spark-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From pwendell <...@git.apache.org>
Subject [GitHub] spark pull request: [SPARK-1132] Persisting Web UI through refacto...
Date Fri, 14 Mar 2014 05:28:49 GMT
Github user pwendell commented on a diff in the pull request:

    https://github.com/apache/spark/pull/42#discussion_r10596857
  
    --- Diff: core/src/main/scala/org/apache/spark/util/FileLogger.scala ---
    @@ -0,0 +1,167 @@
    +/*
    + * 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.util
    +
    +import java.io._
    +import java.net.URI
    +import java.text.SimpleDateFormat
    +import java.util.Date
    +
    +import it.unimi.dsi.fastutil.io.FastBufferedOutputStream
    +import org.apache.hadoop.fs.{FSDataOutputStream, Path}
    +
    +import org.apache.spark.{Logging, SparkConf}
    +import org.apache.spark.io.CompressionCodec
    +
    +/**
    + * A generic class for logging information to file.
    + *
    + * @param logDir Path to the directory in which files are logged
    + * @param outputBufferSize The buffer size to use when writing to an output stream in
bytes
    + * @param compress Whether to compress output
    + * @param overwrite Whether to overwrite existing files
    + */
    +class FileLogger(
    +    logDir: String,
    +    conf: SparkConf = new SparkConf,
    +    outputBufferSize: Int = 8 * 1024,
    +    compress: Boolean = false,
    +    overwrite: Boolean = true)
    +  extends Logging {
    +
    +  private val DATE_FORMAT = new SimpleDateFormat("yyyy/MM/dd HH:mm:ss")
    +  private val fileSystem = Utils.getHadoopFileSystem(new URI(logDir))
    +  private var fileIndex = 0
    +
    +  // Only used if compression is enabled
    +  private lazy val compressionCodec = CompressionCodec.createCodec(conf)
    +
    +  // Only defined if the file system scheme is not local
    +  private var hadoopDataStream: Option[FSDataOutputStream] = None
    +
    +  private var writer: Option[PrintWriter] = {
    +    createLogDir()
    +    Some(createWriter())
    +  }
    +
    +  /** Create a logging directory with the given path. */
    +  private def createLogDir() {
    +    val path = new Path(logDir)
    +    if (fileSystem.exists(path)) {
    +      if (overwrite) {
    +        logWarning("Log directory %s already exists. Overwriting...".format(logDir))
    +        // Second parameter is whether to delete recursively
    +        fileSystem.delete(path, true)
    +      } else {
    +        throw new IOException("Log directory %s already exists!".format(logDir))
    +      }
    +    }
    +    if (!fileSystem.mkdirs(path)) {
    +      throw new IOException("Error in creating log directory: %s".format(logDir))
    +    }
    +  }
    +
    +  /**
    +   * Create a new writer for the file identified by the given path. File systems currently
    +   * supported include HDFS, S3, and the local file system.
    +   */
    +  private def createWriter(): PrintWriter = {
    +    val logPath = logDir + "/" + fileIndex
    +    val uri = new URI(logPath)
    +
    +    /**
    +     * The Hadoop LocalFileSystem (r1.0.4) has known issues with syncing (HADOOP-7844).
    +     * Therefore, for local files, use FileOutputStream instead.
    +     */
    +    val dstream = uri.getScheme match {
    +      case "hdfs" | "s3" =>
    +        val path = new Path(logPath)
    --- End diff --
    
    I'd support all schemes here


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

Mime
View raw message