# Data scale profile. Available value is tiny, small, large, huge, gigantic and bigdata.
# The definition of these profiles can be found in the workload's conf file i.e. conf/workloads/micro/wordcount.conf
hibench.scale.profile                tiny
# Mapper number in hadoop, partition number in Spark
hibench.default.map.parallelism         500

# Reducer nubmer in hadoop, shuffle partition number in Spark
hibench.default.shuffle.parallelism     500


#======================================================
# Report files
#======================================================
# default report formats
hibench.report.formats          "%-12s %-10s %-8s %-20s %-20s %-20s %-20s\n"

# default report dir path
hibench.report.dir              ${hibench.home}/report

# default report file name
hibench.report.name             hibench.report

# input/output format settings. Available formats: Text, Sequence, Null.
sparkbench.inputformat         Sequence
sparkbench.outputformat        Sequence

# hibench config folder
hibench.configure.dir           ${hibench.home}/conf

# default hibench HDFS root
hibench.hdfs.data.dir           ${hibench.hdfs.master}/HiBench

# path of hibench jars
hibench.hibench.datatool.dir              ${hibench.home}/autogen/target/autogen-8.0-SNAPSHOT-jar-with-dependencies.jar
hibench.common.jar                      ${hibench.home}/common/target/hibench-common-8.0-SNAPSHOT-jar-with-dependencies.jar
hibench.sparkbench.jar                  ${hibench.home}/sparkbench/assembly/target/sparkbench-assembly-8.0-SNAPSHOT-dist.jar
hibench.streambench.stormbench.jar      ${hibench.home}/stormbench/streaming/target/stormbench-streaming-8.0-SNAPSHOT.jar
hibench.streambench.gearpump.jar        ${hibench.home}/gearpumpbench/streaming/target/gearpumpbench-streaming-8.0-SNAPSHOT-jar-with-dependencies.jar
hibench.streambench.flinkbench.jar      ${hibench.home}/flinkbench/streaming/target/flinkbench-streaming-8.0-SNAPSHOT-jar-with-dependencies.jar
hibench.hadoop.examples.test.jar        /home/ruroy/hadoop/op/hadoop-3.2.2/share/hadoop/mapreduce/hadoop-mapreduce-client-jobclient-3.2.2-tests.jar
#======================================================
# workload home/input/ouput path
#======================================================
hibench.hive.home               ${hibench.home}/hadoopbench/sql/target/${hibench.hive.release}
hibench.hive.release            apache-hive-3.0.0-bin
hibench.hivebench.template.dir  ${hibench.home}/hadoopbench/sql/hive_template
hibench.bayes.dir.name.input    ${hibench.workload.dir.name.input}
hibench.bayes.dir.name.output   ${hibench.workload.dir.name.output}

hibench.mahout.release.apache   apache-mahout-distribution-0.11.0
hibench.mahout.release.hdp      apache-mahout-distribution-0.11.0
hibench.mahout.release.cdh5         mahout-0.9-cdh5.1.0
hibench.mahout.release                ${hibench.mahout.release.${hibench.hadoop.release}}
hibench.masters.hostnames        10.10.15.78
hibench.slaves.hostnames         10.10.15.78

hibench.workload.input
hibench.workload.output
hibench.workload.dir.name.input         Input
hibench.workload.dir.name.output        Output

hibench.nutch.dir.name.input    ${hibench.workload.dir.name.input}
hibench.nutch.dir.name.output   ${hibench.workload.dir.name.output}
hibench.nutch.nutchindexing.dir ${hibench.home}/hadoopbench/nutchindexing/
hibench.nutch.release           nutch-1.2
hibench.nutch.home              ${hibench.home}/hadoopbench/nutchindexing/target/${hibench.nutch.release}

hibench.dfsioe.dir.name.input   ${hibench.workload.dir.name.input}
hibench.dfsioe.dir.name.output  ${hibench.workload.dir.name.output}


#======================================================
# Streaming General
#======================================================
# Indicate whether in debug mode for correctness verfication (default: false)
hibench.streambench.debugMode false
hibench.streambench.sampleProbability 0.1
hibench.streambench.fixWindowDuration            10000
hibench.streambench.fixWindowSlideStep           10000


#======================================================
# Kafka for streaming benchmarks
#======================================================
hibench.streambench.kafka.home                  /PATH/TO/YOUR/KAFKA/HOME
# zookeeper host:port of kafka cluster, host1:port1,host2:port2...
hibench.streambench.zkHost
# Kafka broker lists, written in mode host:port,host:port,..
hibench.streambench.kafka.brokerList
hibench.streambench.kafka.consumerGroup          HiBench
# number of partitions of generated topic (default 20)
hibench.streambench.kafka.topicPartitions       20
# consumer group of the consumer for kafka (default: HiBench)
hibench.streambench.kafka.consumerGroup HiBench
# Set the starting offset of kafkaConsumer (default: largest)
hibench.streambench.kafka.offsetReset largest


#======================================================
# Data generator for streaming benchmarks
#======================================================
# Interval span in millisecond (default: 50)
hibench.streambench.datagen.intervalSpan         50
# Number of records to generate per interval span (default: 5)
hibench.streambench.datagen.recordsPerInterval   5
# fixed length of record (default: 200)
hibench.streambench.datagen.recordsPerInterval   5
# fixed length of record (default: 200)
hibench.streambench.datagen.recordLength         200
# Number of KafkaProducer running on different thread (default: 1)
hibench.streambench.datagen.producerNumber       1
# Total round count of data send (default: -1 means infinity)
hibench.streambench.datagen.totalRounds          -1
# Number of total records that will be generated (default: -1 means infinity)
hibench.streambench.datagen.totalRecords        -1
# default path to store seed files (default: ${hibench.hdfs.data.dir}/Streaming)
hibench.streambench.datagen.dir                         ${hibench.hdfs.data.dir}/Streaming
# default path setting for genearate data1 & data2
hibench.streambench.datagen.data1.name                  Seed
hibench.streambench.datagen.data1.dir                   ${hibench.streambench.datagen.dir}/${hibench.streambench.datagen.data1.name}
hibench.streambench.datagen.data2_cluster.dir           ${hibench.streambench.datagen.dir}/Kmeans/Cluster
hibench.streambench.datagen.data2_samples.dir           ${hibench.streambench.datagen.dir}/Kmeans/Samples

#======================================================
# MetricsReader for streaming benchmarks
#======================================================
# Number of sample records for `MetricsReader` (default: 5000000)
hibench.streambench.metricsReader.sampleNum      5000000
# Number of thread for `MetricsReader` (default: 20)
hibench.streambench.metricsReader.threadNum      20
# The dir where stored the report of benchmarks (default: ${hibench.home}/report)
hibench.streambench.metricsReader.outputDir      ${hibench.home}/report


hibench.mahout.home                       ${hibench.home}/hadoopbench/mahout/target/${hibench.mahout.release}