Fact-checked by Grok 2 weeks ago

SingleStore

SingleStore is a distributed, relational SQL database management system (RDBMS) that combines transactional and analytical processing in a single platform, enabling ingestion, querying, and AI-driven applications at . Founded in 2011 as MemSQL by co-founders including Nikita Shamgunov and Eric Frenkiel through , the company initially focused on in-memory rowstore databases for high-speed (OLTP). In 2020, it rebranded to SingleStore to better reflect its evolution into a converged data platform supporting both OLTP and (OLAP) workloads across structured, semi-structured, and . Headquartered in , , and led by CEO Raj Verma since 2019, SingleStore has raised significant funding, including a $116 million round in 2022 led by , and in October 2025 completed a growth buyout led by Vector Capital to accelerate its enterprise AI and solutions. The platform's core architecture features Universal Storage, which integrates an in-memory rowstore for low-latency transactions with an on-disk columnstore for efficient , allowing sub-second query responses on massive sets. It supports multi-model handling, including documents, time-series, geospatial, , and vector embeddings for and applications, all queried via standard ANSI SQL. SingleStore optimizes performance through techniques like just-in-time code generation for queries and across clusters, making it suitable for highly concurrent workloads in industries such as , healthcare, and retail. Deployable as SingleStore Helios—a fully managed offering on AWS, , and Cloud—or as self-managed on-premises/ setups, the platform simplifies data architectures by eliminating the need for separate ETL pipelines or data warehouses, potentially reducing by up to 75%. Notable customers include , , , , , and , leveraging it for real-time insights and AI innovation. As of November 2025, SingleStore continues to emphasize AI-native capabilities, with expansions into markets like to support global enterprise adoption.

Overview

Core Functionality

SingleStore is a distributed, relational (RDBMS) that provides full ANSI , enabling , transactional , and querying for data-intensive applications. It supports standard , including joins, filters, and analytical functions, while maintaining compatibility with existing SQL drivers and tools. The database is optimized for mixed (OLTP) and (OLAP) workloads, delivering low-latency query responses, often in milliseconds, even under high concurrency and across petabyte-scale datasets. This performance stems from its ability to handle analytics and operational workloads in a unified , reducing the need for separate systems. Originally launched as MemSQL, the company rebranded to SingleStore in October 2020 to emphasize its vision of a single database that consolidates transactional and analytical processing, thereby simplifying data architectures and eliminating silos between OLTP and OLAP databases. SingleStore achieves this through basic operational modes that leverage for rapid query execution and persistent on-disk storage for data durability and recovery.

Supported Data Models

SingleStore supports a range of models, enabling it to handle diverse workloads within a unified SQL-based system. Originally focused on relational , the database evolved into a multi-model platform with enhancements including the general availability of in 2024 and the native data type in version 8.5 (January 2024), allowing a single instance to manage structured, semi-structured, and specialized without requiring separate databases. At its core, SingleStore provides full support for relational tables using standard SQL for structured data storage and querying, including transactions and joins across large datasets. It also natively handles JSON documents through a dedicated data type that accommodates maps, arrays, and nested structures, with built-in functions for extraction, modification, and aggregation. For geospatial data, SingleStore offers spatial functions and types like GeographyPoint, enabling operations on points, lines, and polygons; while lacking native parsing, it integrates GeoJSON via JSON support and computed columns for flexible ingestion and querying. Additionally, SingleStore can function as a key-value store by leveraging rowstore tables with primary keys and varbinary or text columns for values, supporting high-throughput inserts and lookups akin to systems. It includes a vector data type for storing embeddings, with similarity search functions like cosine and to facilitate AI applications. In November 2025, SingleStore introduced AI Functions, enabling developers to call generative AI models and generate embeddings directly within SQL queries for enhanced AI application development. For time series data, the platform provides specialized functions such as TIME_BUCKET for aggregation and SERIES_TIMESTAMP for efficient ingestion, optimized for rowstore or columnstore tables with timestamp columns. Semi-structured data, including JSON and vectors, integrates seamlessly with SQL queries, allowing relational joins, filtering, and analytics on mixed formats. Full-text search is available on JSON attributes and vector embeddings, enhancing discoverability in document-heavy or AI-driven datasets. This multi-model approach supports use cases like real-time analytics on IoT-generated time series data for monitoring sensor streams or AI-driven vector similarity searches for recommendation engines and semantic retrieval.

Company History

Founding and Early Milestones

SingleStore was founded in January 2011 by Eric Frenkiel, Nikita Shamgunov, and Adam Prout as MemSQL, with an initial focus on building an for operational (OLTP) to enable high-performance, handling. The founders, drawing from their experience at companies like , aimed to combine the speed of in-memory computing with SQL compatibility to address limitations in traditional databases for modern applications. Headquartered in , , the company began operations as a graduate, establishing its core technology around lock-free data structures and distributed architecture for scalable performance. On April 23, 2013, MemSQL launched its first generally available version, introducing a distributed relational database that supported wire-compatibility with MySQL and enabled horizontal scaling for OLTP workloads across clusters. This release marked the company's entry into the market as a high-speed, in-memory solution capable of handling real-time analytics and transactions, positioning it as an alternative to specialized NoSQL systems while retaining relational features. A pivotal early milestone came in with the addition of columnstore functionality, which extended the platform to support analytical (OLAP) queries efficiently by storing data in columnar format for and faster aggregation, bridging OLTP and OLAP in a single system. This enhancement enabled high-speed data ingest rates, up to 1 TB per hour in benchmarks, facilitating real-time pipelines for applications. By 2017, MemSQL had forged key partnerships, including with , to integrate its database with enterprise infrastructure for optimized deployment in production environments. The company also expanded its workforce to around 100 employees by 2018, supporting growth in engineering and customer adoption.

Rebranding and Expansion

On October 27, 2020, the company formerly known as MemSQL rebranded to SingleStore to better align its name with its expanded capabilities as a unified platform for both transactional (OLTP) and analytical (OLAP) workloads, moving beyond its original focus on in-memory databases. This change emphasized the platform's universal storage architecture, enabling efficient handling of diverse data types across multi-cloud and on-premises environments without data replication, thereby broadening its appeal in the data management market. Following the rebrand, SingleStore pursued aggressive global expansion, opening offices in in 2021, in 2022, and in 2023 to support growing international demand. By April 2022, the company's employee count had reached nearly 400, reflecting rapid scaling in engineering, sales, and operations teams. These moves were bolstered by strategic hires, including key executives for revenue, innovation, and marketing, as well as enhanced presence in EMEA and . In April 2023, SingleStore launched real-time AI features, including initial vector search capabilities, to enable faster processing for AI-driven applications. This was followed in May 2023 by the introduction of generative AI (GenAI) tools, such as enhanced analytics integrations to support AI model development and deployment. Key partnerships accelerated this momentum: in July 2023, SingleStore announced a collaboration with AWS to advance real-time data analytics and AI workloads on cloud infrastructure. In August 2023, IBM integrated SingleStore with its watsonx.ai platform to facilitate generative AI application building using real-time data. Further advancements included the general availability of API support via SingleStore Kai in January 2024, allowing over 100x faster analytics on data without application changes. In September 2024, SingleStore partnered with for bi-directional integration with , enabling seamless data sharing and real-time AI processing within Snowflake's ecosystem while maintaining governance. The year culminated in the October 2024 acquisition of BryteFlow, an data integration platform, to strengthen from enterprise sources like and , thereby accelerating real-time analytics and GenAI adoption. In August 2025, SingleStore expanded its global presence by opening an office in , marking its eighth office worldwide and targeting growing demand in the region for enterprise solutions. These developments marked a strategic pivot toward cloud-native, -optimized databases, with SingleStore positioning itself as a frontrunner in as of late 2025 through enhanced ingestion, vector processing, and ecosystem integrations.

Funding Rounds

SingleStore has raised approximately $464 million in equity funding across 11 rounds through October 2022, with key investments supporting product , expansion, and market growth. In September 2025, the company underwent a growth led by Capital Management, which acquired a stake in a speculated at around $500 million; this move provided capital for accelerated growth in and real-time data solutions while retaining investments from long-term shareholders such as Google Ventures, Capital, , and REV Venture Partners. The , expected to close in Q4 2025, represented a strategic alternative to traditional rounds or an IPO. Prominent investors include , Accel, Google Ventures (GV), , and Prosperity7 Ventures, alongside others such as , Capital, and . The company's funding history began with a in January 2013, raising $5 million led by Data Collective (DCVC) and IA Ventures to fund initial platform development and engineering team building. In January 2014, SingleStore secured $35 million in a Series B round led by Accel, with participation from , aimed at accelerating distributed technology for real-time analytics. Subsequent rounds built on this foundation. The Series C in April 2016 raised $36 million, led by Caffeinated Capital and REV Venture Partners, to drive growth in real-time analytics databases. The Series D in May 2018 brought in $30 million, led by GV and Glynn Capital Management, to enhance scalability for insight-driven enterprises. Later-stage funding accelerated amid cloud and AI focus. In December 2020, a Series E round of $80 million was led by Insight Partners, with participation from Dell Technologies Capital and others, supporting global expansion and integration of disparate data silos following the company's rebranding from MemSQL. The Series F in September 2021 raised another $80 million, again led by Insight Partners and Hewlett Packard Pathfinder, to fuel triple-digit cloud growth and strategic initiatives. In 2022, funding reached its peak with two significant raises. A $116 million round in July, led by and including Sanabil Investments, advanced real-time data platform capabilities. This was followed in October by a Series F-2 extension of $30 million from new investor Prosperity7 Ventures (the venture arm of ), bringing the total for that extended round to $146 million and supporting product enhancements, sales investments, and geographic expansion into and Asia. These investments have primarily been directed toward research and development in distributed systems, cloud-native expansions like SingleStore Helios, and emerging features to power data-intensive applications.

Products and Services

SingleStore Database Engine

SingleStore DB serves as the flagship product of SingleStore, functioning as a distributed (RDBMS) that provides high-performance for both transactional and analytical workloads. It achieves ANSI SQL , enabling seamless use of standard for operations such as joins, aggregations, and window functions, while maintaining compatibility with the wire protocol to integrate with existing tools and applications. This design supports real-time ingestion and querying of large-scale datasets, making it suitable for applications requiring low-latency on operational data. At its core, SingleStore DB operates through a distributed architecture comprising aggregator nodes and leaf nodes. Aggregator nodes handle query coordination, parsing, optimization, and result aggregation across the , ensuring efficient distribution of workloads. Leaf nodes, in contrast, manage , partitioning, and local query execution, allowing for horizontal scaling by adding more nodes to increase capacity and performance. This separation enables the system to process complex queries in parallel while maintaining data consistency. SingleStore DB offers flexible licensing options to accommodate various use cases. The free edition is an unlimited-time trial of the edition, restricted to a total capacity of 8 vCPU and 32 GB RAM across the as of July 2025, providing core functionality for development and small-scale testing. The edition extends this for environments, incorporating advanced features like audit logging and compliance certifications (e.g., SOC 2, GDPR), along with premium support and unlimited scaling capabilities. Key integration tools enhance SingleStore DB's usability for data workflows. SingleStore Pipelines facilitate extract, transform, and load (ETL) processes by enabling continuous data ingestion from sources such as for and for batch files, with built-in transformation capabilities to prepare data for analysis. Additionally, it supports for natural language querying of vectorized data and offers native compatibility with tools like Tableau, allowing direct connections via JDBC or ODBC drivers for visualization and reporting. For cloud deployments, the engine can be hosted via SingleStore Helios, the managed service offering.

SingleStore Helios

SingleStore Helios is a fully managed database-as-a-service (DBaaS) offering launched in September 2019, providing elastic scalability and for modern applications. It is available on major public s including , , and , enabling users to deploy clusters without managing underlying infrastructure. Key features include autoscaling, which automatically adjusts compute resources based on workload demand to optimize performance and cost, and zero-downtime upgrades that ensure continuous availability during maintenance. In 2024, SingleStore introduced a "Bring Your Own " (BYOC) option, allowing private deployments within a customer's own for enhanced and . Additionally, serverless compute capabilities, such as Functions, support variable workloads by executing code without provisioning servers. The service builds on the core SingleStore database engine, delivering distributed SQL processing in a cloud-native environment. Pricing follows a pay-per-use model, charged based on compute units (measured in credits per hour) and storage (per GB-month), with granular metering by the second to align costs with actual usage. A free shared tier is available for development and testing, offering limited resources without upfront commitment. Helios reduces operational overhead by handling provisioning, patching, backups, and monitoring automatically, allowing teams to focus on application development. Integrated monitoring provides real-time insights into performance metrics, while tools like SingleStore Flow enable seamless from on-premises or other systems with minimal disruption. This managed approach supports scalable, low-latency workloads for real-time analytics and AI applications.

Management Tools

SingleStore Studio is a web-based graphical user interface designed for interacting with SingleStore clusters in self-managed deployments. It serves as a visual SQL client, enabling users to execute queries, view results in tabular and graphical formats, and perform schema exploration through SQL commands. The tool supports performance visualization via workload monitoring features that analyze query execution details, resource utilization, and cluster health metrics. In SingleStore Helios, the cloud service, management extends to Data Studio, which includes support for Jupyter notebooks allowing development with both SQL and code directly connected to workspaces. This facilitates management, ad-hoc querying, and in a notebook environment. SingleStore Tools provide a (CLI) suite for administering self-managed clusters, encompassing deployment, configuration, backups, and diagnostics. Key components include the singlestoredb-toolbox package, which offers commands such as singlestore-admin for operational tasks like starting, stopping, and reconfiguring nodes, as well as memsqlctl for lower-level management. Historical operations, such as generating diagnostic reports for , are handled through tools like sdb-report, which captures and performance data for analysis. These utilities are packaged for , RPM, and tarball distributions, supporting scripted automation in distributed environments. SingleStore's built-in monitoring capabilities capture cluster events and metrics via a dedicated metrics database and pipelines, integrated with Grafana for visualization. It tracks query latency through historical workload analysis, including execution times and run counts for parameterized queries, and monitors resource usage such as CPU, memory, and disk I/O per node. Alerting is supported through configurable thresholds in the monitoring setup, with compatibility for exporting metrics in Prometheus format starting from version 7.3, enabling integration with external observability tools for proactive notifications on issues like high latency or resource saturation. In 2024, SingleStore introduced enhanced autoscaling tools for users, allowing programmatic adjustment of compute resources based on workload demands to maintain performance without manual intervention; autoscaling is now generally available as of 2025.

Architecture

Data Storage Formats

SingleStore employs a dual storage architecture that combines rowstore and columnstore formats to optimize for diverse workloads, enabling efficient handling of both transactional and analytical queries within the same database. The rowstore format stores data in a row-oriented layout entirely in memory, facilitating rapid inserts, updates, and point lookups ideal for (OLTP) scenarios. In contrast, the columnstore format, also known as Universal Storage, persists data on disk in a columnar orientation, supporting high compression and fast aggregations for (OLAP) tasks. This hybrid approach allows tables to be defined as either rowstore or columnstore based on workload needs, with columnstore serving as the default since version 7.3. The rowstore uses a row-wise storage model where each row's fields are kept together in , minimizing for transactional operations and enabling lock-free concurrency through skiplist and indexes for efficient scans and exact matches. This format excels in high-concurrency environments with frequent writes and deletes, as data remains fully in memory without routine disk I/O during queries. For persistence, rowstore data is synced to disk via periodic checkpoints that capture the table's state, combined with a write-ahead for recovery, ensuring durability without compromising in-memory performance. Columnstore organizes data into row segments—groups of sorted rows—and column segments that store values for each column within those rows, allowing selective access to only relevant columns during scans and aggregations. techniques, such as dictionary encoding for repeating values, reduce storage footprint significantly, while like min/max bounds per segment enables elimination of irrelevant data blocks to accelerate OLAP queries. Tables in columnstore are automatically sorted by one or more sort key columns defined in the table creation statement, optimizing data layout for common access patterns and further enhancing scan efficiency. A hidden in-memory rowstore buffer handles small or incremental inserts before merging into the on-disk columnstore, bridging operational and analytical workloads seamlessly. This dual-format system supports hybrid usage where a single table type—typically columnstore—can manage both OLTP and OLAP demands through appropriate indexing, while rowstore is reserved for pure transactional tables requiring sub-millisecond response times. Persistence in columnstore occurs through checkpoints that write compressed blobs to disk, maintaining across restarts. Overall, the architecture scales to petabyte-level datasets without performance degradation, leveraging distributed nodes for storage and processing.

Indexing Strategies

SingleStore employs a variety of indexing strategies to optimize query performance across its rowstore and columnstore storage formats, enabling efficient data access for both transactional and analytical workloads. These indexes are designed to support fast lookups, range scans, and specialized searches while maintaining low overhead during . Primary indexes form the core structure for each table type, with secondary and specialized indexes providing additional acceleration for targeted query patterns. In rowstores, primary indexing relies on skip lists, which are probabilistic, lock-free linked lists that replace traditional structures for in-memory operations. Skip lists achieve O(log n) average-case performance for insertions, deletions, and lookups by maintaining multiple levels of linked lists, allowing nodes to "skip" ahead during traversals. They support ascending or descending order and are particularly efficient for sorted forward scans, making them suitable for high-velocity transactional data. This implementation ensures fast insert performance without the locking overhead of B-trees. For columnstores, the primary index is defined by the SORT KEY clause, which orders rows within logical s to facilitate segment elimination during queries. Each segment stores with min/max values per column, enabling the query optimizer to skip irrelevant segments based on predicates, such as filters. This sorted organization also improves ratios by grouping similar values and supports efficient column-wise scans without requiring full table sorts. Empty SORT KEY declarations result in unsorted segments, which may suffice for certain append-only workloads but reduce elimination opportunities. Secondary indexes in SingleStore primarily use indexes to accelerate equality-based lookups on non-primary keys. These indexes employ a to map keys to buckets in a sparse , providing constant-time O(1) access for exact matches while supporting multi-column configurations. Only one index per is allowed, and they exclude floating-point types like or due to issues. Queries must reference all indexed columns to leverage the hash structure fully, making them ideal for point lookups in both rowstore and columnstore tables. Full-text indexes utilize inverted structures to enable efficient text searches on , , TEXT, or LONGTEXT columns in columnstores. Created via the FULLTEXT in CREATE TABLE, these indexes map terms to their document locations, supporting MATCH...AGAINST queries across multiple columns. Version 2 of the offers enhanced functionality for broader search expressions, including table-level matching. Geospatial indexes, on the other hand, apply structures to and GEOGRAPHYPOINT columns in rowstores, organizing spatial data hierarchically for fast and queries. An optional parameter (ranging from 6 to 32) controls the granularity of or linestring decomposition, balancing query speed against memory and insert costs—lower values favor ingestion speed, while higher ones improve accuracy. Index maintenance in SingleStore is fully automated, with updates occurring synchronously during data ingestion or modification to ensure consistency without manual intervention. The system supports online index creation, allowing concurrent reads and writes on the , which minimizes for secondary and specialized indexes. This approach keeps overhead low for workloads, as indexes are incrementally updated rather than rebuilt periodically.

Distributed Processing

SingleStore employs a distributed consisting of and nodes to handle large-scale and query execution. nodes are responsible for storing data in partitions and performing computations on those subsets, while nodes manage query coordination. Client applications connect to an , which parses incoming SQL queries, generates execution plans, and distributes subqueries to the appropriate nodes based on data locality. The nodes execute these subqueries in parallel and return intermediate results to the , which then merges and aggregates them before sending the final output back to the client. This allows for efficient scaling by pushing the majority of to the leaves. Data partitioning in SingleStore uses hash-based sharding to distribute s across nodes, ensuring even workload balance and parallelism. For each , rows are assigned to s via a applied to the shard key—typically the or user-defined columns—which determines the partition number. By default, the number of partitions equals the number of nodes multiplied by a configurable factor (default_partitions_per_leaf), with each holding multiple partitions. In columnstore s, data is further organized into segments within these partitions, enabling parallel scans and operations across distributed nodes. This sharding approach minimizes data movement during queries when filters align with the shard key. Replication of partitions across multiple leaves provides , as detailed in the reliability features section. Query execution follows a processing (MPP) model, where operations such as scans, joins, and aggregations are distributed across nodes for concurrent execution. The optimizes the to route operations to relevant partitions, using shard key predicates to target specific leaves and avoid full scans. On the leaves, queries leverage pipelined execution to process operators in a streaming fashion, reducing intermediate materialization and network shuffling—particularly for co-located joins on shard keys. If data redistribution is needed for cross-partition operations, the system employs efficient shuffle mechanisms, but prioritizes local processing to maintain performance. This MPP paradigm supports high-throughput on petabyte-scale datasets by parallelizing both and . Horizontal scaling in SingleStore is achieved by adding leaf nodes to the cluster, which automatically redistributes to balance load and achieve near-linear gains in storage capacity and query throughput. New leaves integrate online without downtime, with data rebalancing occurring in the background via controlled migrations. nodes can also be scaled independently to handle increased connection volumes. The system supports orchestration via operators, enabling automated deployment, resizing, and management in containerized environments for elastic .

Reliability Features

Durability Mechanisms

SingleStore ensures data through a combination of transaction logging and periodic snapshots, which provide for in-memory updates and enable to a consistent state following failures or restarts. These mechanisms support both synchronous and asynchronous modes, configurable during database creation or restoration, where synchronous mode guarantees that log writes complete before transaction commits, while asynchronous mode prioritizes performance by allowing commits before disk . Transaction logs in SingleStore function as a write-ahead log (WAL), asynchronously recording all database updates from DDL and DML operations to disk before they are committed in memory. Each log is partition-specific and captures changes in a non-human-readable format, ensuring that upon restart, the system can replay these logs from the last consistent point to reconstruct the in-memory state. This approach enables by allowing selective replay of logged transactions up to a specific , preventing even in the event of crashes. To manage disk usage, logs are truncated after being incorporated into snapshots, with retention controlled by engine variables like snapshot_retention_period to balance recovery windows and storage efficiency. Snapshots serve as durable checkpoints of committed in-memory rowstore data, created periodically or manually to capture the state of databases across all . Triggered automatically when logs reach a configurable size threshold (defaulting to 1 per via snapshot_trigger_size), snapshots are written to disk and include only rowstore portions, as columnstore data persists separately through segmented files. During , the most recent snapshot is loaded into , followed by replay of any subsequent logs, minimizing time. For columnstores, background compaction merges and optimizes segments to maintain efficiency and durability without interrupting queries, ensuring long-term in analytical workloads. SingleStore achieves compliance, particularly for , through multi-version (MVCC) implemented in its rowstores, which maintains multiple versions of data rows to allow concurrent reads and writes without blocking. This lock-free mechanism, utilizing skip lists and hash tables, ensures read committed level while supporting high-throughput OLTP operations, with atomicity and enforced via the writes. is upheld by validating transactions against MVCC versions during commit, preventing partial updates from surviving failures. Backup strategies in SingleStore include incremental physical backups via the BACKUP DATABASE command, which capture changes since the last full backup to minimize storage and time overhead, applicable to local storage databases but not unlimited storage ones. Logical exports are supported through the MySQL-compatible mysqldump utility, allowing export of databases or tables in SQL format for portability and recovery. In SingleStore , continuous backups to enable to any timestamp within a configurable (default 7 days), combining snapshots and logs for granular restoration without . These approaches ensure comprehensive data protection, with recovery processes leveraging the same logging and snapshot infrastructure for verifiable integrity.

Replication and High Availability

SingleStore implements (HA) through a redundancy model that pairs leaf nodes in availability groups, where data partitions are synchronously replicated from primary to secondary leaves to ensure and minimal . In this setup, the redundancy_level is set to 2, creating replica partitions on secondary leaves that mirror the primaries in , allowing the system to maintain data even if a primary leaf fails. The primary replication type for is synchronous, where writes to a primary are committed only after successful replication to the paired secondary , providing guarantees and preventing data loss in the event of a single . Automatic occurs when the master aggregator detects a primary leaf , promoting the secondary's replicas to primaries immediately, with the process completing in seconds to minutes depending on size and load. Asynchronous replication is available as an option for but is not recommended due to weaker ; it is more commonly used for cross- replication, where a secondary cluster lags behind the primary. To balance durability and performance, SingleStore supports tunable by allowing administrators to switch between sync and async modes via database-level commands like ALTER DATABASE. For read scalability in HA mode, SingleStore employs a master-master-like approach in paired leaf configurations, where each leaf can serve reads from both its primary and replica partitions, distributing query load across the cluster while maintaining synchronous updates. is enforced through quorum-based writes, requiring acknowledgment from the primary and its before commit, though this can be tuned for lower at the cost of potential brief inconsistencies during partitions. are designed to avoid in standard HA setups, as synchronous replication ensures all committed transactions are durably stored on at least two leaves; however, simultaneous failure of both leaves in a pair could lead to temporary unavailability until . scenarios are prevented through monitoring; in synchronous HA, there is no and failover is immediate, while asynchronous replication uses a mechanism of up to 300 seconds for repeated failures to allow recovery and avoid divergent states. This integrates with mechanisms like the write-ahead log (WAL) for local persistence, ensuring replicated data is transactionally safe.

Advanced Integrations

Apache Iceberg Support

SingleStore introduced bi-directional integration with in June 2024 (currently in preview, with public preview for ingestion and private preview for full bi-directional support), enabling seamless interoperability between its database and Iceberg-based data lakes. This support allows users to query Iceberg tables directly within SingleStore without data movement, while also exposing SingleStore tables as Iceberg-compatible catalogs for external access. The integration leverages catalogs such as AWS Glue or Hive Metastore to manage metadata, facilitating shared data ecosystems across tools like or . Key features include ACID-compliant transactions on data through merge pipelines that handle append, overwrite, replace, and delete operations on snapshots, ensuring transactional consistency during ingestion and querying. evolution is supported with automatic detection of changes, such as column additions, renames, or type promotions, allowing pipelines to pause and resume without manual reconfiguration. queries are supported through Iceberg-native features via external table querying, enabling access to historical snapshots of Iceberg tables, while partitioning alignment optimizes data scanning by applying file-level filters to reduce unnecessary reads. This integration supports use cases centered on unifying operational databases with data lakes, where SingleStore acts as a high-speed layer for on large-scale datasets. For instance, organizations can perform SQL-based directly on S3-stored files, combining transactional workloads with to power low-latency applications and AI-driven insights without ETL overhead. Performance benefits stem from access to external tables, which avoids data duplication and minimizes latency by reading files in place. Metadata caching in the catalog further accelerates queries by storing schema and partition details locally, enabling sub-second response times even on petabyte-scale lakes when integrated with SingleStore's distributed processing.

Vector Search and AI Capabilities

SingleStore provides robust vector search capabilities, enabling efficient storage, indexing, and querying of high-dimensional for AI-driven applications. The platform supports data types alongside traditional relational , allowing unified processing of structured and unstructured in a single database. This integration facilitates and similarity searches essential for modern workloads. Vector indexing in SingleStore leverages algorithms such as Hierarchical Navigable Small World (HNSW) for approximate nearest neighbor (ANN) searches, which construct proximity graphs to achieve logarithmic search times with high rates. HNSW variants, including HNSW_FLAT for optimal accuracy and HNSW_PQ using product quantization for reduced memory usage, are built on implementations from AI Similarity Search (Faiss). Additionally, Inverted File (IVF) indexes, such as IVF_FLAT and IVF_PQFS, cluster vectors for scalable indexing on large datasets. For precise results, exact k-nearest neighbor (k-NN) searches perform full scans without indexing, trading speed for 100% accuracy in smaller-scale queries. These indexing options were introduced in SingleStore release 8.5, significantly reducing query times—for instance, from 3-4 seconds to 400 milliseconds on 160 million vectors. Key AI features include real-time vector ingestion and similarity search, launched in advanced form during 2024 to support dynamic AI pipelines with low-latency updates. Similarity metrics like and enable semantic matching for text, images, and embeddings. In 2024, SingleStore enhanced integration with large language models () through the SingleStore Kai API, a MongoDB-compatible interface that allows seamless ingestion of data and vector embeddings for LLM applications without ETL processes. This API delivers over 100x faster analytics on workloads, powering real-time (Retrieval-Augmented Generation) systems. Further advancements in October 2025 introduced AI Functions and ML Functions, enabling direct SQL calls to ML models and LLMs for agentic support, where autonomous agents perform low-latency tasks like decision-making and multi-step reasoning in milliseconds, alongside Aura Analyst for conversational data exploration. These functions, combined with Attach for instant data replication, ensure scalable, reliable execution under heavy AI loads. SingleStore's distributed architecture maintains compliance while handling dynamic agent workflows. Full-text search has been improved with hybrid semantic and keyword capabilities, blending vector-based semantic matching with traditional keyword indexing in a single SQL query via full outer joins and re-ranking using Reciprocal Rank Fusion (RRF). This approach, launched in June 2024, enhances result accuracy—for example, weighting scores at 70% and full-text at 30%—while executing in under 200 milliseconds on datasets exceeding 160 million . Autoscaling features, added in mid-2024, dynamically adjust resources for workloads, optimizing compute for vector searches and ensuring cost efficiency during peak GenAI demands. These capabilities support key use cases such as pipelines, where vectors retrieve context for generation; recommendation systems, leveraging similarity searches on user embeddings; and GenAI analytics on unified data, combining real-time ingestion with SQL-based insights for personalized applications. Integrations with frameworks like and LlamaIndex further streamline development for these scenarios.

Deployment Options

On-Premises Deployments

SingleStore supports on-premises deployments through self-managed installations on customer-owned infrastructure, enabling full control over hardware and data locality. These deployments require Linux-based operating systems, including (RHEL) or 7 and later, 8 or 9 (with 9 preferred), and 14.04 or later, along with a minimum version of 3.10 and glibc 2.17 or higher for SingleStore 8.1 and above. uses RPM packages for RHEL, , or distributions and DEB packages for or , with adequate permissions required on target machines for package management via yum or apt-get. For production high-availability () setups, a minimum of four s is recommended to demonstrate capabilities, typically comprising at least one aggregator node and multiple leaf s. Hardware specifications include an x86_64 CPU with a minimum of four cores (eight vCPUs recommended, especially for nodes), optimized for SSE4.2 and sets, though functional on systems without them. Aggregator nodes require at least eight of RAM, while nodes need a minimum of 32 to align with licensing units and performance expectations. should be at least three times the main capacity per , with SSDs recommended for columnstore workloads, and compatible filesystems such as or ; rowstore data requires approximately five times RAM, while columnstore sizing depends on raw data volume (doubled for ). The setup process begins with deploying the SingleStore engine using (CLI) tools for initialization, supporting both online (internet-connected) and offline modes for air-gapped environments. Online deployments download components directly, while offline setups involve manual transfer of tarballs or packages, ensuring compatibility for regulated or isolated networks. Since 2020, the SingleStore Operator has provided orchestration capabilities for environments, including on-premises s, facilitating automated management on platforms like . This operator, certified for , enables seamless resizing, node replacement, and version upgrades, though prior experience is advised. Scaling in on-premises deployments involves manual addition of nodes via CLI commands or the Operator, allowing horizontal expansion to handle increased workloads without automated provisioning. Security features include (RBAC) for administering user permissions and synchronizing them across the cluster, alongside row-level security (RLS) for fine-grained data access. in transit is enforced via SSL/TLS for client-server and intra-cluster connections, with configurable certificates for secure communications. For at rest, SingleStore integrates with OS-level solutions like LUKS or third-party tools such as Thales CipherTrust Transparent Encryption and Data Encryption, protecting data files, backups, and logs. These measures support compliance in regulated environments by securing persistent storage and network traffic. On-premises deployments lack built-in autoscaling, requiring manual intervention for resource adjustments, which contrasts with cloud-managed options but provides advantages in air-gapped or highly regulated settings where is paramount. Offline installation options ensure operation without external , making it suitable for environments with strict requirements.

Cloud and Managed Services

SingleStore offers SingleStore Helios as its primary cloud database-as-a-service (DBaaS) platform, enabling users to deploy and manage distributed SQL databases without handling underlying infrastructure. Helios supports both transactional (OLTP) and analytical (OLAP) workloads on a unified architecture, with features like low-latency queries (single-digit milliseconds), high concurrency, and real-time data ingestion via pipelines from sources such as Kafka and Amazon S3. It operates on a shared-nothing distributed model with separation of compute and storage, allowing independent scaling of resources to handle elastic demands. As a fully managed service, SingleStore automates key operational tasks, including provisioning, configuration, upgrades, backups, and monitoring, under a shared responsibility model where SingleStore manages the and users secure their data and applications. is ensured through multi-AZ and continuous backups, with agreements (SLAs) of 99.9% uptime for single-AZ deployments and 99.99% for multi-AZ configurations in and editions. Security features include compliance with ISO/IEC 27001, SOC 2 Type 2, GDPR, HIPAA, and CCPA, along with built-in , audit logging ( edition), and customer-managed keys (CMEK). options, such as (PITR) at microsecond granularity, are available in the edition on AWS and GCP. Helios is available across major public cloud providers: (AWS), , and (GCP), with deployments in multiple regions to meet data residency and latency needs. Users can choose from several editions tailored to different use cases:
  • Free Shared Edition: Designed for development, prototyping, and non-production workloads, this edition provides shared workspaces with basic SQL features, monitoring, and self-support but no or production-scale performance guarantees. It incurs no cost and supports limited throughput for evaluation.
  • Standard (Dedicated) Edition: Suited for general-purpose production applications, it offers dedicated workspaces with full compatibility, support for , time-series, vector, geospatial, and functionalities, plus resource governance and multi-AZ . Pricing starts at $0.99 per compute unit-hour, with usage-based billing and 600 free credits for initial setup.
  • Enterprise Edition: Targeted at mission-critical, customer-facing workloads, this builds on Standard features with advanced recovery (online PITR, Smart ), enhanced security (SCIM integration with , audit logging, CMEK), and cross-region replication. It starts at $1.49 per compute unit-hour and supports deployment across multiple clouds and regions.
Additionally, a Bring Your Own Cloud (BYOC) option allows deployment of within a user's (VPC) on AWS, retaining full management benefits like read replicas and SQL programmability while ensuring data isolation. for BYOC is customized via direct contact, with no standard . Across all editions, Helios emphasizes bottomless storage and infinite scalability, decoupling compute from storage to optimize costs for variable workloads.

References

  1. [1]
    SingleStore | The Performance You Need for Enterprise AI
    SingleStore is a high-performance, unified platform for enterprise AI, handling transactions, analytics, and search with real-time capabilities and single- ...Customer Portal · Careers · Contact Sales · SingleStore Helios cloud service
  2. [2]
    SingleStore Helios · SingleStore Documentation
    SingleStore is a distributed SQL database built to power intelligent applications. It is both relational and multi-model, enabling developers to easily build ...Connect to SingleStore · About SingleStore Helios · SingleStore Kai · Amazon S3
  3. [3]
    Celebrating SingleStore Availability Two Years In
    Apr 23, 2015 · SingleStore started in the Y-Combinator winter class of 2011 with just two people – co-founder and CTO Nikita Shamgunov, and myself. Since then, ...
  4. [4]
    The Story Behind SingleStore's Skiplist Indexes
    Dec 18, 2019 · SingleStore, founded in 2011, began as an in-memory, rowstore database. SingleStore's storage design evolved, in the years following, to support ...Missing: history | Show results with:history
  5. [5]
    MemSQL Changes Name to SingleStore
    Oct 27, 2020 · The company is now known as SingleStore, which better describes the organization's expansive value proposition. “It is a momentous day ...
  6. [6]
    SingleStore Announces $116M Financing Led by Goldman Sachs ...
    Jul 12, 2022 · "Our purpose is to unify and simplify modern data,” said SingleStore CEO Raj Verma. “We believe the future is real time, and the future demands ...
  7. [7]
    SingleStore Now 2024: Natively Engineered for AI
    Oct 17, 2024 · Raj looks back on his five years at the helm of the company, and considers how every milestone in SingleStore's history has been about ...
  8. [8]
  9. [9]
  10. [10]
    SingleStore Pricing
    SingleStore has a free tier for evaluation. Standard starts at $0.99/hr, Enterprise at $1.49/hr. Pricing is based on usage, with on-demand and commitment ...
  11. [11]
    SingleStore Expands Presence to Serve Japan and Accelerate ...
    Aug 5, 2025 · “Expanding into Japan is both a strategic and symbolic step in SingleStore's mission to power global AI progress,” said Raj Verma, CEO of ...
  12. [12]
    Frequently Asked Questions about SingleStore
    SingleStore is ANSI SQL compliant and MySQL wire protocol compatible, making it easy to connect with existing tools.
  13. [13]
    How SingleStore Works
    Jun 22, 2022 · It is accessible through standard SQL drivers and supports ANSI SQL syntax including joins, filters, and analytical capabilities (e.g.<|control11|><|separator|>
  14. [14]
    SingleStore Makes Analytics 20-100x Faster
    Jul 2, 2021 · SingleStore's unified database can set analytics and dashboards free from chronic sluggish performance.Missing: petabyte | Show results with:petabyte
  15. [15]
    Understanding the Benefits of a Low Latency Database - SingleStore
    Mar 3, 2025 · Discover how a low latency database can enhance your performance and efficiency. Explore its benefits and find the right fit for your needs.Missing: petabyte | Show results with:petabyte
  16. [16]
    Scale - SingleStore
    SingleStore is built to scale effortlessly, enabling you to handle growing data volumes and workloads without performance bottlenecks. Our elastic scale-out ...Start Small, Scale Big · Features · Processing 100tb Per Day On...Missing: sub- latency
  17. [17]
    MemSQL is Now SingleStore
    Oct 21, 2020 · What's Changed – We are now SingleStore. The renaming of the company to SingleStore also brings new product and service names. SingleStoreDB ...
  18. [18]
    What Is a Multi-Model Database? - SingleStore
    Sep 1, 2022 · A multi-model database natively stores and accesses different data types, such as relational, time series, geospatial, key-value and document.
  19. [19]
    SingleStore Announces Real-time Data Platform to Further ...
    Jan 24, 2024 · Announced in public preview in early 2023, SingleStore Kai is an API to deliver over 100x faster analytics on MongoDB® with no query changes or ...Missing: multi- model
  20. [20]
    Vector Data Type Support in SingleStore
    Jan 19, 2024 · Dive into a new vector type with SingleStore 8.5, designed to make building generative AI and RAG-based applications simpler than ever before.
  21. [21]
    Data Types · SingleStore Helios Documentation
    Feb 12, 2025 · SingleStore Helios supports the following data types. The sizes given are for in-memory rowstore tables. Columnstore (on-disk) tables are stored differently, ...Geospatial Types · Data Type Conversion · String Types · Integer NumbersMissing: GeoJSON | Show results with:GeoJSON
  22. [22]
    Using JSON · SingleStore Helios Documentation
    Sep 24, 2025 · SingleStore provides a set of JSON functions for extracting, searching, analyzing, and modifying JSON data.About JSON in SingleStore · DML: Accessing Data in JSON... · JSON Performance
  23. [23]
    Working with Geospatial Features - SingleStore Documentation
    Jul 2, 2025 · In SingleStore, geospatial data and functions are supported in columnstore (i.e. on-disk) tables. While the native GeographyPoint type is ...<|control11|><|separator|>
  24. [24]
    How to Use SingleStore as a Key-Value Store
    Jan 11, 2022 · In this post, I will show you how you can create a key-value store in SingleStore, using just SQL.
  25. [25]
    Working with Vector Data · SingleStore Helios Documentation
    Aug 22, 2025 · The supported element types are I18 , I16 , I32 , I64 , F32 , and F64 . Refer to Vector Type for more details. Bulk Loading Binary Vectors.
  26. [26]
    Analyzing Time Series Data · SingleStore Helios Documentation
    Mar 8, 2024 · Time series data can be stored in SingleStore Helios using rowstore or columnstore tables. Each row should have a time-valued attribute to hold ...
  27. [27]
    SingleStore Editions · SingleStore Self-Managed Documentation
    Feb 26, 2025 · Robust, unified database with core functionality for data-intensive applications. Database for mission-critical workloads with stringent ...
  28. [28]
    SingleStore raises $30M more to bring its database tech to new ...
    Oct 4, 2022 · SingleStore was founded as MemSQL in 2011 by Eric Frenkiel, Adam Prout and Nikita Shamgunov; Verma became the CEO in 2020 after a year in a co- ...
  29. [29]
    SingleStore: The cloud-native, operational database ... - Y Combinator
    Headquartered in San Francisco, CA with offices in Seattle, WA and Portland OR, MemSQL has raised over $100M from top investors including GV, Accel Partners, ...
  30. [30]
    Why SingleStore Placed a Bet on SQL
    Oct 20, 2015 · When Eric Frenkiel and Nikita Shamgunov founded SingleStore in 2011, they were confident in choosing the SQL relational model as the foundation ...
  31. [31]
    SingleStore 2025 Company Profile: Valuation, Funding & Investors
    When was SingleStore founded? SingleStore was founded in 2011. Where is SingleStore headquartered? SingleStore is headquartered in San Francisco, CA.
  32. [32]
    The Most Scalable Real-time Analytics Platform for Big Data
    SAN FRANCISCO, April 23, 2013 -- SingleStore announced today general availability of the distributed version of its eponymous in-memory database and real-time ...Missing: open- source
  33. [33]
    MemSQL Brings Facebook-Style Big Data Analysis To The Masses
    it was founded in 2011, launched its product in April 2013 and now employs about 40 people — offers two advantages to such ...
  34. [34]
    MemSQL Wants To Be The Storage Engine For Spark
    Sep 28, 2015 · MemSQL has a column store option, which was added to MemSQL last year, can dump data down to disk drives or flash SSDs. (MemSQL has pipelines ...
  35. [35]
    2017 Big Data 100: Coolest Emerging Big Data Vendors - CRN
    May 3, 2017 · In March Tamr announced a global reseller agreement with Hewlett Packard Enterprise under which HPE will resell Tamr's data unification product.
  36. [36]
    The Best Big Data Companies And CEOs To Work For In 2018 ...
    May 11, 2018 · Employees would most recommend Dataiku, StreamSets, 1010 Data ... MemSQL, Nikita Shamgunov, 100%. 1010 Data, Greg Munves, 99%. Salesforce.com ...
  37. [37]
    MemSQL Rebrands as SingleStore
    Oct 27, 2020 · MemSQL Rebrands as SingleStore. Oct 27, 2020. MemSQL, The Database of Now for operational analytics and cloud-native applications, is ...<|control11|><|separator|>
  38. [38]
    Contact SingleStore: The Real-Time Distributed SQL Database
    For immediate sales help, call us at 1-855-463-6775 or email us at team@singlestore.com. Paid Support. Are you encountering an issue and would like to contact ...
  39. [39]
    SingleStore Leads Database Industry With Four Top Rated 2022 ...
    May 12, 2022 · The company's headcount has jumped to nearly 400 employees, and it is quickly expanding into Europe and Asia. Finally, SingleStore recently ...Missing: 380 April
  40. [40]
    365 Days as SingleStore
    Oct 27, 2021 · We've gone from 200 employees to nearly 300 and we're not done growing. We've hired top talent and built out a strong executive team: a chief ...Missing: MemSQL London Hyderabad Lisbon count 2022
  41. [41]
    Reflecting on 2023 - SingleStore
    and a look ahead and what's to come ...Missing: Lisbon office
  42. [42]
    SingleStore Accelerates Go-to-Market Strategy with AWS
    Mar 5, 2024 · The company signs a Strategic Collaboration Agreement with AWS to boost marketing and development of modern generative AI applications. SAN ...Missing: July | Show results with:July
  43. [43]
    Announcing watsonx.ai and SingleStore for generative AI applications
    IBM and SingleStore are taking the next step in their partnership with the integration of watsonx.ai and SingleStoreDB.Missing: August 2023
  44. [44]
    SingleStore Partners With Snowflake to Help Users Build Faster ...
    The company's latest upgrade, launched in June 2024, includes enhanced AI capabilities, 3x faster Hierarchical Navigable Small World (HNSW) index search for ...Missing: GenAI | Show results with:GenAI<|separator|>
  45. [45]
    SingleStore Acquires BryteFlow ​​to Accelerate Adoption of Real ...
    Following on the heels of announcements of a strategic partnership with Snowflake and support for real-time processing on Iceberg data for connecting data ...Missing: 2023 2024 features IBM MongoDB
  46. [46]
  47. [47]
    SingleStore (MemSQL) IPO - Forge Global
    SingleStore was founded in 2011 by Adam Prout, Eric Frenkiel, and Nikita Shamgunov. SingleStore has not officially endorsed a plan to participate in an IPO.
  48. [48]
    SingleStore sidesteps into private equity ownership - Blocks and Files
    Sep 17, 2025 · The public funding history was solid and stable up to 2020 when there was an acceleration from the previous $30 – $36 million rounds to an ...
  49. [49]
    SingleStore Fuels Triple-Digit Cloud Growth with $80M in New ...
    Sep 8, 2021 · This funding follows a Series E round in December 2020 during which SingleStore raised $80 million. The Series F round brings SingleStore's ...
  50. [50]
    How Much Did SingleStore Raise? Funding & Key Investors - Clay
    Feb 26, 2025 · How Much Funding Has SingleStore Raised? · Amount Raised: $30M · Date: May 2018 · Lead Investors: Glynn Capital Management, Google Ventures ...
  51. [51]
    Accel Partners Leads Series B Investment of $35 Million in SingleStore
    Jan 22, 2014 · Founded in 1983, Accel Partners has a long history of partnering with outstanding entrepreneurs and management teams to build world-class ...
  52. [52]
    SingleStore Raises $36m in Series C Round
    SingleStore Raises $36m in Series C Round. Latest round to fuel company growth as the leader in databases for real-time analytics. San Francisco, CA - April 21, ...
  53. [53]
    SingleStore Raises $30 Million in Series D Round
    SingleStore, the scalable database for insight-driven enterprises, today announced it closed its Series D financing, raising $30 million.
  54. [54]
    SingleStore Announces $80 Million Series E Investment, Global ...
    SingleStore, The Single Database for All Data-Intensive Applications, today announced $80 million in new funding and a partnership with advanced analytics ...
  55. [55]
    SingleStore Closes Series F-2 Financing at $146M
    SingleStore Closes Series F-2 Financing at $146M. New investor Prosperity7 joins round, as company continues impressive track record of customer ...
  56. [56]
    Cluster Components · SingleStore Self-Managed Documentation
    Jun 22, 2022 · A cluster encompasses all of the nodes that are included in a complete SingleStore DB installation. A cluster contains aggregator nodes and leaf nodes.Missing: core | Show results with:core
  57. [57]
    Memory Errors · SingleStore Self-Managed Documentation
    Feb 11, 2025 · Error 2373 are caused because the total combined RAM allocated to the nodes in your cluster is larger than the 128 GB limit imposed by the free license.
  58. [58]
    Data Ingestion · SingleStore Self-Managed Documentation
    SingleStore Pipelines is an easy-to-use built-in capability that extracts, transforms, and loads external data using sources such as Kafka, S3, Azure Blob, and ...
  59. [59]
    AI-Powered Semantic Search in SingleStoreDB
    including code examples and a motivating case ...Missing: BI Tableau<|control11|><|separator|>
  60. [60]
    Connect with Tableau · SingleStore Helios Documentation
    Sep 26, 2025 · You can use SingleStore Helios and Tableau together to ingest your data and perform real-time analytics. You can connect with your ...Missing: semantic | Show results with:semantic
  61. [61]
  62. [62]
    About SingleStore Helios
    SingleStore Helios is a database platform built to enable developers to build and power intelligent applications. From customer-facing SaaS platforms to ...
  63. [63]
    Autoscaling in SingleStore Helios®
    Jul 1, 2024 · Autoscaling in SingleStore Helios automatically adjusts compute resources based on workload demand, scaling up or down to handle changing ...
  64. [64]
    SingleStore Helios Technical Overview
    Mar 5, 2020 · With Singlestore Helios, you get effortless deployment and elastic scale, so you can have a cluster up and running in five minutes. We're going ...
  65. [65]
    SingleStore Unveils New Offerings to Unfreeze Data Lakehouses ...
    BYOC), that lets customers enjoy the ease of ...
  66. [66]
    Cloud Functions · SingleStore Helios Documentation
    SingleStore Cloud Functions is a serverless, cloud-based service that allows users to run code without managing compute resources. It enables the execution ...
  67. [67]
    Product Overview | SingleStore Helios cloud service
    SingleStore Helios is a cloud database-as-a-service available on leading public clouds and delivers elastic scalability, high availability and exceptional ...
  68. [68]
    SingleStore Helios - Pricing
    The cloud operational database built for speed and scale. You can now enjoy the ultra high performance and elastic scalability of SingleStore on demand.
  69. [69]
    SingleStoreDB Self-Managed to SingleStoreDB Cloud Migration
    Aug 17, 2022 · In this section, we'll discuss how to easily migrate from SingleStoreDB Self-Managed to Singlestore Helios.
  70. [70]
    SingleStore Studio · SingleStore Self-Managed Documentation
    Aug 6, 2025 · SingleStore Studio is a visual user interface that allows you to interact with all of your SingleStore clusters, and was designed to be lightweight, easy to ...
  71. [71]
    SingleStore Studio Workload Monitoring
    Aug 6, 2025 · Studio allows you to analyze the resource usage of all the queries that were running in the cluster while the recording was taking place. For ...
  72. [72]
    SingleStore Studio SQL Editor
    Sep 24, 2024 · The Studio SQL Editor page is a feature of Studio that allows customers to edit and run SQL queries against their SingleStore clusters.
  73. [73]
    Using Notebooks · SingleStore Helios Documentation
    SingleStore Helios supports Jupyter Notebooks for development using SQL and Python. ... Steps to create a new notebook in Data Studio from +New Notebook drop-down.Import and Run Notebooks · Run Notebooks · Manage Notebooks
  74. [74]
    SingleStore Tools Reference
    Feb 16, 2024 · Overview. The SingleStore management tools allow you to perform cluster management operations for setup, configuration, and diagnostics.
  75. [75]
    Cluster Management with Tools - SingleStore Documentation
    Mar 15, 2023 · Use SingleStore Toolbox to deploy, administer, and manage your cluster. The associated command-line tools are packaged in Debian, RPM, and tarball files.
  76. [76]
    Configure Monitoring · SingleStore Self-Managed Documentation
    Aug 5, 2025 · SingleStore's native monitoring solution is designed to capture and reveal SingleStore cluster events over time.Missing: Prometheus | Show results with:Prometheus
  77. [77]
    Rowstore · SingleStore Helios Documentation
    Jun 3, 2025 · Rowstore is no longer the default table storage format. As of version 7.3 of SingleStore, Columnstore is the default table storage format.Missing: formats | Show results with:formats
  78. [78]
    Choosing a Table Storage Type - SingleStore Documentation
    Feb 8, 2024 · SingleStore supports two types of tables: on-disk columnstores (which is the default table type for SingleStore) and in-memory rowstore.Missing: formats | Show results with:formats
  79. [79]
    Rowstore table persistency - SingleStore Support
    Rowstore data is fully persistent on disk. Data updates on rowstore tables are performed in transaction blocks. SingleStore rowstores include persistence.Missing: checkpoints | Show results with:checkpoints
  80. [80]
    How the Columnstore Works - SingleStore Documentation
    Sep 3, 2025 · Row segment - A row segment is a set of rows within a columnstore index that are stored together, each of which is made up of column segments.Missing: formats | Show results with:formats
  81. [81]
    Columnstore Table Considerations - SingleStore Documentation
    Aug 8, 2025 · Columnstore tables have a hidden rowstore table that buffers small inserts into the columnstore table in memory.<|control11|><|separator|>
  82. [82]
    Understanding Keys and Indexes in SingleStore
    Oct 1, 2025 · SingleStore recommends using SORT KEY() . Creates an index on a column or group of columns to support fast lookups, or uniqueness enforcement. ...
  83. [83]
  84. [84]
    Choosing a Columnstore Key · SingleStore Helios Documentation
    Jul 24, 2025 · Columnstore tables have exactly one index, the sort key. Using this sort key, columnstores group the rows into logical segments, where each ...
  85. [85]
  86. [86]
    CREATE INDEX · SingleStore Self-Managed Documentation
    Dec 14, 2023 · SingleStore supports online CREATE INDEX, which means that you can read and write while the table is being indexed. CREATE INDEX on a sharded table is always ...Missing: strategies | Show results with:strategies
  87. [87]
    Understanding Shard Key Selection - SingleStore Documentation
    Sep 16, 2025 · SingleStore does not support the use of ALTER TABLE to add or change shard keys on existing tables. If your data becomes skewed, there are a ...
  88. [88]
    Distributed DML Query Execution - SingleStore Documentation
    Jun 22, 2022 · You can use the EXPLAIN command to examine a query's aggregator-level and leaf-level query plans. Let's assume the following schema: SQL.
  89. [89]
    Scale Your Speed - SingleStore
    Apr 22, 2022 · SingleStore uses massive parallel processing (MPP) ... Ultra-high performance, accelerated query ingest and elastic scalability starts here.Missing: execution | Show results with:execution
  90. [90]
    Distributed Architecture · SingleStore Self-Managed Documentation
    Jul 29, 2024 · Separate the cluster into two tiers (aggregators and leaves) and push as much work as possible to the leaves. This enables you to scale cluster ...
  91. [91]
    Scale a Cluster · SingleStore Self-Managed Documentation
    Nov 21, 2022 · Scaling a cluster up or down horizontally means increasing or decreasing the number of nodes available. The number of child aggregator and leaf nodes can be ...
  92. [92]
    Kubernetes · SingleStore Self-Managed Documentation
    Nov 21, 2022 · In this tutorial, you will deploy a cluster in a Kubernetes environment using a Kubernetes operator. This operator allows you to easily ...Missing: orchestration | Show results with:orchestration
  93. [93]
    Transaction Logs and Snapshots - SingleStore Documentation
    Nov 17, 2022 · Transaction logs that are committed to snapshots are truncated to save disk space. In addition, old snapshots can be periodically deleted by ...
  94. [94]
    Durability · SingleStore Self-Managed Documentation
    SingleStore loads the server's database partitions from disk to memory. During this process, the databases are in the recovery state. Run SHOW DATABASES with ...
  95. [95]
    How Snapshots and Logs are Used - SingleStore Documentation
    Aug 8, 2025 · How Snapshots and Logs are Used with Durability. In-memory database updates you make using DDL and DML commands are written to logs on disk.
  96. [96]
    Configuring Transaction Logs and Snapshots
    Sep 9, 2024 · In addition to the predefined number of snapshots, transaction logs that were used to create those snapshots will also be preserved.
  97. [97]
    High-Performance for OLTP and OLAP Workloads
    Nov 27, 2024 · SingleStore uses Multi-Version Concurrency Control (MVCC) to support high concurrency, which allows simultaneous reads and writes without ...
  98. [98]
    General · SingleStore Self-Managed Documentation
    Jan 10, 2023 · SingleStore's storage engine uses multi-version concurrency control (MVCC) with lock-free skip lists and lock-free hash tables to enable ...
  99. [99]
    Augmenting Your Data Warehouse to Accelerate BI
    Oct 27, 2024 · However, SingleStore leverages MySQL syntax so there may be some modifications required. SingleStore is also ACID compliant. Things to know for ...
  100. [100]
    Back Up and Restore Data · SingleStore Helios Documentation
    Aug 6, 2025 · This topic applies to database backups made using the BACKUP DATABASE command. Incremental backups cannot be made on unlimited storage databases.Missing: logical | Show results with:logical
  101. [101]
    Manage Data - SingleStore Documentation
    Sep 10, 2025 · In addition, you can create logical backups of one or more databases using the MySQL Dump utility and export them. In this section. Local and ...
  102. [102]
    Continuous Backups and Restore · SingleStore Helios Documentation
    Sep 10, 2025 · 9999% reliability. With a default 7-day retention period, they allow you to restore your data to a point in time within this window using the ...
  103. [103]
    High Availability · SingleStore Self-Managed Documentation
    Jun 13, 2024 · In paired mode, each leaf in an availability group has a corresponding pair node in the other availability group. Each leaf has its own primary ...
  104. [104]
    Managing High Availability - SingleStore Documentation
    Nov 7, 2024 · High Availability Architecture​​ SingleStore stores data redundantly in a set of leaves, called availability groups, to ensure high availability. ...
  105. [105]
    Replication · SingleStore Self-Managed Documentation
    Sep 8, 2022 · SingleStore recommends using synchronous replication; it provides much stronger data consistency guarantees as compared to asynchronous replication.
  106. [106]
    Replication and Durability Concepts - SingleStore Documentation
    Jun 13, 2024 · Replication ensures redundancy in a cluster. There are two types of replication: High availability pairs leaves, and copies all partitions between them.
  107. [107]
    High Availability (HA) and Disaster Recovery (DR) FAQs
    Nov 5, 2024 · For async replication, if a leaf node fails repeatedly and HA is enabled, then a grace period of 300 seconds is initiated (and increases ...
  108. [108]
    Announcing: Bi-Directional Integration for Apache Iceberg
    Jun 26, 2024 · SingleStore supports write-to-iceberg tables with support for Glue catalog for seamless data sharing. Data discovery and metadata management ...
  109. [109]
    Iceberg Ingest · SingleStore Helios Documentation
    SingleStore supports Amazon S3 compatible backend storage for all catalog types used with Iceberg tables. The endpoint_url is an Amazon S3 compatible storage ...
  110. [110]
    Unlocking the Power of Data Lakehouses: The Role of Iceberg and ...
    Oct 29, 2024 · Meanwhile, SingleStore's advancements in vector search, full-text search and scalable autoscaling are designed to support how you build and ...
  111. [111]
    Vector Type · SingleStore Helios Documentation
    Vectors can represent various kinds of data, such as vector embeddings obtained from large language models (LLMs), vector embeddings representing images or ...
  112. [112]
    Vector Indexing · SingleStore Helios Documentation
    Sep 25, 2025 · This topic explains how to create a vector index to enable ANN search, how to write queries that will use the index, and how to determine if the index is being ...Missing: strategies | Show results with:strategies
  113. [113]
    Announcing SingleStore Indexed ANN Vector Search
    Jan 23, 2024 · SingleStore 8.5 supports IVF, IV-FPQ and HNSW based on the implementations of these algorithms in Facebook AI Similarity Search (Faiss), a ...Missing: 2023 | Show results with:2023
  114. [114]
    Introducing SingleStore Kai™ | Turbocharge Your Real-Time ...
    May 18, 2023 · SingleStore Kai™ offers an innovative, fast and easy API to perform blazing-fast analytics on JSON for your MongoDB applications.
  115. [115]
    SingleStore Kai™: Real-Time Analytics Benchmarks
    with some reaching 1000x faster.Missing: April | Show results with:April
  116. [116]
    SingleStore Drops Three Major Upgrades to Power the Next Decade ...
    Aura Analyst, AI Functions, and Zero Copy Attach redefine real-time performance for AI-native apps. New York, NY (October 1, 2025) – Today at SingleStore ...Missing: shift cloud-
  117. [117]
    Build Powerful Agentic AI Applications Using SingleStore
    Oct 23, 2025 · SingleStore's AI Services also aim to reduce data movement by enabling model execution within the database. Hybrid or fallback architectures: In ...Missing: launch | Show results with:launch
  118. [118]
    Hybrid Search: Vector + Full-Text Search - SingleStore
    Feb 22, 2024 · Hybrid search combines vector search (semantic match) and full-text search (keyword match) in one SQL query, using a full outer join.Missing: autoscaling workloads
  119. [119]
  120. [120]
    Choosing a Vector Database for Your Gen AI Stack - SingleStore
    Jun 30, 2023 · These databases focus on ingesting vector data, indexing it for efficient similarity search and querying for nearest neighbors based on vector ...
  121. [121]
    System Requirements and Recommendations
    Jun 27, 2025 · CPU. For each host, an x86_64 CPU and a minimum of 4 cores (8 vCPUs). SingleStore is optimized for architectures supporting SSE4.2 and AVX2 ...
  122. [122]
    Linux · SingleStore Self-Managed Documentation
    Aug 27, 2025 · If you plan to deploy SingleStore using RPM or DEB packages, make sure you have adequate permissions to install packages on the target machine.
  123. [123]
    CLI Offline Deployment - Red Hat Distribution
    Sep 18, 2023 · In this guide, you will deploy a SingleStore cluster onto physical or virtual machines and connect to the cluster using a SQL client.
  124. [124]
    CLI Deployment - Tarball · SingleStore Self-Managed Documentation
    Sep 18, 2023 · The following command deploys a 4-node SingleStore cluster with a Master Aggregator node, a Child Aggregator node, and two leaf nodes. Shell.
  125. [125]
    Deploy · SingleStore Self-Managed Documentation
    Aug 27, 2025 · SingleStore can be deployed on bare metal, on virtual machines, or in the cloud by using SingleStore Tools, or via popular configuration management tools.Missing: premises | Show results with:premises
  126. [126]
    Security · SingleStore Self-Managed Documentation
    Sep 10, 2025 · : This topic covers database security administration, such as role-based access control (RBAC) and row-level security (RLS) deployment ...<|separator|>
  127. [127]
    Encryption · SingleStore Self-Managed Documentation
    Jul 29, 2024 · SingleStore is compatible with at-rest disk-based encryption via LUKS (Linux Unified Key Setup). SingleStore is also compatible with other encryption solutions.Missing: transit | Show results with:transit
  128. [128]
    SingleStore Helios Editions
    SingleStore provides the following editions of SingleStore Helios to meet the unique needs of a variety of customer workloads. Shared Edition. Standard Edition.