1 views collected around this technical thread.
Coupang’s AI platform replaces costly data‑copy steps with a distributed cache that automatically pulls data from a central lake, boosts GPU utilization across regions, cuts storage and operational expenses, and speeds up model training by up to 40% while simplifying deployment via Kubernetes.
The article explains how to design a scalable, highly available backend system capable of handling millions of requests per second by defining key performance metrics, estimating traffic with the 2/8 rule, and applying architectural patterns such as load‑balanced clusters, vertical service splitting, distributed caching, and database master‑slave replication, illustrated with a Taobao case study.
This article explains why traditional relational databases falter under high‑concurrency loads, introduces caching as a solution, compares Redis distributed caching with local in‑process caching, and shows how combining them into a multi‑level cache can dramatically improve performance and reliability.
This article explains four typical cache problems—penetration, avalanche, breakdown, and distributed cache efficiency—describing their causes and offering practical mitigation strategies such as top‑level filtering, Bloom filters, staggered expirations, null caching, and locking mechanisms.
This article explains the motivation, design principles, class diagram, and core Go code for a multi‑level cache library that supports in‑memory and distributed caches (Redis, Memcached) using adapter, builder, and responsibility‑chain patterns, and discusses cache‑database consistency strategies.
This article explains the core design goals, sharding strategies, replication models, communication protocols, cache selection, and monitoring techniques needed to build high‑performance, highly available, and scalable distributed cache systems for large‑scale internet applications.
This article presents REDTao, Xiaohongshu's self‑built graph storage solution that unifies graph queries, reduces development duplication, and delivers low‑latency, high‑availability access to a trillion‑scale social graph through a three‑layer architecture, distributed cache, and cloud‑native deployment.
Alluxio Edge is a library that runs inside Trino or PrestoDB workers, using local SSD or memory to cache data from cloud storage, which restores data locality, cuts storage egress, and delivers up to ten‑fold IO speed gains and up to ten‑fold query performance improvements in real deployments.
Ximalaya’s KV storage progressed from a simple Redis master‑slave setup to client‑side sharding, then adopted Codis clustering for elastic scaling, integrated Pika’s disk‑based store with cold‑hot separation, introduced KV‑blob separation, fast‑slow command pools, second‑level expansion, ehash fields, large‑key circuit breaking, multi‑active data‑center replication, and now targets cloud‑native deployment, advanced features, and AI‑driven operations.
This article outlines the design goals, architecture, and implementation details of a high‑performance distributed caching solution for Spring Boot applications, combining Redis as a first‑level cache with Caffeine as a second‑level cache, and provides configuration, usage examples, and future enhancement plans.
An in‑depth case study shows how GPT‑4, demonstrated by former Google engineer Naman Bhalla, tackles a simulated Uber interview by generating software requirements, design specifications, Java code snippets, and JUnit tests for a distributed cache system, revealing both its strengths and current limitations.
This article explains what caching is, outlines various cache types, analyzes common high‑traffic cache issues such as penetration, breakdown, avalanche, and hot‑key handling, and presents real‑world architectures from Weibo and Zhihu to illustrate effective cache design and operation.
This article examines the storage bottlenecks in large‑scale AI training, evaluates local‑disk and Alluxio‑based distributed caching strategies, proposes uniform cache eviction and replica‑aware global policies, and introduces the SiloD framework for coordinated compute‑storage scheduling to dramatically improve GPU utilization and overall cluster throughput.
This article explores how caching accelerates high‑concurrency systems by reducing CPU and I/O load, compares local and distributed cache types, reviews Java cache implementations and frameworks, and presents real‑world multi‑level cache designs and pitfalls to help you select the optimal solution.
This article explains the fundamentals of caching, why caches (especially Redis) are essential for high‑performance and high‑concurrency scenarios, compares local, distributed, and multi‑level caches, and outlines their advantages, disadvantages, and typical implementation approaches.
This article explains the fundamentals of caching, why caches (especially Redis) are essential for high‑performance and high‑concurrency scenarios, describes local, distributed, and multi‑level cache architectures, outlines their pros and cons, and provides practical implementation guidance.
This article explains the fundamentals of caching, why caches like Redis are essential for high‑performance and high‑concurrency backend systems, and compares local, distributed, and multi‑level cache architectures, including their advantages, drawbacks, and typical implementation approaches.
This article explains the concept of caching, compares it with buffering, outlines common scenarios such as memory, SSD, static, distributed and local caches, discusses their advantages and limitations, and provides a Java Guava Cache example for practical backend performance optimization.
This article explains the fundamentals of consistent hashing, its application in load‑balancing distributed caches, analyzes common issues such as data skew and cache avalanche, introduces virtual nodes for uniform distribution, provides Java code examples, and compares it with Redis's HashSlot approach.
This article provides an in‑depth overview of caching, covering its definition, when to use it, core concepts, various cache types (client, server, CDN, reverse‑proxy, in‑process, distributed), eviction policies, multi‑level cache architectures, common pitfalls such as cache avalanche, penetration and breakdown, and practical mitigation techniques.