The article explains how to leverage Apache Spark for machine‑learning tasks, large‑scale new‑word discovery, and simple intelligent question‑answering by using Spark‑Shell, Scala code, and word2vec‑based similarity, while sharing practical tips and performance considerations.
This article explains how to build a large‑scale, real‑time vehicle monitoring system using Apache Storm and Kafka on Alibaba Cloud, covering the challenges of big‑data ingestion, system architecture, deployment steps, performance testing, and practical lessons learned.
The article explains how IBM's Watson uses AI and big‑data techniques to examine the words people write on platforms like Twitter and Facebook, extracting personality traits such as openness and neuroticism, and discusses the potential business uses and privacy concerns of this technology.
This article explains SparkSQL's query processing pipeline—from parsing and logical planning through optimization and physical execution—highlighting why it often outperforms Hive on MapReduce by reducing I/O, minimizing shuffle stages, and reusing JVMs.
This article explains how to design and implement a distributed web‑crawling framework in Java that can collect, structure, and store massive amounts of data while handling anti‑scraping measures, duplicate detection, and real‑time monitoring.
Over the past decade, open‑source software has surged in the enterprise sector, driven by startups and venture capital, with surveys showing widespread adoption, increased contributions, and strong security advantages that are reshaping IT architecture, cloud, and big‑data strategies.
This article explains Apache Kafka’s core concepts, high‑throughput design choices such as sequential I/O, PageCache, Sendfile, and partitioning, and provides practical performance tips and configuration recommendations for brokers, producers, and consumers in large‑scale data pipelines.
This article explains how Tencent uses big‑data collection, user profiling, and AI‑driven risk learning engines to detect and block malicious accounts, proxy IPs, and fraudulent activities across e‑commerce and other platforms, detailing the architecture, algorithms, and practical defenses employed.
This article dissects JD.com’s Qinglong logistics system, detailing its O2O strategy, big‑data‑driven pre‑sorting, AI algorithms, GIS integration, and the evolution from version 1.0 to 3.0, highlighting how these technologies enable ultra‑fast, agile supply‑chain operations.
IBM announced that its SystemML machine‑learning platform will become an Apache Incubator project, highlighting a broader industry trend where tech giants like Google and Facebook open‑source their AI tools to accelerate data‑driven innovation and expand enterprise‑focused machine‑learning ecosystems.
Time‑series data, defined by a timestamp field, appears everywhere, and the article explains how to choose an appropriate time‑series database by comparing two schema models, their query patterns, performance trade‑offs, and why modern solutions like Elasticsearch, columnar stores, and Druid excel at real‑time massive aggregation.
The article outlines a practical, end‑to‑end data platform architecture for internet businesses, covering data collection, storage and analysis, sharing, real‑time processing, task scheduling, and the importance of simplicity and agility in building an agile data warehouse.
This article explains the design of a distributed, real‑time price‑update service that handles massive product data, combines query‑driven crawling, observer‑pattern notifications, and multiple data sources to keep e‑commerce price and inventory information fresh within minutes.
The article details how LinkedIn has scaled Kafka from handling billions to trillions of messages daily, describing quota enforcement, a ZooKeeper‑free consumer, reliability enhancements, security plans, monitoring frameworks, fault‑injection testing, cluster balancing, and integration with other internal data systems.
This article summarizes a WeChat group Q&A on the current momentum of in‑memory computing, compares TimesTen and SAP HANA, and offers practical advice on building enterprise big‑data platforms, covering cloud vs self‑build, talent, investment, and real‑world case studies.
A recent study analyzes startup technology choices, revealing the most popular programming languages, frontend frameworks, databases, mobile platforms, infrastructure services, DevOps tools, search technologies, API integrations, and advanced big‑data solutions across different performance tiers.
This article presents expert Q&A on effective user behavior analysis techniques for building detailed user profiles and compares mainstream stream‑processing solutions, outlining key factors such as latency, throughput, parallelism, and fault tolerance for selecting the right real‑time data platform.
This article explores Taobao's massive data product architecture, detailing its five-layer design, the use of Hadoop and real‑time systems, hybrid relational and NoSQL storage, a middleware layer for data integration, and systematic caching strategies that enable petabyte‑scale analytics and fast query responses.
This article explains how Dianping built a millisecond‑level real‑time computation platform using Apache Storm, covering use cases, system architecture, core Storm concepts, performance tuning, best practices, and a detailed Q&A on their production deployment.
This article explains how IBM Research leverages Spark to capture and analyze network traffic of microservice‑based applications in an OpenStack cloud, providing real‑time transaction tracing and batch latency statistics to reveal service dependencies and performance bottlenecks.
This article surveys the evolution of Hadoop and its ecosystem, explains core storage and processing concepts, and introduces contemporary big‑data technologies such as Spark, Flink, Kafka, Lambda architecture, NoSQL databases, and cloud‑native solutions, highlighting their roles and trade‑offs.
The article details how Alibaba Cloud's multi‑layered enterprise architecture, built on service‑oriented frameworks, distributed databases, and message queues, enabled record‑breaking Double 11 transactions while offering linear performance scaling, high reliability, and cost‑effective operations for large‑scale internet applications.
Aspiring data specialists should cultivate curiosity and hands‑on experience with production‑grade tools, and this guide highlights seven indispensable Python libraries—IPython, GraphLab Create, pandas, PuLP, matplotlib, scikit‑learn, and Spark—each explained with key features to boost your data‑science career.
The article presents a comprehensive analysis of Weibo's social graph, introducing metrics such as propagation power, intimacy, fan and follow similarity, two‑degree relationships, and relationship circles to model and quantify user interactions and information diffusion within the platform.
To monitor hundreds of web apps on UAE’s PaaS platform in near‑real time, we combined Storm with lightweight log transport, a memcached‑based fqueue, and adaptive cardinality counting to efficiently compute PV, UV, response times, and custom metrics while handling cross‑cluster log aggregation.
The article explores Eric Schmidt's bold claim that the traditional Internet will disappear, outlines how the Internet of Things is poised to dominate with massive market potential, highlights major tech companies' IoT strategies, compares IoT with the Internet, and details the key technologies driving this new ecosystem.
The article outlines the purposes, architecture, data ingestion, storage, analysis, sharing, application, real‑time processing, scheduling, monitoring, and best‑practice recommendations for building a fast, flexible, and reliable big‑data platform in the fast‑changing internet industry.
The article examines why enterprises should consider NoSQL over Hadoop for big data storage, compares the three leading NoSQL databases—MongoDB, Cassandra, and HBase—based on market popularity, technical strengths, scalability, and use‑case suitability, and concludes with guidance on selecting the most appropriate solution.
This article describes how Yahoo integrated deep learning into its massive Hadoop ecosystem by adding GPU nodes, using YARN and Spark to run Caffe at scale, and presents performance results on AlexNet and GoogLeNet alongside open‑source contributions.
Airbnb leverages AWS, Hadoop, Presto, Airflow, and custom machine‑learning tools to power its global marketplace, optimizing search, pricing, and data pipelines while achieving significant cost savings and operational efficiency.
The article explains the need for low‑latency, high‑performance, distributed real‑time processing, outlines the challenges such systems must address, and introduces Storm as a Hadoop‑like framework for stream processing, detailing its architecture, fault‑tolerance mechanisms, transactional topology, and large‑scale deployment at Taobao.
Apache Storm, Spark Streaming, and Samza are three open‑source, low‑latency, scalable distributed systems for real‑time data processing; this article outlines their architectures, key concepts, differences in data handling, state management, delivery guarantees, and typical use‑cases to help you choose the right framework.
This article introduces Apache Storm, Spark Streaming, and Samza, explains their architectures, common features, key differences such as delivery guarantees and state management, and provides guidance on selecting the most suitable framework for various real‑time big‑data use cases.
This article provides a concise overview of several open‑source real‑time stream processing platforms—including S4, Storm, StreamBase, HStreaming, Esper/NEsper, Kafka, Scribe, and Flume—highlighting their main features, programming languages, and project links for further reference.
This article introduces OWL, a distributed, enterprise‑grade monitoring solution that combines infrastructure and business metrics, offers floating alert rules, customizable dashboards, visual asset management, a resilient Golang‑based agent, and a parallel‑scalable HBase storage backend.
The article explains how distributed machine learning evolved from parallel computing to handle massive, long‑tail data sets, discusses the importance of scalability, fault recovery, and data‑parallel algorithms, and reviews frameworks such as MPI, MapReduce, and Pregel for building large‑scale AI systems.
This article presents a PHP‑based web‑scraping experiment that collects and visualizes several months of data from the “Da Gai Er” board of the Caoliu forum, revealing user activity patterns, image hosting distribution, registration trends, and overall forum health through charts and statistical summaries.
Although sites like Taobao appear simple to users, they rely on massive distributed search, caching, storage, load‑balancing, CDN, logging, and data‑analysis systems that demand sophisticated backend engineering, massive infrastructure, and specialized algorithms, explaining why countless top engineers are required to keep them running.
This article records a WeChat Q&A where industry experts discuss selecting open‑source big data solutions, advertising‑specific data scenarios, and share a practical lambda‑style platform architecture featuring Hadoop, Spark, Storm, Elasticsearch, Redis and MySQL.
The article describes a two‑year, 400‑billion‑tweet crawling project, its statistical and sentiment analyses linking sleep patterns, weekdays, holidays, and market indices, and the low‑cost technical infrastructure built to store and query the massive dataset.
The article distills ten pivotal keywords—Industrial 4.0, Internet+, BFV, microservices, distributed systems, big data, multi‑screen fusion, Docker, OpenStack, and large‑platform micro‑apps—explaining how each shapes the evolution of enterprise software architecture and what challenges and opportunities they bring.
Spark’s big‑data analytics ecosystem comprises core components such as the in‑memory RDD data structure, Streaming for real‑time processing, GraphX for graph analytics, MLlib for machine‑learning, Spark SQL for querying, the Tachyon file system, and SparkR, each enabling scalable, distributed computation.
Tracing the evolution of web technologies—from early AJAX challenges and jQuery’s rise, through Chrome’s dominance, GitHub’s impact, OAuth, JSON, and modern frameworks like Node.js and Bootstrap—the article reflects on how these tools reshaped frontend development and the broader software landscape.
Voidbox integrates Docker containers with YARN to simplify distributed application development, improve deployment, boost cluster efficiency, and provide fault‑tolerant, DAG‑based execution modes, enabling seamless resource management for Hadoop‑based big data jobs.
This article explains how Tencent Game's BlueKing platform redesigns operations by building open‑source PaaS capabilities, automating fault self‑healing, enabling fully automated game server region launches, supporting self‑service change releases, leveraging big‑data for real‑time decisions, and moving toward open‑source and hybrid‑cloud solutions.
This article reviews the evolution of big‑data management technologies, discusses the criteria for choosing appropriate big‑data benchmarks, compares existing benchmarks such as MapReduce tests, YCSB, BigBench and BigFrame, and provides an in‑depth analysis of the TPC‑DS benchmark and its certification status.
The article details how Qihoo 360 adopted MongoDB since 2011, scaling to over 100 applications, 1,500 instances and 20 billion daily queries, and shares their architectural choices, backup strategies, best‑practice recommendations, and advice for teams considering MongoDB in large‑scale, cloud‑native environments.
At Airbnb’s inaugural OpenAir conference, the company unveiled three open‑source big‑data tools—Airpal, a Presto‑based visual SQL query engine; Aerosolve, an interpretable machine‑learning engine for pricing recommendations; and Airflow, an internal platform for orchestrating and monitoring data pipelines.
Facebook’s data warehouse, storing over 300 PB and growing by 600 TB daily, transitioned from the RCFile format to an optimized ORCFile implementation, achieving 5‑8× better compression and up to three‑fold faster write performance while maintaining high read efficiency.
This article explains how logs—simple, append‑only, time‑ordered records—serve as the core abstraction behind databases, distributed systems, data integration pipelines, and modern stream‑processing platforms such as Kafka and Hadoop, illustrating their design, scalability, and practical challenges.
Amid heated debate over China’s Hengshui model, educators worldwide are envisioning future schools that leverage big-data analytics, immersive technology, and flexible, student-centered learning to cultivate critical thinking, creativity, and empathy, moving beyond traditional exam-driven curricula toward personalized, interdisciplinary education.
The article compares Apache Storm and Apache Spark, examining their origins, architecture, language support, integration capabilities, and performance characteristics, and offers guidance on selecting the right platform for real‑time business intelligence based on specific workload and infrastructure needs.
This article introduces a series of algorithms for analyzing the Weibo social network, including label propagation, LDA‑based user similarity, time‑aware and interaction‑aware similarity measures, community detection, influence ranking via PageRank variants, and methods for identifying spam users, illustrating how these techniques can be applied to large‑scale social media data.
The article describes how a mobile analytics service processes billions of events daily using a Lambda‑style architecture that combines Kafka, Storm, Amazon EMR, and S3 to achieve scalable, fault‑tolerant batch and real‑time computation, while ensuring reliable event ingestion and graceful degradation.
The interview with Douban's chief architect Hong QN details the platform's online and offline architecture, including load balancing, the DAE PaaS, the BeansDB key‑value store, the DPark big‑data processing engine, and the team organization and operational practices that support these systems.
This article explains HBase's column‑oriented architecture, key concepts such as Rowkey, ColumnFamily, and Region, provides Java API examples for table operations, and offers practical optimization techniques—including pre‑splitting, Rowkey design, caching, and compaction settings—to improve read/write performance.
During a detailed live session, senior Dianping engineer Wang Xinchun explains the company's real‑time computing platform built on Apache Storm, covering use cases such as dashboards, search and recommendation, system architecture, data ingestion tools like Blackhole and Puma, performance tuning, monitoring, and practical best‑practice recommendations.
In his 2015 China Hotel Marketing Summit keynote, Ctrip CTO Ye Yamin explained how machine‑learning models built on purchase behavior and order data improve hotel room availability predictions, shorten confirmation times, personalize recommendations, and evaluate advertising effectiveness, illustrating a data‑driven approach to user experience and operations.
This article explains how LinkedIn uses Apache Kafka as a high‑throughput, fault‑tolerant messaging backbone, detailing its architecture, message categories, layered replication, audit mechanisms, and the engineering practices that keep billions of daily messages reliable and fast.
Pinterest built a real‑time data pipeline that streams user engagement events through Apache Kafka into Spark Streaming, enriches them with location and category information, and persists the results in MemSQL to enable fast, SQL‑based analytics for its recommendation engine.
The article explains the fundamentals of stream processing, event sourcing, and complex event processing, comparing raw event storage with aggregated results, illustrating architectures with Kafka, Samza, and other frameworks, and highlighting benefits such as scalability, flexibility, and decoupling for modern data‑driven systems.
This article explains Hadoop’s tiered storage concept, describing how data is classified by temperature—hot, warm, cold, frozen—and automatically moved across disk and archive layers to optimize cost and performance, with examples from Hadoop versions and eBay’s large‑scale deployment.
This article introduces Apache Storm, Spark Streaming, and Apache Samza, outlines their architectures, highlights commonalities and differences such as delivery guarantees and state management, and offers guidance on selecting the most suitable framework for various real‑time big‑data use cases.
The article details Facebook’s LAMP‑based architecture, describing how HipHop compiles PHP to C++, Thrift‑based services in PHP, C++, and Java run on custom servers, and how MySQL, Memcached, Cassandra, HBase, Hadoop, Hive, Scribe, BigPipe, Varnish, Haystack and other components together enable handling over 60,000 servers, 300 TB of cached data, 1 trillion daily clicks and petabytes of storage.
This article discusses various log collection and analysis architectures, comparing solutions such as Flume‑Kafka‑Storm pipelines, Sentry, MongoDB, ELK stack, and Hadoop, and shares practical experiences, advantages, drawbacks, and deployment tips from multiple engineers.
In 2014 Suning’s IT division built a robust, cloud‑native architecture and big‑data platform that enabled flexible scaling, real‑time analytics, secure CDN delivery, and comprehensive monitoring, supporting high‑traffic promotional events and laying the groundwork for future O2O and financial services expansion.
This article explains how Apache Spark improves on Hadoop MapReduce by keeping intermediate data in memory, introduces the core RDD abstraction, compares Spark’s transformations and actions with Hadoop, and shows how Spark can run on Standalone, YARN, and various programming languages such as Scala, Java, and Python.
At Ctrip’s TDAY event, senior VP Eric Ye explained how big‑data techniques such as cross‑screen processing, real‑time APIs, and predictive models enable personalized travel recommendations and dramatically improve call‑center efficiency, illustrating the commercial impact of data‑driven marketing.
The article examines Baidu’s massive 2014 investment in artificial intelligence—covering Baidu Brain, breakthroughs in vision, speech and NLP, big‑data capabilities, open platforms, IoT hardware, and talent strategy—to explain how these moves may reshape both Baidu and the broader technology landscape.
This article reviews Spark 1.2’s major enhancements—including the External Data Source API, column pruning, predicate pushdown, and in‑memory columnar storage—while also detailing Baidu’s large‑scale Spark deployments, its custom high‑performance Shuffle service, and the integration of Spark with the Tachyon memory file system.
This article provides a comprehensive overview of the Hadoop family—detailing more than twenty open‑source projects, their core functions, and a structured learning roadmap to help developers master Hadoop, Hive, Pig, HBase, Zookeeper, Mahout, and related tools.
At Baidu’s November 25 technical salon, senior leaders Robin Li, Wang Jin and Andrew Ng highlighted the company’s AI‑driven strategy—emphasizing sub‑second search, massive deep‑learning and data infrastructure, a 14% revenue R&D spend, breakthroughs in vision, speech, NLP and autonomous‑driving platforms, and a new AI talent program—positioning Baidu as a leading innovator in big‑data and intelligent connectivity.
The article recaps Huawei's five‑day OpenStack Paris summit, highlighting eleven keynote talks on enterprise OpenStack, multi‑site cascading, deployment tools, a 200‑node big‑data cloud, NFV optimizations, software‑defined infrastructure, and the FusionSphere‑based OpenStack journey.
This article explains Hadoop 2.0's High Availability architecture, comparing the NFS and Quorum Journal Manager methods, detailing their principles, failover mechanisms, and practical tips for reliable NameNode redundancy in big‑data deployments.
This article walks through the essential steps to install and configure Hadoop 2.0 on a two‑node Linux cluster, covering version selection, directory setup, core XML files, YARN settings, service startup, verification commands, and basic troubleshooting tips.
The interview with Fourinone founder Peng Yuan explores the framework's evolution from a parallel computing project to a 220 KB distributed system with its own NoSQL database engine CoolHash, compares it to Hadoop, and discusses its open‑source release, technical design choices, and real‑world deployments in finance and enterprise environments.
This article examines Baidu’s home‑grown real‑time big‑data platforms Dstream and TM, detailing their architectures, performance metrics, key features, and practical use cases such as log ETL and real‑time bidding, while highlighting how they meet millisecond‑level processing demands.
This article examines the true definition of smart hardware, explores why it has become a hot market, analyzes the competition for entry points like routers and TVs, and predicts how future business models will shift from selling devices to selling cloud‑based services.
This article explains how to evaluate Hadoop workloads and select balanced hardware—covering storage, compute, network, and memory specifications for master and worker nodes—to build an efficient, cost‑effective Hadoop cluster.
Analyzing AngelList data for transportation‑sector startups, the report reveals JavaScript/Node.js and Ruby on Rails dominate programming and front‑end, MySQL/MongoDB lead storage, iOS tops mobile, AWS leads infrastructure, Chef leads DevOps, while Python is favored by higher‑tier firms and PHP by lower‑tier ones, though the scoring methodology remains opaque.
This article examines the ongoing debate between SQL and NoSQL databases for big‑data projects, presenting expert arguments on performance, scalability, standardization, and flexibility to help enterprises decide the optimal solution.
Using search query volumes, Baidu’s big‑data engine forecasts tourist numbers for Chinese attractions, achieving over 90% accuracy and partnering with CCTV to broadcast real‑time crowd predictions during the May Day holiday, while also outlining future forecasting plans for flu, sports, finance and real‑estate trends.
The article surveys the rapid growth of big data across sectors, highlights key open‑source technologies such as Hadoop, Spark, HBase and others, and profiles ten influential companies—including AWS, Cloudera, Hortonworks, IBM and Microsoft—offering insight into current trends, capabilities and competitive dynamics in the big‑data ecosystem.
