Kazuaki Ishizaki created SPARK-20479:
----------------------------------------
Summary: Performance degradation for large number of
hash-aggregated columns
Key: SPARK-20479
URL: https://issues.apache.org/jira/browse/SPARK-20479
Project: Spark
Issue Type: Improvement
Components: SQL
Affects Versions: 2.3.0
Reporter: Kazuaki Ishizaki
In comment of SPARK-20184, [~maropu] revealed that performance is degraded when
# of aggregated columns get large with whole-stage codegen.
{code}
./bin/spark-shell --master local[1] --conf spark.driver.memory=2g --conf
spark.sql.shuffle.partitions=1 -v
def timer[R](f: => {}): Unit = {
val count = 9
val iters = (0 until count).map { i =>
val t0 = System.nanoTime()
f
val t1 = System.nanoTime()
val elapsed = t1 - t0 + 0.0
println(s"#$i: ${elapsed / 1000000000.0}")
elapsed
}
println("Elapsed time: " + ((iters.sum / count) / 1000000000.0) + "s")
}
val numCols = 80
val t = s"(SELECT id AS key1, id AS key2, ${((0 until numCols).map(i => s"id AS
c$i")).mkString(", ")} FROM range(0, 100000, 1, 1))"
val sqlStr = s"SELECT key1, key2, ${((0 until numCols).map(i =>
s"SUM(c$i)")).mkString(", ")} FROM $t GROUP BY key1, key2 LIMIT 100"
// Elapsed time: 2.3084404905555553s
sql("SET spark.sql.codegen.wholeStage=true")
timer { sql(sqlStr).collect }
// Elapsed time: 0.527486733s
sql("SET spark.sql.codegen.wholeStage=false")
timer { sql(sqlStr).collect }
{code}
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
