apache / apache/gluten

libvelox.so issue while running Spark tpcds/tpch workload with Gluten

Open
#6,221 0 comments 0 reactions 0 assignees View on GitHub
bug triage
Dominant language
Scala
Stars
1.6k
Forks
657
Avg merge
2d 14h
Merged PRs (30d)
80

Description

### Backend

VL (Velox)

### Bug description

Running on GCP EMR 80 vcpu with Gluten enable ended up below issue . No issue on N2 - ICX 16 VCPU run .

Same issue on both TPCH and TPCDS run : NO Issue to run same code in Vanilla . Using Spark notebook to execute this :

![image](https://github.com/apache/incubator-gluten/assets/104393458/cb7f5f63-c132-4b95-9c8b-142f5fcb3202)

Run parameters below :

![image](https://github.com/apache/incubator-gluten/assets/104393458/0ed27b71-dda8-45f6-bb0d-332cf0a2e5e2)

### Spark version

Spark-3.3.x

### Spark configurations

Standard Gluten configurations - run file on ICX GCP N2 machine

### System information

Ubuntu 20.04 using the Gluten Velox jar

### Relevant logs

_No response_

Contributor guide

Open the contributing guide

Research direction

The report names a Spark notebook, TPCH and TPCDS workloads, and the Gluten Velox jar, but no source files or tests. Start by reproducing the libvelox.so failure on GCP EMR and comparing it with the working N2 ICX run, while collecting the missing logs. Done requires a reproducible diagnosis of the environment-specific failure and a verified fix or actionable next step.

Written by the indexing model from the issue text.

Assessment

Tech stack
gcp, scala, spark, ubuntu
Domain
backend, data-engineering
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.