ANY_VALUE memory regression in Comet 1.2.0

未关闭
  • 哪里不对？
#7,541 1 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看

维护者通常 2 天内回复

@andygrove 已经在做这个了。

开始于 2026年10月26日。

  • #7249 来自 @andygrove —— 未关闭

评估

难度
3/5
预计耗时
1-2 天
新手友好度
68/100
Issue 类型
缺陷
描述清晰度
描述清楚
活跃度
活跃
技术栈
rust, scala, spark
领域
backend, performance

调研方向

Start with the aggregate dependency configuration and native tests for TrivialFirstValueAccumulator::merge_batch; the issue identifies the DataFusion 55.2.0 behavior and upstream fix #26743. Check which released DataFusion version contains that fix and how Comet pins it, then run the focused native regression tests. Done means the dependency includes the fix and the tests pass; validate the rebuilt JAR with the supplied Spark reproducer if possible.

由索引模型根据 Issue 内容生成。

描述

area:aggregation bug priority:medium

Comet 1.2.0 fails ANY_VALUE(array<string>) with an oversized memory reservation.
Spark lowers this to first, which uses DataFusion 55.2.0's
TrivialFirstValueAccumulator::merge_batch. That method retains the input's
backing buffers and counts them repeatedly across groups.

This is fixed by apache/datafusion#26743.
Could we update to a dependency containing it when released?

Reproducer

With Spark 4.1.3, Java 21, and the Comet JAR installed in $SPARK_HOME/jars,
save this as inline_repro.py:

from pyspark.sql import SparkSession

spark = (
    SparkSession.builder.config("spark.ui.enabled", "false")
    .config("spark.sql.adaptive.enabled", "false")
    .config("spark.sql.shuffle.partitions", "2")
    .config("spark.plugins", "org.apache.spark.CometPlugin")
    .config(
        "spark.shuffle.manager",
        "org.apache.spark.sql.comet.execution.shuffle.CometShuffleManager",
    )
    .config("spark.comet.enabled", "true")
    .config("spark.comet.exec.enabled", "true")
    .config("spark.comet.shuffle.enabled", "true")
    .config("spark.comet.nativeLoadRequired", "true")
    .config("spark.comet.exec.aggregate.enabled", "true")
    .config("spark.memory.offHeap.enabled", "true")
    .config("spark.memory.offHeap.size", "128m")
    .getOrCreate()
)

try:
    path = "/tmp/comet-any-value-input"
    spark.range(256, numPartitions=4).selectExpr(
        "CAST(id AS STRING) AS user_id",
        "transform(sequence(0, 199), x -> concat(lpad(CAST(id AS STRING), 8, '0'), ':', lpad(CAST(x AS STRING), 4, '0'))) AS values",
    ).write.mode("overwrite").parquet(path)
    spark.read.parquet(path).createOrReplaceTempView("input")
    result = spark.sql(
        "SELECT user_id, ANY_VALUE(values) AS values FROM input GROUP BY user_id"
    )
    result.explain()
    rows = result.collect()
    expected = {str(i): [f"{i:08d}:{j:04d}" for j in range(200)] for i in range(256)}
    assert len(rows) == 256
    assert {row.user_id: row["values"] for row in rows} == expected
finally:
    spark.stop()

"$SPARK_HOME/bin/spark-submit" --master 'local[1]' --driver-memory 1g \
  inline_repro.py

The script sets a 128 MiB native pool and two shuffle partitions. It fails in
OrderedFinalAggregateStream, requesting 80,775,440 bytes against a
67,108,864-byte share. The strings contain just 650 KiB of data.

The same script succeeds with Comet 1.1.0, or with
spark.comet.exec.aggregate.enabled set to false on 1.2.0. It checks every
output array.

Fix verification

Focused native tests use DataFusion 55.2.0 and Arrow 59.3.0. For the same
selected array, update_batch reports 3,832 bytes while merge_batch reports
1,311,296 bytes. Adding the upstream fix makes both report 3,832 bytes:

 self.first = ScalarValue::try_from_array(first, 0)?;
+self.first.compact();
 self.is_set = true;

Both native regression tests fail before this change and pass afterward,
with unchanged output values. A rebuilt Comet JAR has not yet been tested.

主要语言
Scala
星标
1.3k
派生
414
平均合并
3 天 5 小时
30 天内合并 PR
210

环境准备

从这里开始

  1. 先读完整个 Issue，再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库，在一个分支上完成修改。
  4. 提交 Pull Request，并在描述里引用这个 Issue 编号。

apache/datafusion-comet 的其他 Issue

查看 apache/datafusion-comet 的全部 Issue

相似的 Issue

更多 Scala Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。