The article explains that performance tuning should start with pinpointing bottlenecks using response time, throughput, concurrency and resource utilization metrics, then choose appropriate measures—caching, async processing, database tuning, horizontal scaling, and rate‑limiting—rather than blindly adding a cache.
The article details DeWu's three‑year evolution of its self‑built Redis platform—covering architecture, access method changes, version upgrades, proxy rate limiting, and automated operations—that together reduced request latency by over 90% while supporting more than 1,000 clusters, 160 TB of memory and near‑10‑million QPS.
The article contrasts Elasticsearch’s search‑oriented design—using inverted indexes, near‑real‑time BASE consistency, schema‑free JSON documents, and horizontal scaling—with relational databases’ precise row‑based storage, ACID guarantees, strict schemas, B+‑tree indexes, and vertical scaling, showing how they complement rather than compete.
The article analyzes a real-world sports‑venue management platform, detailing how multi‑level caching, asynchronous processing with RocketMQ, database sharding, service splitting, and Kubernetes auto‑scaling together reduced average response time from 1200 ms to 150 ms, increased throughput eightfold, and achieved 99.95% availability under tens of thousands of QPS.
When a service experiences a sudden 100‑fold QPS surge, this guide walks through immediate emergency measures such as rate limiting, circuit breaking, and traffic shedding, followed by systematic analysis of traffic origins, robust architectural redesign including horizontal scaling, micro‑service decomposition, sharding, pooling, caching, and asynchronous processing, and finally stress testing to ensure resilience.
When a system faces a sudden hundred‑fold increase in QPS, this guide walks backend engineers through emergency response, root‑cause analysis, robust design techniques, scaling options, and pressure testing to keep services stable and performant.
This article explains why interviewers probe sharding, walks through the typical chain of questions, compares partition tables and read/write splitting, shows how to decide between sharding strategies, estimate capacity, plan expansion, and safely migrate data with traffic replication.
This guide walks senior backend engineers through the strategic reasoning, capacity estimation, and step‑by‑step migration techniques for sharding databases, covering when to split, choosing between partitioning, read/write splitting, or full sharding, and how to plan safe expansions.
The article debunks the myth that Spring Boot cannot scale, showing that with WebFlux, Netty, Reactive Redis, GraalVM Native Image and horizontal scaling a Spring Boot service can reliably achieve 500,000 queries per second, backed by concrete benchmark data and a full demo implementation.
This article explains the concepts, differences, advantages, and disadvantages of database sharding and partitioning, provides practical MySQL examples for horizontal sharding by region and range partitioning, and offers guidance on choosing the right approach for scalability and maintainability.
This article explains why database sharding is needed, how to identify performance bottlenecks, and provides step‑by‑step guidance on SQL tuning, table redesign, architectural changes, and practical horizontal and vertical sharding techniques with real‑world e‑commerce examples.
This article explains the concepts of database sharding and partitioning, compares common middleware solutions, and offers practical guidance on choosing and implementing horizontal or vertical splits to handle rapid growth and high concurrency in modern applications.
This guide explains how to design a high‑concurrency, high‑throughput internet architecture that ensures database high availability with double‑master sync and virtual IPs, and how to horizontally shard and smoothly expand the cluster in seconds using configuration changes, reloads, and cleanup steps.
This article explains why database sharding and partitioning become necessary, outlines performance bottlenecks, presents software and hardware optimization techniques, details horizontal and vertical splitting strategies, and discusses the added complexity such as cross‑database joins, distributed transactions, and ID generation.
This article presents five expansion strategies—shutdown, write‑stop, log‑based, dual‑write, and smooth 2N—detailing step‑by‑step procedures for MariaDB installation, master‑master replication, dynamic data‑source configuration, and Keepalived high‑availability setup, enabling seamless horizontal scaling and minimal service disruption for large‑scale databases.
This article explains the AKF Cube methodology for scaling distributed systems, detailing how horizontal replication (X axis), functional decomposition (Y axis), and user‑based sharding (Z axis) can be combined to boost performance while balancing implementation costs.
Database sharding and table partitioning are essential scaling techniques that separate data across multiple databases and tables to handle growing user volume, data size, and concurrency, with explanations of when to split, methods (horizontal vs vertical), and a comparison of popular middleware solutions.
This article introduces the fundamental concepts of database sharding, including data fragmentation, nodes, logical and physical tables, broadcast and single tables, sharding keys, strategies, algorithms, binding tables, SQL parsing, routing, rewriting, execution, result merging, distributed primary keys, data masking, distributed transactions, migration, and shadow databases, providing a comprehensive guide for designing and operating a sharded architecture.
This article explains how to expand a sharded database from three to four nodes, compares five migration schemes—including stop‑service, stop‑write, log‑based, dual‑write, and smooth 2N approaches—and provides step‑by‑step instructions for MariaDB installation, master‑slave configuration, Keepalived high‑availability setup, and dynamic data‑source integration using ShardingJDBC.
The article details how a rapidly growing airline ticket order system was re‑architected by identifying performance bottlenecks, applying vertical and horizontal sharding, optimizing cache layers, implementing dual‑write mechanisms, and planning a phased migration to achieve ten‑fold QPS growth while reducing resource usage and operational risk.
This guide explains how to scale a sharded database horizontally by adding new nodes, handling data migration with stop‑service, stop‑write, log‑based, dual‑write, and smooth 2N strategies, and implementing high‑availability using MariaDB double‑master replication and Keepalived, complete with configuration examples and code snippets.
This article explains why high‑concurrency big‑data systems need database sharding, describes table‑level partitioning methods (modulus and range), shows how to implement them with MySQL and Java code, compares vertical and horizontal database splitting, and evaluates middleware solutions such as Sharding‑JDBC and Mycat.
This article explains how to design and evolve a system from a single‑server deployment to a highly scalable architecture using vertical and horizontal scaling, load balancing, database replication, sharding, caching, CDN, and stateless design to support billions of users.
This article explains the background, challenges, and design principles of horizontal scaling for TDSQL, detailing its architecture, scaling process, shard‑key selection, high availability, distributed transactions, performance optimization, practical case studies, and a Q&A section.
This article explains the motivations, challenges, and design principles of horizontal scaling for databases, using TDSQL as a case study to illustrate architecture, scaling procedures, shard key selection, high‑availability mechanisms, distributed transactions, and performance optimization techniques.
This article explains the three aspects of database sharding—database‑only, table‑only, and both—detailing when to apply each, how to choose sharding keys, common algorithms, ID generation strategies, available open‑source tools, and the new challenges introduced by sharding.
This article explains why high‑traffic systems need database sharding, compares table‑level and database‑level partitioning methods, presents concrete MySQL table‑creation scripts and Java service code, and discusses the advantages, drawbacks, and common middleware solutions such as Sharding‑JDBC and Mycat.
This article details Ctrip's comprehensive redesign of its airline ticket order database, covering the background performance bottlenecks, vertical and hot‑cold data splitting, sharding key selection, multi‑level caching, cross‑shard query optimization, dual‑write mechanisms, fault‑tolerance strategies, project planning, and the resulting improvements in scalability and cost.
The article explains how to build highly available stateless services by using redundant deployment, vertical and horizontal scaling, appropriate load‑balancing algorithms, monitoring, and automated recovery, and also discusses high‑concurrency identification, CDN/OSS usage, and practical recommendations for cloud‑native environments.
This article explains the concepts, motivations, strategies, and challenges of database and table sharding, covering vertical and horizontal partitioning, range and hash algorithms, when to adopt them, and popular middleware solutions for scalable MySQL architectures.
The article explains how to address single‑point failures, limited capacity, and performance bottlenecks when scaling a single‑node service by introducing the AKF microservice design principle—X‑axis horizontal replication, Y‑axis functional separation, and Z‑axis data‑driven partitioning—detailing each split type with diagrams and practical considerations.
This article explains the concepts, methods, advantages, and drawbacks of database sharding, covering vertical and horizontal partitioning, sharding rules, global primary key generation, distributed transaction issues, cross‑node queries, pagination, data migration, and practical case studies, with code examples and diagrams.
This article explains how to evolve a simple single‑server web application into a highly available, horizontally scalable system by introducing DNS routing, vertical and horizontal scaling, load‑balancing, database replication, sharding, denormalization, SQL/NoSQL choices, caching, CDN, and GeoDNS techniques.
Effective MySQL sharding requires sustainable, low‑skew designs, favoring hash‑based methods with proper coprime counts, two‑stage partitioning, routing tables, or consistent hashing, while supporting expansion via doubling or flexible consistent‑hash growth to avoid hot spots and uneven data distribution.
Shopee’s Logistics Channel Service migrated from a shared‑cluster MySQL setup to dedicated clusters, added TiDB for transient tracking data, and ultimately adopted hash‑based sharding with separate order and tracking services plus an asynchronous compensation mechanism, enabling uniform data distribution, cross‑database consistency, six‑month archiving, and scalable growth without rebalancing.
The article examines why growing business complexity and throughput demands necessitate system decomposition and architectural evolution, detailing horizontal scaling, vertical and business splitting, database partitioning strategies, cache and index integration, remote service data sourcing, and asynchronous messaging to achieve scalable, robust micro‑service‑based solutions.
This article explains how to achieve high availability for stateless services by employing redundancy, vertical and horizontal scaling, various load‑balancing algorithms (random, round‑robin, weighted, least‑connections, source‑hash), and automatic scaling techniques in cloud‑native environments, while also covering performance monitoring and CDN/OSS usage.
This article explains how to split large-scale database tables using vertical and horizontal partitioning, compares hash-modulo and range-based sharding, and proposes a hybrid approach that leverages both methods to balance data distribution, avoid hotspot issues, and eliminate the need for costly data migrations during scaling.
The article explains that migrating legacy monolithic systems to the cloud is far from a simple lift‑and‑shift, highlighting the pitfalls of inflexible on‑premise infrastructure, the importance of horizontal scaling, stateless application design, micro‑service decomposition, and asynchronous communication to fully leverage cloud elasticity and cost efficiency.
The article explains why growing business complexity and throughput demands force system decomposition and architectural upgrades, detailing horizontal scaling, vertical and business splitting, database sharding, caching strategies, and the evolution from monolithic to micro‑service structures.
The article explains how increasing business complexity and throughput demands drive system splitting, architectural evolution, and the adoption of scaling, sharding, caching, and asynchronous messaging techniques to improve capacity, robustness, and maintainability of large‑scale backend services.
This article explains the fundamentals of database sharding, covering both vertical and horizontal partitioning concepts, routing algorithms, advantages and drawbacks, practical implementation steps using sharding-jdbc, and discusses related challenges such as distributed transactions, pagination, global IDs, and tool selection.
This article recounts the 2007 challenges faced by Taobao's monolithic MySQL setup and explains how the TDDL middleware introduced SQL optimization, sharding, read‑write separation, caching, and dynamic scaling to transform the system into a distributed, high‑performance database solution.
This article explains what a service registry is, outlines its essential capabilities such as high availability, horizontal scaling, health checking, routing, and multi‑datacenter support, and compares popular open‑source solutions like Zookeeper and Nacos to help you select the right one for your stack.
This article explains how TiDB, a MySQL‑compatible distributed NewSQL database, solves large‑table performance issues with horizontal scaling, describes its core components, deployment guidelines, key advantages, and practical tips such as avoiding auto‑increment IDs, handling hotspots, version quirks, backup strategies, and monitoring with Grafana.
This article explains MySQL performance bottlenecks, compares IO and CPU limits, introduces horizontal and vertical sharding and partitioning concepts, presents practical scenarios, outlines common tools such as Sharding‑Sphere, TDDL and Mycat, and provides step‑by‑step guidance for implementation, troubleshooting and scaling.
TDSQL enables Tencent Meeting’s non‑disruptive, linear horizontal scaling by using a stateless SQL engine, shard‑key selection, two‑phase distributed transactions, and one‑click set expansion, delivering near‑linear performance growth, high availability, and seamless capacity increase for millions of daily users worldwide.
This article explains why relational databases become bottlenecks at large scale, introduces vertical and horizontal sharding techniques, discusses the challenges of distributed transactions, cross‑shard queries, pagination, and global primary‑key generation, and provides practical guidelines and middleware options for implementing sharding in production systems.
This article explains why scalability is essential for web apps and outlines core architectural principles—separation of concerns and horizontal scaling—along with practical server roles, load balancing, CDN usage, and worker processes to handle high traffic efficiently.
lmstfy is a stateless, Redis‑backed task‑queue service from Meitu that provides delayed execution, automatic retries, priority handling, expiration, and a RESTful HTTP API, while supporting horizontal scaling via namespace‑based token routing, rich Prometheus metrics, and future disk‑based storage extensions.
This comprehensive guide explains the motivations behind database sharding, compares vertical and horizontal partitioning methods, discusses the challenges of distributed transactions, global primary keys, cross‑node queries, pagination, and data migration, and provides practical solutions and middleware options for implementing scalable, high‑availability database architectures.
This article explains vertical and horizontal database sharding, compares hash-modulo and range-based partitioning, and proposes a hybrid design that balances load, prevents hotspots, and eliminates costly data migrations during scaling.
58.com tackles the challenge of storing and searching billions of heterogeneous posts by employing a unified post center, a category‑attribute service, and an external search engine, using vertical table splitting, JSON‑based extensible fields, compressed keys, and horizontally sharded indexes to achieve massive scalability and high throughput.
The QLive service powers iQIYI’s massive live‑streaming events—such as the Spring Festival Gala—by combining vertical and horizontal scaling, a three‑layer architecture with dual data‑center isolation, multi‑level caching, circuit‑breaker/degradation controls, and a Flume‑Kafka‑Hive monitoring pipeline to sustain over 400 k QPS and 99.9999 % availability.
Database sharding, a horizontal partitioning technique that splits a table’s rows across multiple nodes, enables scalable performance and fault isolation for high‑traffic applications, but introduces complexity, potential data imbalance, and recovery challenges, so it should be adopted only after simpler optimizations are exhausted.
This article explains why load balancing is essential for high‑traffic systems, describes its underlying principles and classifications from layer‑2 to layer‑7, outlines common software implementations, and presents typical scenarios such as scaling, high availability, and disaster recovery.
This article explains why growing business complexity and throughput demand system decoupling, outlines horizontal scaling, vertical and business splitting, database sharding techniques, and shows how architectural evolution leads to micro‑service‑based, resilient infrastructures.
The article explains how increasing business complexity and throughput require system splitting, decoupling, and architectural evolution—covering horizontal and vertical scaling, database sharding, caching, and micro‑service patterns—to improve capacity, robustness, and performance of large‑scale applications.
The article explains how increasing business complexity and throughput demands drive system splitting—horizontal scaling, vertical and business sharding, and database partitioning—and describes the subsequent architectural evolution toward micro‑services, caching, indexing, and asynchronous processing to improve capacity, robustness, and performance.
This article explains why growing business complexity and throughput demands force a system to be split and refactored, describing horizontal scaling, vertical and business splitting, database sharding, and the resulting architectural evolution toward micro‑services.
The article reviews how increasing business complexity and throughput demands drive the need to split applications and databases, adopt horizontal and vertical scaling, implement business and service-level partitioning, and evolve system architecture toward micro‑services, caching, and asynchronous processing.
The article outlines UDDB’s roadmap from a MySQL‑compatible middleware to a full‑featured distributed database, detailing its three‑stage evolution, system architecture, SQL parsing and routing design, and innovative techniques that enable read‑write separation, vertical sharding, and future horizontal scaling.
This article explains why scalability is a crucial non‑functional requirement, describes vertical (scale‑up) and horizontal (scale‑out) approaches, introduces the AKF model’s X/Y/Z axes, and provides practical guidance for scaling services, databases, caching, and deployment to achieve robust, high‑throughput applications.
DBProxy, an open‑source MySQL middleware derived from Atlas, offers horizontal scaling, read/write separation, load balancing, advanced blacklist filtering, dynamic configuration, and numerous bug fixes, positioning it as a mature, high‑availability solution for enterprise database environments.
This article explains the fundamentals of database sharding, including horizontal partitioning concepts, routing rules, and various sharding strategies such as range, hash, and mapping tables, and how clustering, load balancing, and read/write separation improve scalability, availability, and performance for large‑scale internet applications.
This article explains how load balancing solves high‑traffic, high‑concurrency challenges by distributing requests across multiple servers, covering its core principles, vertical and horizontal scaling, various classification methods such as DNS, IP, link‑layer, and hybrid approaches, along with their advantages, drawbacks, and deployment recommendations.
This article details Dazhong Dianping's practical approach to sharding its massive order database, covering vertical and horizontal partitioning strategies, specific sharding algorithms, unique ID design, data migration phases, and lessons learned for long‑term scalability.
This article distills Will Larson’s insights on designing scalable systems, covering linear capacity growth, redundancy, load‑balancing strategies, multi‑layer caching, cache invalidation, offline processing with message queues, Map‑Reduce integration, and the benefits of a dedicated platform layer.
The article explains the historical background, core characteristics such as scalability, cost‑efficiency, fault tolerance, and elasticity, and outlines essential design principles for distributed systems, emphasizing low hardware requirements, horizontal scaling, avoidance of single points of failure, reduced communication overhead, and stateless services.
Distributed systems, long used since the 1970s and popularized by internet giants like Google, offer scalable, cost‑effective, and fault‑tolerant architectures by leveraging many low‑cost servers, emphasizing horizontal scaling, avoidance of single points of failure, minimal inter‑node communication, and stateless services for elastic application deployment.
The article explains the origins, core features such as scalability, cost‑effectiveness, fault tolerance, and elastic expansion of distributed systems, and outlines design philosophies like low hardware requirements, horizontal scaling, avoidance of single points of failure, minimized inter‑node communication, and stateless service architecture.
The article analyzes the challenges of high‑traffic ticketing platforms, compares business models, identifies concurrency bottlenecks, and presents comprehensive front‑end and back‑end optimization techniques—including load balancing, caching, data partitioning, and queue‑based flow control—to achieve horizontal scalability and reliable performance.
