1.0
Table Of Contents
- Contents
- About the SQLFire User's Guide
- Supported Configurations and System Requirements
- Getting Started with vFabric SQLFire
- Managing Your Data in vFabric SQLFire
- Designing vFabric SQLFire Databases
- Using Server Groups to Manage Data
- Partitioning Tables
- Replicating Tables
- Estimating Memory Requirements
- Using Disk Stores to Persist Data
- Exporting and Importing Data with vFabric SQLFire
- Using Table Functions to Import Data as a SQLFire Tables
- Developing Applications with SQLFire
- Starting SQLFire Servers with the FabricServer Interface
- Developing Java Clients and Peers
- Configuring SQLFire as a JDBC Datasource
- Storing and Loading JAR Files in SQLFire
- Developing ADO.NET Client Applications
- About the ADO.NET Driver
- ADO.NET Driver Classes
- Installing and Using the ADO.NET driver
- Connecting to SQLFire with the ADO.NET Driver
- Managing Connections
- Executing SQL Commands
- Working with Result Sets
- Storing a Table
- Storing Multiple Tables
- Specifying Command Parameters with SQLFParameter
- Updating Row Data
- Adding Rows to a Table
- Managing SQLFire Transactions
- Performing Batch Updates
- Generic Coding with the SQLFire ADO.NET Driver
- Using SQLFire.NET Designer
- Understanding the Data Consistency Model
- Using Distributed Transactions in Your Applications
- Using Data-Aware Stored Procedures
- Using the Procedure Provider API
- Using the Custom Result Processor API
- Programming User-Defined Types
- Using Result Sets and Cursors
- Caching Data with vFabric SQLFire
- Deploying vFabric SQLFire
- SQLFire Deployment Models
- Steps to Plan and Configure a Deployment
- Configuring Discovery Mechanisms
- Starting and Configuring SQLFire Servers
- Configuring Multi-site (WAN) Deployments
- Configuring Authentication and Authorization
- Configuring User Authentication
- User Names in Authentication and Authorization
- Configuring User Authorization
- Configuring Network Encryption and Authentication with SSL/TLS
- Managing and Monitoring vFabric SQLFire
- Configuring and Using SQLFire Log Files
- Querying SQLFire System Tables and Indexes
- Evaluating Query Execution Plans and Query Statistics
- Overriding Optimizer Choices
- Evaluating System and Application Performance
- Using Java Management Extensions (JMX)
- Best Practices for Tuning Performance
- Detecting and Handling Network Segmentation ("Split Brain")
- vFabric SQLFire Reference
- Configuration Properties
- JDBC API
- Mapping java.sql.Types to SQL Types
- java.sql.BatchUpdateException Class
- java.sql.Connection Interface
- java.sql.DatabaseMetaData Interface
- java.sql.Driver Interface
- java.sql.DriverManager.getConnection Method
- java.sql.PreparedStatement Interface
- java.sql.ResultSet Interface
- java.sql.SavePoint Class
- java.sql.SQLException Class
- java.sql.Statement Class
- javax.sql.XADataSource
- sqlf Launcher Commands
- sqlf backup
- sqlf compact-all-disk-stores
- sqlf compact-disk-store
- sqlf encrypt-password
- sqlf install-jar
- sqlf list-missing-disk-stores
- sqlf locator
- sqlf Logging Support
- sqlf merge-logs
- sqlf remove-jar
- sqlf replace-jar
- sqlf revoke-missing-disk-store
- sqlf server
- sqlf shut-down-all
- sqlf stats
- sqlf validate-disk-store
- sqlf version
- sqlf write-data-dtd-to-file
- sqlf write-data-to-db
- sqlf write-data-to-xml
- sqlf write-schema-to-db
- sqlf write-schema-to-sql
- sqlf write-schema-to-xml
- sqlf Interactive Commands
- absolute
- after last
- async
- autocommit
- before first
- close
- commit
- connect
- connect client
- connect peer
- describe
- disconnect
- driver
- elapsedtime
- execute
- exit
- first
- get scroll insensitive cursor
- GetCurrentRowNumber
- help
- last
- LocalizedDisplay
- MaximumDisplayWidth
- next
- prepare
- previous
- protocol
- relative
- remove
- rollback
- run
- set connection
- show
- wait for
- SQLFire API
- SQL Language Reference
- Keywords and Identifiers
- SQL Statements
- SQL Clauses
- SQL Expressions
- JOIN Operations
- Built-in Functions
- Standard Built-in Functions
- Aggregates (set functions)
- ABS or ABSVAL function
- ACOS function
- ASIN function
- ATAN function
- ATAN2 function
- AVG function
- BIGINT function
- CASE expressions
- CAST function
- CEIL or CEILING function
- CHAR function
- COALESCE function
- Concatenation operator
- COS function
- COSH function
- COT function
- COUNT function
- COUNT(*) function
- CURRENT DATE function
- CURRENT_DATE function
- CURRENT ISOLATION function
- CURRENT_ROLE function
- CURRENT SCHEMA function
- CURRENT TIME function
- CURRENT_TIME function
- CURRENT TIMESTAMP function
- CURRENT_TIMESTAMP function
- CURRENT_USER function
- DATE function
- DAY function
- DEGREES function
- DOUBLE function
- EXP function
- FLOOR function
- HOUR function
- INTEGER function
- LCASE or LOWER function
- LENGTH function
- LN or LOG function
- LOG10 function
- LOCATE function
- LTRIM function
- MAX function
- MIN function
- MINUTE function
- MOD function
- MONTH function
- NULLIF expressions
- PI function
- RADIANS function
- RANDOM function
- RAND function
- RTRIM function
- SECOND function
- SESSION_USER function
- SIGN function
- SIN function
- SINH function
- SMALLINT function
- SQRT function
- SUBSTR function
- SUM function
- TAN function
- TANH function
- TIME function
- TIMESTAMP function
- TRIM function
- UCASE or UPPER function
- USER function
- VARCHAR function
- XMLEXISTS operator
- XMLPARSE operator
- XMLQUERY operator
- XMLSERIALIZE operator
- YEAR function
- SQLFire Built-in Functions
- Standard Built-in Functions
- Built-in System Procedures
- Standard Built-in Procedures
- SYSCS_UTIL.EMPTY_STATEMENT_CACHE
- SYSCS_UTIL.EXPORT_QUERY
- SYSCS_UTIL.EXPORT_TABLE
- SYSCS_UTIL.IMPORT_DATA
- SYSCS_UTIL.IMPORT_DATA_EX
- SYSCS_UTIL.IMPORT_DATA_LOBS_FROM_EXTFILE system procedure
- SYSCS_UTIL.IMPORT_TABLE
- SYSCS_UTIL.IMPORT_TABLE_EX
- SYSCS_UTIL.IMPORT_TABLE_LOBS_FROM_EXTFILE
- SYSCS_UTIL.SET_EXPLAIN_CONNECTION
- SYSCS_UTIL.SET_STATISTICS_TIMING
- JAR Installation Procedures
- Callback Configuration Procedures
- Heap Eviction Configuration Procedures
- WAN Configuration Procedures
- Standard Built-in Procedures
- Data Types
- SQL Standards Conformance
- System Tables
- ASYNCEVENTLISTENERS table
- GATEWAYRECEIVERS table
- GATEWAYSENDERS table
- MEMBERS system table
- MEMORYANALYTICS system table
- STATEMENTPLANS system table
- SYSALIASES system table
- SYSCHECKS system table
- SYSCOLPERMS system table
- SYSCOLUMNS system table
- SYSCONGLOMERATES system table
- SYSCONSTRAINTS system table
- SYSDEPENDS system table
- SYSDISKSTORES system table
- SYSFILES system table
- SYSFOREIGNKEYS system table
- SYSKEYS system table
- SYSROLES system table
- SYSROUTINEPERMS system table
- SYSSCHEMAS system table
- SYSSTATEMENTS system table
- SYSSTATISTICS system table
- SYSTABLEPERMS system table
- SYSTABLES system table
- SYSTRIGGERS system table
- SYSVIEWS system table
- Exception Messages and SQL States
- ADO.NET Driver Reference
- SQLFire Data Types in ADO.NET
- VMware.Data.SQLFire.BatchUpdateException
- VMWare.Data.SQLFire.SQLFClientConnection
- VMware.Data.SQLFire.SQLFCommand
- VMware.Data.SQLFire.SQLFCommandBuilder
- VMware.Data.SQLFire.SQLFType
- VMware.Data.SQLFire.SQLFDataAdapter
- VMware.Data.SQLFire.SQLFDataReader
- VMware.Data.SQLFire.SQLFException
- VMware.Data.SQLFire.SQLFParameter
- VMware.Data.SQLFire.SQLFParameterCollection
- VMware.Data.SQLFire.SQLFTransaction
- vFabric SQLFire Limitations
- Troubleshooting Common Problems
- vFabric SQLFire Glossary
- Index
Avoiding Seeks
Random access on disk, which causes disk heads to seek for hundreds of concurrent thread, is probably the single
biggest reason why traditional databases do not scale. Average disk seek times today are still 2ms or higher.
SQLFire manages most (or all) of the data in cluster memory, and all reads are served without navigating through
BTree-based indexes and data files on disk. This is the case when data is persistent. Note, however, that in
overflow-only mode, data files on disk are accessed as necessary.
Buffered Logging
When writes do occur, SQLFire simply logs the operations to disk in "append-only" oplog files. By appending,
SQLFire can continuously write to consecutive sectors on disk without requiring disk head movement. SQLFire
flushes writes to the OS buffer rather than 'fsync' all the way to disk. The writes are buffered by the IO subsystem
in the kernel, which allows the IO scheduler to merge and sort disk writes to achieve the highest possible disk
throughput. Write requests need not initiate any disk I/O until some time in the future.
Thus, from the perspective of a user application, write requests stream at much higher speeds, unencumbered
by the performance of the disk. Risk of data loss due to sudden failures at a hardware level are mitigated by
having multiple members writing in parallel to disk. In fact, it is assumed that hardware will fail, especially in
large clusters and data centers, and that software needs to take these failures into account. The SQLFire system
is designed to recover in parallel from disk and to guarantee data consistency when data copies on disk do not
agree with each other. Each member of the distributed system logs membership changes to its persistent files
and uses this information during recovery to determine the replica that has the latest changes, and members
automatically synchronize these changes at startup.
Guidelines for Designing Disk Stores
Work with your system designers and developers to plan for disk storage requirements in testing and production
database systems. Work with host system administrators to determine where to place your disk store directories
on each peer computer.
vFabric SQLFire User's Guide74
Managing Your Data in vFabric SQLFire