Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- # Template for a Spark Job Server configuration file
- # When deployed these settings are loaded when job server starts
- #
- # Spark Cluster / Job Server configuration
- spark {
- master = "yarn"
- # Default # of CPUs for jobs to use for Spark standalone cluster
- job-number-cpus = 2
- jobserver {
- port = 8090
- context-per-jvm = true
- # Default client mode will start up a new JobManager int local machine
- # You can use mesos-cluster mode with REMOTE_JOBSERVER_DIR and MESOS_SPARK_DISPATCHER
- # environment value set in xxxx.sh file to launch JobManager in remote node
- # Mesos will take responsibility to offer resource to the JobManager process
- #driver-mode = client
- # Note: JobFileDAO is deprecated from v0.7.0 because of issues in
- # production and will be removed in future, now defaults to H2 file.
- jobdao = spark.jobserver.io.JobSqlDAO
- filedao {
- rootdir = /tmp/spark-jobserver/filedao/data
- }
- datadao {
- # storage directory for files that are uploaded to the server
- # via POST/data commands
- rootdir = /tmp/spark-jobserver/upload
- }
- sqldao {
- # Slick database driver, full classpath
- # slick-driver = slick.driver.H2Driver
- slick-driver = slick.driver.MySQLDriver
- # JDBC driver, full classpath
- #jdbc-driver = org.h2.Driver
- jdbc-driver = com.mysql.jdbc.Driver
- # Directory where default H2 driver stores its data. Only needed for H2.
- #rootdir = /tmp/spark-jobserver/sqldao/data
- # Full JDBC URL / init string, along with username and password. Sorry, needs to match above.
- # Substitutions may be used to launch job-server, but leave it out here in the default or tests won't pass
- #jdbc {
- # url = "jdbc:h2:file:/tmp/spark-jobserver/sqldao/data/h2-db"
- # user = ""
- # password = ""
- #}
- jdbc {
- url = "jdbc:mysql://localhost:3666/spark_jobserver?useSSL=false"
- user = "jobserver"
- password = ""
- }
- # DB connection pool settings
- dbcp {
- #enabled = false
- maxactive = 20
- maxidle = 10
- initialsize = 10
- }
- }
- # When using chunked transfer encoding with scala Stream job results, this is the size of each chunk
- result-chunk-size = 1m
- }
- # Predefined Spark contexts
- # contexts {
- # my-low-latency-context {
- # num-cpu-cores = 1 # Number of cores to allocate. Required.
- # memory-per-node = 512m # Executor memory per node, -Xmx style eg 512m, 1G, etc.
- # }
- # # define additional contexts here
- # }
- # Universal context configuration. These settings can be overridden, see README.md
- context-settings {
- #num-cpu-cores = 2 # Number of cores to allocate. Required.
- #memory-per-node = 2g # Executor memory per node, -Xmx style eg 512m, #1G, etc.
- spark.driver.port = 32456
- spark.yarn.jar = "/opt/mapreducelab/spark/jars/*"
- spark.dynamicAllocation.enabled = true
- spark.executor.memory = 6632m
- spark.yarn.executor.memoryOverhead = 664
- # In case spark distribution should be accessed from HDFS (as opposed to being installed on every Mesos slave)
- # spark.executor.uri = "hdfs://namenode:8020/apps/spark/spark.tgz"
- # URIs of Jars to be loaded into the classpath for this context.
- # Uris is a string list, or a string separated by commas ','
- # dependent-jar-uris = ["file:///some/path/present/in/each/mesos/slave/somepackage.jar"]
- # Add settings you wish to pass directly to the sparkConf as-is such as Hadoop connection
- # settings that don't use the "spark." prefix
- passthrough {
- spark.dynamicAllocation.enabled = true
- spark.executor.memory = 6632m
- spark.yarn.executor.memoryOverhead = 664
- spark.cassandra.driver = "org.apache.spark.sql.cassandra"
- spark.cassandra.connection.host = "host1, host2, host3"
- spark.cassandra.connection.port = "9042"
- spark.cassandra.auth.username = "noetl"
- spark.cassandra.auth.password = "noetl"
- spark.driver.allowMultipleContexts = true
- }
- }
- # This needs to match SPARK_HOME for cluster SparkContexts to be created successfully
- home = "/opt/mapreducelab/spark"
- }
- spray.can.server.parsing.max-content-length = 250m
- # Note that you can use this file to define settings not only for job server,
- # but for your Spark jobs as well. Spark job configuration merges with this configuration file as defaults.
- akka {
- remote.netty.tcp {
- # This controls the maximum message size, including job results, that can be sent
- maximum-frame-size = 40 MiB
- }
- }
- #client {
- #connecting-timeout = infinite
- #}
- spray.can.server {
- idle-timeout =70 s
- request-timeout = 60 s
- parsing.max-content-length = 300m
- verbose-error-logging = "on"
- verbose-error-messages = "on"
- }
- flyway.locations="db/mysql/migration"
Add Comment
Please, Sign In to add comment