spring batch remote chunking doesn't queue messages but runs it locally? - spring-batch

Below is my configuration for spring batch remote chunking. My steps are running locally instead of remotely. I cant see messages in rabbitmq.
<beans:bean id="importExchangesChunkItemWriter"
class="org.springframework.batch.integration.chunk.ChunkMessageChannelItemWriter"
scope="step" p:messagingOperations-ref="importExchangesMessagingTemplate"
p:replyChannel-ref="importExchangesReplyChannel">
</beans:bean>
<beans:bean id="importExchangesChunkHandler"
class="org.springframework.batch.integration.chunk.RemoteChunkHandlerFactoryBean"
p:chunkWriter-ref="importExchangesChunkItemWriter" p:step-ref="importExchangesStep">
</beans:bean>
<job id="importExchangesJob" restartable="true">
<step id="importExchangesStep" next="importEclsStep">
<tasklet transaction-manager="transactionManager">
<chunk reader="importExchangesFileItemReader" writer="importExchangesItemWriter"
commit-interval="${import.exchanges.commit.interval}" />
</tasklet>
</step>
</job>
<beans:bean id="passThroughItemProcessor" class="org.springframework.batch.item.support.PassThroughItemProcessor" />
<rabbit:connection-factory id="connectionFactory"
port="${rabbitmq.port}" host="${rabbitmq.host}" username="${rabbitmq.username}"
password="${rabbitmq.password}" />
<rabbit:template id="amqpTemplate" connection-factory="connectionFactory" />
<rabbit:admin id="rmqAdmin" connection-factory="connectionFactory" />
<rabbit:queue name="${import.exchanges.queue}" />
<rabbit:queue name="${import.exchanges.reply.queue}" />
<int:channel id="importExchangesChannel" />
<int:channel id="importExchangesReplyChannel" />
<beans:bean id="importExchangesMessagingTemplate"
class="org.springframework.integration.core.MessagingTemplate"
p:defaultChannel-ref="importExchangesChannel" p:receiveTimeout="${import.exchanges.reply.timeout}" />
<amqp:outbound-channel-adapter id="importExchangesOutboundAdapter"
channel="importExchangesChannel" />
<amqp:inbound-channel-adapter id="importExchangesInboundAdapter"
connection-factory="connectionFactory" channel="importExchangesReplyChannel"
queue-names="${import.exchanges.reply.queue}" />
<amqp:inbound-channel-adapter id="importExchangesSlaveInboundAdapter"
connection-factory="connectionFactory" channel="importExchangesChannel"
queue-names="${import.exchanges.queue}" />
<amqp:outbound-channel-adapter id="importExchangesSlaveOutboundAdapter"
channel="importExchangesReplyChannel" />
<int:service-activator id="serviceActivatorExchanges"
input-channel="importExchangesChannel" output-channel="importExchangesReplyChannel"
ref="chunkProcessorChunkHandlerExchanges" method="handleChunk" />
<beans:bean id="importExchangesItemWriter"
class="com.st.batch.foundation.ImportExchangesItemWriter" p:symfony-ref="symfony" p:replyTimeout="${import.exchanges.reply.timeout}"/>
<beans:bean id="chunkProcessorExchanges"
class="org.springframework.batch.core.step.item.SimpleChunkProcessor"
p:itemWriter-ref="importExchangesItemWriter" p:itemProcessor-ref="passThroughItemProcessor"/>
<beans:bean id="chunkProcessorChunkHandlerExchanges"
class="org.springframework.batch.integration.chunk.ChunkProcessorChunkHandler"
p:chunkProcessor-ref="chunkProcessorExchanges" />
Changed configuration to this, now it queue single message at a time and doesn't process multiple (should process number of messages equal to listener concurrency).
<beans:bean id="simpleThreadScope"
class="org.springframework.context.support.SimpleThreadScope" />
<util:map id="scopesMap">
<beans:entry key="thread" value-ref="simpleThreadScope" />
</util:map>
<beans:bean
class="org.springframework.beans.factory.config.CustomScopeConfigurer"
p:scopes-ref="scopesMap" />
<int:channel id="importExchangesChannel" />
<int:channel id="importExchangesReplyChannel" scope="thread">
<int:queue />
</int:channel>
<beans:bean id="importExchangesMessagingTemplate"
class="org.springframework.integration.core.MessagingTemplate"
p:defaultChannel-ref="importExchangesChannel" p:receiveTimeout="${import.exchanges.reply.timeout}" />
<amqp:outbound-channel-adapter
amqp-template="amqpTemplate" channel="importExchangesChannel"
exchange-name="${import.exchanges.exchange}" routing-key="${import.exchanges.routing.key}" />
<rabbit:listener-container
connection-factory="rabbitConnectionFactory" concurrency="${import.exchanges.listener.concurrency}"
requeue-rejected="false" prefetch="1">
<rabbit:listener queues="${import.exchanges.queue}"
ref="importExchangesChunkHandler" method="handleChunk" />
</rabbit:listener-container>
<int:channel id="importEclsChannel" />
<int:channel id="importEclsReplyChannel" scope="thread">
<int:queue />
</int:channel>
<beans:bean id="importEclsMessagingTemplate"
class="org.springframework.integration.core.MessagingTemplate"
p:defaultChannel-ref="importEclsChannel" p:receiveTimeout="${import.ecls.reply.timeout}" />
<amqp:outbound-channel-adapter
amqp-template="amqpTemplate" channel="importEclsChannel"
exchange-name="${import.ecls.exchange}" routing-key="${import.ecls.routing.key}" />
<rabbit:listener-container
connection-factory="rabbitConnectionFactory" concurrency="${import.ecls.listener.concurrency}"
requeue-rejected="false" prefetch="1">
<rabbit:listener queues="${import.ecls.queue}"
ref="importEclsChunkHandler" method="handleChunk" />
</rabbit:listener-container>
<beans:bean id="importExchangesItemWriter"
class="com.st.batch.foundation.ImportExchangesItemWriter"
p:symfony-ref="symfony" p:replyTimeout="${import.exchanges.reply.timeout}" />
<beans:bean id="importExchangesChunkItemWriter"
class="org.springframework.batch.integration.chunk.ChunkMessageChannelItemWriter"
scope="step" p:messagingOperations-ref="importExchangesMessagingTemplate"
p:replyChannel-ref="importExchangesReplyChannel">
</beans:bean>
<beans:bean id="importExchangesChunkHandler"
class="org.springframework.batch.integration.chunk.RemoteChunkHandlerFactoryBean"
p:chunkWriter-ref="importExchangesChunkItemWriter" p:step-ref="importExchangesStep">
</beans:bean>
<rabbit:queue name="${import.exchanges.queue}" />
<rabbit:queue name="${import.exchanges.reply.queue}" />
<rabbit:direct-exchange name="${import.exchanges.exchange}">
<rabbit:bindings>
<rabbit:binding queue="${import.exchanges.queue}"
key="${import.exchanges.routing.key}" />
</rabbit:bindings>
</rabbit:direct-exchange>
I can see only 1 message in queue at a time. I should sent messages = ${import.exchanges.commit.interval} and all should be picked up by concurrent listeners and processed parallely.

I am not sure what you mean by "running locally" but you don't have any routing information on the outbound adapters; if rabbit doesn't know how to route messages, he simply drops them.
You need to add routing-key="${import.exchanges.queue}" and routing-key="${import.exchanges.reply.queue}" to the adapters. This will use the default exchange ("") where the queues are bound using their names.
Also, you can't use the same channel name on both sides (importExchangesChannel). That way, the outbound adapter and service activator will both be subscribed and messages will be distributed in round-robin fashion.
So, some chunks will run locally; others will be dropped because of the routing key problem.
You need to fix the routing key and use a different channel on service side.

Related

OAuth with Spring Security in RESTful web service WITHOUT hard-coded username and password (should use MongoDB database)

I just implemented OAuth with Spring Security in RESTful web service WITH hard-coded username and password,for that i just added,one spring-security file,
spring-security.xml
<beans:beans xmlns:beans="http://www.springframework.org/schema/beans"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns:context="http://www.springframework.org/schema/context"
xmlns:oauth="http://www.springframework.org/schema/security/oauth2"
xmlns:sec="http://www.springframework.org/schema/security"
xsi:schemaLocation="http://www.springframework.org/schema/beans
http://www.springframework.org/schema/beans/spring-beans-3.0.xsd
http://www.springframework.org/schema/security
http://www.springframework.org/schema/security/spring-security-3.2.xsd
http://www.springframework.org/schema/security/oauth2
http://www.springframework.org/schema/security/spring-security-oauth2-1.0.xsd
http://www.springframework.org/schema/context
http://www.springframework.org/schema/context/spring-context-4.1.6.xsd">
<!-- Definition of the Authentication Service -->
<http pattern="/oauth/token" create-session="stateless" authentication-manager-ref="clientAuthenticationManager"
xmlns="http://www.springframework.org/schema/security">
<intercept-url pattern="/oauth/token" access="IS_AUTHENTICATED_FULLY"/>
<anonymous enabled="false"/>
<http-basic entry-point-ref="clientAuthenticationEntryPoint"/>
<!-- include this only if you need to authenticate clients via request parameters -->
<custom-filter ref="clientCredentialsTokenEndpointFilter" after="BASIC_AUTH_FILTER"/>
<access-denied-handler ref="oauthAccessDeniedHandler"/>
</http>
<!-- Protected resources -->
<http pattern="/admin/**"
create-session="never"
entry-point-ref="oauthAuthenticationEntryPoint"
access-decision-manager-ref="accessDecisionManager"
xmlns="http://www.springframework.org/schema/security">
<anonymous enabled="false"/>
<intercept-url pattern="/admin/**"
access="ROLE_USER"/>
<custom-filter ref="resourceServerFilter"
before="PRE_AUTH_FILTER"/>
<access-denied-handler
ref="oauthAccessDeniedHandler"/>
</http>
<beans:bean id="oauthAuthenticationEntryPoint"
class="org.springframework.security.oauth2.provider.error.OAuth2AuthenticationEntryPoint">
<beans:property name="realmName" value="dstest"/>
</beans:bean>
<beans:bean id="clientAuthenticationEntryPoint"
class="org.springframework.security.oauth2.provider.error.OAuth2AuthenticationEntryPoint">
<beans:property name="realmName" value="dstest/client"/>
<beans:property name="typeName" value="Basic"/>
</beans:bean>
<beans:bean id="oauthAccessDeniedHandler"
class="org.springframework.security.oauth2.provider.error.OAuth2AccessDeniedHandler"/>
<beans:bean id="clientCredentialsTokenEndpointFilter"
class="org.springframework.security.oauth2.provider.client.ClientCredentialsTokenEndpointFilter">
<beans:property name="authenticationManager" ref="clientAuthenticationManager"/>
</beans:bean>
<bean id="accessDecisionManager" class="org.springframework.security.access.vote.UnanimousBased"
xmlns="http://www.springframework.org/schema/beans">
<constructor-arg>
<list>
<bean class="org.springframework.security.oauth2.provider.vote.ScopeVoter"/>
<bean class="org.springframework.security.access.vote.RoleVoter"/>
<bean class="org.springframework.security.access.vote.AuthenticatedVoter"/>
</list>
</constructor-arg>
</bean>
<!-- Authentication in config file -->
<authentication-manager id="clientAuthenticationManager" xmlns="http://www.springframework.org/schema/security">
<authentication-provider user-service-ref="clientDetailsUserService"/>
</authentication-manager>
<authentication-manager alias="authenticationManager" xmlns="http://www.springframework.org/schema/security">
<authentication-provider>
<user-service id="userDetailsService">
<user name="shree" password="pass" authorities="ROLE_USER"/>
</user-service>
</authentication-provider>
</authentication-manager>
<beans:bean id="clientDetailsUserService"
class="org.springframework.security.oauth2.provider.client.ClientDetailsUserDetailsService">
<beans:constructor-arg ref="clientDetails"/>
</beans:bean>
<!-- Token Store -->
<beans:bean id="tokenStore" class="org.springframework.security.oauth2.provider.token.InMemoryTokenStore"/>
<beans:bean id="tokenServices" class="org.springframework.security.oauth2.provider.token.DefaultTokenServices">
<beans:property name="tokenStore" ref="tokenStore"/>
<beans:property name="supportRefreshToken" value="true"/>
<beans:property name="clientDetailsService" ref="clientDetails"/>
<!-- VIV -->
<beans:property name="accessTokenValiditySeconds" value="10"/>
</beans:bean>
<beans:bean id="userApprovalHandler"
class="org.springframework.security.oauth2.provider.approval.TokenServicesUserApprovalHandler">
<beans:property name="tokenServices" ref="tokenServices"/>
</beans:bean>
<!-- Token management -->
<oauth:authorization-server client-details-service-ref="clientDetails" token-services-ref="tokenServices"
user-approval-handler-ref="userApprovalHandler">
<oauth:authorization-code/>
<oauth:implicit/>
<oauth:refresh-token/>
<oauth:client-credentials/>
<oauth:password/>
</oauth:authorization-server>
<oauth:resource-server id="resourceServerFilter"
resource-id="dstest"
token-services-ref="tokenServices"/>
<!-- Client Definition -->
<oauth:client-details-service id="clientDetails">
<oauth:client client-id="my-trusted-client"
authorized-grant-types="password,authorization_code,refresh_token,implicit,redirect"
authorities="ROLE_CLIENT, ROLE_TRUSTED_CLIENT"
redirect-uri="/web"
scope="read,write,trust"
access-token-validity="10"
refresh-token-validity="30"/>
</oauth:client-details-service>
<sec:global-method-security pre-post-annotations="enabled" proxy-target-class="true">
<sec:expression-handler ref="oauthExpressionHandler"/>
</sec:global-method-security>
<oauth:expression-handler id="oauthExpressionHandler"/>
<oauth:web-expression-handler id="oauthWebExpressionHandler"/>
</beans:beans>
means we no need to goto .java file currently,but now I want to check username and password from MongoDB database.I tried searching for this but either I am not understanding because code is different or their different database confuse me,I am not getting some website which really explain flow & use of code.
So my question is How to simply make above code accessible to MongoDB database
and check username,password from their.
are you asking about authentication? spring security oauth use spring security for authentication. that means you could configure this with WebSecurityConfigurerAdapter. like this
#Configuration
#EnableWebSecurity
public class SecurityCfg extends WebSecurityConfigurerAdapter {
#Autowired
public vodie globalUserDetails(AuthenticationManagerBuilder auth)
{
auth.mongoDBAuthentication().dataSource(dataSource)
.passwordEncoder(passwordEncoder());
}
}
you've to look for or implement mongoDBAuthentication class which implements UserDetailsManager. and setup a datasource bean.
would be much easier to use jdbcAuthentication with MySQL or postgresQL.
maybe this would help https://github.com/caelwinner/spring-security-mongo

Passing data through two steps - Custom Field Mapper and Custom Tasklet

This is my job configuration:
<batch:job id="clientesJob" job-repository="jobRepository">
<batch:step id="step1" next="renameFiles">
<tasklet>
<chunk reader="multiResourceReader" writer="sqlWriter"
commit-interval="1" />
</tasklet>
</batch:step>
<batch:step id="renameFiles">
<tasklet ref="fileRenamingTasklet" />
</batch:step>
</batch:job>
<bean id="multiResourceReader"
class=" org.springframework.batch.item.file.MultiResourceItemReader">
<property name="resources" value="file:c:/cvs/basecli*" />
<property name="delegate" ref="flatFileItemReader" />
</bean>
<bean id="flatFileItemReader" class="org.springframework.batch.item.file.FlatFileItemReader">
<property name="lineMapper">
<bean class="org.springframework.batch.item.file.mapping.DefaultLineMapper">
<property name="fieldSetMapper" ref="clienteMapper" />
<property name="lineTokenizer" ref="tickerLineTokenizer" />
</bean>
</property>
</bean>
<bean name="tickerLineTokenizer"
class="org.springframework.batch.item.file.transform.DelimitedLineTokenizer" />
<bean id="clienteMapper" class="com.bind.mapper.ClienteFieldSetMapper">
</bean>
<bean id="fileRenamingTasklet" class="com.bind.tasklet.FileRenamingTasklet">
<property name="directory" value="file:c:/cvs/" />
</bean>
In the first step I'm reading the folder with a MultiResourceItemReader, then write it to a SQL Server.
The second one rename the files like "PROCESSFILE-{originalname}".
I thing I want to archive is in the first step there was a problem rename the file in a diferent way like "PROCESSERROR-{originalname}".
So I have to know the status of the first step in my FileRenamingTasklet.
I read about setting the data to the stepExecutionContext. But I cant access in ClienteFieldSetMapper.
I also try using listeners, but there i can't pass the data through.
For further considerations I need the file name and the status.
Any ideas?
Make your fileRenamingTasklet a StepExecutionListener and listen step1 afterStep result; in StepExecutionListener.afterStep(StepExecution stepExecution) check stepExecution.getExitStatus() and you are able to rename correctly your files.
To add listener you have to modify your xml as:
<batch:step id="step1" next="renameFiles">
<tasklet>
<chunk reader="multiResourceReader" writer="sqlWriter" commit-interval="1" />
</tasklet>
<listeners>
<listener ref="fileRenamingTasklet" />
</listeners>
</batch:step>

Is it possible to secure api by using oauth protocol by my logic to create clientid and generate access token?

Is it possible to secure api by using oauth protocol by my logic to create clientid and generate access token?
As per below spring-security.xml token will be generated automatically but I want to use clientid and access token for this clientid (available in db) for implementing auth in api.
<beans xmlns="http://www.springframework.org/schema/beans"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns:context="http://www.springframework.org/schema/context"
xmlns:oauth="http://www.springframework.org/schema/security/oauth2"
xmlns:sec="http://www.springframework.org/schema/security"
xsi:schemaLocation="http://www.springframework.org/schema/beans
http://www.springframework.org/schema/beans/spring-beans-3.1.xsd
http://www.springframework.org/schema/security
http://www.springframework.org/schema/security/spring-security-3.1.xsd
http://www.springframework.org/schema/security/oauth2
http://www.springframework.org/schema/security/spring-security-oauth2-1.0.xsd
http://www.springframework.org/schema/context
http://www.springframework.org/schema/context/spring-context-3.1.xsd">
<!-- Just for testing... -->
<http pattern="/oauth/cache_approvals" security="none" xmlns="http://www.springframework.org/schema/security" />
<http pattern="/oauth/uncache_approvals" security="none" xmlns="http://www.springframework.org/schema/security" />
<http pattern="/oauth/token" create-session="stateless" authentication-manager-ref="clientAuthenticationManager"
xmlns="http://www.springframework.org/schema/security">
<intercept-url pattern="/oauth/token" access="IS_AUTHENTICATED_FULLY" />
<anonymous enabled="false" />
<http-basic entry-point-ref="clientAuthenticationEntryPoint" />
<!-- include this only if you need to authenticate clients via request parameters -->
<custom-filter ref="clientCredentialsTokenEndpointFilter" after="BASIC_AUTH_FILTER" />
<access-denied-handler ref="oauthAccessDeniedHandler" />
</http>
<!-- The OAuth2 protected resources are separated out into their own block so we can deal with authorization and error handling
separately. This isn't mandatory, but it makes it easier to control the behaviour. -->
<http pattern="/test/*" create-session="never" entry-point-ref="oauthAuthenticationEntryPoint"
access-decision-manager-ref="accessDecisionManager" xmlns="http://www.springframework.org/schema/security">
<anonymous enabled="false" />
<intercept-url pattern="/test/*" access="ROLE_USER" />
<custom-filter ref="resourceServerFilter" before="PRE_AUTH_FILTER" />
<access-denied-handler ref="oauthAccessDeniedHandler" />
</http>
<bean id="oauthAuthenticationEntryPoint" class="org.springframework.security.oauth2.provider.error.OAuth2AuthenticationEntryPoint">
<property name="realmName" value="test" />
</bean>
<bean id="clientAuthenticationEntryPoint" class="org.springframework.security.oauth2.provider.error.OAuth2AuthenticationEntryPoint">
<property name="realmName" value="test/client" />
<property name="typeName" value="Basic" />
</bean>
<bean id="oauthAccessDeniedHandler" class="org.springframework.security.oauth2.provider.error.OAuth2AccessDeniedHandler" />
<bean id="clientCredentialsTokenEndpointFilter" class="org.springframework.security.oauth2.provider.client.ClientCredentialsTokenEndpointFilter">
<property name="authenticationManager" ref="clientAuthenticationManager" />
</bean>
<bean id="accessDecisionManager" class="org.springframework.security.access.vote.UnanimousBased" xmlns="http://www.springframework.org/schema/beans">
<constructor-arg>
<list>
<bean class="org.springframework.security.oauth2.provider.vote.ScopeVoter" />
<bean class="org.springframework.security.access.vote.RoleVoter" />
<bean class="org.springframework.security.access.vote.AuthenticatedVoter" />
</list>
</constructor-arg>
</bean>
<authentication-manager id="clientAuthenticationManager" xmlns="http://www.springframework.org/schema/security">
<authentication-provider user-service-ref="clientDetailsUserService" />
</authentication-manager>
<authentication-manager alias="authenticationManager" xmlns="http://www.springframework.org/schema/security">
<authentication-provider>
<user-service id="userDetailsService">
<user name="user" password="password" authorities="ROLE_USER" />
</user-service>
</authentication-provider>
</authentication-manager>
<bean id="clientDetailsUserService" class="org.springframework.security.oauth2.provider.client.ClientDetailsUserDetailsService">
<constructor-arg ref="clientDetails" />
</bean>
<!-- Used for the persistenceof tokens (currently an in memory implementation) -->
<bean id="tokenStore" class="org.springframework.security.oauth2.provider.token.InMemoryTokenStore" />
<!-- Used to create token and and every thing about them except for their persistence that is reposibility of TokenStore (Given here is a default implementation) -->
<bean id="tokenServices" class="org.springframework.security.oauth2.provider.token.DefaultTokenServices">
<property name="tokenStore" ref="tokenStore" />
<property name="supportRefreshToken" value="true" />
<property name="clientDetailsService" ref="clientDetails" />
</bean>
<bean id="userApprovalHandler" class="org.springframework.security.oauth2.provider.approval.TokenServicesUserApprovalHandler">
<property name="tokenServices" ref="tokenServices" />
</bean>
<!-- authorization-server aka AuthorizationServerTokenServices is an interface that defines everything necessary for token management -->
<oauth:authorization-server client-details-service-ref="clientDetails" token-services-ref="tokenServices"
user-approval-handler-ref="userApprovalHandler">
<oauth:authorization-code />
<oauth:implicit />
<oauth:refresh-token />
<oauth:client-credentials />
<oauth:password />
</oauth:authorization-server>
<oauth:resource-server id="resourceServerFilter" resource-id="test" token-services-ref="tokenServices" />
<!-- ClientsDeailsService: Entry Point to clients database (given is in memory implementation) -->
<oauth:client-details-service id="clientDetails">
<!-- client -->
<oauth:client client-id="the_client" authorized-grant-types="authorization_code,client_credentials"
authorities="ROLE_USER" scope="read,write,trust" secret="secret" />
<oauth:client client-id="my-trusted-client-with-secret" authorized-grant-types="password,authorization_code,refresh_token,implicit"
secret="somesecret" authorities="ROLE_USER" />
</oauth:client-details-service>
<sec:global-method-security pre-post-annotations="enabled" proxy-target-class="true">
<!--you could also wire in the expression handler up at the layer of the http filters. See https://jira.springsource.org/browse/SEC-1452 -->
<sec:expression-handler ref="oauthExpressionHandler" />
</sec:global-method-security>
<oauth:expression-handler id="oauthExpressionHandler" />
<oauth:web-expression-handler id="oauthWebExpressionHandler" />
Thanks
Instead of using
<oauth:client-details-service id="clientDetails">
<oauth:client client-id="the_client" authorized-grant-types="authorization_code,client_credentials" authorities="ROLE_USER" scope="read,write,trust" secret="secret" />
<oauth:client client-id="my-trusted-client-with-secret" authorized-grant-types="password,authorization_code,refresh_token,implicit"
secret="somesecret" authorities="ROLE_USER" />
Use this
<beans:bean id="clientDetails" class="org.springframework.security.oauth2.provider.JdbcClientDetailsService">
<beans:constructor-arg ref="dataSource" />
</beans:bean>
Also you can create your own custom ClientDetailsService like JdbcClientDetailsService provided by spring-oauth.
Note:- When using JdbcClientDetailsService make oauth-client-details table with necessary column which is used by JdbcClientDetailsService.

Database to File program query

I have a spring batch program which reads from a database and writes to a file.
Job is:
<job id="MyTransactionJob" job-repository="jobRepository" incrementer="dynamicJobParameters">
<step id="TransactionfileGenerator">
<tasklet transaction-manager="jobRepository-transactionManager">
<chunk reader="MyItemReader" writer="MyItemWriter" commit-interval="1000" skip-policy="skipPolicy"/>
</tasklet>
<listeners>
<listener ref="MySkipListener"/>
</listeners>
</step>
</job>
Item Reader is:
<beans:bean id="MyItemReader" class="org.springframework.batch.item.database.JdbcCursorItemReader">
<beans:property name="dataSource" ref="jobRepository-dataSource" />
<beans:property name="sql" value="${dbTofileDataReadSQL}"/>
<beans:property name="rowMapper">
<beans:bean class="com.mypackage.MyRowMapper" />
</beans:property>
</beans:bean>
dbTofileDataReadSQL is a simple select sql based on some condition. So if condition is not satisfied, 0 rows will be returned.
Item writer is:
<beans:bean id="MyItemWriter" class="com.mypackage.MyDbToFileItemWriter">
<beans:property name="delegate">
<beans:bean class="org.springframework.batch.item.file.FlatFileItemWriter">
<beans:property name="resource" value="file:c:\output.dat" />
<beans:property name="shouldDeleteIfExists" value="true"/>
<beans:property name="lineAggregator">
<beans:bean class="org.springframework.batch.item.file.transform.PassThroughLineAggregator" />
</beans:property>
</beans:bean>
</beans:property>
</beans:bean>
Issue is even if the number of rows returned are 0 an empty file will be created as the writer will always run.
Is it possible to put in a condition such that the file should be created if and only if there is atleast one row to be written. Else just skip the ItemWriter part completely.
Thanks for reading!!
the file will be opened when the step starts, you can
create a custom FlatFileItemWriter which uses the file in a lazy manner
create an afterstep which deletes the file if there are no written lines, this could be a more general solution, if you use a flow
use a simple shell script which checks the file after the job and deletes it if it is empty

Spring Batch - Steps to Improve Performance

I am currently developing data loaders.Reading a file and writing to database. I am using partition handler to process multiple Comma Separated files in 30 threads. I want to scale and have throughput.Daily i receive 15000 files(each having 1 million records ) , how do i scale using spring batch.i want the job to complete this within a day.Do we have any open source grid computing , that can do this fairly, or is there any simple fine tuning steps.
The spring batch data loader runs stand alone. There is no web container involved. it runs on single solaris machine having 24 cpus. The data is written in to single database.default isolation and propagation is provided.The xml config is given below:
<?xml version="1.0" encoding="UTF-8"?>
<beans xmlns="http://www.springframework.org/schema/beans"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns:batch="http://www.springframework.org/schema/batch"
xmlns:p="http://www.springframework.org/schema/p"
xmlns:aop="http://www.springframework.org/schema/aop"
xmlns:context="http://www.springframework.org/schema/context"
xmlns:tx="http://www.springframework.org/schema/tx"
xmlns:task="http://www.springframework.org/schema/task"
xsi:schemaLocation="http://www.springframework.org/schema/aop http://www.springframework.org/schema/aop/spring-aop.xsd
http://www.springframework.org/schema/batch http://www.springframework.org/schema/batch/spring-batch-2.1.xsd
http://www.springframework.org/schema/beans http://www.springframework.org/schema/beans/spring-beans-3.0.xsd
http://www.springframework.org/schema/context http://www.springframework.org/schema/context/spring-context-3.0.xsd
http://www.springframework.org/schema/tx http://www.springframework.org/schema/tx/spring-tx-3.0.xsd
http://www.springframework.org/schema/task http://www.springframework.org/schema/task/spring-task-3.0.xsd">
<!-- IMPORT DB CONFIG -->
<import resource="classpath:bom/bom/bomloader/job/DataSourcePoolConfig.xml" />
<!-- USE ANNOTATIONS TO CONFIGURE SPRING BEANS -->
<context:component-scan base-package="bom.bom.bom" />
<!-- INJECT THE PROCESS PARAMS HASHMAP BEFORE CONTEXT IS INITIALISED -->
<bean id="holder" class="bom.bom.bom.loader.util.PlaceHolderBean" >
<property name="beanName" value="holder"/>
</bean>
<bean id="logger" class="bom.bom.bom.loader.util.PlaceHolderBean" >
<property name="beanName" value="logger"/>
</bean>
<bean id="dataMap" class="java.util.concurrent.ConcurrentHashMap" />
<!-- JOB REPOSITORY - WE USE DATABASE REPOSITORY -->
<!-- <bean id="jobRepository" class="org.springframework.batch.core.repository.support.JobRepositoryFactoryBean" >-->
<!-- <property name="transactionManager" ref="frdtransactionManager" />-->
<!-- <property name="dataSource" ref="frddataSource" />-->
<!-- <property name="databaseType" value="oracle" />-->
<!-- <property name="tablePrefix" value="batch_"/> -->
<!-- </bean>-->
<!-- JOB REPOSITORY - WE IN MEMORY REPOSITORY -->
<bean id="jobRepository" class="org.springframework.batch.core.repository.support.MapJobRepositoryFactoryBean">
<property name="transactionManager" ref="frdtransactionManager" />
</bean>
<!-- <bean id="jobExplorer" class="org.springframework.batch.core.explore.support.JobExplorerFactoryBean">-->
<!-- <property name="dataSource" ref="frddataSource" />-->
<!-- <property name="tablePrefix" value="batch_"/> -->
<!-- </bean>-->
<!-- LAUNCH JOBS FROM A REPOSITORY -->
<bean id="jobLauncher" class="org.springframework.batch.core.launch.support.SimpleJobLauncher">
<property name="jobRepository" ref="jobRepository" />
<property name="taskExecutor">
<bean class="org.springframework.core.task.SyncTaskExecutor" />
</property>
</bean>
<!-- CONFIGURE SCHEDULING IN QUARTZ -->
<!-- <bean id="jobDetail" class="org.springframework.scheduling.quartz.JobDetailBean">-->
<!-- <property name="jobClass" value="bom.bom.bom.assurance.core.JobLauncherDetails" />-->
<!-- <property name="group" value="quartz-batch" />-->
<!-- <property name="jobDataAsMap">-->
<!-- <map>-->
<!-- <entry key="jobName" value="${jobname}"/>-->
<!-- <entry key="jobLocator" value-ref="jobRegistry"/>-->
<!-- <entry key="jobLauncher" value-ref="jobLauncher"/>-->
<!-- </map>-->
<!-- </property>-->
<!-- </bean>-->
<!-- RUN EVERY 2 HOURS -->
<!-- <bean class="org.springframework.scheduling.quartz.SchedulerFactoryBean">-->
<!-- <property name="triggers">-->
<!-- <bean id="cronTrigger" class="org.springframework.scheduling.quartz.CronTriggerBean">-->
<!-- <property name="jobDetail" ref="jobDetail" />-->
<!-- <property name="cronExpression" value="2/0 * * * * ?" />-->
<!-- </bean>-->
<!-- </property>-->
<!-- </bean>-->
<!-- -->
<!-- RUN STANDALONE -->
<bean id="jobRunner" class="bom.bom.bom.loader.core.DataLoaderJobRunner">
<constructor-arg value="${LOADER_NAME}" />
</bean>
<!-- Get all the files for the exchanges and feed as resource to the MultiResourcePartitioner -->
<bean id="fileresource" class="bom.bom.bom.loader.util.FiltersFoldersResourceFactory" p:dataMap-ref="dataMap">
<property name="filePath" value="${PARENT_PATH}" />
<property name="acceptedFolders" value="${EXCH_CODE}" />
<property name="logger" ref="logger" />
</bean>
<!-- The network Data Loading Configuration goes here -->
<job id="CDR_network _PARALLEL" xmlns="http://www.springframework.org/schema/batch" restartable="false" >
<step id="PREPARE_CLEAN" >
<flow parent="prepareCleanFlow" />
<next on="COMPLETED" to="LOAD_EXCHANGE_DATA" />
<fail on="FAILED" exit-code="Failed on cleaning error records."/>
</step>
<step id="LOAD_EXCHANGE_DATA" >
<tasklet ref="businessData" transaction-manager="ratransactionManager" />
<next on="COMPLETED" to="LOAD_CDR_FILES" />
<fail on="FAILED" exit-code="FAILED ON LOADING EXCHANGE INFORMATION FROM DB." />
</step>
<step id="LOAD_CDR_FILES" >
<tasklet ref="fileresource" transaction-manager="frdtransactionManager" />
<next on="COMPLETED" to="PROCESS_FILE_TO_STAGING_TABLE_PARALLEL" />
<fail on="FAILED" exit-code="FAILED ON LOADING CDR FILES." />
</step>
<step id="PROCESS_FILE_TO_STAGING_TABLE_PARALLEL" next="limitDecision" >
<partition step="filestep" partitioner="filepartitioner" >
<handler grid-size="100" task-executor="executorWithCallerRunsPolicy" />
</partition>
</step>
<decision id="limitDecision" decider="limitDecider">
<next on="COMPLETED" to="MOVE_RECS_STAGING_TO_MAIN_TABLE" />
<next on="CONTINUE" to="PROCESS_FILE_TO_STAGING_TABLE_PARALLEL" />
</decision>
<step id="MOVE_RECS_STAGING_TO_MAIN_TABLE" >
<tasklet ref="moveRecords" transaction-manager="ratransactionManager" >
<transaction-attributes isolation="SERIALIZABLE"/>
</tasklet>
<fail on="FAILED" exit-code="FAILED ON MOVING DATA TO THE MAIN TABLE." />
<next on="*" to="PREPARE_ARCHIVE"/>
</step>
<step id="PREPARE_ARCHIVE" >
<flow parent="prepareArchiveFlow" />
<fail on="FAILED" exit-code="FAILED ON Archiving files" />
<end on="*" />
</step>
</job>
<flow id="prepareCleanFlow" xmlns="http://www.springframework.org/schema/batch">
<step id="CLEAN_ERROR_RECORDS" next="archivefileExistsDecisionInFlow" >
<tasklet ref="houseKeeping" transaction-manager="ratransactionManager" />
</step>
<decision id="archivefileExistsDecisionInFlow" decider="archivefileExistsDecider">
<end on="NO_ARCHIVE_FILE" />
<next on="ARCHIVE_FILE_EXISTS" to="runprepareArchiveFlow" />
</decision>
<step id="runprepareArchiveFlow" >
<flow parent="prepareArchiveFlow" />
</step>
</flow>
<flow id="prepareArchiveFlow" xmlns="http://www.springframework.org/schema/batch" >
<step id="ARCHIVE_CDR_FILES" >
<tasklet ref="archiveFiles" transaction-manager="frdtransactionManager" />
</step>
</flow>
<bean id="archivefileExistsDecider" class="bom.bom.bom.loader.util.ArchiveFileExistsDecider" >
<property name="logger" ref="logger" />
<property name="frdjdbcTemplate" ref="frdjdbcTemplate" />
</bean>
<bean id="filepartitioner" class="org.springframework.batch.core.partition.support.MultiResourcePartitioner" scope="step" >
<property name="resources" value="#{dataMap[processFiles]}"/>
</bean>
<task:executor id="executorWithCallerRunsPolicy"
pool-size="90-95"
queue-capacity="6"
rejection-policy="CALLER_RUNS"/>
<!-- <bean id="dynamicJobParameters" class="bom.bom.bom.assurance.core.DynamicJobParameters" />-->
<bean id="houseKeeping" class="bom.bom.bom.loader.core.HousekeepingOperation">
<property name="logger" ref="logger" />
<property name="jdbcTemplate" ref="rajdbcTemplate" />
<property name="frdjdbcTemplate" ref="frdjdbcTemplate" />
</bean>
<bean id="businessData" class="bom.bom.bom.loader.core.BusinessValidatorData">
<property name="logger" ref="logger" />
<property name="jdbcTemplate" ref="NrajdbcTemplate" />
<property name="param" value="${EXCH_CODE}" />
<property name="sql" value="${LOOKUP_QUERY}" />
</bean>
<step id="filestep" xmlns="http://www.springframework.org/schema/batch">
<tasklet transaction-manager="ratransactionManager" allow-start-if-complete="true" >
<chunk writer="jdbcItenWriter" reader="fileItemReader" processor="itemProcessor" commit-interval="500" retry-limit="2">
<retryable-exception-classes>
<include class="org.springframework.dao.DeadlockLoserDataAccessException"/>
</retryable-exception-classes>
</chunk>
<listeners>
<listener ref="customStepExecutionListener">
</listener>
</listeners>
</tasklet>
</step>
<bean id="moveRecords" class="bom.bom.bom.loader.core.MoveDataFromStaging">
<property name="logger" ref="logger" />
<property name="jdbcTemplate" ref="rajdbcTemplate" />
</bean>
<bean id="archiveFiles" class="bom.bom.bom.loader.core.ArchiveCDRFile" >
<property name="logger" ref="logger" />
<property name="jdbcTemplate" ref="frdjdbcTemplate" />
<property name="archiveFlag" value="${ARCHIVE_FILE}" />
<property name="archiveDir" value="${ARCHIVE_LOCATION}" />
</bean>
<bean id="limitDecider" class="bom.bom.bom.loader.util.LimitDecider" p:dataMap-ref="dataMap">
<property name="logger" ref="logger" />
</bean>
<!-- <bean id="multifileReader" class="org.springframework.batch.item.file.MultiResourceItemReader" scope="step" >-->
<!-- <property name="resources" value="#{stepExecutionContext[fileName]}" />-->
<!-- <property name="delegate" ref="fileItemReader" />-->
<!-- </bean>-->
<!-- READ EACH FILE PARALLELY -->
<bean id="fileItemReader" scope="step" autowire-candidate="false" parent="itemReaderParent">
<property name="resource" value="#{stepExecutionContext[fileName]}" />
<property name="saveState" value="false" />
</bean>
<!-- LISTEN AT THE END OF EACH FILE TO DO POST PROCESSING -->
<bean id="customStepExecutionListener" class="bom.bom.bom.loader.core.StagingStepExecutionListener" scope="step">
<property name="logger" ref="logger" />
<property name="frdjdbcTemplate" ref="frdjdbcTemplate" />
<property name="jdbcTemplate" ref="rajdbcTemplate" />
<property name="sql" value="${INSERT_IA_QUERY_COLUMNS}" />
</bean>
<!-- CONFIGURE THE ITEM PROCESSOR TO DO BUSINESS LOGIC ON EACH ITEM -->
<bean id="itemProcessor" class="bom.bom.bom.loader.core.StagingLogicProcessor" scope="step">
<property name="logger" ref="logger" />
<property name="params" ref="businessData" />
</bean>
<!-- CONFIGURE THE JDBC ITEM WRITER TO WRITE IN TO DB -->
<bean id="jdbcItenWriter" class="org.springframework.batch.item.database.JdbcBatchItemWriter" scope="step">
<property name="dataSource" ref="radataSource"/>
<property name="sql">
<value>
<![CDATA[
${SQL1A}
]]>
</value>
</property>
<property name="itemSqlParameterSourceProvider">
<bean class="org.springframework.batch.item.database.BeanPropertyItemSqlParameterSourceProvider">
</bean>
</property>
</bean>
<!-- <bean id="itemWriter" class="bom.bom.bom.assurance.core.LoaderDBWriter" scope="step">-->
<!-- <property name="sQL" value="${loader.sql}" />-->
<!-- <property name="jdbcTemplate" ref="NrajdbcTemplate" />-->
<!-- </bean>-->
<!-- CONFIGURE THE FLAT FILE ITEM READER TO READ INDIVIDUAL BATCH -->
<bean id="itemReaderParent" class="org.springframework.batch.item.file.FlatFileItemReader" abstract="true">
<property name="strict" value="false"/>
<property name="lineMapper">
<bean class="org.springframework.batch.item.file.mapping.DefaultLineMapper">
<property name="lineTokenizer">
<bean class="org.springframework.batch.item.file.transform.FixedLengthTokenizer">
<property name="names" value="${COLUMNS}" />
<property name="columns" value="${RANGE}" />
</bean>
</property>
<property name="fieldSetMapper">
<bean class="bom.bom.bom.loader.util.DataLoaderMapper">
<property name="params" value="${BEANPROPERTIES}"/>
</bean>
</property>
</bean>
</property>
</bean>
</beans>
Tried:
i could see that the ThreadPoolExecutor hangs after 3 hours.The prstat in solaris says it is processing, but no processing in the log.
Tried with less chunk size 500 ,due memory foot print,no progress.
Since it inserts in to single database( 30 pooled connections).is there anythin i can do here.
Instances from visual vm
stacktrace of thread all are locked at connection level
Full thread dump Java HotSpot(TM) Server VM (11.3-b02 mixed mode):
"Attach Listener" daemon prio=3 tid=0x00bbf800 nid=0x26 waiting on condition [0x00000000..0x00000000]
java.lang.Thread.State: RUNNABLE
"executorWithCallerRunsPolicy-1" prio=3 tid=0x008a7000 nid=0x25 runnable [0xd5a7d000..0xd5a7fb70]
java.lang.Thread.State: RUNNABLE
at java.net.SocketInputStream.socketRead0(Native Method)
at java.net.SocketInputStream.read(SocketInputStream.java:129)
at oracle.net.ns.Packet.receive(Packet.java:240)
at oracle.net.ns.DataPacket.receive(DataPacket.java:92)
at oracle.net.ns.NetInputStream.getNextPacket(NetInputStream.java:172)
at oracle.net.ns.NetInputStream.read(NetInputStream.java:117)
at oracle.net.ns.NetInputStream.read(NetInputStream.java:92)
at oracle.net.ns.NetInputStream.read(NetInputStream.java:77)
at oracle.jdbc.driver.T4CMAREngine.unmarshalUB1(T4CMAREngine.java:1034)
at oracle.jdbc.driver.T4CMAREngine.unmarshalSB1(T4CMAREngine.java:1010)
at oracle.jdbc.driver.T4C8Oall.receive(T4C8Oall.java:588)
at oracle.jdbc.driver.T4CPreparedStatement.doOall8(T4CPreparedStatement.java:194)
at oracle.jdbc.driver.T4CPreparedStatement.executeForRows(T4CPreparedStatement.java:953)
at oracle.jdbc.driver.OracleStatement.doExecuteWithTimeout(OracleStatement.java:1222)
at oracle.jdbc.driver.OraclePreparedStatement.executeInternal(OraclePreparedStatement.java:3387)
at oracle.jdbc.driver.OraclePreparedStatement.executeUpdate(OraclePreparedStatement.java:3468)
- locked <0xdbdafa30> (a oracle.jdbc.driver.T4CConnection)
at oracle.jdbc.driver.OraclePreparedStatementWrapper.executeUpdate(OraclePreparedStatementWrapper.java:1350)
at org.springframework.jdbc.core.JdbcTemplate$2.doInPreparedStatement(JdbcTemplate.java:818)
at org.springframework.jdbc.core.JdbcTemplate$2.doInPreparedStatement(JdbcTemplate.java:1)
at org.springframework.jdbc.core.JdbcTemplate.execute(JdbcTemplate.java:587)
at org.springframework.jdbc.core.JdbcTemplate.update(JdbcTemplate.java:812)
at org.springframework.jdbc.core.JdbcTemplate.update(JdbcTemplate.java:868)
at org.springframework.jdbc.core.JdbcTemplate.update(JdbcTemplate.java:876)
at
I would suggest you lower the chunk size to 50.
500 seems to be too big : you wait too much while talking with the DB.
At the same time, lower the TaskExecutor's pool size or increase your DB pool size.
You can choose which on by watching your DB host : if it's CPU and IO is not maxxed, increase your DB pool size to increase the DB load. If your DB CPU is already at it's maximum, lower the TaskExecutor's pool size. The objective is to have a fluid process.
I think the DB will be your main limitating element. So begin by adjusting the DB pool size according to the DB host capacities. When it's done, adjust your TaskExecutor's pool size according to the DB pool size (TE pool size = DB pool size * 1.5), plus the batch's host capacities (CPU, memory and IOs).
Splitting your incoming files on multiple hard drives may help too (if possible).
I think the problem here is million records in the file. Since you already reduced the chunk size , you should process smaller records. For testing sake, reduce the number of records in each file to 10k. My guess is you creating creating objects, doing some processing and you are doing this for 1m records in a loop. Each thread will hold the object in memory unless the processing is completed. My guess is because of volume of data, there are too many objects in your memory which are not garbage collected. If reducing the size helps, then you can try to use lightweight objects in your code and try setting each object to null at end of processing.
just a fix in your cron expression. This is the correct for 2 hours:
0 0 0/2 1/1 * ? *
Is your batch job relying on reflection(e.g., BeanPropertyRowMapper)? That can hamper performance.
If your database is causing problems, you may want to profile it. Don't have much concrete to offer here.
Already mentioned, drop that chunk size.