mirror of
https://github.com/NationalSecurityAgency/datawave.git
synced 2026-11-10 17:31:14 -10:00
9b2b652221
…s from NationalSecurityAgency/datawave-stack-docker-images --------- Co-authored-by: Moriarty <[email protected]> Co-authored-by: Claude Opus 5 <[email protected]>
55 lines
2.6 KiB
YAML
Executable File
55 lines
2.6 KiB
YAML
Executable File
datawave:
|
|
query:
|
|
mapreduce:
|
|
fsConfigResources:
|
|
- ${HADOOP_CONF_DIR:/etc/hadoop/conf}/core-site.xml
|
|
- ${HADOOP_CONF_DIR:/etc/hadoop/conf}/hdfs-site.xml
|
|
- ${HADOOP_CONF_DIR:/etc/hadoop/conf}/mapred-site.xml
|
|
- ${HADOOP_CONF_DIR:/etc/hadoop/conf}/yarn-site.xml
|
|
callbackServletURL: "http://query:8080/query/v1/mapreduce/updateState"
|
|
mapReduceBaseDirectory: "/datawave/MapReduceService"
|
|
restrictInputFormats: true
|
|
validInputFormats:
|
|
- "org.apache.accumulo.core.client.mapreduce.AccumuloInputFormat"
|
|
- "datawave.mr.bulk.BulkInputFormat"
|
|
jobs:
|
|
'BulkResultsJob':
|
|
startingClass: datawave.microservice.query.mapreduce.MapReduce
|
|
jobJarName: "MapReduceQueryCoreJob.jar"
|
|
description: "MapReduce job that runs a query and either puts the results into a table or files in HDFS"
|
|
hdfsUri: "hdfs://${HADOOP_HOST}:9000/"
|
|
jobTracker: "${YARN_HOST}:8032"
|
|
requiredRuntimeParameters:
|
|
queryId: java.lang.String
|
|
format: datawave.microservice.mapreduce.bulkresults.map.SerializationFormat
|
|
optionalRuntimeParameters:
|
|
outputTableName: java.lang.String
|
|
outputFormat: java.lang.String
|
|
jobConfigurationProperties:
|
|
"mapreduce.map.speculative": "false"
|
|
"mapreduce.map.output.compress": "false"
|
|
"mapreduce.output.fileoutputformat.compress": "false"
|
|
"mapreduce.job.user.classpath.first": "true"
|
|
# NOTE: Disable spring components which should not be run in a map-reduce context
|
|
jobSystemProperties:
|
|
"datawave.table.cache.enabled": "false"
|
|
"spring.profiles.active": "query,mrquery"
|
|
"spring.cloud.bus.enabled": "false"
|
|
"spring.cloud.discovery.enabled": "false"
|
|
"spring.cloud.consul.enabled": "false"
|
|
"spring.rabbitmq.discovery.enabled": "false"
|
|
"datawave.query.messaging.backend": "none"
|
|
"datawave.query.messaging.claimCheck.enabled": "false"
|
|
"datawave.query.storage.cache.enabled": "false"
|
|
"hazelcast.client.enabled": "false"
|
|
"spring.cloud.config.enabled": "false"
|
|
"datawave.query.metric.client.enabled": "false"
|
|
accumulo:
|
|
zookeepers: '${accumulo.zookeepers}'
|
|
instanceName: '${accumulo.instanceName}'
|
|
username: '${accumulo.username}'
|
|
password: '${accumulo.password}'
|
|
'OozieJob':
|
|
hdfsUri: "hdfs://${HADOOP_HOST}:9000/"
|
|
jobTracker: "${YARN_HOST}:8032"
|