distributed computing system, cluster of nodes, master node, worker nodes, resilient distributed dataset (RDD), directed acyclic graph (DAG), in-memory processing, parallel operations, fault tolerance, lazy evaluation, Spark SQL, DataFrame, Dataset, Spark Streaming, real-time processing, machine learning library (MLlib), graph processing (GraphX), storage layer abstraction (Hadoop Distributed File System - HDFS, Amazon S3), YARN cluster manager, standalone mode, Mesos, resource allocation, executor process, driver program, task scheduling, shuffle operation, partitioning, caching, persistence, broadcast variables, accumulator, API, Scala, Java, Python, data partition, efficient data serialization, optimization engine (Catalyst), tungsten execution engine, web UI for monitoring, stage, job, action, transformation, event log, light pipeline, structured streaming, checkpointing, query planner, code generation, adaptive query execution.