500 lines
29 KiB
JSON
500 lines
29 KiB
JSON
[
|
|
{
|
|
"desc": "The health test thresholds for monitoring of free space on the filesystem that contains this role's log directory. Specified as a percentage of the capacity on that filesystem. This setting is not used if a Log Directory Free Space Monitoring Absolute Thresholds setting is configured.",
|
|
"display_name": "Log Directory Free Space Monitoring Percentage Thresholds",
|
|
"name": "log_directory_free_space_percentage_thresholds",
|
|
"value": "{\"critical\":\"never\",\"warning\":\"never\"}"
|
|
},
|
|
{
|
|
"desc": "The check interval for session/operation timeout, in milliseconds, which can be disabled by setting to zero or a negative value. ",
|
|
"display_name": "Session Check Interval",
|
|
"name": "hiveserver2_session_check_interval",
|
|
"value": "0"
|
|
},
|
|
{
|
|
"desc": "Number of cores per Spark executor.",
|
|
"display_name": "Spark Executor Cores",
|
|
"name": "hiveserver2_spark_executor_cores",
|
|
"value": "1"
|
|
},
|
|
{
|
|
"desc": "Ratio between 0.0 and 1.0 of entries in the vectorized group-by aggregation hash that is flushed when the memory threshold is exceeded.",
|
|
"display_name": "Vectorized GroupBy Flush Ratio",
|
|
"name": "hiveserver2_vectorized_groupby_flush_ratio",
|
|
"value": "0.1"
|
|
},
|
|
{
|
|
"desc": "Operation will be closed when not accessed for this duration of time, in milliseconds; disable by setting to zero. For a positive value, checked for operations in terminal state only (FINISHED, CANCELED, CLOSED, ERROR). For a negative value, checked for all of the operations regardless of state.",
|
|
"display_name": "Idle Operation Timeout",
|
|
"name": "hiveserver2_idle_operation_timeout",
|
|
"value": "0"
|
|
},
|
|
{
|
|
"desc": "Whether or not periodic stacks collection is enabled.",
|
|
"display_name": "Stacks Collection Enabled",
|
|
"name": "stacks_collection_enabled",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "Address of the load balancer used for HiveServer2 roles, specified in host:port format. If port is not specified, the port used by HiveServer2 is used. <b>Note:</b> Changing this property regenerates Kerberos keytabs for all HiveServer2 roles.",
|
|
"display_name": "HiveServer2 Load Balancer",
|
|
"name": "hiverserver2_load_balancer",
|
|
"value": null
|
|
},
|
|
{
|
|
"desc": "Initial number of executors used by the application at any given time. This is required if the dynamic executor allocation feature is enabled.",
|
|
"display_name": "Initial Number of Executors",
|
|
"name": "hiveserver2_spark_dynamic_allocation_initial_executors",
|
|
"value": "1"
|
|
},
|
|
{
|
|
"desc": "The health test thresholds for monitoring of free space on the filesystem that contains this role's Directory in HDFS where Hive writes intermediate data between MapReduce jobs. If not specified, Hive uses a default location..",
|
|
"display_name": "Hive HDFS Scratch Directory Free Space Monitoring Absolute Thresholds",
|
|
"name": "hiveserver2_exec_scratch_directory_free_space_absolute_thresholds",
|
|
"value": "{\"critical\":\"5.36870912E9\",\"warning\":\"1.073741824E10\"}"
|
|
},
|
|
{
|
|
"desc": "HiveServer2 will impersonate the beeline client user when talking to other services such as Mapreduce and Hdfs.",
|
|
"display_name": "HiveServer2 Enable Impersonation",
|
|
"name": "hiveserver2_enable_impersonation",
|
|
"value": "true"
|
|
},
|
|
{
|
|
"desc": "The health test thresholds for monitoring of free space on the filesystem that contains this role's heap dump directory. Specified as a percentage of the capacity on that filesystem. This setting is not used if a Heap Dump Directory Free Space Monitoring Absolute Thresholds setting is configured.",
|
|
"display_name": "Heap Dump Directory Free Space Monitoring Percentage Thresholds",
|
|
"name": "heap_dump_directory_free_space_percentage_thresholds",
|
|
"value": "{\"critical\":\"never\",\"warning\":\"never\"}"
|
|
},
|
|
{
|
|
"desc": "Enable optimization that checks if a query can be answered using statistics. If so, answers the query using only statistics stored in metastore.",
|
|
"display_name": "Enable Stats Optimization",
|
|
"name": "hiveserver2_compute_query_using_stats",
|
|
"value": "true"
|
|
},
|
|
{
|
|
"desc": "Lower bound on the number of executors used by the application at any given time. This is used by dynamic executor allocation",
|
|
"display_name": "Lower Bound on Number of Executors",
|
|
"name": "hiveserver2_spark_dynamic_allocation_min_executors",
|
|
"value": "1"
|
|
},
|
|
{
|
|
"desc": "When enabled, Spark will add and remove executors dynamically to Hive jobs. This is done based on the workload.",
|
|
"display_name": "Enable Dynamic Executor Allocation",
|
|
"name": "hiveserver2_spark_dynamic_allocation_enabled",
|
|
"value": "true"
|
|
},
|
|
{
|
|
"desc": "The health test thresholds on the swap memory usage of the process.",
|
|
"display_name": "Process Swap Memory Thresholds",
|
|
"name": "process_swap_memory_thresholds",
|
|
"value": "{\"critical\":\"never\",\"warning\":\"any\"}"
|
|
},
|
|
{
|
|
"desc": "The method used to collect stacks. The jstack option involves periodically running the jstack command against the role's daemon process. The servlet method is available for those roles that have an HTTP server endpoint exposing the current stacks traces of all threads. When the servlet method is selected, that HTTP endpoint is periodically scraped.",
|
|
"display_name": "Stacks Collection Method",
|
|
"name": "stacks_collection_method",
|
|
"value": "jstack"
|
|
},
|
|
{
|
|
"desc": "Port on which HiveServer2 will listen for connections.",
|
|
"display_name": "HiveServer2 Port",
|
|
"name": "hs2_thrift_address_port",
|
|
"value": "10000"
|
|
},
|
|
{
|
|
"desc": "Enable optimization that converts common join into MapJoin based on input file size.",
|
|
"display_name": "Enable MapJoin Optimization",
|
|
"name": "hiveserver2_enable_mapjoin",
|
|
"value": "true"
|
|
},
|
|
{
|
|
"desc": "The desired file size after merging. This should be larger than hive.merge.smallfiles.avgsize.",
|
|
"display_name": "Desired File Size After Merging",
|
|
"name": "hiveserver2_merge_size_per_task",
|
|
"value": "268435456"
|
|
},
|
|
{
|
|
"desc": "When set, this role's process is automatically (and transparently) restarted in the event of an unexpected failure.",
|
|
"display_name": "Automatically Restart Process",
|
|
"name": "process_auto_restart",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "<p>The configured triggers for this role. This is a JSON formatted list of triggers. These triggers are evaluated as part as the health system. Every trigger expression is parsed, and if the trigger condition is met, the list of actions provided in the trigger expression is executed.</p><p>Each trigger has all of the following fields:</p><ul><li><code>triggerName</code> <strong>(mandatory)</strong> - The name of the trigger. This value must be unique for the specific role. </li><li><code>triggerExpression</code> <strong>(mandatory)</strong> - A tsquery expression representing the trigger. </li><li><code>streamThreshold</code> <strong>(optional)</strong> - The maximum number of streams that can satisfy a condition of a trigger before the condition fires. By default set to 0, and any stream returned causes the condition to fire. </li><li><code>enabled</code> <strong> (optional)</strong> - By default set to 'true'. If set to 'false', the trigger will not be evaluated.</li><li><code>expressionEditorConfig</code> <strong> (optional)</strong> - Metadata for the trigger editor. If present, the trigger should only be edited from the Edit Trigger page; editing the trigger here may lead to inconsistencies.</li></ul></p><p>For example, the following JSON formatted trigger configured for a DataNode fires if the DataNode has more than 1500 file-descriptors opened:</p><p><pre>[{\"triggerName\": \"sample-trigger\",\n \"triggerExpression\": \"IF (SELECT fd_open WHERE roleName=$ROLENAME and last(fd_open) > 1500) DO health:bad\",\n \"streamThreshold\": 0, \"enabled\": \"true\"}]</pre></p><p>See the trigger rules documentation for more details on how to write triggers using tsquery.</p><p>The JSON format is evolving and may change in the future and, as a result, backward compatibility is not guaranteed between releases at this time.</p>",
|
|
"display_name": "Role Triggers",
|
|
"name": "role_triggers",
|
|
"value": "[]"
|
|
},
|
|
{
|
|
"desc": "Merge small files at the end of a Spark job. When enabled, a map-only job is created to merge the files in the destination table/partitions.",
|
|
"display_name": "Enable Merging Small Files - Spark Job",
|
|
"name": "hiveserver2_merge_sparkfiles",
|
|
"value": "true"
|
|
},
|
|
{
|
|
"desc": "When the average output file size of a job is less than the value of this property, Hive will start an additional map-only job to merge the output files into bigger files. This is only done for map-only jobs if hive.merge.mapfiles is true, for map-reduce jobs if hive.merge.mapredfiles is true, and for Spark jobs if hive.merge.sparkfiles is true.",
|
|
"display_name": "Small File Average Size Merge Threshold",
|
|
"name": "hiveserver2_merge_smallfiles_avgsize",
|
|
"value": "16777216"
|
|
},
|
|
{
|
|
"desc": "The health test thresholds for monitoring of free space on the filesystem that contains this role's Local Directory where Hive stores jars and data when performing a MapJoin optimization. If not specified, Hive uses a default location..",
|
|
"display_name": "Hive Local Scratch Directory Free Space Monitoring Absolute Thresholds",
|
|
"name": "hiveserver2_exec_local_scratch_directory_free_space_absolute_thresholds",
|
|
"value": "{\"critical\":\"5.36870912E9\",\"warning\":\"1.073741824E10\"}"
|
|
},
|
|
{
|
|
"desc": "For advanced use only, a string to be inserted into <strong>hive-site.xml</strong> for this role only.",
|
|
"display_name": "HiveServer2 Advanced Configuration Snippet (Safety Valve) for hive-site.xml",
|
|
"name": "hive_hs2_config_safety_valve",
|
|
"value": null
|
|
},
|
|
{
|
|
"desc": "Soft memory limit to assign to this role, enforced by the Linux kernel. When the limit is reached, the kernel will reclaim pages charged to the process if and only if the host is facing memory pressure. If reclaiming fails, the kernel may kill the process. Both anonymous as well as page cache pages contribute to the limit. Use a value of -1 B to specify no limit. By default processes not managed by Cloudera Manager will have no limit.",
|
|
"display_name": "Cgroup Memory Soft Limit",
|
|
"name": "rm_memory_soft_limit",
|
|
"value": "-1"
|
|
},
|
|
{
|
|
"desc": "Local directory where Hive stores jars downloaded for remote file systems (HDFS). If not specified, Hive uses a default location.",
|
|
"display_name": "Hive Downloaded Resources Directory",
|
|
"name": "hiveserver2_downloaded_resources_dir",
|
|
"value": null
|
|
},
|
|
{
|
|
"desc": "When set, generates heap dump file when java.lang.OutOfMemoryError is thrown.",
|
|
"display_name": "Dump Heap When Out of Memory",
|
|
"name": "oom_heap_dump_enabled",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "Number of CPU shares to assign to this role. The greater the number of shares, the larger the share of the host's CPUs that will be given to this role when the host experiences CPU contention. Must be between 2 and 262144. Defaults to 1024 for processes not managed by Cloudera Manager.",
|
|
"display_name": "Cgroup CPU Shares",
|
|
"name": "rm_cpu_shares",
|
|
"value": "1024"
|
|
},
|
|
{
|
|
"desc": "The max percentage of heap to be used for hash in ReduceSink operator for Top-K selection. A 0 means the optimization is disabled. Values accepted are between 0 and 1.",
|
|
"display_name": "Maximum ReduceSink Top-K Memory Usage",
|
|
"name": "hiveserver2_limit_pushdown_memory_usage",
|
|
"value": "0.1"
|
|
},
|
|
{
|
|
"desc": "Whether to try sorted merge bucket (SMB) join.",
|
|
"display_name": "Hive Optimize Sorted Merge Bucket Join",
|
|
"name": "hiveserver2_optimize_bucketmapjoin_sortedmerge",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "When computing the overall HiveServer2 health, consider the host's health.",
|
|
"display_name": "HiveServer2 Host Health Test",
|
|
"name": "hiveserver2_host_health_enabled",
|
|
"value": "true"
|
|
},
|
|
{
|
|
"desc": "Maximum size of each Spark executor's Java heap memory when Hive is running on Spark.",
|
|
"display_name": "Spark Executor Maximum Java Heap Size",
|
|
"name": "hiveserver2_spark_executor_memory",
|
|
"value": "268435456"
|
|
},
|
|
{
|
|
"desc": "Maximum size of each Spark driver's Java heap memory when Hive is running on Spark.",
|
|
"display_name": "Spark Driver Maximum Java Heap Size",
|
|
"name": "hiveserver2_spark_driver_memory",
|
|
"value": "268435456"
|
|
},
|
|
{
|
|
"desc": "If Hive auto convert join is on, and the sum of the size for n-1 of the tables/partitions for a n-way join is smaller than the specified size, the join is directly converted to a MapJoin (there is no conditional task).",
|
|
"display_name": "Hive Auto Convert Join Noconditional Size",
|
|
"name": "hiveserver2_auto_convert_join_noconditionaltask_size",
|
|
"value": "20971520"
|
|
},
|
|
{
|
|
"desc": "The health test thresholds for monitoring of free space on the filesystem that contains this role's Local Directory where Hive stores jars and data when performing a MapJoin optimization. If not specified, Hive uses a default location.. Specified as a percentage of the capacity on that filesystem. This setting is not used if a Local Directory where Hive stores jars and data when performing a MapJoin optimization. If not specified, Hive uses a default location. Free Space Monitoring Absolute Thresholds setting is configured.",
|
|
"display_name": "Hive Local Scratch Directory Free Space Monitoring Percentage Thresholds",
|
|
"name": "hiveserver2_exec_local_scratch_directory_free_space_percentage_thresholds",
|
|
"value": "{\"critical\":\"never\",\"warning\":\"never\"}"
|
|
},
|
|
{
|
|
"desc": "The period to review when computing unexpected exits.",
|
|
"display_name": "Unexpected Exits Monitoring Period",
|
|
"name": "unexpected_exits_window",
|
|
"value": "5"
|
|
},
|
|
{
|
|
"desc": "The health test thresholds for monitoring of free space on the filesystem that contains this role's Directory in HDFS where Hive writes intermediate data between MapReduce jobs. If not specified, Hive uses a default location.. Specified as a percentage of the capacity on that filesystem. This setting is not used if a Directory in HDFS where Hive writes intermediate data between MapReduce jobs. If not specified, Hive uses a default location. Free Space Monitoring Absolute Thresholds setting is configured.",
|
|
"display_name": "Hive HDFS Scratch Directory Free Space Monitoring Percentage Thresholds",
|
|
"name": "hiveserver2_exec_scratch_directory_free_space_percentage_thresholds",
|
|
"value": "{\"critical\":\"never\",\"warning\":\"never\"}"
|
|
},
|
|
{
|
|
"desc": "Weight for the read I/O requests issued by this role. The greater the weight, the higher the priority of the requests when the host experiences I/O contention. Must be between 100 and 1000. Defaults to 1000 for processes not managed by Cloudera Manager.",
|
|
"display_name": "Cgroup I/O Weight",
|
|
"name": "rm_io_weight",
|
|
"value": "500"
|
|
},
|
|
{
|
|
"desc": "The amount of stacks data that is retained. After the retention limit is reached, the oldest data is deleted.",
|
|
"display_name": "Stacks Collection Data Retention",
|
|
"name": "stacks_collection_data_retention",
|
|
"value": "104857600"
|
|
},
|
|
{
|
|
"desc": "Hard memory limit to assign to this role, enforced by the Linux kernel. When the limit is reached, the kernel will reclaim pages charged to the process. If reclaiming fails, the kernel may kill the process. Both anonymous as well as page cache pages contribute to the limit. Use a value of -1 B to specify no limit. By default processes not managed by Cloudera Manager will have no limit.",
|
|
"display_name": "Cgroup Memory Hard Limit",
|
|
"name": "rm_memory_hard_limit",
|
|
"value": "-1"
|
|
},
|
|
{
|
|
"desc": "The health test thresholds for monitoring of free space on the filesystem that contains this role's heap dump directory.",
|
|
"display_name": "Heap Dump Directory Free Space Monitoring Absolute Thresholds",
|
|
"name": "heap_dump_directory_free_space_absolute_thresholds",
|
|
"value": "{\"critical\":\"5.36870912E9\",\"warning\":\"1.073741824E10\"}"
|
|
},
|
|
{
|
|
"desc": "For advanced use only, a string to be inserted into <strong>log4j.properties</strong> for this role only.",
|
|
"display_name": "HiveServer2 Logging Advanced Configuration Snippet (Safety Valve)",
|
|
"name": "log4j_safety_valve",
|
|
"value": null
|
|
},
|
|
{
|
|
"desc": "For advanced use only, key-value pairs (one on each line) to be inserted into a role's environment. Applies to configurations of this role except client configuration.",
|
|
"display_name": "HiveServer2 Environment Advanced Configuration Snippet (Safety Valve)",
|
|
"name": "hive_hs2_env_safety_valve",
|
|
"value": null
|
|
},
|
|
{
|
|
"desc": "The health test thresholds for monitoring of free space on the filesystem that contains this role's log directory.",
|
|
"display_name": "Log Directory Free Space Monitoring Absolute Thresholds",
|
|
"name": "log_directory_free_space_absolute_thresholds",
|
|
"value": "{\"critical\":\"5.36870912E9\",\"warning\":\"1.073741824E10\"}"
|
|
},
|
|
{
|
|
"desc": "Directory in HDFS where Hive writes intermediate data between MapReduce jobs. If not specified, Hive uses a default location.",
|
|
"display_name": "Hive HDFS Scratch Directory",
|
|
"name": "hiveserver2_exec_scratchdir",
|
|
"value": null
|
|
},
|
|
{
|
|
"desc": "Some select queries can be converted to a single FETCH task instead of MapReduce task, minimizing latency. A value of none disables all conversion, minimal converts simple queries such as SELECT * and filter on partition columns, and more will convert SELECT queries including FILTERS.",
|
|
"display_name": "Fetch Task Query Conversion",
|
|
"name": "hiveserver2_fetch_task_conversion",
|
|
"value": "minimal"
|
|
},
|
|
{
|
|
"desc": "Remove extra map-reduce jobs if the data is already clustered by the same key, eliminating the need to repartition the dataset again.",
|
|
"display_name": "Enable ReduceDeDuplication Optimization",
|
|
"name": "hiveserver2_optimize_reducededuplication",
|
|
"value": "true"
|
|
},
|
|
{
|
|
"desc": "In vectorized group-by, the number of row entries added to the hash table before re-checking average variable size for memory usage estimation.",
|
|
"display_name": "Vectorized GroupBy Check Interval",
|
|
"name": "hiveserver2_vectorized_groupby_checkinterval",
|
|
"value": "4096"
|
|
},
|
|
{
|
|
"desc": "If configured, overrides the process soft and hard rlimits (also called ulimits) for file descriptors to the configured value.",
|
|
"display_name": "Maximum Process File Descriptors",
|
|
"name": "rlimit_fds",
|
|
"value": null
|
|
},
|
|
{
|
|
"desc": "Session will be closed when not accessed for this duration of time, in milliseconds; disable by setting to zero or a negative value.",
|
|
"display_name": "Idle Session Timeout",
|
|
"name": "hiveserver2_idle_session_timeout",
|
|
"value": "0"
|
|
},
|
|
{
|
|
"desc": "When set, Cloudera Manager will send alerts when the health of this role reaches the threshold specified by the EventServer setting eventserver_health_events_alert_threshold",
|
|
"display_name": "Enable Health Alerts for this Role",
|
|
"name": "enable_alerts",
|
|
"value": "true"
|
|
},
|
|
{
|
|
"desc": "The maximum size, in megabytes, per log file for HiveServer2 logs. Typically used by log4j or logback.",
|
|
"display_name": "HiveServer2 Max Log Size",
|
|
"name": "max_log_size",
|
|
"value": "200"
|
|
},
|
|
{
|
|
"desc": "When set, a SIGKILL signal is sent to the role process when java.lang.OutOfMemoryError is thrown.",
|
|
"display_name": "Kill When Out of Memory",
|
|
"name": "oom_sigkill_enabled",
|
|
"value": "true"
|
|
},
|
|
{
|
|
"desc": "Whether to vectorize the reduce side of query execution.",
|
|
"display_name": "Enable Reduce-Side Vectorization",
|
|
"name": "hiveserver2_vectorized_reduce_enabled",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "Merge small files at the end of a map-reduce job. When enabled, a map-only job is created to merge the files in the destination table/partitions.",
|
|
"display_name": "Enable Merging Small Files - Map-Reduce Job",
|
|
"name": "hiveserver2_merge_mapredfiles",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "The health test thresholds for unexpected exits encountered within a recent period specified by the unexpected_exits_window configuration for the role.",
|
|
"display_name": "Unexpected Exits Thresholds",
|
|
"name": "unexpected_exits_thresholds",
|
|
"value": "{\"critical\":\"any\",\"warning\":\"never\"}"
|
|
},
|
|
{
|
|
"desc": "Minimum number of worker threads in HiveServer2's thread pool",
|
|
"display_name": "Min HiveServer2 Threads",
|
|
"name": "hiveserver2_min_threads",
|
|
"value": "5"
|
|
},
|
|
{
|
|
"desc": "Enabled the Calcite based Cost Based Optimizer for HiveServer2.",
|
|
"display_name": "Enable Cost Based Optimizer for Hive",
|
|
"name": "hiveserver2_enable_cbo",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "Portion of total memory used in map-side partial aggregation. When exceeded, the partially aggregated results will be flushed from the map task to the reducers.",
|
|
"display_name": "Ratio of Memory Usage for Map-Side Aggregation",
|
|
"name": "hiveserver2_map_aggr_hash_memory_ratio",
|
|
"value": "0.5"
|
|
},
|
|
{
|
|
"desc": "Enable map-side partial aggregation, which cause the mapper to generate fewer rows. This reduces the data to be sorted and distributed to reducers.",
|
|
"display_name": "Enable Map-Side Aggregation",
|
|
"name": "hiveserver2_map_aggr",
|
|
"value": "true"
|
|
},
|
|
{
|
|
"desc": "Number of Spark executors assigned to each application. This should not be set when Dynamic Executor Allocation is enabled.",
|
|
"display_name": "Spark Executors Per Application",
|
|
"name": "hiveserver2_spark_executor_instances",
|
|
"value": null
|
|
},
|
|
{
|
|
"desc": "These arguments will be passed as part of the Java command line. Commonly, garbage collection flags or extra debugging flags would be passed here.",
|
|
"display_name": "Java Configuration Options for HiveServer2",
|
|
"name": "hiveserver2_java_opts",
|
|
"value": "-XX:+UseParNewGC -XX:+UseConcMarkSweepGC -XX:-CMSConcurrentMTEnabled -XX:CMSInitiatingOccupancyFraction=70 -XX:+CMSParallelRemarkEnabled"
|
|
},
|
|
{
|
|
"desc": "The minimum log level for HiveServer2 logs",
|
|
"display_name": "HiveServer2 Logging Threshold",
|
|
"name": "log_threshold",
|
|
"value": "INFO"
|
|
},
|
|
{
|
|
"desc": "Local Directory where Hive stores jars and data when performing a MapJoin optimization. If not specified, Hive uses a default location.",
|
|
"display_name": "Hive Local Scratch Directory",
|
|
"name": "hiveserver2_exec_local_scratchdir",
|
|
"value": null
|
|
},
|
|
{
|
|
"desc": "The directory in which stacks logs are placed. If not set, stacks are logged into a <span class='code'>stacks</span> subdirectory of the role's log directory.",
|
|
"display_name": "Stacks Collection Directory",
|
|
"name": "stacks_collection_directory",
|
|
"value": null
|
|
},
|
|
{
|
|
"desc": "When dynamic partition is enabled, reducers keep only one record writer at all times, which lowers the memory pressure on reducers.",
|
|
"display_name": "Enable Sorted Dynamic Partition Optimizer",
|
|
"name": "hiveserver2_optimize_sort_dynamic_partition",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "The maximum number of rolled log files to keep for HiveServer2 logs. Typically used by log4j or logback.",
|
|
"display_name": "HiveServer2 Maximum Log File Backups",
|
|
"name": "max_log_backup_index",
|
|
"value": "10"
|
|
},
|
|
{
|
|
"desc": "Enables the health test that the HiveServer2's process state is consistent with the role configuration",
|
|
"display_name": "HiveServer2 Process Health Test",
|
|
"name": "hiveserver2_scm_health_enabled",
|
|
"value": "true"
|
|
},
|
|
{
|
|
"desc": "Merge small files at the end of a map-only job. When enabled, a map-only job is created to merge the files in the destination table/partitions.",
|
|
"display_name": "Enable Merging Small Files - Map-Only Job",
|
|
"name": "hiveserver2_merge_mapfiles",
|
|
"value": "true"
|
|
},
|
|
{
|
|
"desc": "Maximum size in bytes for the Java Process heap memory. Passed to Java -Xmx.",
|
|
"display_name": "Java Heap Size of HiveServer2 in Bytes",
|
|
"name": "hiveserver2_java_heapsize",
|
|
"value": "268435456"
|
|
},
|
|
{
|
|
"desc": "Above this size, queries will not be converted to fetch tasks.",
|
|
"display_name": "Fetch Task Query Conversion Threshold",
|
|
"name": "hiveserver2_fetch_task_conversion_threshold",
|
|
"value": "268435456"
|
|
},
|
|
{
|
|
"desc": "Path to directory where heap dumps are generated when java.lang.OutOfMemoryError error is thrown. This directory is automatically created if it does not exist. If this directory already exists, role user must have write access to this directory. If this directory is shared among multiple roles, it should have 1777 permissions. The heap dump files are created with 600 permissions and are owned by the role user. The amount of free space in this directory should be greater than the maximum Java Process heap size configured for this role.",
|
|
"display_name": "Heap Dump Directory",
|
|
"name": "oom_heap_dump_dir",
|
|
"value": "/tmp"
|
|
},
|
|
{
|
|
"desc": "Directory where HiveServer2 will place its log files.",
|
|
"display_name": "HiveServer2 Log Directory",
|
|
"name": "hive_log_dir",
|
|
"value": "/var/log/hive"
|
|
},
|
|
{
|
|
"desc": "The frequency with which stacks are collected.",
|
|
"display_name": "Stacks Collection Frequency",
|
|
"name": "stacks_collection_frequency",
|
|
"value": "5.0"
|
|
},
|
|
{
|
|
"desc": "This is the amount of extra off-heap memory that can be requested from YARN, per driver. This, together with spark.driver.memory, is the total memory that YARN can use to create JVM for a driver process.",
|
|
"display_name": "Spark Driver Memory Overhead",
|
|
"name": "hiveserver2_spark_yarn_driver_memory_overhead",
|
|
"value": "26"
|
|
},
|
|
{
|
|
"desc": "When set, Cloudera Manager will send alerts when this entity's configuration changes.",
|
|
"display_name": "Enable Configuration Change Alerts",
|
|
"name": "enable_config_alerts",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "Maximum number of worker threads in HiveServer2's thread pool",
|
|
"display_name": "Max HiveServer2 Threads",
|
|
"name": "hiveserver2_max_threads",
|
|
"value": "100"
|
|
},
|
|
{
|
|
"desc": "The health test thresholds of the number of file descriptors used. Specified as a percentage of file descriptor limit.",
|
|
"display_name": "File Descriptor Monitoring Thresholds",
|
|
"name": "hiveserver2_fd_thresholds",
|
|
"value": "{\"critical\":\"70.0\",\"warning\":\"50.0\"}"
|
|
},
|
|
{
|
|
"desc": "When the number of ReduceSink operators after merging is less than this number, the ReduceDeDuplication optimization will be disabled.",
|
|
"display_name": "Mininum Reducers for ReduceDeDuplication Optimization",
|
|
"name": "hiveserver2_optimize_reducededuplication_min_reducer",
|
|
"value": "4"
|
|
},
|
|
{
|
|
"desc": "This is the amount of extra off-heap memory that can be requested from YARN, per executor process. This, together with spark.executor.memory, is the total memory that YARN can use to create JVM for an executor process.",
|
|
"display_name": "Spark Executor Memory Overhead",
|
|
"name": "hiveserver2_spark_yarn_executor_memory_overhead",
|
|
"value": "26"
|
|
},
|
|
{
|
|
"desc": "Enable optimization that vectorizes query execution by streamlining operations by processing a block of 1024 rows at a time.",
|
|
"display_name": "Enable Vectorization Optimization",
|
|
"name": "hiveserver2_vectorized_enabled",
|
|
"value": "true"
|
|
},
|
|
{
|
|
"desc": "The number of rows with the same key value to be cached in memory per SMB-joined table.",
|
|
"display_name": "Hive SMB Join Cache Rows",
|
|
"name": "hiveserver2_smbjoin_cache_rows",
|
|
"value": "10000"
|
|
}
|
|
] |