[
https://issues.apache.org/jira/browse/SPARK-48950?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18021061#comment-18021061
]
Thomas Newton commented on SPARK-48950:
---------------------------------------
We've been running spark 3.5.x with https://github.com/apache/spark/pull/39950
reverted for about a year now. I'm not aware of the problem reoccurring, but
given that the change looks totally sensible it makes me think that it's not
the root cause, and likely reverting it just reduces probability of occurrence.
I separately became aware of
https://issues.apache.org/jira/browse/HADOOP-18521. I have some suspicion that
this could be related, but I haven't had a chance investigate.
> Corrupt data from parquet scans
> -------------------------------
>
> Key: SPARK-48950
> URL: https://issues.apache.org/jira/browse/SPARK-48950
> Project: Spark
> Issue Type: Bug
> Components: Input/Output
> Affects Versions: 3.5.0, 3.5.1, 3.5.2, 4.1.0, 4.0.0
> Environment: Spark 3.5.0
> Running on kubernetes
> Using Azure Blob storage with hierarchical namespace enabled
> Reporter: Thomas Newton
> Priority: Major
> Labels: correctness, data-corruption
> Attachments: corrupt_data_examples.zip, example_task_errors.txt,
> generate_data_to_reproduce_spark-48950.ipynb, job_dag.png,
> reproduce_spark-48950.py, sql_query_plan.png
>
>
> Its very rare and non-deterministic but since Spark 3.5.0 we have started
> seeing a correctness bug in parquet scans when using the vectorized reader.
> We've noticed this on double type columns where occasionally small groups
> (typically 10s to 100s) of rows are replaced with crazy values like
> `-1.29996470e+029, 3.56717569e-184, 7.23323243e+307, -1.05929677e+045,
> -7.60562076e+240, -3.18088886e-064, 2.89435993e-116`. I think this is the
> result of interpreting uniform random bits as a double type. Most of my
> testing has been on an array of double type column but we have also seen it
> on un-nested plain double type columns.
> I've been testing this by adding a filter that should return zero results but
> will return non-zero if the parquet scan has problems. I've attached
> screenshots of this from the Spark UI.
> I did a `git bisect` and found that the problem starts with
> [https://github.com/apache/spark/pull/39950], but I haven't yet understood
> why. Its possible that this change is fine but it reveals a problem
> elsewhere? I did also notice [https://github.com/apache/spark/pull/44853]
> which appears to be a different implementation of the same thing so maybe
> that could help.
> Its not a major problem by itself but another symptom appears to be that
> Parquet scan tasks fail at a rate of approximately 0.03% with errors like
> those in the attached `example_task_errors.txt`. If I revert
> [https://github.com/apache/spark/pull/39950] I get exactly 0 task failures on
> the same test.
>
> The problem seems to be a bit dependant on how the parquet files happen to be
> organised on blob storage so I don't yet have a reproduce that I can share
> that doesn't depend on private data.
> I tested on a pre-release 4.0.0 and the problem was still present.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
