interset.conf #2

#---------------------------------------------------------------------------------
#Dynamic Ingest Configuration - Changes to any of the below will be picked up on the fly
#---------------------------------------------------------------------------------
#mode = daemon|runonce
mode = daemon
#scmType = github_enterprise|perforce|repository
scmType = perforce

# If scmType=repository then repoFormat must also be provided.

# repoFormat required columns: TIMESTAMP, USER, PROJECT, ACTION
# repoFormat optional columns: CLIENT_IP, SIZE
# Ignore fields with '_'

# Example:
# repoFormat = TIMESTAMP,USER,CLIENT_IP,ACTION,_,PROJECT

# Perforce structured audit logs:
# repoFormat = _,_,_,TIMESTAMP,_,_,USER,_,_,CLIENT_IP,_,_,_,ACTION,PROJECT,_

ingestFolder = /tmp/ingest
ingestingFolder = /tmp/ingest/ingesting
ingestedFolder = /tmp/ingest/ingested
ingestErrorFolder = /tmp/ingest/ingesterror
lastModifiedThreshold = 60000
folderScansInterval = 1200000
p4ProjectDepth = 1

tenantID = 0
zkPhoenix = $htd-analytics-master$
tableName = SE
batchSize = 100000

#--------------------------------------------------------------------------------
#Static Ingest Configuration - Changes to any of the below will need a restart
#--------------------------------------------------------------------------------
maxEntriesUserCache = 7500
maxEntriesProjectCache = 1500
maxEntriesActionCache = 128
maxEntriesClientCache = 250000
maxEntriesIpCache = 35000
maxEntriesFolderCache = 1000000
cacheUpdateConcurrency = 1

#--------------------------------------------------------------------------------
#Index Generation Configuration
#--------------------------------------------------------------------------------

# Amount of memory to allocate to indexing
indexMemory = 8192m

# Comma separated list of report server hostnames. This can be localhost if
# reporting is also on the current server.
#reportServers = server1,server2,server3
reportServers = $htd-investigators$

# Root location for search indices on reporting server. (Needs to match
# `search.luceneIndexPath` from .yml file on reporting server.)
investigatorPath=/opt/interset/reporting/search

# Root folder for temporary search indices. New indices in this folder will be
# distinguished by tenant ID so this configuration item can be the same in 
# each tenant's copy of interset.conf.
tempLuceneIndexPath = /opt/interset/reporting/search_tmp


#--------------------------------------------------------------------------------
#Configuration Setting
#--------------------------------------------------------------------------------

logDirectory = /opt/interset/analytics/logs
logbackConfigurationFile = /opt/interset/analytics/conf/logback.xml
indexConfigurationFile = /opt/interset/analytics/conf/index.yml
envVariables = /opt/interset/analytics/bin/env.sh

#--------------------------------------------------------------------------------
# Spark runtime configuration
#--------------------------------------------------------------------------------

# Number of spark tasks to split tasks by. Should be 2x - 3x cluster cores
parallelism = 48