-
Notifications
You must be signed in to change notification settings - Fork 28.3k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[SPARK-14482][SQL] Change default Parquet codec from gzip to snappy
## What changes were proposed in this pull request? Based on our tests, gzip decompression is very slow (< 100MB/s), making queries decompression bound. Snappy can decompress at ~ 500MB/s on a single core. This patch changes the default compression codec for Parquet output from gzip to snappy, and also introduces a ParquetOptions class to be more consistent with other data sources (e.g. CSV, JSON). ## How was this patch tested? Should be covered by existing unit tests. Author: Reynold Xin <rxin@databricks.com> Closes #12256 from rxin/SPARK-14482.
- Loading branch information
Showing
4 changed files
with
65 additions
and
33 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
59 changes: 59 additions & 0 deletions
59
...re/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetOptions.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,59 @@ | ||
/* | ||
* Licensed to the Apache Software Foundation (ASF) under one or more | ||
* contributor license agreements. See the NOTICE file distributed with | ||
* this work for additional information regarding copyright ownership. | ||
* The ASF licenses this file to You under the Apache License, Version 2.0 | ||
* (the "License"); you may not use this file except in compliance with | ||
* the License. You may obtain a copy of the License at | ||
* | ||
* http://www.apache.org/licenses/LICENSE-2.0 | ||
* | ||
* Unless required by applicable law or agreed to in writing, software | ||
* distributed under the License is distributed on an "AS IS" BASIS, | ||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
* See the License for the specific language governing permissions and | ||
* limitations under the License. | ||
*/ | ||
|
||
package org.apache.spark.sql.execution.datasources.parquet | ||
|
||
import org.apache.parquet.hadoop.metadata.CompressionCodecName | ||
|
||
import org.apache.spark.internal.Logging | ||
import org.apache.spark.sql.internal.SQLConf | ||
|
||
/** | ||
* Options for the Parquet data source. | ||
*/ | ||
class ParquetOptions( | ||
@transient private val parameters: Map[String, String], | ||
@transient private val sqlConf: SQLConf) | ||
extends Logging with Serializable { | ||
|
||
import ParquetOptions._ | ||
|
||
/** | ||
* Compression codec to use. By default use the value specified in SQLConf. | ||
* Acceptable values are defined in [[shortParquetCompressionCodecNames]]. | ||
*/ | ||
val compressionCodec: String = { | ||
val codecName = parameters.getOrElse("compression", sqlConf.parquetCompressionCodec).toLowerCase | ||
if (!shortParquetCompressionCodecNames.contains(codecName)) { | ||
val availableCodecs = shortParquetCompressionCodecNames.keys.map(_.toLowerCase) | ||
throw new IllegalArgumentException(s"Codec [$codecName] " + | ||
s"is not available. Available codecs are ${availableCodecs.mkString(", ")}.") | ||
} | ||
shortParquetCompressionCodecNames(codecName).name() | ||
} | ||
} | ||
|
||
|
||
object ParquetOptions { | ||
// The parquet compression short names | ||
private val shortParquetCompressionCodecNames = Map( | ||
"none" -> CompressionCodecName.UNCOMPRESSED, | ||
"uncompressed" -> CompressionCodecName.UNCOMPRESSED, | ||
"snappy" -> CompressionCodecName.SNAPPY, | ||
"gzip" -> CompressionCodecName.GZIP, | ||
"lzo" -> CompressionCodecName.LZO) | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
none
should also be available, right? What do you @rxin think about replacing the hard-coded values intomap.keys
?