spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From tdas <...@git.apache.org>
Subject [GitHub] spark pull request: [SPARK-14678][SQL]Add a file sink log to suppo...
Date Mon, 18 Apr 2016 20:25:38 GMT
Github user tdas commented on a diff in the pull request:

    https://github.com/apache/spark/pull/12435#discussion_r60127866
  
    --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/FileStreamSinkLog.scala
---
    @@ -0,0 +1,241 @@
    +/*
    + * 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.streaming
    +
    +import java.io.IOException
    +import java.nio.charset.StandardCharsets.UTF_8
    +
    +import org.apache.hadoop.fs.{Path, PathFilter}
    +import org.json4s.NoTypeHints
    +import org.json4s.jackson.Serialization
    +import org.json4s.jackson.Serialization.{read, write}
    +
    +import org.apache.spark.sql.SQLContext
    +import org.apache.spark.sql.internal.SQLConf
    +
    +/**
    + * @param path the file path
    + * @param size the file size
    + * @param action the file action. Must be either "add" or "delete".
    + */
    +case class FileLog(path: String, size: Long, action: String)
    +
    +/**
    + * A special log for [[FileStreamSink]]. It will write one log file for each batch. The
first line
    + * of the log file is the version number, and there are multiple JSON lines following.
Each JSON
    + * line is a JSON format of [[FileLog]].
    + *
    + * As reading from many small files is usually pretty slow, [[FileStreamSinkLog]] will
compact log
    + * files every "spark.sql.sink.file.log.compactLen" batches into a big file. When doing
a compact,
    + * it will read all history logs and merge them with the new batch. During the compaction,
it will
    + * also delete the files that are deleted (marked by [[FileLog.action]]). When the reader
uses
    + * `allLogs` to list all files, this method only returns the visible files (drops the
deleted
    + * files).
    + */
    +class FileStreamSinkLog(sqlContext: SQLContext, path: String)
    +  extends HDFSMetadataLog[Seq[FileLog]](sqlContext, path) {
    +
    +  import FileStreamSinkLog._
    +
    +  private implicit val formats = Serialization.formats(NoTypeHints)
    +
    +  /**
    +   * If we delete the old files after compaction at once, there is a race condition in
S3: other
    +   * processes may see the old files are deleted but still cannot see the compaction
file. The user
    +   * should set a reasonable `fileExpiredTimeMS`. We will wait until then so that the
compaction
    +   * file is guaranteed to be visible for all readers
    +   */
    +  private val fileExpiredTimeMS = sqlContext.getConf(SQLConf.FILE_STREAM_SINK_LOG_EXPIRED_TIME)
    +
    +  private val isDeletingExpiredLog = sqlContext.getConf(SQLConf.FILE_STREAM_SINK_LOG_DELETE)
    +
    +  private val compactLength = sqlContext.getConf(SQLConf.FILE_STREAM_SINK_LOG_COMPACT_LEN)
    +
    +  override def batchIdToPath(batchId: Long): Path = {
    +    if (isCompactionBatch(batchId, compactLength)) {
    +      new Path(metadataPath, s"$batchId$COMPACT_FILE_SUFFIX")
    +    } else {
    +      new Path(metadataPath, batchId.toString)
    +    }
    +  }
    +
    +  override def pathToBatchId(path: Path): Long = {
    +    getBatchIdFromFileName(path.getName)
    +  }
    +
    +  override def isBatchFile(path: Path): Boolean = {
    +    try {
    +      getBatchIdFromFileName(path.getName)
    +      true
    +    } catch {
    +      case _: NumberFormatException => false
    +    }
    +  }
    +
    +  override def serialize(logs: Seq[FileLog]): Array[Byte] = {
    --- End diff --
    
    logs -> logData


---
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.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org


Mime
View raw message