You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by GitBox <gi...@apache.org> on 2022/12/21 07:16:31 UTC

[GitHub] [spark] zhengruifeng commented on pull request #39151: [WIP] Introduce a proto message to make plan deterministic

zhengruifeng commented on PR #39151:
URL: https://github.com/apache/spark/pull/39151#issuecomment-1360941255

   quick tests:
   
   1, cache (after make some private ones public)
   
   ```
   
   scala> val df = spark.range(0, 100)
   df: org.apache.spark.sql.Dataset[Long] = [id: bigint]
   
   scala> df.cache()
   res0: df.type = [id: bigint]
   
   scala> val plan = df.logicalPlan
   plan: org.apache.spark.sql.catalyst.plans.logical.LogicalPlan =
   Range (0, 100, step=1, splits=Some(10))
   
   scala> import org.apache.spark.sql.{Column, Dataset, SparkSession}
   import org.apache.spark.sql.{Column, Dataset, SparkSession}
   
   scala> val df2 = Dataset.ofRows(spark, plan)
   df2: org.apache.spark.sql.DataFrame = [id: bigint]
   
   scala> df.storageLevel
   res1: org.apache.spark.storage.StorageLevel = StorageLevel(disk, memory, deserialized, 1 replicas)
   
   scala> df2.storageLevel
   res2: org.apache.spark.storage.StorageLevel = StorageLevel(disk, memory, deserialized, 1 replicas)
   
   scala>  df == df2
   res3: Boolean = false
   
   scala> df2.explain
   == Physical Plan ==
   InMemoryTableScan [id#0L]
      +- InMemoryRelation [id#0L], StorageLevel(disk, memory, deserialized, 1 replicas)
            +- *(1) Range (0, 100, step=1, splits=10)
   
   
   
   scala> df.explain
   == Physical Plan ==
   InMemoryTableScan [id#0L]
      +- InMemoryRelation [id#0L], StorageLevel(disk, memory, deserialized, 1 replicas)
            +- *(1) Range (0, 100, step=1, splits=10)
   
   ```
   
   2, relation
   
   ```
   scala> val df = spark.range(0, 100)
   df: org.apache.spark.sql.Dataset[Long] = [id: bigint]
   
   scala> df.write.parquet("/tmp/1.pq")
                                                                                   
   scala> val df2 = spark.read.parquet("/tmp/1.pq")
   df2: org.apache.spark.sql.DataFrame = [id: bigint]
   
   scala> df2.queryExecution.logical.deterministic
   res2: Boolean = true
   
   ```


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org