[KYUUBI #7192] Fix filestatus not cached #7191
+445
−21
There are no files selected for viewing
This file contains hidden or 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 hidden or 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 hidden or 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 +1,142 @@ | ||
| /* | ||
| * 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.kyuubi.spark.connector.hive.read | ||
|
|
||
| import java.util.concurrent.TimeUnit | ||
| import java.util.concurrent.atomic.AtomicBoolean | ||
|
|
||
| import scala.collection.JavaConverters._ | ||
|
|
||
| import com.google.common.cache._ | ||
| import org.apache.hadoop.fs.{FileStatus, Path} | ||
| import org.apache.spark.internal.Logging | ||
| import org.apache.spark.sql.SparkSession | ||
| import org.apache.spark.sql.execution.datasources.{FileStatusCache, NoopCache} | ||
| import org.apache.spark.util.SizeEstimator | ||
|
|
||
| /** | ||
| * Use [[HiveFileStatusCache.getOrCreate()]] to construct a globally shared file status cache. | ||
| */ | ||
| object HiveFileStatusCache { | ||
| private var sharedCache: HiveSharedInMemoryCache = _ | ||
|
|
||
| /** | ||
| * @return a new FileStatusCache based on session configuration. Cache memory quota is | ||
| * shared across all clients. | ||
| */ | ||
| def getOrCreate(session: SparkSession, qualifiedName: String): FileStatusCache = | ||
| synchronized { | ||
| if (session.sessionState.conf.manageFilesourcePartitions && | ||
| session.sessionState.conf.filesourcePartitionFileCacheSize > 0) { | ||
| if (sharedCache == null) { | ||
| sharedCache = new HiveSharedInMemoryCache( | ||
| session.sessionState.conf.filesourcePartitionFileCacheSize, | ||
| session.sessionState.conf.metadataCacheTTL) | ||
| } | ||
| sharedCache.createForNewClient(qualifiedName) | ||
| } else { | ||
| NoopCache | ||
| } | ||
| } | ||
|
|
||
| def resetForTesting(): Unit = synchronized { | ||
| sharedCache = null | ||
| } | ||
| } | ||
|
|
||
| /** | ||
| * An implementation that caches partition file statuses in memory. | ||
|
There was a problem hiding this comment. if the code is forked from spark, clarify where and which version it comes from, and briefly explain your modification and expectation |
||
| * | ||
| * @param maxSizeInBytes max allowable cache size before entries start getting evicted | ||
| */ | ||
| private class HiveSharedInMemoryCache(maxSizeInBytes: Long, cacheTTL: Long) extends Logging { | ||
|
|
||
| // Opaque object that uniquely identifies a shared cache user | ||
| private type ClientId = Object | ||
|
|
||
| private val warnedAboutEviction = new AtomicBoolean(false) | ||
|
|
||
| // we use a composite cache key in order to distinguish entries inserted by different clients | ||
| private val cache: Cache[(ClientId, Path), Array[FileStatus]] = { | ||
| // [[Weigher]].weigh returns Int so we could only cache objects < 2GB | ||
| // instead, the weight is divided by this factor (which is smaller | ||
| // than the size of one [[FileStatus]]). | ||
| // so it will support objects up to 64GB in size. | ||
| val weightScale = 32 | ||
| val weigher = new Weigher[(ClientId, Path), Array[FileStatus]] { | ||
| override def weigh(key: (ClientId, Path), value: Array[FileStatus]): Int = { | ||
| val estimate = (SizeEstimator.estimate(key) + SizeEstimator.estimate(value)) / weightScale | ||
| if (estimate > Int.MaxValue) { | ||
| logWarning(s"Cached table partition metadata size is too big. Approximating to " + | ||
| s"${Int.MaxValue.toLong * weightScale}.") | ||
| Int.MaxValue | ||
| } else { | ||
| estimate.toInt | ||
| } | ||
| } | ||
| } | ||
| val removalListener = new RemovalListener[(ClientId, Path), Array[FileStatus]]() { | ||
| override def onRemoval( | ||
| removed: RemovalNotification[(ClientId, Path), Array[FileStatus]]): Unit = { | ||
| if (removed.getCause == RemovalCause.SIZE && | ||
| warnedAboutEviction.compareAndSet(false, true)) { | ||
| logWarning( | ||
| "Evicting cached table partition metadata from memory due to size constraints " + | ||
| "(spark.sql.hive.filesourcePartitionFileCacheSize = " | ||
| + maxSizeInBytes + " bytes). This may impact query planning performance.") | ||
| } | ||
| } | ||
| } | ||
|
|
||
| var builder = CacheBuilder.newBuilder() | ||
| .weigher(weigher) | ||
| .removalListener(removalListener) | ||
| .maximumWeight(maxSizeInBytes / weightScale) | ||
|
|
||
| if (cacheTTL > 0) { | ||
| builder = builder.expireAfterWrite(cacheTTL, TimeUnit.SECONDS) | ||
| } | ||
|
|
||
| builder.build[(ClientId, Path), Array[FileStatus]]() | ||
| } | ||
|
|
||
| /** | ||
| * @return a FileStatusCache that does not share any entries with any other client, but does | ||
| * share memory resources for the purpose of cache eviction. | ||
| */ | ||
| def createForNewClient(clientId: Object): HiveFileStatusCache = new HiveFileStatusCache { | ||
|
|
||
| override def getLeafFiles(path: Path): Option[Array[FileStatus]] = { | ||
| Option(cache.getIfPresent((clientId, path))) | ||
| } | ||
|
|
||
| override def putLeafFiles(path: Path, leafFiles: Array[FileStatus]): Unit = { | ||
| cache.put((clientId, path), leafFiles) | ||
| } | ||
|
|
||
| override def invalidateAll(): Unit = { | ||
| cache.asMap.asScala.foreach { case (key, value) => | ||
| if (key._1 == clientId) { | ||
| cache.invalidate(key) | ||
| } | ||
| } | ||
| } | ||
| } | ||
|
|
||
| abstract class HiveFileStatusCache extends FileStatusCache {} | ||
| } | ||
This file contains hidden or 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 hidden or 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
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
TBH, the "globally shared" concept does not match the Spark's multi-session architecture, especially for Kyuubi use cases, it's possible that multi users share one Spark application.
I know that there are many hive-related instances are globally shared in Spark, as we are improving this part, let's make it possible to be session shared, and have a config to allow it to be global shared.