diff options
author | Calvin Jia <jia.calvin@gmail.com> | 2015-04-24 17:57:41 -0400 |
---|---|---|
committer | Sean Owen <sowen@cloudera.com> | 2015-04-24 17:57:41 -0400 |
commit | 438859eb7c4e605bb4041d9a547a16be9c827c75 (patch) | |
tree | 83b0589ea748fd090559532b3756c15ffbab6adb /core | |
parent | caf0136ec5838cf5bf61f39a5b3474a505a6ae11 (diff) | |
download | spark-438859eb7c4e605bb4041d9a547a16be9c827c75.tar.gz spark-438859eb7c4e605bb4041d9a547a16be9c827c75.tar.bz2 spark-438859eb7c4e605bb4041d9a547a16be9c827c75.zip |
[SPARK-6122] [CORE] Upgrade tachyon-client version to 0.6.3
This is a reopening of #4867.
A short summary of the issues resolved from the previous PR:
1. HTTPClient version mismatch: Selenium (used for UI tests) requires version 4.3.x, and Tachyon included 4.2.5 through a transitive dependency of its shaded thrift jar. To address this, Tachyon 0.6.3 will promote the transitive dependencies of the shaded jar so they can be excluded in spark.
2. Jackson-Mapper-ASL version mismatch: In lower versions of hadoop-client (ie. 1.0.4), version 1.0.1 is included. The parquet library used in spark sql requires version 1.8+. Its unclear to me why upgrading tachyon-client would cause this dependency to break. The solution was to exclude jackson-mapper-asl from hadoop-client.
It seems that the dependency management in spark-parent will not work on transitive dependencies, one way to make sure jackson-mapper-asl is included with the correct version is to add it as a top level dependency. The best solution would be to exclude the dependency in the modules which require a higher version, but that did not fix the unit tests. Any suggestions on the best way to solve this would be appreciated!
Author: Calvin Jia <jia.calvin@gmail.com>
Closes #5354 from calvinjia/upgrade_tachyon_0.6.3 and squashes the following commits:
0eefe4d [Calvin Jia] Handle httpclient version in maven dependency management. Remove httpclient version setting from profiles.
7c00dfa [Calvin Jia] Set httpclient version to 4.3.2 for selenium. Specify version of httpclient for sql/hive (previously 4.2.5 transitive dependency of libthrift).
9263097 [Calvin Jia] Merge master to test latest changes
dbfc1bd [Calvin Jia] Use Tachyon 0.6.4 for cleaner dependencies.
e2ff80a [Calvin Jia] Exclude the jetty and curator promoted dependencies from tachyon-client.
a3a29da [Calvin Jia] Update tachyon-client exclusions.
0ae6c97 [Calvin Jia] Change tachyon version to 0.6.3
a204df9 [Calvin Jia] Update make distribution tachyon version.
a93c94f [Calvin Jia] Exclude jackson-mapper-asl from hadoop client since it has a lower version than spark's expected version.
a8a923c [Calvin Jia] Exclude httpcomponents from Tachyon
910fabd [Calvin Jia] Update to master
eed9230 [Calvin Jia] Update tachyon version to 0.6.1.
11907b3 [Calvin Jia] Use TachyonURI for tachyon paths instead of strings.
71bf441 [Calvin Jia] Upgrade Tachyon client version to 0.6.0.
Diffstat (limited to 'core')
-rw-r--r-- | core/pom.xml | 6 | ||||
-rw-r--r-- | core/src/main/scala/org/apache/spark/storage/TachyonBlockManager.scala | 16 | ||||
-rw-r--r-- | core/src/main/scala/org/apache/spark/util/Utils.scala | 4 |
3 files changed, 16 insertions, 10 deletions
diff --git a/core/pom.xml b/core/pom.xml index e80829b7a7..5e89d548cd 100644 --- a/core/pom.xml +++ b/core/pom.xml @@ -74,6 +74,10 @@ <groupId>javax.servlet</groupId> <artifactId>servlet-api</artifactId> </exclusion> + <exclusion> + <groupId>org.codehaus.jackson</groupId> + <artifactId>jackson-mapper-asl</artifactId> + </exclusion> </exclusions> </dependency> <dependency> @@ -275,7 +279,7 @@ <dependency> <groupId>org.tachyonproject</groupId> <artifactId>tachyon-client</artifactId> - <version>0.5.0</version> + <version>0.6.4</version> <exclusions> <exclusion> <groupId>org.apache.hadoop</groupId> diff --git a/core/src/main/scala/org/apache/spark/storage/TachyonBlockManager.scala b/core/src/main/scala/org/apache/spark/storage/TachyonBlockManager.scala index 951897cead..583f1fdf04 100644 --- a/core/src/main/scala/org/apache/spark/storage/TachyonBlockManager.scala +++ b/core/src/main/scala/org/apache/spark/storage/TachyonBlockManager.scala @@ -20,8 +20,8 @@ package org.apache.spark.storage import java.text.SimpleDateFormat import java.util.{Date, Random} -import tachyon.client.TachyonFS -import tachyon.client.TachyonFile +import tachyon.TachyonURI +import tachyon.client.{TachyonFile, TachyonFS} import org.apache.spark.Logging import org.apache.spark.executor.ExecutorExitCode @@ -40,7 +40,7 @@ private[spark] class TachyonBlockManager( val master: String) extends Logging { - val client = if (master != null && master != "") TachyonFS.get(master) else null + val client = if (master != null && master != "") TachyonFS.get(new TachyonURI(master)) else null if (client == null) { logError("Failed to connect to the Tachyon as the master address is not configured") @@ -60,11 +60,11 @@ private[spark] class TachyonBlockManager( addShutdownHook() def removeFile(file: TachyonFile): Boolean = { - client.delete(file.getPath(), false) + client.delete(new TachyonURI(file.getPath()), false) } def fileExists(file: TachyonFile): Boolean = { - client.exist(file.getPath()) + client.exist(new TachyonURI(file.getPath())) } def getFile(filename: String): TachyonFile = { @@ -81,7 +81,7 @@ private[spark] class TachyonBlockManager( if (old != null) { old } else { - val path = tachyonDirs(dirId) + "/" + "%02x".format(subDirId) + val path = new TachyonURI(s"${tachyonDirs(dirId)}/${"%02x".format(subDirId)}") client.mkdir(path) val newDir = client.getFile(path) subDirs(dirId)(subDirId) = newDir @@ -89,7 +89,7 @@ private[spark] class TachyonBlockManager( } } } - val filePath = subDir + "/" + filename + val filePath = new TachyonURI(s"$subDir/$filename") if(!client.exist(filePath)) { client.createFile(filePath) } @@ -113,7 +113,7 @@ private[spark] class TachyonBlockManager( tries += 1 try { tachyonDirId = "%s-%04x".format(dateFormat.format(new Date), rand.nextInt(65536)) - val path = rootDir + "/" + "spark-tachyon-" + tachyonDirId + val path = new TachyonURI(s"$rootDir/spark-tachyon-$tachyonDirId") if (!client.exist(path)) { foundLocalDir = client.mkdir(path) tachyonDir = client.getFile(path) diff --git a/core/src/main/scala/org/apache/spark/util/Utils.scala b/core/src/main/scala/org/apache/spark/util/Utils.scala index 2feb7341b1..667aa168e7 100644 --- a/core/src/main/scala/org/apache/spark/util/Utils.scala +++ b/core/src/main/scala/org/apache/spark/util/Utils.scala @@ -42,6 +42,8 @@ import org.apache.hadoop.security.UserGroupInformation import org.apache.log4j.PropertyConfigurator import org.eclipse.jetty.util.MultiException import org.json4s._ + +import tachyon.TachyonURI import tachyon.client.{TachyonFS, TachyonFile} import org.apache.spark._ @@ -955,7 +957,7 @@ private[spark] object Utils extends Logging { * Delete a file or directory and its contents recursively. */ def deleteRecursively(dir: TachyonFile, client: TachyonFS) { - if (!client.delete(dir.getPath(), true)) { + if (!client.delete(new TachyonURI(dir.getPath()), true)) { throw new IOException("Failed to delete the tachyon dir: " + dir) } } |