我正在编写一个在集群上运行的C#mapreduce程序。系统返回错误 System.Threading.Tasks.Task
在超时32毫秒后取消任务。数据非常庞大。我甚至改变了数据大小来检查,但错误仍然存在,所以我假设它不是由于数据大小。
有没有办法将任务超时更改为32毫秒。
我正在使用Azure,Visual Studio 2013和一个包含4个节点的群集。
mscorlib.dll中出现系统聚合异常
using System;
using System.Collections.Generic;
using System.Globalization;
using System.Linq;
using System.Text;
using System.Xml.Linq;
using System.Threading;
using Microsoft.Hadoop.MapReduce;
using Microsoft.WindowsAzure.Management.HDInsight;
using System.IO;
using System.Security.Cryptography.X509Certificates;
using Microsoft.Hadoop.Client;
namespace StackExtractor
{
//Our Mapper that takes a line of XML input and spits out the {OwnerUserId,ParentId,Score}
//i.e, {User,Question,Weightage}
public class UserQuestionsMapper : MapperBase
{
public override void Map(string inputLine, MapperContext context)
{
try
{
var obj = XElement.Parse(inputLine);
var postType = obj.Attribute("PostTypeId");
if (postType != null && postType.Value == "2")
{
var owner = obj.Attribute("OwnerUserId");
var parent = obj.Attribute("ParentId");
// Write output data. Ignore records will null values if any
if (owner != null && parent != null)
{
context.EmitLine(string.Format("{0},{1}", owner.Value, parent.Value));
}
}
}
catch
{
//Ignore this line if we can't parse
}
}
}
//Our Extraction Job using our Mapper
public class UserQuestionsExtractionJob : HadoopJob<UserQuestionsMapper>
{
public override HadoopJobConfiguration Configure(ExecutorContext context)
{
var config = new HadoopJobConfiguration();
config.DeleteOutputFolder = true;
config.InputPath = "/input/recommender";
config.OutputFolder = "/output/recommender";
return config;
}
}
//Driver that submits this to the cluster in the cloud
//And will wait for the result. This will push your executables to the Azure storage
//and will execute the command line in the head node (HDFS for Hadoop on Azure uses Azure storage)
public class Driver
{
public static void Main()
{
try
{
var azureCluster = new Uri("https://name r.azurehdinsight.net:563");
const string clusterUserName = "****";
const string clusterPassword = "****";
// This is the name of the account under which Hadoop will execute jobs.
// Normally this is just "Hadoop".
const string hadoopUserName = "Hadoop";
// Azure Storage Information.
const string azureStorageAccount = "name.blob.core.windows.net";
const string azureStorageKey = "id;
const string azureStorageContainer = "namecontainer";
const bool createContainerIfNotExist = true;
Console.WriteLine("Connecting : {0} ", DateTime.Now);
var hadoop = Hadoop.Connect(azureCluster,
clusterUserName,
hadoopUserName,
clusterPassword,
azureStorageAccount,
azureStorageKey,
azureStorageContainer,
createContainerIfNotExist);
Console.WriteLine("Starting: {0} ", DateTime.Now);
var result = hadoop.MapReduceJob.ExecuteJob <UserQuestionsExtractionJob>();
var info = result.Info;
Console.WriteLine("Done: {0} ", DateTime.Now);
Console.WriteLine("\nInfo From Server\n----------------------");
Console.WriteLine("StandardError: " + info.StandardError);
Console.WriteLine("\n----------------------");
Console.WriteLine("StandardOut: " + info.StandardOut);
Console.WriteLine("\n----------------------");
Console.WriteLine("ExitCode: " + info.ExitCode);
}
catch (Exception ex)
{
Console.WriteLine("Error: {0} ", ex.StackTrace.ToString(CultureInfo.InvariantCulture));
}
Console.WriteLine("Press Any Key To Exit..");
Console.ReadLine();
}
}
}