[SPARK-28042] Support mapping spark.local.dir to hostPath volume

• Type: Improvement
• Status: Resolved
• Priority: Minor
• Resolution: Fixed
• Affects Version/s: 3.0.0
• Fix Version/s: 3.0.0
• Component/s: Kubernetes, Spark Core
• Assignee: Junjie Chen
• Reporter: Junjie Chen
• Created: 13/Jun/19 23:35
• Updated: 17/May/20 18:24
• Resolved: 29/Jul/19 17:44

Description

Currently, the k8s executor builder mount spark.local.dir as emptyDir or memory, it should satisfy some small workload, while in some heavily workload like TPCDS, both of them can have some problem, such as pods are evicted due to disk pressure when using emptyDir, and OOM when using tmpfs.

In particular on cloud environment, users may allocate cluster with minimum configuration and add cloud storage when running workload. In this case, we can specify multiple elastic storage as spark.local.dir to accelerate the spilling.

Issue Links

• is duplicated by: SPARK-28407 Support mapping spark.local.dir to hostPath volume
• links to: GitHub Pull Request #24879