{"id":940,"date":"2011-07-11T20:41:19","date_gmt":"2011-07-12T00:41:19","guid":{"rendered":"http:\/\/hstore.cs.brown.edu\/?page_id=940"},"modified":"2016-06-03T13:12:04","modified_gmt":"2016-06-03T17:12:04","slug":"site","status":"publish","type":"page","link":"https:\/\/hstore.cs.brown.edu\/documentation\/configuration\/properties-file\/site\/","title":{"rendered":"Site Parameters"},"content":{"rendered":"<p id=\"top\" \/><div class=\"prevpage\"><B>\u00ab<\/B> <a href=\"https:\/\/hstore.cs.brown.edu\/documentation\/configuration\/properties-file\/client\/\" title=\"Client Parameters\">Client Parameters<\/a><\/div> <div class=\"nextpage\"><a href=\"https:\/\/hstore.cs.brown.edu\/documentation\/configuration\/cluster-file\/\" title=\"Cluster Configuration File\">Cluster Configuration File<\/a> <B>\u00bb<\/B><\/div><div style=\"clear:both;\"><\/div><\/p>\n<h2 class=\"property-list\">System &amp; Environment Parameters<\/h2>\n<ul class=\"property-list\">\n<p><a name=\"jvm_asserts\"><\/a><\/p>\n<li><tt class=\"property\">site.jvm_asserts<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Execute each HStoreSite with JVM asserts enabled. This should be set to false when running benchmark experiments.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"memory\"><\/a><\/p>\n<li><tt class=\"property\">site.memory<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>2048<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">The amount of memory to allocate for each site process (in MB)<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"preload\"><\/a><\/p>\n<li><tt class=\"property\">site.preload<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">When enabled, the HStoreSite will preload objects when the system is started. This should only be disabled for regression test cases.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"profiling\"><\/a><\/p>\n<li><tt class=\"property\">site.profiling<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Enable profiling for the HStoreSite. This data can be retrieved using the <a href=\"\/documentation\/system-procedures\/statistics\" class=\"sysproc\">@Statistics<\/a> sysproc.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<\/ul>\n<p><a name=\"log\"><\/a><\/p>\n<h2 class=\"property-list\">Debug Logging Parameters<\/h2>\n<ul class=\"property-list\">\n<p><a name=\"log_dir\"><\/a><\/p>\n<li><tt class=\"property\">site.log_dir<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt><a href=\"\/documentation\/configuration\/properties-file\/global#log_dir\" class=\"property\">global.log_dir<\/a>\/sites<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>string<\/tt><\/td>\n<tr>\n<td colspan=\"2\">HStoreSite log directory on the host that the BenchmarkController is invoked from.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"log_backup\"><\/a><\/p>\n<li><tt class=\"property\">site.log_backup<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Whether to back-up log files before the benchmark is exceuted<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<\/ul>\n<p><a name=\"cpu\"><\/a><\/p>\n<h2 class=\"property-list\">CPU Affinity Parameters<\/h2>\n<ul class=\"property-list\">\n<p><a name=\"cpu_affinity\"><\/a><\/p>\n<li><tt class=\"property\">site.cpu_affinity<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">When enabled, the PartitionExecutor threads will be pinned to the first n CPU cores (where n is the total number of partitions hosted by the local HStoreSite). All other threads (e.g., for network handling) will be pinned to the remaining CPU cores. If there are fewer CPU cores than partitions, then this option will be disabled. <\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"cpu_affinity_one_partition_per_core\"><\/a><\/p>\n<li><tt class=\"property\">site.cpu_affinity_one_partition_per_core<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">When used in conjunction with <a href=\"\/documentation\/configuration\/properties-file\/site#cpu_affinity\" class=\"property\">site.cpu_affinity<\/a>, each PartitionExecutor thread will be assigned to one and only CPU core. No other thread within the HStoreSite (including all other PartitionExecutors) will be allowed to execute on that core. This configuration option is mostly used for debugging and is unlikely to provide any speed improvement because the operating system will automatically maintain CPU affinity.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"cpu_partition_blacklist\"><\/a><\/p>\n<li><tt class=\"property\">site.cpu_partition_blacklist<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>0<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>string<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Comma-separated list of CPU Ids (starting at zero) that the PartitionExecutors should not be scheduled to execute on. This is used whenever we need to doscaling experiments and want to avoid hyper-threading cores. We will always avoid executing on the first CPU by default because that&#8217;s where the JVM likes to execute system threads.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"cpu_utility_blacklist\"><\/a><\/p>\n<li><tt class=\"property\">site.cpu_utility_blacklist<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>null<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>string<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Comma-separated list of CPU Ids (starting at zero) that the HStoreSite&#8217;s utility should not be scheduled to execute on. This is used whenever we need to doscaling experiments and want to avoid hyper-threading cores.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<\/ul>\n<p><a name=\"exec\"><\/a><\/p>\n<h2 class=\"property-list\">Execution Parameters<\/h2>\n<ul class=\"property-list\">\n<p><a name=\"exec_ee_log_level\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_ee_log_level<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>500<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">ExecutionEngine log level.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"exec_profiling\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_profiling<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Enable execution site profiling. This will keep track of how busy each PartitionExecutor thread is during execution (i.e., the percentage of time that it spends executing a transaction versus waiting for work to be added to its queue). The profiling data collected can be retrieved using the <a href=\"\/documentation\/system-procedures\/statistics\" class=\"sysproc\">@Statistics<\/a> sysproc.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"exec_speculative_execution\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_speculative_execution<\/tt> <b class=\"experimental\">Experimental<\/b>  <b class=\"deprecated\">Deprecated<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td class=\"prop-replaced\">Replaced By:<\/td>\n<td><tt><a href=\"\/documentation\/configuration\/properties-file\/site#specexec_enable\" class=\"property\">site.specexec_enable<\/a><\/tt><\/td>\n<tr>\n<td colspan=\"2\">If this feature is enabled, then each HStoreSite will attempt to speculatively execute single-partition transactions whenever it completes a work request for a multi-partition transaction running on a different node.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"exec_no_undo_logging\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_no_undo_logging<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If this feature is enabled, then those non-speculative single partition transactions that are deemed to never abort will be executed without undo logging. Requires Markov model estimations.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"exec_no_undo_logging_all\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_no_undo_logging_all<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">All transactions are executed without any undo logging. For testing purposes only.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"exec_force_undo_logging_all\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_force_undo_logging_all<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Force all transactions to execute with undo logging. For testing purposes only.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"exec_db2_redirects\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_db2_redirects<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If this configuration parameter is true, then H-Store will use DB2-style transaction redirects. Each request will execute as a single-partition transaction at a random partition on the node that the request originally arrives on. When the transaction makes a query request that needs to touch data from a partition that is different than its base partition, then that transaction is immediately aborted, rolled back, and restarted on the partition that has the data that it was requesting. If the transaction requested more than partition when it was aborted, then it will be executed as a multi-partition transaction on the partition that was requested most often by queries using random tie breakers). See <a href=\"http:\/\/ibm.co\/fLR2cH\">http:\/\/ibm.co\/fLR2cH<\/a> for more information.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"exec_force_singlepartitioned\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_force_singlepartitioned<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Always execute transactions as single-partitioned (excluding sysprocs). If a transaction requests data on a partition that is different than where it is executing, then it is aborted, rolled back, and re-executed on the same partition as a multi-partition transaction that touches all partitions. Note that this is independent of how H-Store decides whatpartition to execute the transaction&#8217;s Java control code on.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"exec_force_allpartitions\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_force_allpartitions<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Always execute all requests as distributed transactions that lock all partitions in the cluster.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"exec_voltdb_procinfo\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_voltdb_procinfo<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Use the VoltDB @ProcInfo annotations for stored procedures to determine whether a new request will be executed as a single-partitioned or distributed transaction. Note that if this option is enabled, any distributed transaction will have to lock all of the partitions in the cluster.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"exec_force_localexecution\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_force_localexecution<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Always execute each transaction on a random partition on the node where the request originally arrived on. Note that this is independent of whether the transaction is selected to be single-partitioned or not. It is likely that you do not want to use this option.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"exec_mispredict_crash\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_mispredict_crash<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Whether the VoltProcedure should crash the HStoreSite when a transaction is mispredicted. A mispredicted transaction is one that was originally identified as single-partitioned but then executed a query that attempted to access multiple partitions. This is primarily used for debugging the TransactionEstimator.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"exec_preprocessing_threads\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_preprocessing_threads<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If this enabled, HStoreSite will use a separate thread to process inbound requests from the clients.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"exec_preprocessing_threads_count\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_preprocessing_threads_count<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>-1<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">The number of TransactionPreProcessor threads to use per HStoreSite. If this parameter is set to -1, then the system will automatically use all of the non-PartitionExecutor cores for these processing threads. The <a href=\"\/documentation\/configuration\/properties-file\/site#exec_preprocessing_threads\" class=\"property\">site.exec_preprocessing_threads<\/a> parameter must be set to true. <\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"exec_postprocessing_threads\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_postprocessing_threads<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Use a separate TransactionPostProcessor thread in the HStoreSite to return results back to the client. This will to improve the throughput of the CommandLogWriter, since this thread will take care of all of the outbound network communication with clients.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"exec_queued_response_ee_bypass\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_queued_response_ee_bypass<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If this enabled with speculative execution, then HStoreSite only invoke the commit operation in the EE for the last transaction in the queued responses. This will cascade to all other queued responses successful transactions that were speculatively executed.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"exec_response_timeout\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_response_timeout<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>10000<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">The maximum amount of time that the PartitionExecutor will wait for the results of a distributed query to return to the transaction&#8217;s base partition. Usually if this limit is reached, then there is something very wrong with the distributed transaction protocol.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"exec_validate_work\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_validate_work<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If this parameter is enabled, then the PartitionExecutor will check for every SQLStmt batch for each distributed transaction contains valid WorkFragments.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"exec_early_prepare\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_early_prepare<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Enables the early 2PC prepare optimization.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"exec_adhoc_sql\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_adhoc_sql<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Setting this configuration parameter to true allows clients to issue ad hoc query requests use the <a href=\"\/documentation\/system-procedures\/adhoc\" class=\"sysproc\">@AdHoc<\/a> sysproc. This should be set to false if you are running benchmarking experiments because it will reduce the number of threads that are started per HStoreSite.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"exec_prefetch_queries\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_prefetch_queries<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If this parameter is enabled, then the DBMS will attempt to prefetch commutative queries on remote partitions for distributed transactions.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"exec_deferrable_queries\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_deferrable_queries<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If this parameter is enabled, then the DBMS will queue up any single-partitioned queries for later execution if they are marked as deferrable.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"exec_periodic_interval\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_periodic_interval<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>50<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">How often in milliseconds should the HStoreSite check for periodic work. This work includes checking for dead network connections and processing any ad-hoc SQL invocatons. You probably do not need to change this unless you want a lower latency for ad-hoc SQL queries or you want to completely remove the overhead of performing periodic checks.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"exec_readwrite_tracking\"><\/a><\/p>\n<li><tt class=\"property\">site.exec_readwrite_tracking<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Enables H-Store&#8217;s ExecutionEngine to track of what tuples a transaction reads and writes at each partition. This is currently only used for the OPTIMISTIC speculative executionconflict checker. See <a href=\"\/documentation\/configuration\/properties-file\/site#specexec_scheduler_checker\" class=\"property\">site.specexec_scheduler_checker<\/a>.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<\/ul>\n<p><a name=\"specexec\"><\/a><\/p>\n<h2 class=\"property-list\">Speculative Execution Parameters<\/h2>\n<ul class=\"property-list\">\n<p><a name=\"specexec_enable\"><\/a><\/p>\n<li><tt class=\"property\">site.specexec_enable<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If this feature is enabled, then each HStoreSite will attempt to speculatively execute single-partition transactions whenever it completes a work request for a multi-partition transaction running on a different node.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"specexec_scheduler_checker\"><\/a><\/p>\n<li><tt class=\"property\">site.specexec_scheduler_checker<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>TABLE<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>string<\/tt><\/td>\n<tr>\n<td class=\"prop-values\">Permitted Values:<\/td>\n<td><tt>[TABLE, MARKOV, UNSAFE, OPTIMISTIC]<\/tt><\/td>\n<tr>\n<td class=\"prop-values\">See Also:<\/td>\n<td><tt>org.voltdb.types.SpeculationConflictCheckerType<\/tt><\/td>\n<tr>\n<td colspan=\"2\">This controls what conflict detection algorithm the SpecExecScheduler will use to use at run time to decide what transactions to run speculatively.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"specexec_scheduler_policy\"><\/a><\/p>\n<li><tt class=\"property\">site.specexec_scheduler_policy<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>FIRST<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>string<\/tt><\/td>\n<tr>\n<td class=\"prop-values\">Permitted Values:<\/td>\n<td><tt>[FIRST, LAST, SHORTEST, LONGEST]<\/tt><\/td>\n<tr>\n<td class=\"prop-values\">See Also:<\/td>\n<td><tt>org.voltdb.types.SpecExecSchedulerPolicyType<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Speculative policy to pick the transactions to run speculatively. <\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"specexec_scheduler_window\"><\/a><\/p>\n<li><tt class=\"property\">site.specexec_scheduler_window<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>10<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">The window size to pick up txn to run speculatively. <\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"specexec_ignore_all_local\"><\/a><\/p>\n<li><tt class=\"property\">site.specexec_ignore_all_local<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If this parameter is true, then the SpecExecScheduler will not attempt to speculatively execute any transactions if the current distributed transaction is using only partitions that are all on the same site.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"specexec_ignore_queue_size_change\"><\/a><\/p>\n<li><tt class=\"property\">site.specexec_ignore_queue_size_change<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If this parameter is true, then the SpecExecScheduler will not reset its internal iterator if the partition&#8217;s lock queue changes in size. This will provide a minor speed up when checking for speculative transactions, but it also means that new transactions that are added to the front of the queue will be missed.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"specexec_ignore_interruptions\"><\/a><\/p>\n<li><tt class=\"property\">site.specexec_ignore_interruptions<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">This parameter controls whether the SpecExecScheduler will ignore any interrupts from incoming WorkFragments added to its PartitionExecutor&#8217;s queue. You most likely do not want to enable this because it will slow down the execution of distributed transactions.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"specexec_ignore_stallpoints\"><\/a><\/p>\n<li><tt class=\"property\">site.specexec_ignore_stallpoints<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>null<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>string<\/tt><\/td>\n<tr>\n<td class=\"prop-values\">Permitted Values:<\/td>\n<td><tt>[NULL, SP1_IDLE, SP1_LOCAL, SP2_LOCAL, SP3_REMOTE_BEFORE, SP3_REMOTE_AFTER, SP4_LOCAL, SP4_REMOTE]<\/tt><\/td>\n<tr>\n<td class=\"prop-values\">See Also:<\/td>\n<td><tt>org.voltdb.types.SpeculationType<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Disable speculative execution at the given stall points. <\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"specexec_nonblocking\"><\/a><\/p>\n<li><tt class=\"property\">site.specexec_nonblocking<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Experimental non-blocking remote query execution. All query results will be wrapped in a special VoltTable that acts as a placeholder for a remote query whose result has not returned yet. A transaction when it tries to access the real result. Otherwise, it will proceed as normal. This does not require any changes to existing stored procedure code.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"specexec_unsafe_limit\"><\/a><\/p>\n<li><tt class=\"property\">site.specexec_unsafe_limit<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>-1<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Note that <a href=\"\/documentation\/configuration\/properties-file\/site#markov_enable\" class=\"property\">site.markov_enable<\/a> must be set to true.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"specexec_profiling\"><\/a><\/p>\n<li><tt class=\"property\">site.specexec_profiling<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If enabled, then the SpecExecScheduler will keep track of various internal profile statistics. The profiling data collected can be retrieved using the <a href=\"\/documentation\/system-procedures\/statistics\" class=\"sysproc\">@Statistics<\/a> sysproc.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"specexec_profiling_sample\"><\/a><\/p>\n<li><tt class=\"property\">site.specexec_profiling_sample<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>0.05<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>double<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Sample factor for speculative execution scheduler profiling (0.0 &#8211; 1.0). Note that the the <a href=\"\/documentation\/configuration\/properties-file\/site#specexec_profiling\" class=\"property\">site.specexec_profiling<\/a> parameter must also be enabled.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"specexec_disable_partitions\"><\/a><\/p>\n<li><tt class=\"property\">site.specexec_disable_partitions<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>null<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>string<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Comma-separated list of partition ids to disable speculative execution on. This is only needed for debugging and experiments.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<\/ul>\n<p><a name=\"commandlog\"><\/a><\/p>\n<h2 class=\"property-list\">Command Logging Parameters<\/h2>\n<ul class=\"property-list\">\n<p><a name=\"commandlog_enable\"><\/a><\/p>\n<li><tt class=\"property\">site.commandlog_enable<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If enabled, log all transaction requests to disk<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"commandlog_dir\"><\/a><\/p>\n<li><tt class=\"property\">site.commandlog_dir<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt><a href=\"\/documentation\/configuration\/properties-file\/global#temp_dir\" class=\"property\">global.temp_dir<\/a>\/cmdlog<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>string<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Directory for storage of command logging files<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"commandlog_timeout\"><\/a><\/p>\n<li><tt class=\"property\">site.commandlog_timeout<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>10<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Timeout in milliseconds before group commit buffer flushes, if it does not fill<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"commandlog_profiling\"><\/a><\/p>\n<li><tt class=\"property\">site.commandlog_profiling<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If enabled, then the CommandLogWriter will keep track of various internal profile statistics.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<\/ul>\n<p><a name=\"anticache\"><\/a><\/p>\n<h2 class=\"property-list\">Anti-Caching Parameters<\/h2>\n<ul class=\"property-list\">\n<p><a name=\"anticache_enable\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_enable<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Enable the anti-cache feature. This requires that the system is compiled with <a href=\"\/documentation\/configuration\/properties-file\/site#anticache_build\" class=\"property\">site.anticache_build<\/a> set to true.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_warmup_eviction_enable\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_warmup_eviction_enable<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Enable anti-caching warmup feature. This requires that the system is compiled with both <a href=\"\/documentation\/configuration\/properties-file\/site#anticache_enabled\" class=\"property\">site.anticache_enabled<\/a> and ${site.anticache_build set to true.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_warmup_eviction_time\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_warmup_eviction_time<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>0<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Reserved eviction time for anti-caching after warmup of the benchmark. This requires that the system is compiled with <a href=\"\/documentation\/configuration\/properties-file\/site#anticache_warmup_eviction_enable\" class=\"property\">site.anticache_warmup_eviction_enable<\/a>  set to true.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_enable_multilevel\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_enable_multilevel<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Enable multilevel anti-caching feature. This requires that the system is compiled with both <a href=\"\/documentation\/configuration\/properties-file\/site#anticache_enabled\" class=\"property\">site.anticache_enabled<\/a> and ${site.anticache_build set to true.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_build\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_build<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Build the anti-cache feature when compiling the H-Store source code. You probably always want to leave this flag enabled.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_reversible_lru\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_reversible_lru<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Use a doubly-linked list for the anti-cache&#8217;s LRU tracker. This will increase the memory overhead of the anti-cache&#8217;s metatadata but it will improve the performance of eviction operations.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_profiling\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_profiling<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Enable the anti-cache profiling.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_dir\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_dir<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt><a href=\"\/documentation\/configuration\/properties-file\/global#temp_dir\" class=\"property\">global.temp_dir<\/a>\/anticache<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>string<\/tt><\/td>\n<tr>\n<td colspan=\"2\">The directory to use to store the evicted tuples.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_levels\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_levels<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>NVM,true,256K,64G;BERKELEY,false,256K,128G<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>string<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Configuration options for multilevel anticaching. Up to five levels can be set up. The format is type,blocking,block_size,db_size; The default is &#8216;NVM,true,256K,64G;BERKELEY,false,256K,128G&#8217;.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_multilevel_dirs\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_multilevel_dirs<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt><a href=\"\/documentation\/configuration\/properties-file\/global#temp_dir\" class=\"property\">global.temp_dir<\/a>\/ac-level1;<a href=\"\/documentation\/configuration\/properties-file\/global#temp_dir\" class=\"property\">global.temp_dir<\/a>\/ac-level2;<a href=\"\/documentation\/configuration\/properties-file\/global#temp_dir\" class=\"property\">global.temp_dir<\/a>\/ac-level3;<a href=\"\/documentation\/configuration\/properties-file\/global#temp_dir\" class=\"property\">global.temp_dir<\/a>\/ac-level4;<a href=\"\/documentation\/configuration\/properties-file\/global#temp_dir\" class=\"property\">global.temp_dir<\/a>\/ac-level5<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>string<\/tt><\/td>\n<tr>\n<td colspan=\"2\">The directories used for multilevel anticaching databases.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_block_size\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_block_size<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>262144<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>long<\/tt><\/td>\n<tr>\n<td colspan=\"2\">The size (in bytes) for the anti-cache&#8217;s blocks on disk.WARNING: this seem to be buggy\/broken. Please leave the default value of 256KB (262144) unless you know what you&#8217;re doing.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_dbsize\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_dbsize<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>2G<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>string<\/tt><\/td>\n<tr>\n<td colspan=\"2\">The size of the anticache database.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_reset\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_reset<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Reset the anti-cache database directory for each partition when the HStoreSite is started.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_check_interval\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_check_interval<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>30000<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">How often in milliseconds should the AntiCacheManager check whether the HStoreSite is using too much memory and should start evicting tuples.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_threshold_mb\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_threshold_mb<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>200<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Memory usage threshold, in MB, at which to start evicting<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_max_evicted_blocks\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_max_evicted_blocks<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>200000<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Maximum number of blocks evicted on this site<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_blocks_per_eviction\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_blocks_per_eviction<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>200<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Maximum number of blocks per eviction<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_eviction_distribution\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_eviction_distribution<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>UNEVICTION_RATIO<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>string<\/tt><\/td>\n<tr>\n<td class=\"prop-values\">Permitted Values:<\/td>\n<td><tt>[EVEN, PROPORTIONAL, UNEVICTION_RATIO, ACCESS_RATE]<\/tt><\/td>\n<tr>\n<td class=\"prop-values\">See Also:<\/td>\n<td><tt>org.voltdb.types.AntiCacheEvictionPolicyType<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Policy specifying how to distribute eviction load over partitions and tables.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_batching\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_batching<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Turn on batching for anticaching<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_dbtype\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_dbtype<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>BERKELEY<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>string<\/tt><\/td>\n<tr>\n<td class=\"prop-values\">Permitted Values:<\/td>\n<td><tt>[NONE, BERKELEY, NVM, ALLOCATORNVM]<\/tt><\/td>\n<tr>\n<td class=\"prop-values\">See Also:<\/td>\n<td><tt>org.voltdb.types.AntiCacheDBType<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Type of database for the highest level eviction<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_db_blocks\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_db_blocks<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Top level database blocks for evictions<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_block_merge\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_block_merge<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Merge entire block when unevicting. False merges just a single tuple<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_counter\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_counter<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Enable the anti-cache counted merge-back feature. This requires that the system is compiled with <a href=\"\/documentation\/configuration\/properties-file\/site#anticache_enable\" class=\"property\">site.anticache_enable<\/a> set to true and <a href=\"\/documentation\/configuration\/properties-file\/site#anticache_db_blocks\" class=\"property\">site.anticache_db_blocks<\/a> set to true.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_timestamps\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_timestamps<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Enable the anti-cache timestamps feature. This requires that the system is compiled with <a href=\"\/documentation\/configuration\/properties-file\/site#anticache_enable\" class=\"property\">site.anticache_enable<\/a> set to true.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"anticache_timestamps_prime\"><\/a><\/p>\n<li><tt class=\"property\">site.anticache_timestamps_prime<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Enable the anti-cache timestamps use a prime sample strategy instead of radom-tuple sampling.This is compiled with <a href=\"\/documentation\/configuration\/properties-file\/site#anticache_timestamps\" class=\"property\">site.anticache_timestamps<\/a> set to true.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<\/ul>\n<p><a name=\"storage\"><\/a><\/p>\n<h2 class=\"property-list\">Internal Storage Parameters<\/h2>\n<ul class=\"property-list\">\n<p><a name=\"storage_mmap\"><\/a><\/p>\n<li><tt class=\"property\">site.storage_mmap<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Use mmap to store database on local filesystem. <\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"storage_mmap_dir\"><\/a><\/p>\n<li><tt class=\"property\">site.storage_mmap_dir<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt><a href=\"\/documentation\/configuration\/properties-file\/global#temp_dir\" class=\"property\">global.temp_dir<\/a>\/mmap<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>string<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Location of where H-Store will store mmap files for each partition. This is only used if <a href=\"\/documentation\/configuration\/properties-file\/site#storage_mmap\" class=\"property\">site.storage_mmap<\/a> is enabled. <\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"storage_mmap_file_size\"><\/a><\/p>\n<li><tt class=\"property\">site.storage_mmap_file_size<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>2097152<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>long<\/tt><\/td>\n<tr>\n<td colspan=\"2\">The size (in bytes) for the mmap file objects on NVM device.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"storage_mmap_reset\"><\/a><\/p>\n<li><tt class=\"property\">site.storage_mmap_reset<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Reset the mmap directory for each partition when the HStoreSite is started.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"storage_mmap_sync_frequency\"><\/a><\/p>\n<li><tt class=\"property\">site.storage_mmap_sync_frequency<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>100000<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>long<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Frequency with which changes are synced via msync with memory<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<\/ul>\n<p><a name=\"aries\"><\/a><\/p>\n<h2 class=\"property-list\">ARIES-based Recovery Parameters<\/h2>\n<ul class=\"property-list\">\n<p><a name=\"aries\"><\/a><\/p>\n<li><tt class=\"property\">site.aries<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">ARIES recovery enabled. <\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"aries_forward_only\"><\/a><\/p>\n<li><tt class=\"property\">site.aries_forward_only<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">ARIES forward processing only enabled, recovery disabled &#8211; for throughput evaluation<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"aries_dir\"><\/a><\/p>\n<li><tt class=\"property\">site.aries_dir<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt><a href=\"\/documentation\/configuration\/properties-file\/global#temp_dir\" class=\"property\">global.temp_dir<\/a>\/aries<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>string<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Location of where H-Store will store ARIES log files for each partition. This is only used if <a href=\"\/documentation\/configuration\/properties-file\/site#aries\" class=\"property\">site.aries<\/a> is enabled. <\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"aries_reset\"><\/a><\/p>\n<li><tt class=\"property\">site.aries_reset<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Reset the ARIES directory for each partition when the HStoreSite is started (disabled by default).<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<\/ul>\n<p><a name=\"snapshot\"><\/a><\/p>\n<h2 class=\"property-list\">Snapshot Checkpoints Parameters<\/h2>\n<ul class=\"property-list\">\n<p><a name=\"snapshot\"><\/a><\/p>\n<li><tt class=\"property\">site.snapshot<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Logical recovery using snapshots enabled. <\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"snapshot_dir\"><\/a><\/p>\n<li><tt class=\"property\">site.snapshot_dir<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt><a href=\"\/documentation\/configuration\/properties-file\/global#temp_dir\" class=\"property\">global.temp_dir<\/a>\/snapshot<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>string<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Location of where H-Store will store snapshot files for each partition&#8217;s tables. This is only used if <a href=\"\/documentation\/configuration\/properties-file\/site#snapshot\" class=\"property\">site.snapshot<\/a> is enabled. <\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"snapshot_reset\"><\/a><\/p>\n<li><tt class=\"property\">site.snapshot_reset<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Reset the snapshot directory for each partition when the HStoreSite is started (disabled by default).<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"snapshot_interval\"><\/a><\/p>\n<li><tt class=\"property\">site.snapshot_interval<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>10000<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">How often in milliseconds should we take snapshots in HStoreSite <\/td>\n<\/tr>\n<\/table>\n<\/li>\n<\/ul>\n<p><a name=\"mr\"><\/a><\/p>\n<h2 class=\"property-list\">MapReduce Parameters<\/h2>\n<ul class=\"property-list\">\n<p><a name=\"mr_map_blocking\"><\/a><\/p>\n<li><tt class=\"property\">site.mr_map_blocking<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If set to true, then the MAP phase of a MapReduceTransaction will be executed as a distributed transaction that blocks the entire cluster. This ensures that the aggregates computed by the MAP phase reads from consistent a consistent state of the database.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"mr_reduce_blocking\"><\/a><\/p>\n<li><tt class=\"property\">site.mr_reduce_blocking<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">The way to execute reduce job, blocking or non-blocking by MapReduceHelperThread<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<\/ul>\n<p><a name=\"network\"><\/a><\/p>\n<h2 class=\"property-list\">Network Parameters<\/h2>\n<ul class=\"property-list\">\n<p><a name=\"network_heartbeats_interval\"><\/a><\/p>\n<li><tt class=\"property\">site.network_heartbeats_interval<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>10000<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">How often in milliseconds the HStoreCoordinator at each HStoreSite should send heartbeat notifications to the other coordinators in the cluster. <\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"network_startup_wait\"><\/a><\/p>\n<li><tt class=\"property\">site.network_startup_wait<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>15000<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">How long in milliseconds should the HStoreCoordinator wait to establish the initial connections to other nodes in the cluster at start-up. Increasing this number will help with larger cluster deployments.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"network_startup_retries\"><\/a><\/p>\n<li><tt class=\"property\">site.network_startup_retries<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>2<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If the HStoreCoordinator fails to connect to all of the other nodes in the cluster after <a href=\"\/documentation\/configuration\/properties-file\/site#network_startup_wait\" class=\"property\">site.network_startup_wait<\/a> has passed, this parameter defines the number of times that it is allowed to attempt to reconnect to them. This helps with some rare network issues with the ProtoRpc framework where the initial network connection attempt hangs or fails, even though both sites are available.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"network_incoming_max_per_partition\"><\/a><\/p>\n<li><tt class=\"property\">site.network_incoming_max_per_partition<\/tt>  <b class=\"deprecated\">Deprecated<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>5000<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td class=\"prop-replaced\">Replaced By:<\/td>\n<td><tt><a href=\"\/documentation\/configuration\/properties-file\/site#network_incoming_limit_txns\" class=\"property\">site.network_incoming_limit_txns<\/a><\/tt><\/td>\n<tr>\n<td colspan=\"2\">Max size of queued transactions before an HStoreSite will stop accepting new requests from clients and will block the network connections.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"network_incoming_limit_txns\"><\/a><\/p>\n<li><tt class=\"property\">site.network_incoming_limit_txns<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>8000<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Max size of queued transactions before an HStoreSite will stop accepting new requests from clients and will block the network connections. This is per partition.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"network_incoming_limit_bytes\"><\/a><\/p>\n<li><tt class=\"property\">site.network_incoming_limit_bytes<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>67108864<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>long<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Max number of bytes in the queued transactions before an HStoreSite will stop accepting new requests from clients and will block the network connections.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<\/ul>\n<p><a name=\"txn\"><\/a><\/p>\n<h2 class=\"property-list\">Transaction Parameters<\/h2>\n<ul class=\"property-list\">\n<p><a name=\"txn_client_debug\"><\/a><\/p>\n<li><tt class=\"property\">site.txn_client_debug<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If this parameter is set to true, then the ClientResponse returned by the server will include a special ClientResponseDebug handle that contains additional information about the transaction. Note that enabling this option will break compatibility with VoltDB&#8217;s client libraries.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"txn_profiling\"><\/a><\/p>\n<li><tt class=\"property\">site.txn_profiling<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Enable transaction profiling. This will measure the amount of time a transaction spends in different parts of the system (e.g., waiting in the work queue, planning, executing). The profiling data collected can be retrieved using the <a href=\"\/documentation\/system-procedures\/statistics\" class=\"sysproc\">@Statistics<\/a> sysproc.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"txn_profiling_sample\"><\/a><\/p>\n<li><tt class=\"property\">site.txn_profiling_sample<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>0.1<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>double<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Sample factor for transaction profiling (0.0 &#8211; 1.0). This will be used at runtime to determine whether a transaction is executed with the profiling hooks enabled. Note that the the <a href=\"\/documentation\/configuration\/properties-file\/site#txn_profiling\" class=\"property\">site.txn_profiling<\/a> parameter must also be enabled.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"txn_profiling_dump\"><\/a><\/p>\n<li><tt class=\"property\">site.txn_profiling_dump<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If this is set to true, then each HStoreSite will write out a CSV file on its local filesystem that contains a dump of the runtime profiling information for each transaction. Check the site log for the output name of each file. Note that the the <a href=\"\/documentation\/configuration\/properties-file\/site#txn_profiling\" class=\"property\">site.txn_profiling<\/a> parameter must also be enabled.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"txn_counters\"><\/a><\/p>\n<li><tt class=\"property\">site.txn_counters<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Enable transaction execution mode counting. This will cause the HStoreSite to keep track of various properties about tranasctions, such as the number that were speculatively executed or had to be restarted.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"txn_incoming_delay\"><\/a><\/p>\n<li><tt class=\"property\">site.txn_incoming_delay<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>5<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">The amount of time in milliseconds that the TransactionQueueManager will wait before letting a distributed transaction acquire a lock on a partition.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"txn_restart_limit\"><\/a><\/p>\n<li><tt class=\"property\">site.txn_restart_limit<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>10<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">The number of times that a distributed transaction is allowed to be restarted (due to things like network delays) before it is outright rejected and the request is returned to the client.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"txn_restart_limit_sysproc\"><\/a><\/p>\n<li><tt class=\"property\">site.txn_restart_limit_sysproc<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>10<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\"><\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"txn_partition_id_managers\"><\/a><\/p>\n<li><tt class=\"property\">site.txn_partition_id_managers<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If set to true, then the HStoreSite will use a separate TransactionIdManagerper partition. This can reduce some lock contention for workloads where transactions are restarted a lot. This actually doesn&#8217;t work very well, so you probably do not want to bother with this parameter.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<\/ul>\n<p><a name=\"queue\"><\/a><\/p>\n<h2 class=\"property-list\">Workload Queue Parameters<\/h2>\n<ul class=\"property-list\">\n<p><a name=\"queue_profiling\"><\/a><\/p>\n<li><tt class=\"property\">site.queue_profiling<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Enable profiling in the TransactionQueueManager and PartitionLockQueue in the HStoreSite. The profiling data collected can be retrieved using the <a href=\"\/documentation\/system-procedures\/statistics\" class=\"sysproc\">@Statistics<\/a> sysproc.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"queue_threshold_factor\"><\/a><\/p>\n<li><tt class=\"property\">site.queue_threshold_factor<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>1.0<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>double<\/tt><\/td>\n<tr>\n<td colspan=\"2\">The initial throttling threshold for the PartitionLockQueue.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"queue_autoscale_delta\"><\/a><\/p>\n<li><tt class=\"property\">site.queue_autoscale_delta<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>50<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\"><\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"queue_allow_decrease\"><\/a><\/p>\n<li><tt class=\"property\">site.queue_allow_decrease<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\"><\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"queue_allow_increase\"><\/a><\/p>\n<li><tt class=\"property\">site.queue_allow_increase<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\"><\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"queue_min_factor\"><\/a><\/p>\n<li><tt class=\"property\">site.queue_min_factor<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>0.5<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>double<\/tt><\/td>\n<tr>\n<td colspan=\"2\">The initial throttling threshold for the PartitionLockQueue.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"queue_max_factor\"><\/a><\/p>\n<li><tt class=\"property\">site.queue_max_factor<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>1.5<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>double<\/tt><\/td>\n<tr>\n<td colspan=\"2\">The initial throttling threshold for the PartitionLockQueue.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"queue_release_factor\"><\/a><\/p>\n<li><tt class=\"property\">site.queue_release_factor<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>0.5<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>double<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If the HStoreSite is throttling incoming client requests at individual partitions, then that HStoreSite will not accept new requests until the number of queued transactions is less than this percentage in a partition&#8217;s lock queue. Note that this only considers the total number of transactions that are in the PartitionLockQueue, not transactions that are waiting to be initialized or have already completed.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<\/ul>\n<p><a name=\"mappings\"><\/a><\/p>\n<h2 class=\"property-list\">Parameter Mappings Parameters<\/h2>\n<ul class=\"property-list\">\n<p><a name=\"mappings_path\"><\/a><\/p>\n<li><tt class=\"property\">site.mappings_path<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>null<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>string<\/tt><\/td>\n<tr>\n<td colspan=\"2\"><\/td>\n<\/tr>\n<\/table>\n<\/li>\n<\/ul>\n<p><a name=\"markov\"><\/a><\/p>\n<h2 class=\"property-list\">Transaction Prediction Models Parameters<\/h2>\n<ul class=\"property-list\">\n<p><a name=\"markov_enable\"><\/a><\/p>\n<li><tt class=\"property\">site.markov_enable<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Predict what transactions will do before they execute using TransactionEstimator&#8217;s Markov models.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"markov_force_traversal\"><\/a><\/p>\n<li><tt class=\"property\">site.markov_force_traversal<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Force the MarkovPathEstimator to always choose a transition from an execution state in a Markov model even if there is not a state that matches the prediction.  This ensures that the estimated path always reaches either the COMMIT or ABORT terminal states and therefore a valid estimation can be created.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"markov_learning_enable\"><\/a><\/p>\n<li><tt class=\"property\">site.markov_learning_enable<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Allow the MarkovPathEstimator to automatically learn new execution states for transactions if it is unable to find the correct one for the current transaction. The updated models can be retrieved using the <a href=\"\/documentation\/system-procedures\/markovupdate\" class=\"sysproc\">@MarkovUpdate<\/a> system procedure. Note that <a href=\"\/documentation\/configuration\/properties-file\/site#markov_force_traversal\" class=\"property\">site.markov_force_traversal<\/a> must be set to true.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"markov_singlep_updates\"><\/a><\/p>\n<li><tt class=\"property\">site.markov_singlep_updates<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If this parameter is set to true, then the PartitionExecutor will use its TransactionEstimator to calculate updated estimates after a single-partition transaction submits a new batch of queries for execution.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"markov_dtxn_updates\"><\/a><\/p>\n<li><tt class=\"property\">site.markov_dtxn_updates<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If this parameter is set to true, then the PartitionExecutor will use its TransactionEstimator to calculate updated estimates after a distributed transaction submits a new batch of queries for execution.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"markov_mispredict_recompute\"><\/a><\/p>\n<li><tt class=\"property\">site.markov_mispredict_recompute<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Recompute a Markov model&#8217;s execution state probabilities every time a transaction is aborted due to a misprediction.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"markov_path\"><\/a><\/p>\n<li><tt class=\"property\">site.markov_path<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>null<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>string<\/tt><\/td>\n<tr>\n<td colspan=\"2\"><\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"markov_path_caching\"><\/a><\/p>\n<li><tt class=\"property\">site.markov_path_caching<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If this is set to true, TransactionEstimator will try to reuse the last successfully estimate path in a MarkovGraph for transactions that use thesame graph.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"markov_path_caching_threshold\"><\/a><\/p>\n<li><tt class=\"property\">site.markov_path_caching_threshold<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>1.0<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>double<\/tt><\/td>\n<tr>\n<td colspan=\"2\">This threshold defines how accurate our cached MarkovPathEstimators have to be in order to keep using them. If (# of accurate txs \/ total txns) for a paritucular MarkovGraph goes below this threshold, then we will disable the caching<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"markov_fast_path\"><\/a><\/p>\n<li><tt class=\"property\">site.markov_fast_path<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If this is set to true, the MarkovEstimator will attempt to use the initial path estimate to quickly calculate the new path for a running transaction.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"markov_endpoint_caching\"><\/a><\/p>\n<li><tt class=\"property\">site.markov_endpoint_caching<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">This enables the ability for the MarkovEstimator to cache the end points of path segments in a MarkovGraph so that it can just quickly identify the last MarkovVertex for a new batch of queries requested by the transaction.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"markov_batch_caching_min\"><\/a><\/p>\n<li><tt class=\"property\">site.markov_batch_caching_min<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>3<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">The minimum number of queries that must be in a batch for the TransactionEstimator to cache the path segment in the procedure&#8217;s MarkovGraph. Provides a minor speed improvement for large batches with little variability in their execution paths.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"markov_fixed\"><\/a><\/p>\n<li><tt class=\"property\">site.markov_fixed<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Use a fixed transaction estimator to predict the initial properties of an incoming transaction request from the client. This is a quick and dirty approximation. Not all benchmarks are supported and it does not generate predictions updates after the transaction starts running<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"markov_profiling\"><\/a><\/p>\n<li><tt class=\"property\">site.markov_profiling<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Enable profiling in the MarkovEstimator. The profiling data collected can be retrieved using the <a href=\"\/documentation\/system-procedures\/statistics\" class=\"sysproc\">@Statistics<\/a> sysproc.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<\/ul>\n<p><a name=\"planner\"><\/a><\/p>\n<h2 class=\"property-list\">Runtime SQL Batch Planner Parameters<\/h2>\n<ul class=\"property-list\">\n<p><a name=\"planner_profiling\"><\/a><\/p>\n<li><tt class=\"property\">site.planner_profiling<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Enable BatchPlanner profiling. This will keep of how long the BatchPlanner spends performing certain operations when generating an execution plan for a batch of queries submitted by a running transaction. The profiling data collected can be retrieved using the <a href=\"\/documentation\/system-procedures\/statistics\" class=\"sysproc\">@Statistics<\/a> sysproc.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"planner_caching\"><\/a><\/p>\n<li><tt class=\"property\">site.planner_caching<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Enable caching in the BatchPlanner. This will provide a significant speed improvement for single-partitioned queries because the BatchPlanner is able to quickly identify what partitions a batch of queries will access without having to process the request using the PartitionEstimator. This parameter is so great I should probably just hardcode to be always on, but maybe you don&#8217;t believe me and want to see how slow things go with out this&#8230;<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"planner_max_round_size\"><\/a><\/p>\n<li><tt class=\"property\">site.planner_max_round_size<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>10<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">The maximum number of execution rounds allowed per batch.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"planner_max_batch_size\"><\/a><\/p>\n<li><tt class=\"property\">site.planner_max_batch_size<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>128<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">The maximum number of SQLStmts that can be queued per batch in a transaction.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"planner_unique_dependency_ids\"><\/a><\/p>\n<li><tt class=\"property\">site.planner_unique_dependency_ids<\/tt> <b class=\"experimental\">Experimental<\/b><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Use globally unique Dependency Ids for each unique SQLStmt batch when generating WorkFragments at run time.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<\/ul>\n<p><a name=\"coordinator\"><\/a><\/p>\n<h2 class=\"property-list\">Cluster Coordinator Parameters<\/h2>\n<ul class=\"property-list\">\n<p><a name=\"coordinator_init_thread\"><\/a><\/p>\n<li><tt class=\"property\">site.coordinator_init_thread<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If this enabled, HStoreCoordinator will use a separate thread to process incoming initialization requests from other HStoreSites. This is useful when <a href=\"\/documentation\/configuration\/properties-file\/client#txn_hints\" class=\"property\">client.txn_hints<\/a> is disabled.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"coordinator_finish_thread\"><\/a><\/p>\n<li><tt class=\"property\">site.coordinator_finish_thread<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If this enabled, HStoreCoordinator will use a separate thread to process incoming finish requests for restarted transactions from other HStoreSites. <\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"coordinator_redirect_thread\"><\/a><\/p>\n<li><tt class=\"property\">site.coordinator_redirect_thread<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If this enabled, HStoreCoordinator will use a separate thread to process incoming redirect requests from other HStoreSites. This is useful when <a href=\"\/documentation\/configuration\/properties-file\/client#txn_hints\" class=\"property\">client.txn_hints<\/a> is disabled.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"coordinator_sync_time\"><\/a><\/p>\n<li><tt class=\"property\">site.coordinator_sync_time<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>true<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">If this enabled, HStoreCoordinator will use an NTP style protocol to find the time difference between sites in the cluster.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<\/ul>\n<p><a name=\"trace\"><\/a><\/p>\n<h2 class=\"property-list\">Workload Traces Parameters<\/h2>\n<ul class=\"property-list\">\n<p><a name=\"trace_txn_output\"><\/a><\/p>\n<li><tt class=\"property\">site.trace_txn_output<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">When this property is set to true, all TransactionTrace records will include the stored procedure output result<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"trace_query_output\"><\/a><\/p>\n<li><tt class=\"property\">site.trace_query_output<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">When this property is set to true, all QueryTrace records will include the query output result<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<\/ul>\n<p><a name=\"status\"><\/a><\/p>\n<h2 class=\"property-list\">Site Debug Status Parameters<\/h2>\n<ul class=\"property-list\">\n<p><a name=\"status_enable\"><\/a><\/p>\n<li><tt class=\"property\">site.status_enable<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Enable HStoreSite&#8217;s Status thread.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"status_interval\"><\/a><\/p>\n<li><tt class=\"property\">site.status_interval<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>20000<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">How often the HStoreSite&#8217;s StatusThread will print a status update (in milliseconds).<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"status_kill_if_hung\"><\/a><\/p>\n<li><tt class=\"property\">site.status_kill_if_hung<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Allow the HStoreSiteStatus thread to kill the cluster if the local HStoreSite appears to be hung. The site is considered hung if it has executed at least one transaction and has not completed (either committed or aborted) any new transactions since the last time it took a status snapshot.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"status_check_for_zombies\"><\/a><\/p>\n<li><tt class=\"property\">site.status_check_for_zombies<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Allow the HStoreSiteStatus thread to check whether there any zombie transactions. This can occur if the transaction has already sent back the ClientResponse, but its internal state has not been cleaned up.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"status_exec_info\"><\/a><\/p>\n<li><tt class=\"property\">site.status_exec_info<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">When this property is set to true, HStoreSite status will include information about each PartitionExecutor, such as the number of transactions currently queued, blocked for execution, or waiting to have their results returned to the client.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"status_thread_info\"><\/a><\/p>\n<li><tt class=\"property\">site.status_thread_info<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">When this property is set to true, HStoreSite status will include a snapshot of running threads<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<\/ul>\n<p><a name=\"pool\"><\/a><\/p>\n<h2 class=\"property-list\">Object Pools Parameters<\/h2>\n<ul class=\"property-list\">\n<p><a name=\"pool_scale_factor\"><\/a><\/p>\n<li><tt class=\"property\">site.pool_scale_factor<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>1.0<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>double<\/tt><\/td>\n<tr>\n<td colspan=\"2\">The scale factor to apply to the object pool configuration values.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"pool_profiling\"><\/a><\/p>\n<li><tt class=\"property\">site.pool_profiling<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>false<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>boolean<\/tt><\/td>\n<tr>\n<td colspan=\"2\">Whether to track the number of objects created, passivated, and destroyed from the pool. Results are shown in HStoreSiteStatus updates.<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<p><a name=\"pool_pathestimators_idle\"><\/a><\/p>\n<li><tt class=\"property\">site.pool_pathestimators_idle<\/tt><br \/>\n<table>\n<tr>\n<td class=\"prop-default\">Default:<\/td>\n<td><tt>100<\/tt><\/td>\n<tr>\n<td class=\"prop-type\">Permitted Tye:<\/td>\n<td><tt>int<\/tt><\/td>\n<tr>\n<td colspan=\"2\">The max number of MarkovPathEstimators to keep in the pool per partition<\/td>\n<\/tr>\n<\/table>\n<\/li>\n<\/ul>\n<p><div class=\"prevpage\"><B>\u00ab<\/B> <a href=\"https:\/\/hstore.cs.brown.edu\/documentation\/configuration\/properties-file\/client\/\" title=\"Client Parameters\">Client Parameters<\/a><\/div> <div class=\"nextpage\"><a href=\"https:\/\/hstore.cs.brown.edu\/documentation\/configuration\/cluster-file\/\" title=\"Cluster Configuration File\">Cluster Configuration File<\/a> <B>\u00bb<\/B><\/div><div style=\"clear:both;\"><\/div><\/p>\n","protected":false},"excerpt":{"rendered":"<p>System &amp; Environment Parameters site.jvm_asserts Default: false Permitted Tye: boolean Execute each HStoreSite with JVM asserts enabled. This should be set to false when running benchmark experiments. site.memory Default: 2048 Permitted Tye: int The amount of memory to allocate for each site process (in MB) site.preload Default: true Permitted Tye: boolean When enabled, the HStoreSite [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"parent":591,"menu_order":3,"comment_status":"closed","ping_status":"open","template":"","meta":[],"_links":{"self":[{"href":"https:\/\/hstore.cs.brown.edu\/wp-json\/wp\/v2\/pages\/940"}],"collection":[{"href":"https:\/\/hstore.cs.brown.edu\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/hstore.cs.brown.edu\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/hstore.cs.brown.edu\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/hstore.cs.brown.edu\/wp-json\/wp\/v2\/comments?post=940"}],"version-history":[{"count":40,"href":"https:\/\/hstore.cs.brown.edu\/wp-json\/wp\/v2\/pages\/940\/revisions"}],"predecessor-version":[{"id":2499,"href":"https:\/\/hstore.cs.brown.edu\/wp-json\/wp\/v2\/pages\/940\/revisions\/2499"}],"up":[{"embeddable":true,"href":"https:\/\/hstore.cs.brown.edu\/wp-json\/wp\/v2\/pages\/591"}],"wp:attachment":[{"href":"https:\/\/hstore.cs.brown.edu\/wp-json\/wp\/v2\/media?parent=940"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}