/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java
Java | 1720 lines | 1161 code | 228 blank | 331 comment | 89 complexity | f6c3d3a755169fd464147422d4ca8c23 MD5 | raw file
Possible License(s): Apache-2.0
Large files files are truncated, but you can click here to view the full file
- /**
- * 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.
- */
- package org.apache.hadoop.hive.conf;
- import java.io.ByteArrayOutputStream;
- import java.io.File;
- import java.io.IOException;
- import java.io.InputStream;
- import java.io.PrintStream;
- import java.net.URL;
- import java.util.ArrayList;
- import java.util.HashMap;
- import java.util.Iterator;
- import java.util.LinkedHashSet;
- import java.util.List;
- import java.util.Map;
- import java.util.Map.Entry;
- import java.util.Properties;
- import java.util.Set;
- import java.util.regex.Matcher;
- import java.util.regex.Pattern;
- import javax.security.auth.login.LoginException;
- import org.apache.commons.lang.StringUtils;
- import org.apache.commons.logging.Log;
- import org.apache.commons.logging.LogFactory;
- import org.apache.hadoop.conf.Configuration;
- import org.apache.hadoop.hive.common.classification.InterfaceAudience.LimitedPrivate;
- import org.apache.hadoop.hive.shims.ShimLoader;
- import org.apache.hadoop.mapred.JobConf;
- import org.apache.hadoop.security.UserGroupInformation;
- import org.apache.hadoop.util.Shell;
- import org.apache.hive.common.HiveCompat;
- /**
- * Hive Configuration.
- */
- public class HiveConf extends Configuration {
- protected String hiveJar;
- protected Properties origProp;
- protected String auxJars;
- private static final Log l4j = LogFactory.getLog(HiveConf.class);
- private static URL hiveDefaultURL = null;
- private static URL hiveSiteURL = null;
- private static byte[] confVarByteArray = null;
- private static final Map<String, ConfVars> vars = new HashMap<String, ConfVars>();
- private final List<String> restrictList = new ArrayList<String>();
- private boolean isWhiteListRestrictionEnabled = false;
- private final List<String> modWhiteList = new ArrayList<String>();
- static {
- ClassLoader classLoader = Thread.currentThread().getContextClassLoader();
- if (classLoader == null) {
- classLoader = HiveConf.class.getClassLoader();
- }
- hiveDefaultURL = classLoader.getResource("hive-default.xml");
- // Look for hive-site.xml on the CLASSPATH and log its location if found.
- hiveSiteURL = classLoader.getResource("hive-site.xml");
- for (ConfVars confVar : ConfVars.values()) {
- vars.put(confVar.varname, confVar);
- }
- }
- /**
- * Metastore related options that the db is initialized against. When a conf
- * var in this is list is changed, the metastore instance for the CLI will
- * be recreated so that the change will take effect.
- */
- public static final HiveConf.ConfVars[] metaVars = {
- HiveConf.ConfVars.METASTOREDIRECTORY,
- HiveConf.ConfVars.METASTOREWAREHOUSE,
- HiveConf.ConfVars.METASTOREURIS,
- HiveConf.ConfVars.METASTORETHRIFTCONNECTIONRETRIES,
- HiveConf.ConfVars.METASTORETHRIFTFAILURERETRIES,
- HiveConf.ConfVars.METASTORE_CLIENT_CONNECT_RETRY_DELAY,
- HiveConf.ConfVars.METASTORE_CLIENT_SOCKET_TIMEOUT,
- HiveConf.ConfVars.METASTOREPWD,
- HiveConf.ConfVars.METASTORECONNECTURLHOOK,
- HiveConf.ConfVars.METASTORECONNECTURLKEY,
- HiveConf.ConfVars.METASTOREFORCERELOADCONF,
- HiveConf.ConfVars.METASTORESERVERMINTHREADS,
- HiveConf.ConfVars.METASTORESERVERMAXTHREADS,
- HiveConf.ConfVars.METASTORE_TCP_KEEP_ALIVE,
- HiveConf.ConfVars.METASTORE_INT_ORIGINAL,
- HiveConf.ConfVars.METASTORE_INT_ARCHIVED,
- HiveConf.ConfVars.METASTORE_INT_EXTRACTED,
- HiveConf.ConfVars.METASTORE_KERBEROS_KEYTAB_FILE,
- HiveConf.ConfVars.METASTORE_KERBEROS_PRINCIPAL,
- HiveConf.ConfVars.METASTORE_USE_THRIFT_SASL,
- HiveConf.ConfVars.METASTORE_CACHE_PINOBJTYPES,
- HiveConf.ConfVars.METASTORE_CONNECTION_POOLING_TYPE,
- HiveConf.ConfVars.METASTORE_VALIDATE_TABLES,
- HiveConf.ConfVars.METASTORE_VALIDATE_COLUMNS,
- HiveConf.ConfVars.METASTORE_VALIDATE_CONSTRAINTS,
- HiveConf.ConfVars.METASTORE_STORE_MANAGER_TYPE,
- HiveConf.ConfVars.METASTORE_AUTO_CREATE_SCHEMA,
- HiveConf.ConfVars.METASTORE_AUTO_START_MECHANISM_MODE,
- HiveConf.ConfVars.METASTORE_TRANSACTION_ISOLATION,
- HiveConf.ConfVars.METASTORE_CACHE_LEVEL2,
- HiveConf.ConfVars.METASTORE_CACHE_LEVEL2_TYPE,
- HiveConf.ConfVars.METASTORE_IDENTIFIER_FACTORY,
- HiveConf.ConfVars.METASTORE_PLUGIN_REGISTRY_BUNDLE_CHECK,
- HiveConf.ConfVars.METASTORE_AUTHORIZATION_STORAGE_AUTH_CHECKS,
- HiveConf.ConfVars.METASTORE_BATCH_RETRIEVE_MAX,
- HiveConf.ConfVars.METASTORE_EVENT_LISTENERS,
- HiveConf.ConfVars.METASTORE_EVENT_CLEAN_FREQ,
- HiveConf.ConfVars.METASTORE_EVENT_EXPIRY_DURATION,
- HiveConf.ConfVars.METASTORE_RAW_STORE_IMPL,
- HiveConf.ConfVars.METASTORE_END_FUNCTION_LISTENERS,
- HiveConf.ConfVars.METASTORE_PART_INHERIT_TBL_PROPS,
- HiveConf.ConfVars.METASTORE_BATCH_RETRIEVE_TABLE_PARTITION_MAX,
- HiveConf.ConfVars.METASTORE_INIT_HOOKS,
- HiveConf.ConfVars.METASTORE_PRE_EVENT_LISTENERS,
- HiveConf.ConfVars.HMSHANDLERATTEMPTS,
- HiveConf.ConfVars.HMSHANDLERINTERVAL,
- HiveConf.ConfVars.HMSHANDLERFORCERELOADCONF,
- HiveConf.ConfVars.METASTORE_PARTITION_NAME_WHITELIST_PATTERN,
- HiveConf.ConfVars.METASTORE_DISALLOW_INCOMPATIBLE_COL_TYPE_CHANGES,
- HiveConf.ConfVars.USERS_IN_ADMIN_ROLE,
- HiveConf.ConfVars.HIVE_AUTHORIZATION_MANAGER,
- HiveConf.ConfVars.HIVE_TXN_MANAGER,
- HiveConf.ConfVars.HIVE_TXN_TIMEOUT,
- HiveConf.ConfVars.HIVE_TXN_MAX_OPEN_BATCH,
- };
- /**
- * dbVars are the parameters can be set per database. If these
- * parameters are set as a database property, when switching to that
- * database, the HiveConf variable will be changed. The change of these
- * parameters will effectively change the DFS and MapReduce clusters
- * for different databases.
- */
- public static final HiveConf.ConfVars[] dbVars = {
- HiveConf.ConfVars.HADOOPBIN,
- HiveConf.ConfVars.METASTOREWAREHOUSE,
- HiveConf.ConfVars.SCRATCHDIR
- };
- /**
- * ConfVars.
- *
- * These are the default configuration properties for Hive. Each HiveConf
- * object is initialized as follows:
- *
- * 1) Hadoop configuration properties are applied.
- * 2) ConfVar properties with non-null values are overlayed.
- * 3) hive-site.xml properties are overlayed.
- *
- * WARNING: think twice before adding any Hadoop configuration properties
- * with non-null values to this list as they will override any values defined
- * in the underlying Hadoop configuration.
- */
- public static enum ConfVars {
- // QL execution stuff
- SCRIPTWRAPPER("hive.exec.script.wrapper", null),
- PLAN("hive.exec.plan", ""),
- PLAN_SERIALIZATION("hive.plan.serialization.format","kryo"),
- SCRATCHDIR("hive.exec.scratchdir", "/tmp/hive-" + System.getProperty("user.name")),
- LOCALSCRATCHDIR("hive.exec.local.scratchdir", System.getProperty("java.io.tmpdir") + File.separator + System.getProperty("user.name")),
- SCRATCHDIRPERMISSION("hive.scratch.dir.permission", "700"),
- SUBMITVIACHILD("hive.exec.submitviachild", false),
- SUBMITLOCALTASKVIACHILD("hive.exec.submit.local.task.via.child", true),
- SCRIPTERRORLIMIT("hive.exec.script.maxerrsize", 100000),
- ALLOWPARTIALCONSUMP("hive.exec.script.allow.partial.consumption", false),
- STREAMREPORTERPERFIX("stream.stderr.reporter.prefix", "reporter:"),
- STREAMREPORTERENABLED("stream.stderr.reporter.enabled", true),
- COMPRESSRESULT("hive.exec.compress.output", false),
- COMPRESSINTERMEDIATE("hive.exec.compress.intermediate", false),
- COMPRESSINTERMEDIATECODEC("hive.intermediate.compression.codec", ""),
- COMPRESSINTERMEDIATETYPE("hive.intermediate.compression.type", ""),
- BYTESPERREDUCER("hive.exec.reducers.bytes.per.reducer", (long) (256 * 1000 * 1000)),
- MAXREDUCERS("hive.exec.reducers.max", 1009), // pick a prime
- PREEXECHOOKS("hive.exec.pre.hooks", ""),
- POSTEXECHOOKS("hive.exec.post.hooks", ""),
- ONFAILUREHOOKS("hive.exec.failure.hooks", ""),
- CLIENTSTATSPUBLISHERS("hive.client.stats.publishers", ""),
- EXECPARALLEL("hive.exec.parallel", false), // parallel query launching
- EXECPARALLETHREADNUMBER("hive.exec.parallel.thread.number", 8),
- HIVESPECULATIVEEXECREDUCERS("hive.mapred.reduce.tasks.speculative.execution", true),
- HIVECOUNTERSPULLINTERVAL("hive.exec.counters.pull.interval", 1000L),
- DYNAMICPARTITIONING("hive.exec.dynamic.partition", true),
- DYNAMICPARTITIONINGMODE("hive.exec.dynamic.partition.mode", "strict"),
- DYNAMICPARTITIONMAXPARTS("hive.exec.max.dynamic.partitions", 1000),
- DYNAMICPARTITIONMAXPARTSPERNODE("hive.exec.max.dynamic.partitions.pernode", 100),
- MAXCREATEDFILES("hive.exec.max.created.files", 100000L),
- DOWNLOADED_RESOURCES_DIR("hive.downloaded.resources.dir",
- System.getProperty("java.io.tmpdir") + File.separator + "${hive.session.id}_resources"),
- DEFAULTPARTITIONNAME("hive.exec.default.partition.name", "__HIVE_DEFAULT_PARTITION__"),
- DEFAULT_ZOOKEEPER_PARTITION_NAME("hive.lockmgr.zookeeper.default.partition.name", "__HIVE_DEFAULT_ZOOKEEPER_PARTITION__"),
- // Whether to show a link to the most failed task + debugging tips
- SHOW_JOB_FAIL_DEBUG_INFO("hive.exec.show.job.failure.debug.info", true),
- JOB_DEBUG_CAPTURE_STACKTRACES("hive.exec.job.debug.capture.stacktraces", true),
- JOB_DEBUG_TIMEOUT("hive.exec.job.debug.timeout", 30000),
- TASKLOG_DEBUG_TIMEOUT("hive.exec.tasklog.debug.timeout", 20000),
- OUTPUT_FILE_EXTENSION("hive.output.file.extension", null),
- HIVE_IN_TEST("hive.in.test", false), // internal usage only, true in test mode
- // should hive determine whether to run in local mode automatically ?
- LOCALMODEAUTO("hive.exec.mode.local.auto", false),
- // if yes:
- // run in local mode only if input bytes is less than this. 128MB by default
- LOCALMODEMAXBYTES("hive.exec.mode.local.auto.inputbytes.max", 134217728L),
- // run in local mode only if number of tasks (for map and reduce each) is
- // less than this
- LOCALMODEMAXINPUTFILES("hive.exec.mode.local.auto.input.files.max", 4),
- // if true, DROP TABLE/VIEW does not fail if table/view doesn't exist and IF EXISTS is
- // not specified
- DROPIGNORESNONEXISTENT("hive.exec.drop.ignorenonexistent", true),
- // ignore the mapjoin hint
- HIVEIGNOREMAPJOINHINT("hive.ignore.mapjoin.hint", true),
- // Max number of lines of footer user can set for a table file.
- HIVE_FILE_MAX_FOOTER("hive.file.max.footer", 100),
- // Make column names unique in the result set by using table alias if needed
- HIVE_RESULTSET_USE_UNIQUE_COLUMN_NAMES("hive.resultset.use.unique.column.names", true),
- // Hadoop Configuration Properties
- // Properties with null values are ignored and exist only for the purpose of giving us
- // a symbolic name to reference in the Hive source code. Properties with non-null
- // values will override any values set in the underlying Hadoop configuration.
- HADOOPBIN("hadoop.bin.path", findHadoopBinary()),
- HIVE_FS_HAR_IMPL("fs.har.impl", "org.apache.hadoop.hive.shims.HiveHarFileSystem"),
- HADOOPFS(ShimLoader.getHadoopShims().getHadoopConfNames().get("HADOOPFS"), null),
- HADOOPMAPFILENAME(ShimLoader.getHadoopShims().getHadoopConfNames().get("HADOOPMAPFILENAME"), null),
- HADOOPMAPREDINPUTDIR(ShimLoader.getHadoopShims().getHadoopConfNames().get("HADOOPMAPREDINPUTDIR"), null),
- HADOOPMAPREDINPUTDIRRECURSIVE(ShimLoader.getHadoopShims().getHadoopConfNames().get("HADOOPMAPREDINPUTDIRRECURSIVE"), false),
- MAPREDMAXSPLITSIZE(ShimLoader.getHadoopShims().getHadoopConfNames().get("MAPREDMAXSPLITSIZE"), 256000000L),
- MAPREDMINSPLITSIZE(ShimLoader.getHadoopShims().getHadoopConfNames().get("MAPREDMINSPLITSIZE"), 1L),
- MAPREDMINSPLITSIZEPERNODE(ShimLoader.getHadoopShims().getHadoopConfNames().get("MAPREDMINSPLITSIZEPERNODE"), 1L),
- MAPREDMINSPLITSIZEPERRACK(ShimLoader.getHadoopShims().getHadoopConfNames().get("MAPREDMINSPLITSIZEPERRACK"), 1L),
- // The number of reduce tasks per job. Hadoop sets this value to 1 by default
- // By setting this property to -1, Hive will automatically determine the correct
- // number of reducers.
- HADOOPNUMREDUCERS(ShimLoader.getHadoopShims().getHadoopConfNames().get("HADOOPNUMREDUCERS"), -1),
- HADOOPJOBNAME(ShimLoader.getHadoopShims().getHadoopConfNames().get("HADOOPJOBNAME"), null),
- HADOOPSPECULATIVEEXECREDUCERS(ShimLoader.getHadoopShims().getHadoopConfNames().get("HADOOPSPECULATIVEEXECREDUCERS"), true),
- MAPREDSETUPCLEANUPNEEDED(ShimLoader.getHadoopShims().getHadoopConfNames().get("MAPREDSETUPCLEANUPNEEDED"), false),
- MAPREDTASKCLEANUPNEEDED(ShimLoader.getHadoopShims().getHadoopConfNames().get("MAPREDTASKCLEANUPNEEDED"), false),
- // Metastore stuff. Be sure to update HiveConf.metaVars when you add
- // something here!
- METASTOREDIRECTORY("hive.metastore.metadb.dir", ""),
- METASTOREWAREHOUSE("hive.metastore.warehouse.dir", "/user/hive/warehouse"),
- METASTOREURIS("hive.metastore.uris", ""),
- // Number of times to retry a connection to a Thrift metastore server
- METASTORETHRIFTCONNECTIONRETRIES("hive.metastore.connect.retries", 3),
- // Number of times to retry a Thrift metastore call upon failure
- METASTORETHRIFTFAILURERETRIES("hive.metastore.failure.retries", 1),
- // Number of seconds the client should wait between connection attempts
- METASTORE_CLIENT_CONNECT_RETRY_DELAY("hive.metastore.client.connect.retry.delay", 1),
- // Socket timeout for the client connection (in seconds)
- METASTORE_CLIENT_SOCKET_TIMEOUT("hive.metastore.client.socket.timeout", 600),
- METASTOREPWD("javax.jdo.option.ConnectionPassword", "mine"),
- // Class name of JDO connection url hook
- METASTORECONNECTURLHOOK("hive.metastore.ds.connection.url.hook", ""),
- METASTOREMULTITHREADED("javax.jdo.option.Multithreaded", true),
- // Name of the connection url in the configuration
- METASTORECONNECTURLKEY("javax.jdo.option.ConnectionURL",
- "jdbc:derby:;databaseName=metastore_db;create=true"),
- // Whether to force reloading of the metastore configuration (including
- // the connection URL, before the next metastore query that accesses the
- // datastore. Once reloaded, this value is reset to false. Used for
- // testing only.
- METASTOREFORCERELOADCONF("hive.metastore.force.reload.conf", false),
- // Number of attempts to retry connecting after there is a JDO datastore err
- HMSHANDLERATTEMPTS("hive.hmshandler.retry.attempts", 1),
- // Number of miliseconds to wait between attepting
- HMSHANDLERINTERVAL("hive.hmshandler.retry.interval", 1000),
- // Whether to force reloading of the HMSHandler configuration (including
- // the connection URL, before the next metastore query that accesses the
- // datastore. Once reloaded, this value is reset to false. Used for
- // testing only.
- HMSHANDLERFORCERELOADCONF("hive.hmshandler.force.reload.conf", false),
- METASTORESERVERMINTHREADS("hive.metastore.server.min.threads", 200),
- METASTORESERVERMAXTHREADS("hive.metastore.server.max.threads", 100000),
- METASTORE_TCP_KEEP_ALIVE("hive.metastore.server.tcp.keepalive", true),
- // Intermediate dir suffixes used for archiving. Not important what they
- // are, as long as collisions are avoided
- METASTORE_INT_ORIGINAL("hive.metastore.archive.intermediate.original",
- "_INTERMEDIATE_ORIGINAL"),
- METASTORE_INT_ARCHIVED("hive.metastore.archive.intermediate.archived",
- "_INTERMEDIATE_ARCHIVED"),
- METASTORE_INT_EXTRACTED("hive.metastore.archive.intermediate.extracted",
- "_INTERMEDIATE_EXTRACTED"),
- METASTORE_KERBEROS_KEYTAB_FILE("hive.metastore.kerberos.keytab.file", ""),
- METASTORE_KERBEROS_PRINCIPAL("hive.metastore.kerberos.principal",
- "hive-metastore/_HOST@EXAMPLE.COM"),
- METASTORE_USE_THRIFT_SASL("hive.metastore.sasl.enabled", false),
- METASTORE_USE_THRIFT_FRAMED_TRANSPORT("hive.metastore.thrift.framed.transport.enabled", false),
- METASTORE_CLUSTER_DELEGATION_TOKEN_STORE_CLS(
- "hive.cluster.delegation.token.store.class",
- "org.apache.hadoop.hive.thrift.MemoryTokenStore"),
- METASTORE_CLUSTER_DELEGATION_TOKEN_STORE_ZK_CONNECTSTR(
- "hive.cluster.delegation.token.store.zookeeper.connectString", ""),
- METASTORE_CLUSTER_DELEGATION_TOKEN_STORE_ZK_ZNODE(
- "hive.cluster.delegation.token.store.zookeeper.znode", "/hive/cluster/delegation"),
- METASTORE_CLUSTER_DELEGATION_TOKEN_STORE_ZK_ACL(
- "hive.cluster.delegation.token.store.zookeeper.acl", ""),
- METASTORE_CACHE_PINOBJTYPES("hive.metastore.cache.pinobjtypes", "Table,StorageDescriptor,SerDeInfo,Partition,Database,Type,FieldSchema,Order"),
- METASTORE_CONNECTION_POOLING_TYPE("datanucleus.connectionPoolingType", "BONECP"),
- METASTORE_VALIDATE_TABLES("datanucleus.validateTables", false),
- METASTORE_VALIDATE_COLUMNS("datanucleus.validateColumns", false),
- METASTORE_VALIDATE_CONSTRAINTS("datanucleus.validateConstraints", false),
- METASTORE_STORE_MANAGER_TYPE("datanucleus.storeManagerType", "rdbms"),
- METASTORE_AUTO_CREATE_SCHEMA("datanucleus.autoCreateSchema", true),
- METASTORE_FIXED_DATASTORE("datanucleus.fixedDatastore", false),
- METASTORE_SCHEMA_VERIFICATION("hive.metastore.schema.verification", false),
- METASTORE_AUTO_START_MECHANISM_MODE("datanucleus.autoStartMechanismMode", "checked"),
- METASTORE_TRANSACTION_ISOLATION("datanucleus.transactionIsolation", "read-committed"),
- METASTORE_CACHE_LEVEL2("datanucleus.cache.level2", false),
- METASTORE_CACHE_LEVEL2_TYPE("datanucleus.cache.level2.type", "none"),
- METASTORE_IDENTIFIER_FACTORY("datanucleus.identifierFactory", "datanucleus1"),
- METASTORE_USE_LEGACY_VALUE_STRATEGY("datanucleus.rdbms.useLegacyNativeValueStrategy", true),
- METASTORE_PLUGIN_REGISTRY_BUNDLE_CHECK("datanucleus.plugin.pluginRegistryBundleCheck", "LOG"),
- METASTORE_BATCH_RETRIEVE_MAX("hive.metastore.batch.retrieve.max", 300),
- METASTORE_BATCH_RETRIEVE_TABLE_PARTITION_MAX(
- "hive.metastore.batch.retrieve.table.partition.max", 1000),
- // A comma separated list of hooks which implement MetaStoreInitListener and will be run at
- // the beginning of HMSHandler initialization
- METASTORE_INIT_HOOKS("hive.metastore.init.hooks", ""),
- METASTORE_PRE_EVENT_LISTENERS("hive.metastore.pre.event.listeners", ""),
- METASTORE_EVENT_LISTENERS("hive.metastore.event.listeners", ""),
- // should we do checks against the storage (usually hdfs) for operations like drop_partition
- METASTORE_AUTHORIZATION_STORAGE_AUTH_CHECKS("hive.metastore.authorization.storage.checks", false),
- METASTORE_EVENT_CLEAN_FREQ("hive.metastore.event.clean.freq",0L),
- METASTORE_EVENT_EXPIRY_DURATION("hive.metastore.event.expiry.duration",0L),
- METASTORE_EXECUTE_SET_UGI("hive.metastore.execute.setugi", true),
- METASTORE_PARTITION_NAME_WHITELIST_PATTERN(
- "hive.metastore.partition.name.whitelist.pattern", ""),
- // Whether to enable integral JDO pushdown. For partition columns storing integers
- // in non-canonical form, (e.g. '012'), it may not work, so it's off by default.
- METASTORE_INTEGER_JDO_PUSHDOWN("hive.metastore.integral.jdo.pushdown", false),
- METASTORE_TRY_DIRECT_SQL("hive.metastore.try.direct.sql", true),
- METASTORE_TRY_DIRECT_SQL_DDL("hive.metastore.try.direct.sql.ddl", true),
- METASTORE_DISALLOW_INCOMPATIBLE_COL_TYPE_CHANGES(
- "hive.metastore.disallow.incompatible.col.type.changes", false),
- // Default parameters for creating tables
- NEWTABLEDEFAULTPARA("hive.table.parameters.default", ""),
- // Parameters to copy over when creating a table with Create Table Like.
- DDL_CTL_PARAMETERS_WHITELIST("hive.ddl.createtablelike.properties.whitelist", ""),
- METASTORE_RAW_STORE_IMPL("hive.metastore.rawstore.impl",
- "org.apache.hadoop.hive.metastore.ObjectStore"),
- METASTORE_CONNECTION_DRIVER("javax.jdo.option.ConnectionDriverName",
- "org.apache.derby.jdbc.EmbeddedDriver"),
- METASTORE_MANAGER_FACTORY_CLASS("javax.jdo.PersistenceManagerFactoryClass",
- "org.datanucleus.api.jdo.JDOPersistenceManagerFactory"),
- METASTORE_EXPRESSION_PROXY_CLASS("hive.metastore.expression.proxy",
- "org.apache.hadoop.hive.ql.optimizer.ppr.PartitionExpressionForMetastore"),
- METASTORE_DETACH_ALL_ON_COMMIT("javax.jdo.option.DetachAllOnCommit", true),
- METASTORE_NON_TRANSACTIONAL_READ("javax.jdo.option.NonTransactionalRead", true),
- METASTORE_CONNECTION_USER_NAME("javax.jdo.option.ConnectionUserName", "APP"),
- METASTORE_END_FUNCTION_LISTENERS("hive.metastore.end.function.listeners", ""),
- METASTORE_PART_INHERIT_TBL_PROPS("hive.metastore.partition.inherit.table.properties",""),
- // Parameters for exporting metadata on table drop (requires the use of the)
- // org.apache.hadoop.hive.ql.parse.MetaDataExportListener preevent listener
- METADATA_EXPORT_LOCATION("hive.metadata.export.location", ""),
- MOVE_EXPORTED_METADATA_TO_TRASH("hive.metadata.move.exported.metadata.to.trash", true),
- // CLI
- CLIIGNOREERRORS("hive.cli.errors.ignore", false),
- CLIPRINTCURRENTDB("hive.cli.print.current.db", false),
- CLIPROMPT("hive.cli.prompt", "hive"),
- CLIPRETTYOUTPUTNUMCOLS("hive.cli.pretty.output.num.cols", -1),
- HIVE_METASTORE_FS_HANDLER_CLS("hive.metastore.fs.handler.class", "org.apache.hadoop.hive.metastore.HiveMetaStoreFsImpl"),
- // Things we log in the jobconf
- // session identifier
- HIVESESSIONID("hive.session.id", ""),
- // whether session is running in silent mode or not
- HIVESESSIONSILENT("hive.session.silent", false),
- // Whether to enable history for this session
- HIVE_SESSION_HISTORY_ENABLED("hive.session.history.enabled", false),
- // query being executed (multiple per session)
- HIVEQUERYSTRING("hive.query.string", ""),
- // id of query being executed (multiple per session)
- HIVEQUERYID("hive.query.id", ""),
- // id of the mapred plan being executed (multiple per query)
- HIVEPLANID("hive.query.planid", ""),
- // max jobname length
- HIVEJOBNAMELENGTH("hive.jobname.length", 50),
- // hive jar
- HIVEJAR("hive.jar.path", ""),
- HIVEAUXJARS("hive.aux.jars.path", ""),
- // hive added files and jars
- HIVEADDEDFILES("hive.added.files.path", ""),
- HIVEADDEDJARS("hive.added.jars.path", ""),
- HIVEADDEDARCHIVES("hive.added.archives.path", ""),
- HIVE_CURRENT_DATABASE("hive.current.database", ""), // internal usage only
- // for hive script operator
- HIVES_AUTO_PROGRESS_TIMEOUT("hive.auto.progress.timeout", 0),
- HIVETABLENAME("hive.table.name", ""),
- HIVEPARTITIONNAME("hive.partition.name", ""),
- HIVESCRIPTAUTOPROGRESS("hive.script.auto.progress", false),
- HIVESCRIPTIDENVVAR("hive.script.operator.id.env.var", "HIVE_SCRIPT_OPERATOR_ID"),
- HIVESCRIPTTRUNCATEENV("hive.script.operator.truncate.env", false),
- HIVEMAPREDMODE("hive.mapred.mode", "nonstrict"),
- HIVEALIAS("hive.alias", ""),
- HIVEMAPSIDEAGGREGATE("hive.map.aggr", true),
- HIVEGROUPBYSKEW("hive.groupby.skewindata", false),
- HIVE_OPTIMIZE_MULTI_GROUPBY_COMMON_DISTINCTS("hive.optimize.multigroupby.common.distincts",
- true),
- HIVEJOINEMITINTERVAL("hive.join.emit.interval", 1000),
- HIVEJOINCACHESIZE("hive.join.cache.size", 25000),
- // hive.mapjoin.bucket.cache.size has been replaced by hive.smbjoin.cache.row,
- // need to remove by hive .13. Also, do not change default (see SMB operator)
- HIVEMAPJOINBUCKETCACHESIZE("hive.mapjoin.bucket.cache.size", 100),
- HIVEMAPJOINUSEOPTIMIZEDTABLE("hive.mapjoin.optimized.hashtable", true),
- HIVEMAPJOINUSEOPTIMIZEDKEYS("hive.mapjoin.optimized.keys", true),
- HIVEMAPJOINLAZYHASHTABLE("hive.mapjoin.lazy.hashtable", true),
- HIVEHASHTABLEWBSIZE("hive.mapjoin.optimized.hashtable.wbsize", 10 * 1024 * 1024),
- HIVESMBJOINCACHEROWS("hive.smbjoin.cache.rows", 10000),
- HIVEGROUPBYMAPINTERVAL("hive.groupby.mapaggr.checkinterval", 100000),
- HIVEMAPAGGRHASHMEMORY("hive.map.aggr.hash.percentmemory", (float) 0.5),
- HIVEMAPJOINFOLLOWEDBYMAPAGGRHASHMEMORY("hive.mapjoin.followby.map.aggr.hash.percentmemory", (float) 0.3),
- HIVEMAPAGGRMEMORYTHRESHOLD("hive.map.aggr.hash.force.flush.memory.threshold", (float) 0.9),
- HIVEMAPAGGRHASHMINREDUCTION("hive.map.aggr.hash.min.reduction", (float) 0.5),
- HIVEMULTIGROUPBYSINGLEREDUCER("hive.multigroupby.singlereducer", true),
- HIVE_MAP_GROUPBY_SORT("hive.map.groupby.sorted", false),
- HIVE_MAP_GROUPBY_SORT_TESTMODE("hive.map.groupby.sorted.testmode", false),
- HIVE_GROUPBY_ORDERBY_POSITION_ALIAS("hive.groupby.orderby.position.alias", false),
- HIVE_NEW_JOB_GROUPING_SET_CARDINALITY("hive.new.job.grouping.set.cardinality", 30),
- // for hive udtf operator
- HIVEUDTFAUTOPROGRESS("hive.udtf.auto.progress", false),
- // Default file format for CREATE TABLE statement
- // Options: TextFile, SequenceFile
- HIVEDEFAULTFILEFORMAT("hive.default.fileformat", "TextFile",
- new StringsValidator("TextFile", "SequenceFile", "RCfile", "ORC")),
- HIVEQUERYRESULTFILEFORMAT("hive.query.result.fileformat", "TextFile",
- new StringsValidator("TextFile", "SequenceFile", "RCfile")),
- HIVECHECKFILEFORMAT("hive.fileformat.check", true),
- // default serde for rcfile
- HIVEDEFAULTRCFILESERDE("hive.default.rcfile.serde",
- "org.apache.hadoop.hive.serde2.columnar.LazyBinaryColumnarSerDe"),
- SERDESUSINGMETASTOREFORSCHEMA("hive.serdes.using.metastore.for.schema","org.apache.hadoop.hive.ql.io.orc.OrcSerde,"
- + "org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe,org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe,"
- + "org.apache.hadoop.hive.serde2.dynamic_type.DynamicSerDe,org.apache.hadoop.hive.serde2.MetadataTypedColumnsetSerDe,"
- + "org.apache.hadoop.hive.serde2.columnar.LazyBinaryColumnarSerDe,org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe,"
- + "org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe"),
- //Location of Hive run time structured log file
- HIVEHISTORYFILELOC("hive.querylog.location", System.getProperty("java.io.tmpdir") + File.separator + System.getProperty("user.name")),
- // Whether to log the plan's progress every time a job's progress is checked
- HIVE_LOG_INCREMENTAL_PLAN_PROGRESS("hive.querylog.enable.plan.progress", true),
- // The interval between logging the plan's progress in milliseconds
- HIVE_LOG_INCREMENTAL_PLAN_PROGRESS_INTERVAL("hive.querylog.plan.progress.interval", 60000L),
- // Default serde and record reader for user scripts
- HIVESCRIPTSERDE("hive.script.serde", "org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"),
- HIVESCRIPTRECORDREADER("hive.script.recordreader",
- "org.apache.hadoop.hive.ql.exec.TextRecordReader"),
- HIVESCRIPTRECORDWRITER("hive.script.recordwriter",
- "org.apache.hadoop.hive.ql.exec.TextRecordWriter"),
- HIVESCRIPTESCAPE("hive.transform.escape.input", false),
- HIVEBINARYRECORDMAX("hive.binary.record.max.length", 1000 ),
- // HWI
- HIVEHWILISTENHOST("hive.hwi.listen.host", "0.0.0.0"),
- HIVEHWILISTENPORT("hive.hwi.listen.port", "9999"),
- HIVEHWIWARFILE("hive.hwi.war.file", System.getenv("HWI_WAR_FILE")),
- // mapper/reducer memory in local mode
- HIVEHADOOPMAXMEM("hive.mapred.local.mem", 0),
- //small table file size
- HIVESMALLTABLESFILESIZE("hive.mapjoin.smalltable.filesize",25000000L), //25M
- // random number for split sampling
- HIVESAMPLERANDOMNUM("hive.sample.seednumber", 0),
- // test mode in hive mode
- HIVETESTMODE("hive.test.mode", false),
- HIVETESTMODEPREFIX("hive.test.mode.prefix", "test_"),
- HIVETESTMODESAMPLEFREQ("hive.test.mode.samplefreq", 32),
- HIVETESTMODENOSAMPLE("hive.test.mode.nosamplelist", ""),
- HIVETESTMODEDUMMYSTATAGGR("hive.test.dummystats.aggregator", ""), // internal variable
- HIVETESTMODEDUMMYSTATPUB("hive.test.dummystats.publisher", ""), // internal variable
- HIVEMERGEMAPFILES("hive.merge.mapfiles", true),
- HIVEMERGEMAPREDFILES("hive.merge.mapredfiles", false),
- HIVEMERGETEZFILES("hive.merge.tezfiles", false),
- HIVEMERGEMAPFILESSIZE("hive.merge.size.per.task", (long) (256 * 1000 * 1000)),
- HIVEMERGEMAPFILESAVGSIZE("hive.merge.smallfiles.avgsize", (long) (16 * 1000 * 1000)),
- HIVEMERGERCFILEBLOCKLEVEL("hive.merge.rcfile.block.level", true),
- HIVEMERGEINPUTFORMATBLOCKLEVEL("hive.merge.input.format.block.level",
- "org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat"),
- HIVEMERGECURRENTJOBHASDYNAMICPARTITIONS(
- "hive.merge.current.job.has.dynamic.partitions", false),
- HIVEUSEEXPLICITRCFILEHEADER("hive.exec.rcfile.use.explicit.header", true),
- HIVEUSERCFILESYNCCACHE("hive.exec.rcfile.use.sync.cache", true),
- HIVE_RCFILE_RECORD_INTERVAL("hive.io.rcfile.record.interval", Integer.MAX_VALUE),
- HIVE_RCFILE_COLUMN_NUMBER_CONF("hive.io.rcfile.column.number.conf", 0),
- HIVE_RCFILE_TOLERATE_CORRUPTIONS("hive.io.rcfile.tolerate.corruptions", false),
- HIVE_RCFILE_RECORD_BUFFER_SIZE("hive.io.rcfile.record.buffer.size", 4194304), // 4M
- // Maximum fraction of heap that can be used by ORC file writers
- HIVE_ORC_FILE_MEMORY_POOL("hive.exec.orc.memory.pool", 0.5f), // 50%
- // Define the version of the file to write
- HIVE_ORC_WRITE_FORMAT("hive.exec.orc.write.format", null),
- // Define the default ORC stripe size
- HIVE_ORC_DEFAULT_STRIPE_SIZE("hive.exec.orc.default.stripe.size",
- 256L * 1024 * 1024),
- HIVE_ORC_DICTIONARY_KEY_SIZE_THRESHOLD(
- "hive.exec.orc.dictionary.key.size.threshold", 0.8f),
- // Define the default ORC index stride
- HIVE_ORC_DEFAULT_ROW_INDEX_STRIDE("hive.exec.orc.default.row.index.stride"
- , 10000),
- // Define the default ORC buffer size
- HIVE_ORC_DEFAULT_BUFFER_SIZE("hive.exec.orc.default.buffer.size", 256 * 1024),
- // Define the default block padding
- HIVE_ORC_DEFAULT_BLOCK_PADDING("hive.exec.orc.default.block.padding",
- true),
- // Define the default compression codec for ORC file
- HIVE_ORC_DEFAULT_COMPRESS("hive.exec.orc.default.compress", "ZLIB"),
- // Define the default encoding strategy to use
- HIVE_ORC_ENCODING_STRATEGY("hive.exec.orc.encoding.strategy", "SPEED",
- new StringsValidator("SPEED", "COMPRESSION")),
- HIVE_ORC_INCLUDE_FILE_FOOTER_IN_SPLITS("hive.orc.splits.include.file.footer", false),
- HIVE_ORC_CACHE_STRIPE_DETAILS_SIZE("hive.orc.cache.stripe.details.size", 10000),
- HIVE_ORC_COMPUTE_SPLITS_NUM_THREADS("hive.orc.compute.splits.num.threads", 10),
- HIVE_ORC_SKIP_CORRUPT_DATA("hive.exec.orc.skip.corrupt.data", false),
- HIVE_ORC_ZEROCOPY("hive.exec.orc.zerocopy", false),
- // Whether extended literal set is allowed for LazySimpleSerde.
- HIVE_LAZYSIMPLE_EXTENDED_BOOLEAN_LITERAL("hive.lazysimple.extended_boolean_literal", false),
- HIVESKEWJOIN("hive.optimize.skewjoin", false),
- HIVECONVERTJOIN("hive.auto.convert.join", true),
- HIVECONVERTJOINNOCONDITIONALTASK("hive.auto.convert.join.noconditionaltask", true),
- HIVECONVERTJOINNOCONDITIONALTASKTHRESHOLD("hive.auto.convert.join.noconditionaltask.size",
- 10000000L),
- HIVECONVERTJOINUSENONSTAGED("hive.auto.convert.join.use.nonstaged", false),
- HIVESKEWJOINKEY("hive.skewjoin.key", 100000),
- HIVESKEWJOINMAPJOINNUMMAPTASK("hive.skewjoin.mapjoin.map.tasks", 10000),
- HIVESKEWJOINMAPJOINMINSPLIT("hive.skewjoin.mapjoin.min.split", 33554432L), //32M
- HIVESENDHEARTBEAT("hive.heartbeat.interval", 1000),
- HIVELIMITMAXROWSIZE("hive.limit.row.max.size", 100000L),
- HIVELIMITOPTLIMITFILE("hive.limit.optimize.limit.file", 10),
- HIVELIMITOPTENABLE("hive.limit.optimize.enable", false),
- HIVELIMITOPTMAXFETCH("hive.limit.optimize.fetch.max", 50000),
- HIVELIMITPUSHDOWNMEMORYUSAGE("hive.limit.pushdown.memory.usage", -1f),
- HIVELIMITTABLESCANPARTITION("hive.limit.query.max.table.partition", -1),
- HIVEHASHTABLETHRESHOLD("hive.hashtable.initialCapacity", 100000),
- HIVEHASHTABLELOADFACTOR("hive.hashtable.loadfactor", (float) 0.75),
- HIVEHASHTABLEFOLLOWBYGBYMAXMEMORYUSAGE("hive.mapjoin.followby.gby.localtask.max.memory.usage", (float) 0.55),
- HIVEHASHTABLEMAXMEMORYUSAGE("hive.mapjoin.localtask.max.memory.usage", (float) 0.90),
- HIVEHASHTABLESCALE("hive.mapjoin.check.memory.rows", (long)100000),
- HIVEDEBUGLOCALTASK("hive.debug.localtask",false),
- HIVEINPUTFORMAT("hive.input.format", "org.apache.hadoop.hive.ql.io.CombineHiveInputFormat"),
- HIVETEZINPUTFORMAT("hive.tez.input.format", "org.apache.hadoop.hive.ql.io.HiveInputFormat"),
- HIVETEZCONTAINERSIZE("hive.tez.container.size", -1),
- HIVETEZJAVAOPTS("hive.tez.java.opts", null),
- HIVETEZLOGLEVEL("hive.tez.log.level", "INFO"),
- HIVEENFORCEBUCKETING("hive.enforce.bucketing", false),
- HIVEENFORCESORTING("hive.enforce.sorting", false),
- HIVEOPTIMIZEBUCKETINGSORTING("hive.optimize.bucketingsorting", true),
- HIVEPARTITIONER("hive.mapred.partitioner", "org.apache.hadoop.hive.ql.io.DefaultHivePartitioner"),
- HIVEENFORCESORTMERGEBUCKETMAPJOIN("hive.enforce.sortmergebucketmapjoin", false),
- HIVEENFORCEBUCKETMAPJOIN("hive.enforce.bucketmapjoin", false),
- HIVE_AUTO_SORTMERGE_JOIN("hive.auto.convert.sortmerge.join", false),
- HIVE_AUTO_SORTMERGE_JOIN_BIGTABLE_SELECTOR(
- "hive.auto.convert.sortmerge.join.bigtable.selection.policy",
- "org.apache.hadoop.hive.ql.optimizer.AvgPartitionSizeBasedBigTableSelectorForAutoSMJ"),
- HIVE_AUTO_SORTMERGE_JOIN_TOMAPJOIN(
- "hive.auto.convert.sortmerge.join.to.mapjoin", false),
- HIVESCRIPTOPERATORTRUST("hive.exec.script.trust", false),
- HIVEROWOFFSET("hive.exec.rowoffset", false),
- HIVE_COMBINE_INPUT_FORMAT_SUPPORTS_SPLITTABLE("hive.hadoop.supports.splittable.combineinputformat", false),
- // Optimizer
- HIVEOPTINDEXFILTER("hive.optimize.index.filter", false), // automatically use indexes
- HIVEINDEXAUTOUPDATE("hive.optimize.index.autoupdate", false), //automatically update stale indexes
- HIVEOPTPPD("hive.optimize.ppd", true), // predicate pushdown
- HIVEPPDRECOGNIZETRANSITIVITY("hive.ppd.recognizetransivity", true), // predicate pushdown
- HIVEPPDREMOVEDUPLICATEFILTERS("hive.ppd.remove.duplicatefilters", true),
- HIVEMETADATAONLYQUERIES("hive.optimize.metadataonly", true),
- // push predicates down to storage handlers
- HIVEOPTPPD_STORAGE("hive.optimize.ppd.storage", true),
- HIVEOPTGROUPBY("hive.optimize.groupby", true), // optimize group by
- HIVEOPTBUCKETMAPJOIN("hive.optimize.bucketmapjoin", false), // optimize bucket map join
- HIVEOPTSORTMERGEBUCKETMAPJOIN("hive.optimize.bucketmapjoin.sortedmerge", false), // try to use sorted merge bucket map join
- HIVEOPTREDUCEDEDUPLICATION("hive.optimize.reducededuplication", true),
- HIVEOPTREDUCEDEDUPLICATIONMINREDUCER("hive.optimize.reducededuplication.min.reducer", 4),
- // when enabled dynamic partitioning column will be globally sorted.
- // this way we can keep only one record writer open for each partition value
- // in the reducer thereby reducing the memory pressure on reducers
- HIVEOPTSORTDYNAMICPARTITION("hive.optimize.sort.dynamic.partition", true),
- HIVESAMPLINGFORORDERBY("hive.optimize.sampling.orderby", false),
- HIVESAMPLINGNUMBERFORORDERBY("hive.optimize.sampling.orderby.number", 1000),
- HIVESAMPLINGPERCENTFORORDERBY("hive.optimize.sampling.orderby.percent", 0.1f),
- // whether to optimize union followed by select followed by filesink
- // It creates sub-directories in the final output, so should not be turned on in systems
- // where MAPREDUCE-1501 is not present
- HIVE_OPTIMIZE_UNION_REMOVE("hive.optimize.union.remove", false),
- HIVEOPTCORRELATION("hive.optimize.correlation", false), // exploit intra-query correlations
- // whether hadoop map-reduce supports sub-directories. It was added by MAPREDUCE-1501.
- // Some optimizations can only be performed if the version of hadoop being used supports
- // sub-directories
- HIVE_HADOOP_SUPPORTS_SUBDIRECTORIES("hive.mapred.supports.subdirectories", false),
- // optimize skewed join by changing the query plan at compile time
- HIVE_OPTIMIZE_SKEWJOIN_COMPILETIME("hive.optimize.skewjoin.compiletime", false),
- // Indexes
- HIVEOPTINDEXFILTER_COMPACT_MINSIZE("hive.optimize.index.filter.compact.minsize", (long) 5 * 1024 * 1024 * 1024), // 5G
- HIVEOPTINDEXFILTER_COMPACT_MAXSIZE("hive.optimize.index.filter.compact.maxsize", (long) -1), // infinity
- HIVE_INDEX_COMPACT_QUERY_MAX_ENTRIES("hive.index.compact.query.max.entries", (long) 10000000), // 10M
- HIVE_INDEX_COMPACT_QUERY_MAX_SIZE("hive.index.compact.query.max.size", (long) 10 * 1024 * 1024 * 1024), // 10G
- HIVE_INDEX_COMPACT_BINARY_SEARCH("hive.index.compact.binary.search", true),
- // Statistics
- HIVESTATSAUTOGATHER("hive.stats.autogather", true),
- HIVESTATSDBCLASS("hive.stats.dbclass", "fs",
- new PatternValidator("jdbc(:.*)", "hbase", "counter", "custom", "fs")), // StatsSetupConst.StatDB
- HIVESTATSJDBCDRIVER("hive.stats.jdbcdriver",
- "org.apache.derby.jdbc.EmbeddedDriver"), // JDBC driver specific to the dbclass
- HIVESTATSDBCONNECTIONSTRING("hive.stats.dbconnectionstring",
- "jdbc:derby:;databaseName=TempStatsStore;create=true"), // automatically create database
- HIVE_STATS_DEFAULT_PUBLISHER("hive.stats.default.publisher",
- ""), // default stats publisher if none of JDBC/HBase is specified
- HIVE_STATS_DEFAULT_AGGREGATOR("hive.stats.default.aggregator",
- ""), // default stats aggregator if none of JDBC/HBase is specified
- HIVE_STATS_JDBC_TIMEOUT("hive.stats.jdbc.timeout",
- 30), // default timeout in sec for JDBC connection & SQL statements
- HIVE_STATS_ATOMIC("hive.stats.atomic",
- false), // whether to update metastore stats only if all stats are available
- HIVE_STATS_RETRIES_MAX("hive.stats.retries.max",
- 0), // maximum # of retries to insert/select/delete the stats DB
- HIVE_STATS_RETRIES_WAIT("hive.stats.retries.wait",
- 3000), // # milliseconds to wait before the next retry
- HIVE_STATS_COLLECT_RAWDATASIZE("hive.stats.collect.rawdatasize", true),
- // should the raw data size be collected when analyzing tables
- CLIENT_STATS_COUNTERS("hive.client.stats.counters", ""),
- //Subset of counters that should be of interest for hive.client.stats.publishers (when one wants to limit their publishing). Non-display names should be used".
- HIVE_STATS_RELIABLE("hive.stats.reliable", false),
- // number of threads used by partialscan/noscan stats gathering for partitioned tables.
- // This is applicable only for file formats that implement StatsProvidingRecordReader
- // interface (like ORC)
- HIVE_STATS_GATHER_NUM_THREADS("hive.stats.gather.num.threads", 10),
- // Collect table access keys information for operators that can benefit from bucketing
- HIVE_STATS_COLLECT_TABLEKEYS("hive.stats.collect.tablekeys", false),
- // Collect column access information
- HIVE_STATS_COLLECT_SCANCOLS("hive.stats.collect.scancols", false),
- // standard error allowed for ndv estimates. A lower value indicates higher accuracy and a
- // higher compute cost.
- HIVE_STATS_NDV_ERROR("hive.stats.ndv.error", (float)20.0),
- HIVE_STATS_KEY_PREFIX_MAX_LENGTH("hive.stats.key.prefix.max.length", 150),
- HIVE_STATS_KEY_PREFIX_RESERVE_LENGTH("hive.stats.key.prefix.reserve.length", 24),
- HIVE_STATS_KEY_PREFIX("hive.stats.key.prefix", ""), // internal usage only
- // if length of variable length data type cannot be determined this length will be used.
- HIVE_STATS_MAX_VARIABLE_LENGTH("hive.stats.max.variable.length", 100),
- // if number of elements in list cannot be determined, this value will be used
- HIVE_STATS_LIST_NUM_ENTRIES("hive.stats.list.num.entries", 10),
- // if number of elements in map cannot be determined, this value will be used
- HIVE_STATS_MAP_NUM_ENTRIES("hive.stats.map.num.entries", 10),
- // to accurately compute statistics for GROUPBY map side parallelism needs to be known
- HIVE_STATS_MAP_SIDE_PARALLELISM("hive.stats.map.parallelism", 1),
- // statistics annotation fetches stats for each partition, which can be expensive. turning
- // this off will result in basic sizes being fetched from namenode instead
- HIVE_STATS_FETCH_PARTITION_STATS("hive.stats.fetch.partition.stats", true),
- // statistics annotation fetches column statistics for all required columns which can
- // be very expensive sometimes
- HIVE_STATS_FETCH_COLUMN_STATS("hive.stats.fetch.column.stats", false),
- // in the absence of column statistics, the estimated number of rows/data size that will
- // be emitted from join operator will depend on this factor
- HIVE_STATS_JOIN_FACTOR("hive.stats.join.factor", (float) 1.1),
- // in the absence of uncompressed/raw data size, total file size will be used for statistics
- // annotation. But the file may be compressed, encoded and serialized which may be lesser in size
- // than the actual uncompressed/raw data size. This factor will be multiplied to file size to estimate
- // the raw data size.
- HIVE_STATS_DESERIALIZATION_FACTOR("hive.stats.deserialization.factor", (float) 1.0),
- // Concurrency
- HIVE_SUPPORT_CONCURRENCY("hive.support.concurrency", false),
- HIVE_LOCK_MANAGER("hive.lock.manager", "org.apache.hadoop.hive.ql.lockmgr.zookeeper.ZooKeeperHiveLockManager"),
- HIVE_LOCK_NUMRETRIES("hive.lock.numretries", 100),
- HIVE_UNLOCK_NUMRETRIES("hive.unlock.numretries", 10),
- HIVE_LOCK_SLEEP_BETWEEN_RETRIES("hive.lock.sleep.between.retries", 60),
- HIVE_LOCK_MAPRED_ONLY("hive.lock.mapred.only.operation", false),
- HIVE_ZOOKEEPER_QUORUM("hive.zookeeper.quorum", ""),
- HIVE_ZOOKEEPER_CLIENT_PORT("hive.zookeeper.client.port", "2181"),
- HIVE_ZOOKEEPER_SESSION_TIMEOUT("hive.zookeeper.session.timeout", 600*1000),
- HIVE_ZOOKEEPER_NAMESPACE("hive.zookeeper.namespace", "hive_zookeeper_namespace"),
- HIVE_ZOOKEEPER_CLEAN_EXTRA_NODES("hive.zookeeper.clean.extra.nodes", false),
- // Transactions
- HIVE_TXN_MANAGER("hive.txn.manager",
- "org.apache.hadoop.hive.ql.lockmgr.DummyTxnManager"),
- // time after which transactions are declared aborted if the client has
- // not sent a heartbeat, in seconds.
- HIVE_TXN_TIMEOUT("hive.txn.timeout", 300),
- // Maximum number of transactions that can be fetched in one call to
- // open_txns().
- // Increasing this will decrease the number of delta files created when
- // streaming data into Hive. But it will also increase the number of
- // open transactions at any given time, possibly impacting read
- // performance.
- HIVE_TXN_MAX_OPEN_BATCH("hive.txn.max.open.batch", 1000),
- // Whether to run the compactor's initiator thread in this metastore instance or not.
- HIVE_COMPACTOR_INITIATOR_ON("hive.compactor.initiator.on", false),
- // Number of compactor worker threads to run on this metastore instance.
- HIVE_COMPACTOR_WORKER_THREADS("hive.compactor.worker.threads", 0),
- // Time, in seconds, before a given compaction in working state is declared a failure and
- // returned to the initiated state.
- HIVE_COMPACTOR_WORKER_TIMEOUT("hive.compactor.worker.timeout", 86400L),
- // Time in seconds between checks to see if any partitions need compacted. This should be
- // kept high because each check for compaction requires many calls against the NameNode.
- HIVE_COMPACTOR_CHECK_INTERVAL("hive.compactor.check.interval", 300L),
- // Number of delta files that must exist in a directory before the compactor will attempt a
- // minor compaction.
- HIVE_COMPACTOR_DELTA_NUM_THRESHOLD("hive.compactor.delta.num.threshold", 10),
- // Percentage (by size) of base that deltas can be before major compaction is initiated.
- HIVE_COMPACTOR_DELTA_PCT_THRESHOLD("hive.compactor.delta.pct.threshold", 0.1f),
- // Number of aborted transactions involving a particular table or partition before major
- // compaction is initiated.
- HIVE_COMPACTOR_ABORTEDTXN_THRESHOLD("hive.compactor.abortedtxn.threshold", 1000),
- // For HBase storage handler
- HIVE_HBASE_WAL_ENABLED("hive.hbase.wal.enabled", true),
- HIVE_HBASE_GENERATE_HFILES("hive.hbase.generatehfiles", false),
- // For har files
- HIVEARCHIVEENABLED("hive.archive.enabled", false),
- //Enable/Disable gbToIdx rewrite rule
- HIVEOPTGBYUSINGINDEX("hive.optimize.index.groupby", false),
- HIVEOUTERJOINSUPPORTSFILTERS("hive.outerjoin.supports.filters", true),
- // 'minimal', 'more' (and 'all' later)
- HIVEFETCHTASKCONVERSION("hive.fetch.task.conversion", "minimal",
- new StringsValidator("minimal", "more")),
- HIVEFETCHTASKCONVERSIONTHRESHOLD("hive.fetch.task.conversion.threshold", -1l),
- HIVEFETCHTASKAGGR("hive.fetch.task.aggr", false),
- HIVEOPTIMIZEMETADATAQUERIES("hive.compute.query.using.stats", false),
- // Serde for FetchTask
- HIVEFETCHOUTPUTSERDE("hive.fetch.output.serde", "org.apache.hadoop.hive.serde2.DelimitedJSONSerDe"),
- HIVEEXPREVALUATIONCACHE("hive.cache.expr.evaluation", true),
- // Hive Variables
- HIVEVARIABLESUBSTITUTE("hive.variable.substitute", true),
- HIVEVARIABLESUBSTITUTEDEPTH("hive.variable.substitute.depth", 40),
- HIVECONFVALIDATION("hive.conf.validation", true),
- SEMANTIC_ANALYZER_HOOK("hive.semantic.analyzer.hook", ""),
- HIVE_AUTHORIZATION_ENABLED("hive.security.authorization.enabled", false),
- HIVE_AUTHORIZATION_MANAGER("hive.security.authorization.manager",
- "org.apache.hadoop.hive.ql.security.authorization.DefaultHiveAuthorizationProvider"),
- HIVE_AUTHENTICATOR_MANAGER("hive.security.authenticator.manager",
- "org.apache.hadoop.hive.ql.security.HadoopDefaultAuthenticator"),
- HIVE_METASTORE_AUTHORIZATION_MANAGER("hive.security.metastore.authorization.manager",
- "org.apache.hadoop.hive.ql.security.authorization."
- + "DefaultHiveMetastoreAuthorizationProvider"),
- HIVE_METASTORE_AUTHENTICATOR_MANAGER("hive.security.metastore.authenticator.manager",
- "org.apache.hadoop.hive.ql.security.HadoopDefaultMetastoreAuthenticator"),
- HIVE_AUTHORIZATION_TABLE_USER_GRANTS("hive.security.authorization.createtable.user.grants", ""),
- HIVE_AUTHORIZATION_TABLE_GROUP_GRANTS("hive.security.authorization.createtable.group.grants",
- ""),
- HIVE_AUTHORIZATION_TABLE_ROLE_GRANTS("hive.security.authorization.createtable.role.grants", ""),
- HIVE_AUTHORIZATION_TABLE_OWNER_GRANTS("hive.security.authorization.createtable.owner.grants",
- ""),
- // if this is not set default value is added by sql standard authorizer.
- // Default value can't be set in this constructor as it would refer names in other ConfVars
- // whose constructor would not have been called
- HIVE_AUTHORIZATION_SQL_STD_AUTH_CONFIG_WHITELIST("hive.security.authorization.sqlstd.confwhitelist", ""),
- // Print column names in output
- HIVE_CLI_PRINT_HEADER("hive.cli.print.header", false),
- HIVE_ERROR_ON_EMPTY_PARTITION("hive.error.on.empty.partition", false),
- HIVE_INDEX_COMPACT_FILE("hive.index.compact.file", ""), // internal variable
- HIVE_INDEX_BLOCKFILTER_FILE("hive.index.blockfilter.file", ""), // internal variable
- HIVE_INDEX_IGNORE_HDFS_LOC("hive.index.compact.file.ignore.hdfs", false),
- HIVE_EXIM_URI_SCHEME_WL("hive.exim.uri.scheme.whitelist", "hdfs,pfile"),
- // temporary variable for testing. This is added just to turn off this feature in case of a bug in
- // deployment. It has not been documented in hive-default.xml intentionally, this should be removed
- // once the feature is stable
- HIVE_MAPPER_CANNOT_SPAN_MULTIPLE_PARTITIONS("hive.mapper.cannot.span.multiple.partitions", false),
- HIVE_REWORK_MAPREDWORK("hive.rework.mapredwork", false),
- HIVE_CONCATENATE_CHECK_INDEX ("hive.exec.concatenate.check.index", true),
- HIVE_IO_EXCEPTION_HANDLERS("hive.io.exception.handlers", ""),
- // logging configuration
- HIVE_LOG4J_FILE("hive.log4j.file", ""),
- HIVE_EXEC_LOG4J_FILE("hive.exec.log4j.file", ""),
- // prefix used to auto generated column aliases (this should be started with '_')
- HIVE_AUTOGEN_COLUMNALIAS_PREFIX_LABEL("hive.autogen.columnalias.prefix.label", "_c"),
- HIVE_AUTOGEN_COLUMNALIAS_PREFIX_INCLUDEFUNCNAME(
- "hive.autogen.columnalias.prefix.includefuncname", false),
- // The class responsible for logging client side performance metrics
- // Must be a subclass of org.apache.hadoop.hive.ql.log.PerfLogger
- HIVE_PERF_LOGGER("hive.exec.perf.logger", "org.apache.hadoop.hive.ql.log.PerfLogger"),
- // Whether to delete the scratchdir while startup
- HIVE_START_CLEANUP_SCRATCHDIR("hive.start.cleanup.scratchdir", false),
- HIVE_INSERT_INTO_MULTILEVEL_DIRS("hive.insert.into.multilevel.dirs", false),
- HIVE_WAREHOUSE_SUBDIR_INHERIT_PERMS("hive.warehouse.subdir.inherit.perms", false),
- HIVE_WAREHOUSE_DATA_SKIPTRASH("hive.warehouse.data.skipTrash", false),
- // whether insert into external tables is allowed
- HIVE_INSERT_INTO_EXTERNAL_TABLES("hive.insert.into.external.tables", true),
- // A comma separated list of hooks which implement HiveDriverRunHook and will be run at the
- // beginning and end of Dr…
Large files files are truncated, but you can click here to view the full file