/// <summary>
/// Populates Azure Storage with the required files, and
/// submits the job to the Azure Batch service.
/// </summary>
public async Task RunAsync()
{
Console.WriteLine("Running with the following settings: ");
Console.WriteLine("----------------------------------------");
Console.WriteLine(this.textSearchSettings.ToString());
Console.WriteLine(this.accountSettings.ToString());
CloudStorageAccount cloudStorageAccount = new CloudStorageAccount(
new StorageCredentials(
this.accountSettings.StorageAccountName,
this.accountSettings.StorageAccountKey),
this.accountSettings.StorageServiceUrl,
useHttps: true);
//Upload resources if required.
if (this.textSearchSettings.ShouldUploadResources)
{
Console.WriteLine("Splitting file: {0} into {1} subfiles",
Constants.TextFilePath,
this.textSearchSettings.NumberOfMapperTasks);
//Split the text file into the correct number of files for consumption by the mapper tasks.
FileSplitter splitter = new FileSplitter();
List <string> mapperTaskFiles = await splitter.SplitAsync(
Constants.TextFilePath,
this.textSearchSettings.NumberOfMapperTasks);
List <string> files = Constants.RequiredExecutableFiles.Union(mapperTaskFiles).ToList();
await SampleHelpers.UploadResourcesAsync(
cloudStorageAccount,
this.textSearchSettings.BlobContainer,
files);
}
//Generate a SAS for the container.
string containerSasUrl = SampleHelpers.ConstructContainerSas(
cloudStorageAccount,
this.textSearchSettings.BlobContainer);
//Set up the Batch Service credentials used to authenticate with the Batch Service.
BatchSharedKeyCredentials credentials = new BatchSharedKeyCredentials(
this.accountSettings.BatchServiceUrl,
this.accountSettings.BatchAccountName,
this.accountSettings.BatchAccountKey);
using (BatchClient batchClient = await BatchClient.OpenAsync(credentials))
{
//
// Construct the job properties in local memory before commiting them to the Batch Service.
//
//Allow enough compute nodes in the pool to run each mapper task, and 1 extra to run the job manager.
int numberOfPoolComputeNodes = 1 + this.textSearchSettings.NumberOfMapperTasks;
//Define the pool specification for the pool which the job will run on.
PoolSpecification poolSpecification = new PoolSpecification()
{
TargetDedicated = numberOfPoolComputeNodes,
VirtualMachineSize = "small",
//You can learn more about os families and versions at:
//http://azure.microsoft.com/documentation/articles/cloud-services-guestos-update-matrix
OSFamily = "4",
TargetOSVersion = "*"
};
//Use the auto pool feature of the Batch Service to create a pool when the job is created.
//This creates a new pool for each job which is added.
AutoPoolSpecification autoPoolSpecification = new AutoPoolSpecification()
{
AutoPoolIdPrefix = "TextSearchPool",
KeepAlive = false,
PoolLifetimeOption = PoolLifetimeOption.Job,
PoolSpecification = poolSpecification
};
//Define the pool information for this job -- it will run on the pool defined by the auto pool specification above.
PoolInformation poolInformation = new PoolInformation()
{
AutoPoolSpecification = autoPoolSpecification
};
//Define the job manager for this job. This job manager will run first and will submit the tasks for
//the job. The job manager is the executable which manages the lifetime of the job
//and all tasks which should run for the job. In this case, the job manager submits the mapper and reducer tasks.
List <ResourceFile> jobManagerResourceFiles = SampleHelpers.GetResourceFiles(containerSasUrl, Constants.RequiredExecutableFiles);
const string jobManagerTaskId = "JobManager";
JobManagerTask jobManagerTask = new JobManagerTask()
{
ResourceFiles = jobManagerResourceFiles,
CommandLine = Constants.JobManagerExecutable,
//Determines if the job should terminate when the job manager process exits.
KillJobOnCompletion = true,
Id = jobManagerTaskId
};
//Create the unbound job in local memory. An object which exists only in local memory (and not on the Batch Service) is "unbound".
string jobId = Environment.GetEnvironmentVariable("USERNAME") + DateTime.UtcNow.ToString("yyyyMMdd-HHmmss");
CloudJob unboundJob = batchClient.JobOperations.CreateJob(jobId, poolInformation);
unboundJob.JobManagerTask = jobManagerTask; //Assign the job manager task to this job
try
{
//Commit the unbound job to the Batch Service.
Console.WriteLine("Adding job: {0} to the Batch Service.", unboundJob.Id);
await unboundJob.CommitAsync(); //Issues a request to the Batch Service to add the job which was defined above.
//
// Wait for the job manager task to complete.
//
//An object which is backed by a corresponding Batch Service object is "bound."
CloudJob boundJob = await batchClient.JobOperations.GetJobAsync(jobId);
CloudTask boundJobManagerTask = await boundJob.GetTaskAsync(jobManagerTaskId);
TimeSpan maxJobCompletionTimeout = TimeSpan.FromMinutes(30);
// Monitor the current tasks to see when they are done.
// Occasionally a task may get killed and requeued during an upgrade or hardware failure, including the job manager
// task. The job manager will be re-run in this case. Robustness against this was not added into the sample for
// simplicity, but should be added into any production code.
Console.WriteLine("Waiting for job's tasks to complete");
TaskStateMonitor taskStateMonitor = batchClient.Utilities.CreateTaskStateMonitor();
bool timedOut = await taskStateMonitor.WaitAllAsync(new List <CloudTask> {
boundJobManagerTask
}, TaskState.Completed, maxJobCompletionTimeout);
Console.WriteLine("Done waiting for job manager task.");
await boundJobManagerTask.RefreshAsync();
//Check to ensure the job manager task exited successfully.
await Helpers.CheckForTaskSuccessAsync(boundJobManagerTask, dumpStandardOutOnTaskSuccess : false);
if (timedOut)
{
throw new TimeoutException(string.Format("Timed out waiting for job manager task to complete."));
}
//
// Download and write out the reducer tasks output
//
string reducerText = await SampleHelpers.DownloadBlobTextAsync(cloudStorageAccount, this.textSearchSettings.BlobContainer, Constants.ReducerTaskResultBlobName);
Console.WriteLine("Reducer reuslts:");
Console.WriteLine(reducerText);
}
finally
{
//Delete the job.
//This will delete the auto pool associated with the job as long as the pool
//keep alive property is set to false.
if (this.textSearchSettings.ShouldDeleteJob)
{
Console.WriteLine("Deleting job {0}", jobId);
batchClient.JobOperations.DeleteJob(jobId);
}
//Note that there were files uploaded to a container specified in the
//configuration file. This container will not be deleted or cleaned up by this sample.
}
}
}
/// <summary>
/// Populates Azure Storage with the required files, and
/// submits the job to the Azure Batch service.
/// </summary>
public async Task RunAsync()
{
Console.WriteLine("Running with the following settings: ");
Console.WriteLine("----------------------------------------");
Console.WriteLine(this.textSearchSettings.ToString());
Console.WriteLine(this.accountSettings.ToString());
CloudStorageAccount cloudStorageAccount = new CloudStorageAccount(
new StorageCredentials(
this.accountSettings.StorageAccountName,
this.accountSettings.StorageAccountKey),
this.accountSettings.StorageServiceUrl,
useHttps: true);
//Upload resources if required
Console.WriteLine($"Creating container {this.textSearchSettings.OutputBlobContainer} if it doesn't exist...");
var blobClient = cloudStorageAccount.CreateCloudBlobClient();
var outputContainer = blobClient.GetContainerReference(this.textSearchSettings.OutputBlobContainer);
await outputContainer.CreateIfNotExistsAsync();
if (this.textSearchSettings.ShouldUploadResources)
{
Console.WriteLine("Splitting file: {0} into {1} subfiles",
Constants.TextFilePath,
this.textSearchSettings.NumberOfMapperTasks);
//Split the text file into the correct number of files for consumption by the mapper tasks.
FileSplitter splitter = new FileSplitter();
List <string> mapperTaskFiles = await splitter.SplitAsync(
Constants.TextFilePath,
this.textSearchSettings.NumberOfMapperTasks);
List <string> files = Constants.RequiredExecutableFiles.Union(mapperTaskFiles).ToList();
await SampleHelpers.UploadResourcesAsync(
cloudStorageAccount,
this.textSearchSettings.InputBlobContainer,
files);
}
//Generate a SAS for the container.
string inputContainerSasUrl = SampleHelpers.ConstructContainerSas(
cloudStorageAccount,
this.textSearchSettings.InputBlobContainer,
permissions: WindowsAzure.Storage.Blob.SharedAccessBlobPermissions.Read);
string outputContainerSasUrl = SampleHelpers.ConstructContainerSas(
cloudStorageAccount,
this.textSearchSettings.OutputBlobContainer,
permissions: WindowsAzure.Storage.Blob.SharedAccessBlobPermissions.Read |
WindowsAzure.Storage.Blob.SharedAccessBlobPermissions.Write);
//Set up the Batch Service credentials used to authenticate with the Batch Service.
BatchSharedKeyCredentials credentials = new BatchSharedKeyCredentials(
this.accountSettings.BatchServiceUrl,
this.accountSettings.BatchAccountName,
this.accountSettings.BatchAccountKey);
using (BatchClient batchClient = BatchClient.Open(credentials))
{
//
// Construct the job properties in local memory before commiting them to the Batch Service.
//
//Allow enough compute nodes in the pool to run each mapper task
int numberOfPoolComputeNodes = this.textSearchSettings.NumberOfMapperTasks;
//Define the pool specification for the pool which the job will run on.
PoolSpecification poolSpecification = new PoolSpecification()
{
TargetDedicatedComputeNodes = numberOfPoolComputeNodes,
VirtualMachineSize = "standard_d1_v2",
//You can learn more about os families and versions at:
//http://azure.microsoft.com/documentation/articles/cloud-services-guestos-update-matrix
CloudServiceConfiguration = new CloudServiceConfiguration(osFamily: "5")
};
//Use the auto pool feature of the Batch Service to create a pool when the job is created.
//This creates a new pool for each job which is added.
AutoPoolSpecification autoPoolSpecification = new AutoPoolSpecification()
{
AutoPoolIdPrefix = "TextSearchPool",
KeepAlive = false,
PoolLifetimeOption = PoolLifetimeOption.Job,
PoolSpecification = poolSpecification
};
//Define the pool information for this job -- it will run on the pool defined by the auto pool specification above.
PoolInformation poolInformation = new PoolInformation()
{
AutoPoolSpecification = autoPoolSpecification
};
//Create the unbound job in local memory. An object which exists only in local memory (and not on the Batch Service) is "unbound".
string jobId = Environment.GetEnvironmentVariable("USERNAME") + DateTime.UtcNow.ToString("yyyyMMdd-HHmmss");
CloudJob unboundJob = batchClient.JobOperations.CreateJob(jobId, poolInformation);
unboundJob.UsesTaskDependencies = true;
try
{
//Commit the unbound job to the Batch Service.
Console.WriteLine($"Adding job: {unboundJob.Id} to the Batch Service.");
await unboundJob.CommitAsync(); //Issues a request to the Batch Service to add the job which was defined above.
// Add tasks to the job
var mapperTasks = CreateMapperTasks(inputContainerSasUrl, outputContainerSasUrl);
var reducerTask = CreateReducerTask(inputContainerSasUrl, outputContainerSasUrl, mapperTasks);
var tasksToAdd = Enumerable.Concat(mapperTasks, new[] { reducerTask });
//Submit the unbound task collection to the Batch Service.
//Use the AddTask method which takes a collection of CloudTasks for the best performance.
Console.WriteLine("Submitting {0} mapper tasks", this.textSearchSettings.NumberOfMapperTasks);
Console.WriteLine("Submitting 1 reducer task");
await batchClient.JobOperations.AddTaskAsync(jobId, tasksToAdd);
//An object which is backed by a corresponding Batch Service object is "bound."
CloudJob boundJob = await batchClient.JobOperations.GetJobAsync(jobId);
// Update the job now that we've added tasks so that when all of the tasks which we have added
// are complete, the job will automatically move to the completed state.
boundJob.OnAllTasksComplete = OnAllTasksComplete.TerminateJob;
boundJob.Commit();
boundJob.Refresh();
//
// Wait for the tasks to complete.
//
List <CloudTask> tasks = await batchClient.JobOperations.ListTasks(jobId).ToListAsync();
TimeSpan maxJobCompletionTimeout = TimeSpan.FromMinutes(30);
// Monitor the current tasks to see when they are done.
// Occasionally a task may get killed and requeued during an upgrade or hardware failure,
// Robustness against this was not added into the sample for
// simplicity, but should be added into any production code.
Console.WriteLine("Waiting for job's tasks to complete");
TaskStateMonitor taskStateMonitor = batchClient.Utilities.CreateTaskStateMonitor();
try
{
await taskStateMonitor.WhenAll(tasks, TaskState.Completed, maxJobCompletionTimeout);
}
finally
{
Console.WriteLine("Done waiting for all tasks to complete");
// Refresh the task list
tasks = await batchClient.JobOperations.ListTasks(jobId).ToListAsync();
//Check to ensure the job manager task exited successfully.
foreach (var task in tasks)
{
await Helpers.CheckForTaskSuccessAsync(task, dumpStandardOutOnTaskSuccess : false);
}
}
//
// Download and write out the reducer tasks output
//
string reducerText = await SampleHelpers.DownloadBlobTextAsync(cloudStorageAccount, this.textSearchSettings.OutputBlobContainer, Constants.ReducerTaskResultBlobName);
Console.WriteLine("Reducer reuslts:");
Console.WriteLine(reducerText);
}
finally
{
//Delete the job.
//This will delete the auto pool associated with the job as long as the pool
//keep alive property is set to false.
if (this.textSearchSettings.ShouldDeleteJob)
{
Console.WriteLine($"Deleting job {jobId}");
await batchClient.JobOperations.DeleteJobAsync(jobId);
}
if (this.textSearchSettings.ShouldDeleteContainers)
{
Console.WriteLine("Deleting containers");
var inputContainer = blobClient.GetContainerReference(this.textSearchSettings.InputBlobContainer);
await inputContainer.DeleteIfExistsAsync();
await outputContainer.DeleteIfExistsAsync();
}
}
}
}