Redis achieves million‑level concurrency by keeping all data in RAM, using epoll/kqueue for non‑blocking I/O, employing highly optimized data structures with O(1) or O(log N) operations, and evolving from a single‑threaded core to optional multi‑threaded I/O, boosting throughput up to 12×.
Redis achieves single‑machine million‑level QPS not merely because it stores data in memory, but through a tightly coordinated set of four core design principles—pure in‑memory operation, single‑threaded architecture, I/O multiplexing, and highly optimized data structures—that together deliver ultra‑low latency and massive throughput.
Explore comprehensive Redis data type operations—including strings, hashes, lists, sets, and sorted sets—through detailed command examples, usage scenarios, and practical tips, while also learning how to manage keys, expiration, and messaging queue concepts for effective in‑memory data handling.
Redis achieves exceptional speed by storing all data in memory, using a single‑threaded event‑driven architecture with epoll/kqueue, employing efficient I/O multiplexing, optimizing data structures such as strings, hashes and sorted sets, and providing flexible persistence and high‑availability options, all of which are detailed in this article.
Redis achieves remarkable speed by storing data entirely in memory, employing a single‑threaded event loop with I/O multiplexing, and using highly optimized in‑memory data structures while balancing durability through efficient persistence mechanisms, all of which combine to minimize latency and maximize throughput.
This article explores multiple in‑memory strategies—using a simple map with timers, per‑driver goroutine management, and especially a Go‑implemented timing wheel—to identify Uber drivers who haven’t reported for ten minutes, comparing their complexities, memory usage, and suitability for large‑scale systems.
This article explains why Redis achieves extremely high performance, reaching up to 100,000 QPS, by leveraging its in‑memory design, I/O multiplexing, optimized data structures such as SDS, ziplist and skiplist, and a single‑threaded event loop, each detailed with examples and code.
The article explains that Redis achieves exceptional performance through four main factors—its in‑memory storage, optimized data structures, a single‑threaded architecture, and non‑blocking I/O—detailing how each contributes to speed and efficiency.
Redis 7.0, now officially stable for production, introduces nearly 50 new commands, major features like Redis Functions, ACLv2, command introspection, and Sharded Pub/Sub, while enhancing memory, compute, network, and storage subsystems for better performance and efficiency.
This article walks through the step‑by‑step rewrite of the Dagoba in‑memory graph database from JavaScript to Python, covering data modeling, primary‑key management, eager and lazy query implementations, bidirectional edge support, performance optimizations, and how to extend the query language with custom methods.
This article explains why Redis needs persistence, describes the two main persistence mechanisms—RDB snapshots and AOF command logging—their configuration, internal structures, operational principles, and trade‑offs, and provides practical code examples for implementing and tuning them.
At Gopher China 2021, Go expert Yang Le Duo presented a detailed exploration of a proactive in‑memory cache architecture, describing how his team tackled real‑time data, complex queries, hot‑cold data swapping, and language constraints to improve performance and developer productivity in large‑scale streaming applications.
This article outlines Redis's key advantages such as high performance and flexible data types, discusses its limitations like lack of relational features, describes ideal in‑memory use cases, compares it with Memcached, and provides detailed instructions for shutting down, configuring, and connecting to Redis using command‑line and graphical clients.
This article explains why Redis achieves extremely high performance by leveraging pure in‑memory operations, a global O(1) hash table, efficient data structures such as SDS, ziplist, quicklist and skiplist, a single‑threaded event loop with non‑blocking I/O multiplexing, and adaptive encoding strategies.
This article explains how to create a simple single‑node in‑memory cache that supports per‑entry expiration by defining a generic cache interface and implementing it with Caffeine, using ConcurrentHashMap to store multiple caches keyed by expiration time.
Redis achieves exceptionally high performance despite its single‑threaded request handling by leveraging pure in‑memory operations, I/O multiplexing, non‑CPU‑intensive tasks, and specific single‑threaded advantages, while also incorporating multithreaded optimizations such as lazy‑free mechanisms and protocol parsing in newer versions.
The article explains SAP HANA’s performance advantages by combining four key technologies—high‑speed memory, columnar storage, data compression, and an insert‑only model—detailing their individual pros and cons, how they complement each other, and the trade‑offs involved in scaling and persistence.
Redis 6.0.0 GA, the biggest release to date, adds a redesigned client cache, ACL improvements, faster RDB loading, a new STRALGO command, and optional multithreaded I/O that can double network performance, while urging careful testing before production use.
Redis achieves exceptional speed by combining a C‑based implementation, pure in‑memory data storage, a single‑threaded event loop, and non‑blocking epoll I/O multiplexing, while supporting rich data structures and advanced features such as transactions, Lua scripting, and clustering.
The article explains Oracle 12c Release 2's launch, decodes its version numbering, highlights new capabilities such as Global Service Manager, In‑Memory, Multitenant and Sharding, compares parameter growth across releases, and offers practical upgrade timelines and key parameter recommendations.
This article explains Oracle 12c's In‑Memory Column Store feature, its compression levels, step‑by‑step testing results for full scans and joins, a real‑world production case from Zhejiang Mobile, and practical maintenance commands to keep the in‑memory area healthy.
Disque is an experimental, distributed, fault‑tolerant in‑memory message queue built in C that extends Redis concepts with synchronous replication, configurable delivery semantics, explicit acknowledgments, fast‑ack support, dead‑letter handling, and optional disk persistence for robust backend messaging workloads.
This article explains Oracle 12c's key memory‑related enhancements—including the extended database cache (Smart Flash Cache), PGA aggregate limit, In‑Memory column store with compression, SIMD processing, temperature‑based replacement, and big‑table cache—detailing their parameters, operation, and monitoring methods for improved database performance.
This article examines Oracle Database 12c’s key innovations—including multitenant architecture, the Database In‑Memory option, enhanced security controls, and integrated big‑data analytics—while sharing real‑world production experiences, benefits, and practical limitations for enterprises adopting cloud‑ready databases.
This article explains how Oracle 12c's In-Memory feature enables hybrid OLTP/OLAP workloads by storing columnar data in a dedicated memory area, covering its architecture, data loading, consistency mechanisms, query acceleration techniques, and integration with RAC for high‑availability deployments.
Oracle 12c’s In‑Memory Option (IMO) lets you store table, partition, and materialized view data in a columnar format within the SGA, offering faster query performance, configurable compression, priority settings, and detailed management via INMEMORY clauses, parameters, and specialized dictionary views.
This article explains how to activate Oracle 12c's In‑Memory feature at the column level by first enabling it at the table level, demonstrates verification with V$IM_COLUMN_LEVEL, shows ALTER TABLE commands, and compares execution plans to illustrate performance benefits.
In a lively Q&A session, Oracle experts discuss how China’s “post‑IOE” shift, cloud migration, big‑data collaboration with Hadoop, and the strengths of In‑Memory, TimesTen, and Exadata shape the future direction of Oracle databases.
This article presents a detailed, categorized catalogue of more than fifty open‑source big‑data projects—including Hadoop‑related utilities, analytics platforms, databases, BI solutions, data‑mining packages, query engines, programming languages, search tools, and in‑memory technologies—highlighting their primary functions, supported operating systems, and official links.
Since the 1970s databases have become essential middleware, and modern large‑scale parallel databases, designed for extreme parallelism on clustered hardware, face trade‑offs in performance, scalability, and fault tolerance, prompting a shift toward cloud‑native, micro‑service architectures and new hardware such as SSDs and memory‑centric designs.
