| # |
| # Licensed to the Apache Software Foundation (ASF) under one |
| # or more contributor license agreements. See the NOTICE file |
| # distributed with this work for additional information |
| # regarding copyright ownership. The ASF licenses this file |
| # to you under the Apache License, Version 2.0 (the |
| # "License"); you may not use this file except in compliance |
| # with the License. You may obtain a copy of the License at |
| # |
| # http://www.apache.org/licenses/LICENSE-2.0 |
| # |
| # Unless required by applicable law or agreed to in writing, software |
| # distributed under the License is distributed on an "AS IS" BASIS, |
| # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| # See the License for the specific language governing permissions and |
| # limitations under the License. |
| # |
| |
| #################### System Configuration ################## |
| #Mandatory. Carbon Store path |
| carbon.storelocation=hdfs://hacluster/Opt/CarbonStore |
| #Base directory for Data files |
| carbon.ddl.base.hdfs.url=hdfs://hacluster/opt/data |
| #Path where the bad records are stored |
| carbon.badRecords.location=/opt/Carbon/Spark/badrecords |
| #Mandatory. path to kettle home |
| carbon.kettle.home=$<SPARK_HOME>/carbonlib/carbonplugins |
| |
| #################### Performance Configuration ################## |
| ######## DataLoading Configuration ######## |
| #File read buffer size used during sorting(in MB) :MIN=1:MAX=100 |
| carbon.sort.file.buffer.size=20 |
| #Rowset size exchanged between data load graph steps :MIN=500:MAX=1000000 |
| carbon.graph.rowset.size=100000 |
| #Number of cores to be used while data loading |
| carbon.number.of.cores.while.loading=6 |
| #Record count to sort and write to temp intermediate files |
| carbon.sort.size=500000 |
| #Algorithm for hashmap for hashkey calculation |
| carbon.enableXXHash=true |
| #Number of cores to be used for block sort while dataloading |
| #carbon.number.of.cores.block.sort=7 |
| #max level cache size upto which level cache will be loaded in memory |
| #carbon.max.level.cache.size=-1 |
| #enable prefetch of data during merge sort while reading data from sort temp files in data loading |
| #carbon.merge.sort.prefetch=true |
| ######## Compaction Configuration ######## |
| #Number of cores to be used while compacting |
| carbon.number.of.cores.while.compacting=2 |
| #For minor compaction, Number of segments to be merged in stage 1, number of compacted segments to be merged in stage 2. |
| carbon.compaction.level.threshold=4,3 |
| #default size (in MB) for major compaction to be triggered |
| carbon.major.compaction.size=1024 |
| ######## Query Configuration ######## |
| #Number of cores to be used while querying |
| carbon.number.of.cores=4 |
| #Number of records to be in memory while querying :MIN=100000:MAX=240000 |
| carbon.inmemory.record.size=120000 |
| #Improves the performance of filter query |
| carbon.enable.quick.filter=false |
| ##number of core to load the blocks in driver |
| #no.of.cores.to.load.blocks.in.driver=10 |
| |
| #################### Extra Configuration ################## |
| ##Timestamp format of input data used for timestamp data type. |
| #carbon.timestamp.format=yyyy-MM-dd HH:mm:ss |
| ######## Dataload Configuration ######## |
| ##File write buffer size used during sorting. |
| #carbon.sort.file.write.buffer.size=10485760 |
| ##Locking mechanism for data loading on a table |
| #carbon.lock.type=LOCALLOCK |
| ##Minimum no of intermediate files after which sort merged to be started. |
| #carbon.sort.intermediate.files.limit=20 |
| ##space reserved in percentage for writing block meta data in carbon data file |
| #carbon.block.meta.size.reserved.percentage=10 |
| ##csv reading buffer size. |
| #carbon.csv.read.buffersize.byte=1048576 |
| ##To identify and apply compression for non-high cardinality columns |
| #high.cardinality.value=100000 |
| ##maximum no of threads used for reading intermediate files for final merging. |
| #carbon.merge.sort.reader.thread=3 |
| ##Carbon blocklet size. Note: this configuration cannot be change once store is generated |
| #carbon.blocklet.size=120000 |
| ##number of retries to get the metadata lock for loading data to table |
| #carbon.load.metadata.lock.retries=3 |
| ##Maximum number of blocklets written in a single file :Min=1:Max=1000 |
| #carbon.max.file.size=100 |
| ##Minimum blocklets needed for distribution. |
| #carbon.blockletdistribution.min.blocklet.size=10 |
| ##Interval between the retries to get the lock |
| #carbon.load.metadata.lock.retry.timeout.sec=5 |
| ##Temporary store location, By default it will take System.getProperty("java.io.tmpdir") |
| #carbon.tempstore.location=/opt/Carbon/TempStoreLoc |
| ##data loading records count logger |
| #carbon.load.log.counter=500000 |
| ######## Compaction Configuration ######## |
| ##to specify number of segments to be preserved from compaction |
| #carbon.numberof.preserve.segments=0 |
| ##To determine the loads of number of days to be compacted |
| #carbon.allowed.compaction.days=0 |
| ##To enable compaction while data loading |
| #carbon.enable.auto.load.merge=false |
| ######## Query Configuration ######## |
| ##Maximum time allowed for one query to be executed. |
| #max.query.execution.time=60 |
| ##Min max is feature added to enhance query performance. To disable this feature, make it false. |
| #carbon.enableMinMax=true |
| ######## Global Dictionary Configurations ######## |
| ##To enable/disable identify high cardinality during first data loading |
| #high.cardinality.identify.enable=true |
| ##threshold to identify whether high cardinality column |
| #high.cardinality.threshold=1000000 |
| ##Percentage to identify whether column cardinality is more than configured percent of total row count |
| #high.cardinality.row.count.percentage=80 |
| ##The property to set the date to be considered as start date for calculating the timestamp. |
| #carbon.cutOffTimestamp=2000-01-01 00:00:00 |
| ##The property to set the timestamp (ie milis) conversion to the SECOND, MINUTE, HOUR or DAY level. |
| #carbon.timegranularity=SECOND |
