| sm_omp_threads | Set the number of OpenMP threads that will be used to service filter & aggregation requests to the specified integer value. |
| kernel_omp_threads | Set the number of kernel OpenMP threads to the specified integer value. |
| concurrent_kernel_execution | Enables concurrent kernel execution if the value is true and disables it if the value is false. The supported values are: |
| subtask_concurrency_limit | Sets the maximum number of simultaneous threads allocated to a given request, on each rank. Note that thread allocation may also be limted by resource group limits and/or system load. |
| chunk_size | Sets the number of records per chunk to be used for all new tables. |
| evict_columns | Attempts to evict columns from memory to the persistent store. Value string is a semicolon separated list of entries, each entry being a table name optionally followed by a comma and a comma separated list of column names to attempt to evict. An empty value string will attempt to evict all tables and columns. |
| execution_mode | Sets the execution_mode for kernel executions to the specified string value. Possible values are host, device, default (engine decides) or an integer value that indicates max chunk size to exec on host |
| external_files_directory | Sets the root directory path where external table data files are accessed from. Path must exist on the head node |
| flush_to_disk | Flushes any changes to any tables to the persistent store. These changes include updates to the vector store, object store, and text search store, Value string is ignored |
| clear_cache | Clears cached results. Useful to allow repeated timing of endpoints. Value string is the name of the table for which to clear the cached results, or an empty string to clear the cached results for all tables. |
| communicator_test | Invoke the communicator test and report timing results. Value string is a semicolon separated list of [key]=[value] expressions. Expressions are: num_transactions=[num] where num is the number of request reply transactions to invoke per test; message_size=[bytes] where bytes is the size in bytes of the messages to send; check_values=[enabled] where if enabled is true the value of the messages received are verified. |
| network_speed | Invoke the network speed test and report timing results. Value string is a semicolon-separated list of [key]=[value] expressions. Valid expressions are: seconds=[time] where time is the time in seconds to run the test; data_size=[bytes] where bytes is the size in bytes of the block to be transferred; threads=[number of threads]; to_ranks=[space-separated list of ranks] where the list of ranks is the ranks that rank 0 will send data to and get data from. If to_ranks is unspecified then all worker ranks are used. |
| request_timeout | Number of minutes after which filtering (e.g.,
Filter
) and aggregating (e.g.,
Aggregate Group By
) queries will timeout. The default value is '20'.The minimum allowed value is 0. The maximum allowed value is 1440. |
| max_get_records_size | The maximum number of records the database will serve for a given data retrieval call. The default value is '20000'.The minimum allowed value is 0. The maximum allowed value is 1000000. |
| max_grbc_batch_size | <DEVELOPER> |
| enable_audit | Enable or disable auditing. |
| audit_headers | Enable or disable auditing of request headers. |
| audit_body | Enable or disable auditing of request bodies. |
| audit_data | Enable or disable auditing of request data. |
| audit_response | Enable or disable auditing of response information. |
| shadow_agg_size | Size of the shadow aggregate chunk cache in bytes. The default value is '10000000'.The minimum allowed value is 0. The maximum allowed value is 2147483647. |
| shadow_filter_size | Size of the shadow filter chunk cache in bytes. The default value is '10000000'.The minimum allowed value is 0. The maximum allowed value is 2147483647. |
| synchronous_compression | compress vector on set_compression (instead of waiting for background thread). The default value is 'false'. |
| enable_overlapped_equi_join | Enable overlapped-equi-join filter. The default value is 'true'. |
| kafka_batch_size | Maximum number of records to be ingested in a single batch. The default value is '1000'.The minimum allowed value is 1. The maximum allowed value is 10000000. |
| kafka_poll_timeout | Maximum time (milliseconds) for each poll to get records from kafka. The default value is '0'.The minimum allowed value is 0. The maximum allowed value is 1000. |
| kafka_wait_time | Maximum time (seconds) to buffer records received from kafka before ingestion. The default value is '30'.The minimum allowed value is 1. The maximum allowed value is 120. |
| egress_parquet_compression | Parquet file compression type The default value is snappy. The supported values are: |
| egress_single_file_max_size | Max file size (in MB) to allow saving to a single file. May be overridden by target limitations. The default value is '10000'.The minimum allowed value is 1. The maximum allowed value is 200000. |
| max_concurrent_kernels | Sets the max_concurrent_kernels value of the conf. The minimum allowed value is 0. The maximum allowed value is 256. |
| tcs_per_tom | Sets the tcs_per_tom value of the conf. The minimum allowed value is 2. The maximum allowed value is 8192. |
| tps_per_tom | Sets the tps_per_tom value of the conf. The minimum allowed value is 2. The maximum allowed value is 8192. |
| ai_api_provider | AI API provider type |
| ai_api_url | AI API URL |
| ai_api_key | AI API key |
| ai_api_connection_timeout | AI API connection timeout in seconds |
| postgres_proxy_idle_connection_timeout | Idle connection timeout in seconds |
| postgres_proxy_keep_alive | Enable postgres proxy keep alive. The default value is 'false'. |
