Offset overflow - Comet's grouped accumulators build one array for all emitted groups

Abierto
  • ¿Algo no está bien?
#7,501 0 comentarios 0 reacciones 0 asignados Ver en GitHub

Los mantenedores suelen responder en 2 días

Nadie ha tomado este issue todavía.

Evaluación

Dificultad
4/5
Tiempo estimado
3-5 días
Aptitud para principiantes
42/100
Tipo de issue
Error
Claridad
Bastante claro
Estado de actividad
Activo
Stack tecnológico
rust, scala, spark
Área
backend, databases

Línea de trabajo

Start with the Rust accumulator implementations named in the issue: native/spark-expr/src/agg_funcs/collect.rs, max_min_by.rs, list_agg.rs, and approx_percentile.rs; trace their evaluate, state, and EmitTo::First paths. Check how errors are returned and how repeated partial emits handle retained groups. Add focused tests for overflow and repeated emits; done means overflow returns an error instead of panicking and chunked emits avoid quadratic work.

Escrito por el modelo de indexación a partir del texto del issue.

Descripción

area:aggregation bug priority:high

Part of #7267.

Problem

Comet's own GroupsAccumulators build one array for all the groups they emit, in evaluate and in state (which also runs when the aggregate spills). With EmitTo::All that is every group in the task, so the array overflows once the values collected across all groups pass 2 GiB, even though each group's own value is small. Spark keeps one buffer per group.

  • collect_list (native/spark-expr/src/agg_funcs/collect.rs:382-428) uses concat or interleave, which return OffsetOverflowError.
  • collect_set (collect.rs:717-732) and max_by/min_by (max_min_by.rs) decode with arrow-row's convert_rows, which panics with offset overflow (arrow-row 59.3.2 src/variable.rs:294).
  • listagg (list_agg.rs:304-317) and the approx_percentile state (approx_percentile.rs:414-421) build with StringArray::from and BinaryBuilder, which panic with byte array offset overflow.

For example, a final collect_list(json) GROUP BY user whose reduce partition holds more than 2 GiB of strings fails.

This is the accumulator side of #7278. Two things here matter for #7278's fix:

  • Chunked emit would call EmitTo::First(n) repeatedly, and in these accumulators each call costs time proportional to everything still retained. collect_list's compact (collect.rs:259) re-takes every retained batch, and collect_set's (collect.rs:622) re-inserts every remaining entry. Emitting in chunks would be quadratic.
  • The comment at collect.rs:509-518 says the element count is what limits the emitted List<i32>. For string and binary elements, the child's bytes are limited to 2 GiB as well.

Line references are for main at 4e6b12290f.

Workaround

Raise spark.sql.shuffle.partitions, so each task emits fewer groups.

Proposed fix

  • Return errors instead of panicking.
  • Make EmitTo::First(n) cheap, so the aggregate can emit groups in chunks bounded by bytes, together with #7278.

Tests

Check that an emit whose total passes the limit returns an error rather than panicking, using a few groups with large values (or a limit lowered for the test). Check the cost of repeated EmitTo::First with enough groups to show the quadratic time.

Lenguaje dominante
Scala
Estrellas
1.3k
Forks
414
Merge medio
3 d 5 h
PR fusionados (30 d)
210

Preparar el entorno

Primeros pasos

  1. Lee el issue completo y luego la guía de contribución del proyecto.
  2. Comenta en el issue que vas a ocuparte — evita que dos personas hagan lo mismo.
  3. Haz un fork del repositorio y trabaja en una rama.
  4. Abre un pull request que haga referencia al número del issue.

Más de apache/datafusion-comet

Todos los issues de apache/datafusion-comet

Issues similares

Más issues de Scala

Recibe los nuevos issues en tu correo

Un resumen breve de issues de GitHub para principiantes.