                runningJob.setEndTime(new Date());
                jobRepository.update(runningJob);
                jobOperator.restart(runningJob.getId());
                logger.info("Restarted: " + runningJob);
            }
        }
    } catch (Exception e) {
        logger.error(e.getMessage(), e);
    }
}

Answered By - alexanoid
Answer Checked By - Robin (JavaFixing Admin)