nerdexam
Huawei

H13-711_V3.5 · Question #340

An Executor of a Spark task can run multiple tasks at the same time

The correct answer is A. True. Option A is correct because a Spark Executor is a JVM process that holds a thread pool, and each thread can run an independent task concurrently - the degree of parallelism within a single Executor is controlled by spark.executor.cores, which defaults to more than 1 in many…

Big Data Processing Technologies (MapReduce, Spark, Hive)

Question

An Executor of a Spark task can run multiple tasks at the same time

Options

  • ATrue
  • BFalse

How the community answered

(31 responses)
  • A
    81% (25)
  • B
    19% (6)

Explanation

Option A is correct because a Spark Executor is a JVM process that holds a thread pool, and each thread can run an independent task concurrently - the degree of parallelism within a single Executor is controlled by spark.executor.cores, which defaults to more than 1 in many configurations. This means a single Executor can process multiple partitions simultaneously rather than sequentially.

Option B is wrong because it conflates an Executor (a long-lived worker process) with a single-threaded worker - Spark intentionally allocates multiple cores per Executor to maximize CPU utilization on each node.

Memory tip: Think of an Executor as a manager with a team of workers (threads/cores). One manager can direct multiple workers at the same time - executor.cores is the team size.

Topics

#Spark Executors#Task Parallelism#Concurrent Execution#Execution Model

Community Discussion

No community discussion yet for this question.

Full H13-711_V3.5 Practice