apache/pinot

[Segment ingestion job] Multi-threaded segment copy from staging dir to final destination

Open

#7,510 opened on Oct 4, 2021

View on GitHub
 (3 comments) (0 reactions) (0 assignees)Java (1,234 forks)batch import
enhancementhelp wantedingestion

Repository metrics

Stars
 (4,937 stars)
PR merge metrics
 (Avg merge 6d 7h) (186 merged PRs in 30d)

Description

SparkIngestionJob uses single threaded copy for segments copy from staging dir to final deep store dir(e.g. S3): https://github.com/apache/pinot/blob/7ce8b756dff2b153151517afd552759e44d46c75/pinot-plugins/pinot-batch-ingestion/pinot-batch-ingestion-spark/src/main/java/org/apache/pinot/plugin/ingestion/batch/spark/SparkSegmentGenerationJobRunner.java#L345

For a few hundred segments being uploaded, it can take forever. In this case, we should consider generating a list of source and destination paths for segment copy then use RDD to parallel this job.

Contributor guide

Research direction
Explore using Spark RDD to parallelize segment copy from staging to final destination.
Tech stack
java
Domain
backenddata
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
JavaSparkPinot
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
70