Awesome GitHub RepositoriesData Shuffling Algorithms

Ray is a distributed computing framework designed to scale Python and Java applications across clusters by abstracting task scheduling and resource management. It functions as a resource-aware execution engine that manages task dependencies, placement, and fault tolerance across networked compute nodes. At its core, the system provides a stateful actor model, allowing developers to define classes that run in dedicated processes to maintain and mutate internal state across remote method calls. The framework distinguishes itself through a robust cross-language interoperability layer, enabling f

This project serves as a comprehensive technical reference for the architecture and design of data-intensive applications. It provides a structured analysis of the fundamental principles required to build reliable, scalable, and maintainable software systems, covering the core trade-offs inherent in modern data infrastructure. The repository explores the mechanics of distributed data management, including strategies for replication, partitioning, and achieving consensus across multiple nodes. It details the design of storage engines, indexing techniques, and transaction management models, whi

Apache Druid is a real-time analytics database and distributed columnar time-series store designed for sub-second analytical queries. It functions as a data platform featuring a distributed SQL query engine and a real-time data ingestion system for moving historical and streaming data from external sources. The system is distinguished by its ability to provide low-latency analytics under high concurrency to power operational dashboards. It implements a Kerberos-secured environment for user authentication and employs a shared-nothing cluster architecture to enable horizontal scaling. The plat

SparkInternals est une référence technique et un guide d'architecture détaillant la conception interne et l'implémentation du moteur de calcul distribué Apache Spark. Il sert d'étude sur l'analyse des moteurs de big data, en se concentrant sur la gestion de l'exécution en cluster et l'interaction entre les nœuds drivers, les exécuteurs et les workers. Le projet fournit une décomposition détaillée de la manière dont les plans logiques sont convertis en étapes d'exécution physiques. Il analyse spécifiquement la mécanique des opérations de shuffle, la gestion de la mémoire et la coordination de la planification des jobs distribués. La documentation couvre un large éventail de capacités de calcul distribué, incluant la planification de l'exécution des requêtes, la gestion des dépendances de données et les stratégies de mise en cache en mémoire. Elle examine également la distribution des tâches, l'exécution parallèle et les processus utilisés pour la reprise sur erreur et la persistance des données.