Join us on YugabyteDB Community Slack
Star us on
Get Started
Slack
GitHub
Get Started
v2.13 (latest) v2.12 (stable) v2.8 (earlier version) v2.6 (earlier version) v2.4 (earlier version) v2.2 (earlier version) v2.1 (earlier version) v2.0 (earlier version) v1.3 (earlier version)
  • YUGABYTEDB CORE
    • Quick start
      • 1. Install YugabyteDB
      • 2. Create a local cluster
      • 3. Explore distributed SQL
      • 4. Build an application
        • Java
        • Node.js
        • Go
        • Python
        • Ruby
        • C#
        • PHP
        • C++
        • C
        • Scala
    • Explore
      • SQL features
        • Schemas and Tables
        • Data Types
        • Data Manipulation
        • Queries and Joins
        • Expressions and Operators
        • Stored Procedures
        • Triggers
        • Advanced features
          • Cursors
          • Table Partitioning
          • Views
          • Savepoints
          • Collations
          • Extensions
        • Going beyond SQL
          • Follower reads
          • Tablespaces
      • Fault tolerance
      • Horizontal scalability
        • Scaling Transactions
        • Sharding Data
      • Transactions
        • Distributed Transactions
        • Isolation Levels
        • Explicit Locking
      • Indexes and Constraints
        • Overview
        • Unique Indexes
        • Partial Indexes
        • Expression Indexes
        • Generalized Inverted Indexes
        • Primary Key
        • Foreign Key
        • Other Constraints
      • JSON support
      • Multi-region deployments
        • Sync replication (3+ regions)
        • Async Replication (2+ regions)
        • Row-Level Geo-Partitioning
        • Read replicas
      • Query tuning
        • Introduction
        • Get query statistics using pg_stat_statements
        • Viewing live queries with pg_stat_activity
        • Analyzing queries with EXPLAIN
        • Optimizing YSQL queries using pg_hint_plan
      • Cluster management
        • Point-in-time recovery
      • Security
      • Observability
        • Prometheus Integration
        • Grafana Dashboard
    • Develop
      • Learn app development
        • 1. SQL vs NoSQL
        • 2. Data modeling
        • 3. Data types
        • 4. ACID transactions
        • 5. Aggregations
        • 6. Batch operations
        • 7. Date and time
        • 8. Strings and text
        • 9. TTL for data expiration
      • Real-world examples
        • E-Commerce app
        • IoT fleet management
      • Explore sample apps
      • Best practices
      • Cloud-native development
        • Codespaces
        • Gitpod
    • Migrate
      • Migration process overview
      • Migrate from PostgreSQL
        • Convert a PostgreSQL schema
        • Migrate a PostgreSQL application
        • Export PostgreSQL data
        • Prepare a cluster
        • Import PostgreSQL data
        • Verify Migration
    • Deploy
      • Deployment checklist
      • Manual deployment
        • 1. System configuration
        • 2. Install software
        • 3. Start YB-Masters
        • 4. Start YB-TServers
        • 5. Verify deployment
      • Kubernetes
        • Single-zone
          • Open Source
          • Amazon EKS
          • Google Kubernetes Engine
          • Azure Kubernetes Service
        • Multi-zone
          • Amazon EKS
          • Google Kubernetes Engine
        • Multi-cluster
          • Google Kubernetes Engine
        • Best practices
        • Connect Clients
      • Docker
      • Public clouds
        • Amazon Web Services
        • Google Cloud Platform
        • Microsoft Azure
      • Multi-DC deployments
        • Three+ data center (3DC)
        • Asynchronous Replication
        • Read replica clusters
    • Benchmark
      • TPC-C
      • sysbench
      • YCSB
      • Key-value workload
      • Large datasets
      • Scalability
        • Scaling queries
      • Resilience
        • Jepsen testing
      • Performance Troubleshooting
    • Secure
      • Security checklist
      • Enable Authentication
        • Enable User Authentication
        • Configure ysql_hba_conf_csv
      • Authentication Methods
        • Password Authentication
        • LDAP Authentication
        • Host-Based Authentication
        • Trust Authentication
      • Role-Based Access Control
        • Overview
        • Manage Users and Roles
        • Grant Privileges
        • Row-Level Security (RLS)
        • Column-Level Security
      • Encryption in Transit
        • Create server certificates
        • Enable server-to-server encryption
        • Enable client-to-server encryption
        • Connect to Clusters
        • TLS and authentication
      • Encryption at rest
      • Column-level encryption
      • Audit Logging
        • Configure Audit Logging
        • Session-Level Audit Logging
        • Object-Level Audit Logging
      • Vulnerability disclosure policy
    • Manage
      • Back up and restore
        • Back up data
        • Restore data
        • Point-in-time recovery
        • Snapshot and restore data
      • Migrate data
        • Bulk import
        • Bulk export
      • Change cluster configuration
      • Diagnostics reporting
      • Upgrade a deployment
      • Grow cluster
    • Troubleshoot
      • Troubleshooting
      • Cluster level issues
        • YCQL connection issues
        • YEDIS connection Issues
        • Recover tserver/master
        • Replace a failed YB-TServer
        • Replace a failed YB-Master
        • Manual remote bootstrap when a majority of peers fail
      • Node level issues
        • Check servers
        • Inspect logs
        • System statistics
        • Disk failure
        • Common error messages
    • Contribute
      • Core database
        • Contribution checklist
        • Build the source
        • Configure a CLion project
        • Run the tests
        • Coding style
  • YUGABYTE PLATFORM
    • Overview
      • Install
      • Configure
    • Install Yugabyte Platform
      • Prerequisites
      • Prepare the environment
      • Install software
      • Prepare nodes (on-prem)
      • Uninstall software
    • Configure Yugabyte Platform
      • Create admin user
      • Configure the cloud provider
      • Configure the backup target
      • Configure alerts
    • Create deployments
      • Multi-zone universe
      • Multi-region universe
      • Multi-cloud universe
      • Read replica cluster
      • Asynchronous replication
    • Manage deployments
      • Start and stop processes
      • Add a node
      • Eliminate an unresponsive node
      • Enable high availability
      • Edit configuration flags
      • Edit a universe
      • Delete a universe
      • Configure instance tags
      • Upgrade YugabyteDB software
      • Migrate to Helm 3
    • Back up universes
      • Configure backup storage
      • Back up universe data
      • Restore universe data
      • Schedule data backups
    • Security
      • Security checklist
      • Customize ports
      • LDAP authentication
      • Authorization platform
      • Create a KMS configuration
      • Enable encryption at rest
      • Enable encryption in transit (TLS)
      • Network security
    • Alerts and monitoring
      • Alerts
      • Live Queries dashboard
      • Slow Queries dashboard
    • Troubleshoot
      • Install and upgrade issues
      • Universe issues
    • Administer Yugabyte Platform
      • Back Up Yugabyte Platform
      • Authenticate with LDAP
    • Upgrade Yugabyte Platform
      • Upgrade using Replicated
  • YUGABYTE CLOUD
    • Overview
    • Quick start
      • Create a free cluster
      • Connect to the cluster
      • Create a database
      • Explore distributed SQL
      • Build an application
        • Before you begin
        • Java
        • Go
        • Python
        • Node.js
        • C
        • C++
        • C#
        • Ruby
        • Rust
        • PHP
    • Deploy clusters
      • Planning a cluster
      • Create a free cluster
      • Create a standard cluster
      • VPC network
        • Overview
        • Set up a VPC network
        • VPCs
        • Peering Connections
    • Secure clusters
      • IP allow lists
      • Database authorization
      • Add database users
      • Encryption in transit
      • Audit cloud activity
    • Connect to clusters
      • Cloud Shell
      • Client shell
      • Connect applications
    • Alerts and monitoring
      • Alerts
      • Performance metrics
      • Live queries
      • Slow YSQL queries
      • Cluster activity
    • Manage clusters
      • Backup and restore
      • Scale and configure clusters
      • Create extensions
    • Administer Yugabyte Cloud
      • Manage cloud users
      • Manage billing
      • Cluster costs
    • Example applications
      • Connect a Spring application
      • Connect a YCQL Java application
      • Hasura Cloud
      • Deploy a GraphQL application
    • Security architecture
      • Security architecture
      • Shared responsibility model
    • Troubleshoot
    • Yugabyte Cloud FAQ
    • What's new
  • INTEGRATIONS
    • Apache Kafka
    • Apache Spark
    • JanusGraph
    • KairosDB
    • Presto
    • Metabase
    • WSO2 Identity Server
    • YSQL Loader
    • Yugabyte JDBC Driver
    • Prisma
    • Hasura
      • Application Development
      • Benchmarking
    • Spring Framework
      • Spring Data YugabyteDB
      • Spring Data Cassandra
    • Flyway
    • GORM
    • Liquibase
    • Sequelize
    • SQLAlchemy
    • Entity Framework
    • Django REST framework
  • REFERENCE
    • Architecture
      • Design goals
      • Key concepts
        • Universe
        • YB-TServer Service
        • YB-Master Service
      • Core functions
        • Universe creation
        • Table creation
        • Write IO path
        • Read IO path
        • High availability
      • Layered architecture
      • Query layer
        • Overview
      • DocDB transactions layer
        • Transactions overview
        • Transaction isolation levels
        • Explicit locking
        • Read Committed
        • Single-row transactions
        • Distributed transactions
        • Transactional IO path
      • DocDB sharding layer
        • Hash & range sharding
        • Tablet splitting
        • Colocated tables
      • DocDB replication layer
        • Replication
        • xCluster replication
        • Read replicas
        • Change data capture (CDC)
      • DocDB storage layer
        • Persistence
        • Performance
    • APIs
      • YSQL
        • The SQL language
          • SQL statements
            • ABORT
            • ALTER DATABASE
            • ALTER DEFAULT PRIVILEGES
            • ALTER DOMAIN
            • ALTER GROUP
            • ALTER POLICY
            • ALTER ROLE
            • ALTER SEQUENCE
            • ALTER TABLE
            • ALTER USER
            • ANALYZE
            • BEGIN
            • CALL
            • COMMENT
            • COMMIT
            • COPY
            • CREATE AGGREGATE
            • CREATE CAST
            • CREATE DATABASE
            • CREATE DOMAIN
            • CREATE EXTENSION
            • CREATE FUNCTION
            • CREATE GROUP
            • CREATE INDEX
            • CREATE MATERIALIZED VIEW
            • CREATE OPERATOR
            • CREATE OPERATOR CLASS
            • CREATE POLICY
            • CREATE PROCEDURE
            • CREATE ROLE
            • CREATE RULE
            • CREATE SCHEMA
            • CREATE SEQUENCE
            • CREATE TABLE
            • CREATE TABLE AS
            • CREATE TRIGGER
            • CREATE TYPE
            • CREATE USER
            • CREATE VIEW
            • DEALLOCATE
            • DELETE
            • DO
            • DROP AGGREGATE
            • DROP CAST
            • DROP DATABASE
            • DROP DOMAIN
            • DROP EXTENSION
            • DROP FUNCTION
            • DROP GROUP
            • DROP MATERIALIZED VIEW
            • DROP OPERATOR
            • DROP OPERATOR CLASS
            • DROP OWNED
            • DROP POLICY
            • DROP PROCEDURE
            • DROP ROLE
            • DROP RULE
            • DROP SEQUENCE
            • DROP TABLE
            • DROP TRIGGER
            • DROP TYPE
            • DROP USER
            • END
            • EXECUTE
            • EXPLAIN
            • GRANT
            • INSERT
            • LOCK
            • PREPARE
            • REASSIGN OWNED
            • REFRESH MATERIALIZED VIEW
            • RELEASE SAVEPOINT
            • RESET
            • REVOKE
            • ROLLBACK
            • ROLLBACK TO SAVEPOINT
            • SAVEPOINT
            • SELECT
            • SET
            • SET CONSTRAINTS
            • SET ROLE
            • SET SESSION AUTHORIZATION
            • SET TRANSACTION
            • SHOW
            • SHOW TRANSACTION
            • TRUNCATE
            • UPDATE
            • VALUES
          • WITH clause
            • WITH clause—SQL syntax and semantics
            • recursive CTE
            • case study—traversing an employee hierarchy
            • traversing general graphs
              • graph representation
              • common code
              • undirected cyclic graph
              • directed cyclic graph
              • directed acyclic graph
              • rooted tree
              • Unique containing paths
              • Stress testing find_paths()
            • case study—Bacon Numbers from IMDb
              • Bacon numbers for synthetic data
              • Bacon numbers for IMDb data
        • Data types
          • Array
            • array[] constructor
            • Literals
              • Text typecasting and literals
              • Array of primitive values
              • Row
              • Array of rows
            • FOREACH loop (PL/pgSQL)
            • array of DOMAINs
            • Functions and operators
              • ANY and ALL
              • Array comparison
              • Array slice operator
              • Array concatenation
              • Array properties
              • array_agg(), unnest(), generate_subscripts()
              • array_fill()
              • array_position(), array_positions()
              • array_remove()
              • array_replace() / set value
              • array_to_string()
              • string_to_array()
          • Binary
          • Boolean
          • Character
          • Date and time
            • Conceptual background
            • Timezones and UTC offsets
              • Catalog views
              • Extended_timezone_names
                • Unrestricted full projection
                • Real timezones with DST
                • Real timezones no DST
                • Synthetic timezones no DST
              • Offset/timezone-sensitive operations
                • Timestamptz to/from timestamp conversion
                • Pure 'day' interval arithmetic
              • Four ways to specify offset
                • Name-resolution rules
                  • 1 case-insensitive resolution
                  • 2 ~names.abbrev never searched
                  • 3 'set timezone' string not resolved in ~abbrevs.abbrev
                  • 4 ~abbrevs.abbrev before ~names.name
                  • Helper functions
              • Syntax contexts for offset
              • Recommended practice
            • Typecasting between date-time and text-values
            • Semantics of the date-time data types
              • Date data type
              • Time data type
              • Plain timestamp and timestamptz
              • Interval data type
                • Interval representation
                  • Ad hoc examples
                  • Representation model
                • Interval value limits
                • Declaring intervals
                • Justify() and extract(epoch...)
                • Interval arithmetic
                  • Interval-interval comparison
                  • Interval-interval addition and subtraction
                  • Interval-number multiplication
                  • Moment-moment overloads of "-"
                  • Moment-interval overloads of "+" and "-"
                • Custom interval domains
                • Interval utility functions
            • Typecasting between date-time datatypes
            • Operators
              • Test comparison overloads
              • Test addition overloads
              • Test subtraction overloads
              • Test multiplication overloads
              • Test division overloads
            • General-purpose functions
              • Creating date-time values
              • Manipulating date-time values
              • Current date-time moment
              • Delaying execution
              • Miscellaneous
                • Function age()
                • Function extract() | date_part()
                • Implementations that model the overlaps operator
            • Formatting functions
            • Case study—SQL stopwatch
            • Download & install the date-time utilities
            • ToC
          • JSON
            • JSON literals
            • Primitive and compound data types
            • Code example conventions
            • Indexes and check constraints
            • Functions & operators
              • ::jsonb, ::json, ::text (typecast)
              • ->, ->>, #>, #>> (JSON subvalues)
              • - and #- (remove)
              • || (concatenation)
              • = (equality)
              • @> and <@ (containment)
              • ? and ?| and ?& (key or value existence)
              • array_to_json()
              • jsonb_agg()
              • jsonb_array_elements()
              • jsonb_array_elements_text()
              • jsonb_array_length()
              • jsonb_build_object()
              • jsonb_build_array()
              • jsonb_each()
              • jsonb_each_text()
              • jsonb_extract_path()
              • jsonb_extract_path_text() and json_extract_path_text()
              • jsonb_object()
              • jsonb_object_agg()
              • jsonb_object_keys()
              • jsonb_populate_record()
              • jsonb_populate_recordset()
              • jsonb_pretty()
              • jsonb_set() and jsonb_insert()
              • jsonb_strip_nulls()
              • jsonb_to_record()
              • jsonb_to_recordset()
              • jsonb_typeof()
              • row_to_json()
              • to_jsonb()
          • Money
          • Numeric
          • Range
          • Serial
          • UUID
        • Functions and operators
          • Aggregate functions
            • Informal functionality overview
            • Invocation syntax and semantics
            • grouping sets, rollup, cube
            • Per function signature and purpose
              • avg(), count(), max(), min(), sum()
              • array_agg(), string_agg(), jsonb_agg(), jsonb_object_agg()
              • bit_and(), bit_or(), bool_and(), bool_or()
              • variance(), var_pop(), var_samp(), stddev(), stddev_pop(), stddev_samp()
              • linear regression
                • covar_pop(), covar_samp(), corr()
                • regr_%()
              • mode(), percentile_disc(), percentile_cont()
              • rank(), dense_rank(), percent_rank(), cume_dist()
            • case study—percentile_cont() and the "68–95–99.7" rule
            • case study—linear regression on COVID data
              • Download the COVIDcast data
              • Ingest the COVIDcast data
                • Inspect the COVIDcast data
                • Copy the .csv files to staging tables
                • Check staged data conforms to the rules
                • Join the staged data into a single table
                • SQL scripts
                  • Create cr_staging_tables()
                  • Create cr_copy_from_scripts()
                  • Create assert_assumptions_ok()
                  • Create xform_to_covidcast_fb_survey_results()
                  • ingest-the-data.sql
              • Analyze the COVIDcast data
                • symptoms vs mask-wearing by day
                • Data for scatter-plot for 21-Oct-2020
                • Scatter-plot for 21-Oct-2020
                • SQL scripts
                  • analysis-queries.sql
                  • synthetic-data.sql
          • currval()
          • lastval()
          • nextval()
          • Window functions
            • Informal functionality overview
            • Invocation syntax and semantics
            • Per function signature and purpose
              • row_number(), rank() and dense_rank()
              • percent_rank(), cume_dist() and ntile()
              • first_value(), nth_value(), last_value()
              • lag(), lead()
              • Tables for the code examples
                • table t1
                • table t2
                • table t3
                • table t4
            • case study—analyzing a normal distribution
              • Bucket allocation scheme
              • do_clean_start.sql
              • cr_show_t4.sql
              • cr_dp_views.sql
              • cr_int_views.sql
              • cr_pr_cd_equality_report.sql
              • cr_bucket_using_width_bucket.sql
              • cr_bucket_dedicated_code.sql
              • do_assert_bucket_ok
              • cr_histogram.sql
              • cr_do_ntile.sql
              • cr_do_percent_rank.sql
              • cr_do_cume_dist.sql
              • do_populate_results.sql
              • do_report_results.sql
              • do_compare_dp_results.sql
              • do_demo.sql
              • Reports
                • Histogram report
                • dp-results
                • compare-dp-results
                • int-results
          • yb_hash_code()
        • Extensions
        • Keywords
        • Reserved names
      • YCQL
        • ALTER KEYSPACE
        • ALTER ROLE
        • ALTER TABLE
        • CREATE INDEX
        • CREATE KEYSPACE
        • CREATE ROLE
        • CREATE TABLE
        • CREATE TYPE
        • DROP INDEX
        • DROP KEYSPACE
        • DROP ROLE
        • DROP TABLE
        • DROP TYPE
        • GRANT PERMISSION
        • GRANT ROLE
        • REVOKE PERMISSION
        • REVOKE ROLE
        • USE
        • INSERT
        • SELECT
        • EXPLAIN
        • UPDATE
        • DELETE
        • TRANSACTION
        • TRUNCATE
        • Simple expressions
        • Subscripted expressions
        • Function call
        • Operators
        • BLOB
        • BOOLEAN
        • Collection
        • FROZEN
        • INET
        • Integer and counter
        • Non-integer
        • TEXT
        • DATE, TIME, and TIMESTAMP
        • UUID and TIMEUUID
        • JSONB
        • Date and time
        • BATCH
    • CLIs
      • yb-ctl
      • yb-docker-ctl
      • ysqlsh
      • ycqlsh
      • yb-admin
      • yb-ts-cli
      • ysql_dump
      • ysql_dumpall
    • Configuration
      • yb-tserver
      • yb-master
      • yugabyted
      • Default ports
    • Drivers
      • Client drivers for YSQL
      • Client drivers for YCQL
    • Connectors
      • Kafka Connect YugabyteDB
    • Third party tools
      • Arctype
      • DBeaver
      • DbSchema
      • pgAdmin
      • SQL Workbench/J
      • TablePlus
      • Visual Studio Code
    • Sample datasets
      • Chinook
      • Northwind
      • PgExercises
      • SportsDB
      • Retail Analytics
  • RELEASES
    • Releases overview
      • v2.13 series (latest)
      • v2.12 series (stable)
      • v2.11 series
      • v2.9 series
      • v2.8 series
      • v2.7 series
      • v2.6 series
      • v2.5 series
      • v2.4 series
      • v2.3 series
      • v2.2 series
      • v2.1 series
      • v2.0 series
      • v1.3 series
      • v1.2 series
    • Release versioning
  • FAQ
    • Comparisons
      • Amazon Aurora
      • Google Cloud Spanner
      • CockroachDB
      • TiDB
      • Vitess
      • MongoDB
      • FoundationDB
      • Amazon DynamoDB
      • Azure Cosmos DB
      • Apache Cassandra
      • PostgreSQL
      • Redis in-memory store
      • Apache HBase
    • General FAQ
    • Operations FAQ
    • API compatibility FAQ
    • Yugabyte Platform FAQ
  • MISC
    • YEDIS
      • Quick start
      • Develop
        • Build an application
        • C#
        • C++
        • Go
        • Java
        • NodeJS
        • Python
      • API reference
        • APPEND
        • AUTH
        • CONFIG
        • CREATEDB
        • DELETEDB
        • LISTDB
        • SELECT
        • DEL
        • ECHO
        • EXISTS
        • EXPIRE
        • EXPIREAT
        • FLUSHALL
        • FLUSHDB
        • GET
        • GETRANGE
        • GETSET
        • HDEL
        • HEXISTS
        • HGET
        • HGETALL
        • HINCRBY
        • HKEYS
        • HLEN
        • HMGET
        • HMSET
        • HSET
        • HSTRLEN
        • HVALS
        • INCR
        • INCRBY
        • KEYS
        • MONITOR
        • PEXPIRE
        • PEXPIREAT
        • PTTL
        • ROLE
        • SADD
        • SCARD
        • RENAME
        • SET
        • SETEX
        • PSETEX
        • SETRANGE
        • SISMEMBER
        • SMEMBERS
        • SREM
        • STRLEN
        • ZRANGE
        • TSADD
        • TSCARD
        • TSGET
        • TSLASTN
        • TSRANGEBYTIME
        • TSREM
        • TSREVRANGEBYTIME
        • TTL
        • ZADD
        • ZCARD
        • ZRANGEBYSCORE
        • ZREM
        • ZREVRANGE
        • ZSCORE
        • PUBSUB
        • PUBLISH
        • SUBSCRIBE
        • UNSUBSCRIBE
        • PSUBSCRIBE
        • PUNSUBSCRIBE
    • Legal
      • Third party software
> Architecture > DocDB storage layer >

Performance

Report a doc issue Suggest new content
  • Enhancements to RocksDB
    • Efficiently model documents
    • Raft vs RocksDB WAL logs
    • MVCC at a higher layer
    • Backups and snapshots
  • Data model aware Bloom filters
  • Range query optimizations
  • Efficient memory usage
    • Server-global block cache
    • Server-global memstore limits
  • Scan-resistant block cache

DocDB uses a highly customized version of RocksDB, a log-structured merge tree (LSM) based key-value store.

DocDB Document Storage Layer

A number of enhancements or customizations were done to RocksDB in order to achieve scalability and performance. These are described below.

Enhancements to RocksDB

Efficiently model documents

To implement a flexible data model—such as a row (comprising of columns), or collections types (such as list, map, set) with arbitrary nesting—on top of a key-value store, but, more importantly, to implement efficient operations on this data model such as:

  • fine-grained updates to a part of the row or collection without incurring a read-modify-write penalty of the entire row or collection
  • deleting/overwriting a row or collection/object at an arbitrary nesting level without incurring a read penalty to determine what specific set of KVs need to be deleted
  • enforcing row/object level TTL based expiration

A tighter coupling into the “read/compaction” layers of the underlying RocksDB key-value store is needed. Yugabyte uses RocksDB as an append-only store and operations, such as row or collection delete, are modeled as an insert of a special “delete marker”. This allows deleting an entire subdocument efficiently by just adding one key-value pair to RocksDB. Read hooks automatically recognize these markers and suppress expired data. Expired values within the subdocument are cleaned up/garbage collected by our customized compaction hooks.

Raft vs RocksDB WAL logs

DocDB uses Raft for replication. Changes to the distributed system are already recorded or journaled as part of Raft logs. When a change is accepted by a majority of peers, it is applied to each tablet peer’s DocDB, but the additional WAL mechanism in RocksDB (under DocDB) is unnecessary and adds overhead. For correctness, in addition to disabling the WAL mechanism in RocksDB, YugabyteDB tracks the Raft “sequence id” up to which data has been flushed from RocksDB’s memtables to SSTable files. This ensures that we can correctly garbage collect the Raft WAL logs as well as replay the minimal number of records from Raft WAL logs on a server crash or restart.

MVCC at a higher layer

Multi-version concurrency control (MVCC) in DocDB is done at a higher layer, and does not use the MVCC mechanism of RocksDB.

The mutations to records in the system are versioned using hybrid-timestamps maintained at the YBase layer. As a result, the notion of MVCC as implemented in a vanilla RocksDB (using sequence IDs) is not necessary and only adds overhead. YugabyteDB does not use RocksDB’s sequence IDs, and instead uses hybrid-timestamps that are part of the encoded key to implement MVCC.

Backups and snapshots

These need to be higher level operations that take into consideration data in DocDB as well as in the Raft logs to get a consistent cut of the state of the system.

Data model aware Bloom filters

The keys stored by DocDB in RocksDB consist of a number of components, where the first component is a "document key", followed by a few scalar components, and finally followed by a timestamp (sorted in reverse order).

The bloom filter needs to be aware of what components of the key need be added to the bloom so that only the relevant SSTable files in the LSM store are looked up during a read operation.

In a traditional KV store, range scans do not make use of bloom filters because exact keys that fall in the range are unknown. However, we have implemented a data-model aware bloom filter, where range scans within keys that share the same hash component can also benefit from Bloom filters. For example, a scan to get all the columns within row or all the elements of a collection can also benefit from bloom filters.

Range query optimizations

The ordered (or range) components of the compound-keys in DocDB frequently have a natural order. For example, it may be an int that represents a message ID (for a messaging application) or a timestamp (for a IoT/time series use case). See example below. By keeping hints with each SSTable file in the LSM store about the minimum and maximum values for these components of the “key”, range queries can intelligently prune away the lookup of irrelevant SSTable files during the read operation.

SELECT message_txt
  FROM messages
WHERE user_id = 17
  AND message_id > 50
  AND message_id < 100;

Or, in the context of a time-series application:

SELECT metric_value
  FROM metrics
WHERE metric_name = ’system.cpu’
  AND metric_timestamp < ?
  AND metric_timestamp > ?

Efficient memory usage

There are two instances where memory usage across components in a manner that is global to the server yields benefits, as described below.

Server-global block cache

A shared block cache is used across the DocDB/RocksDB instances of all the tablets hosted by a YB-TServer. This maximizes the use of memory resources, and avoids creating silos of cache that each need to be sized accurately for different user tables.

Server-global memstore limits

While per-memstore flush sizes can be configured, in practice, because the number of memstores may change over time as users create new tables, or tablets of a table move between servers, we have enhanced the storage engine to enforce a global memstore threshold. When such a threshold is reached, selection of which memstore to flush takes into account what memstores carry the oldest records (determined using hybrid timestamps) and therefore are holding up Raft logs and preventing them from being garbage collected.

Scan-resistant block cache

We have enhanced RocksDB’s block cache to be scan resistant. The motivation was to prevent operations such as long-running scans (e.g., due to an occasional large query or background Spark jobs) from polluting the entire cache with poor quality data and wiping out useful/hot data.

  • Enhancements to RocksDB
    • Efficiently model documents
    • Raft vs RocksDB WAL logs
    • MVCC at a higher layer
    • Backups and snapshots
  • Data model aware Bloom filters
  • Range query optimizations
  • Efficient memory usage
    • Server-global block cache
    • Server-global memstore limits
  • Scan-resistant block cache
Ask our community
  • Slack
  • Github
  • Forum
  • StackOverflow
Yugabyte
Contact Us
Copyright © 2017-2022 Yugabyte, Inc. All rights reserved.