
Answer-first summary for fast verification
Answer: Stage
In Apache Spark, a **Stage** is composed of multiple narrow transformations (operations that do not require data shuffling, like `map` or `filter`) that can be executed sequentially within the same stage. Stages are separated by wide transformations (e.g., `join` or `groupBy`), which require shuffling. A **Job** corresponds to an action (e.g., `collect()`) and is divided into stages. **Tasks** are the smallest units of work within a stage, executed per partition. **Slots** and **Executors** relate to resource management, not operation sequencing. Thus, the correct answer is **C (Stage)**.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
No comments yet.