private static void CreateDatabase(Args arguments)
{
// and a couple of checks here
Contract.Requires(arguments.OutputDirectory != null, "You must specify an output directory");
Contract.Requires(arguments.InputDirectory != null, "You must specify an input directory");
Contract.Requires(Directory.Exists(arguments.OutputDirectory), "The output directory must exist");
Contract.Requires(Directory.Exists(arguments.InputDirectory), "The input directory must exist");
// create the pipeline. The first step here is to parse the input files, and we can do this in parallel
var buildArtifactParsingBlock = new TransformBlock <ParseBuildArtifactsInput, TimedActionResult <ParseBuildArtifactsOutput> >(i =>
{
var action = new ParseBuildArtifacts();
return(action.PerformAction(i));
},
new ExecutionDataflowBlockOptions()
{
MaxDegreeOfParallelism = arguments.AppConfig.ConcurrencyConfig.MaxBuildParsingTasks
}
);
// the second is to save artifacts in a central folder
var storeArtifactBlock = new ActionBlock <TimedActionResult <ParseBuildArtifactsOutput> >(i =>
{
// the exception will be logged even if we dont do it here
if (i.ExecutionStatus)
{
var action = new StoreBuildArtifacts(arguments.OutputDirectory);
action.PerformAction(i.Result);
}
},
new ExecutionDataflowBlockOptions()
{
MaxDegreeOfParallelism = arguments.AppConfig.ConcurrencyConfig.MaxArtifactStoreTasks
}
);
// link them
var numParsingTasks = 0;
buildArtifactParsingBlock.LinkTo(storeArtifactBlock, new DataflowLinkOptions {
PropagateCompletion = true
});
// do now we can post to the initial queue
foreach (var file in Directory.EnumerateFiles(arguments.InputDirectory, "*.json"))
{
buildArtifactParsingBlock.Post(new ParseBuildArtifactsInput(file));
++numParsingTasks;
}
s_logger.Info($"Posted {numParsingTasks} parsing tasks, processing");
// now wait
buildArtifactParsingBlock.Complete();
storeArtifactBlock.Completion.Wait();
// done
}
private static void ClassifyInstances(Args arguments)
{
// and a couple of checks here
Contract.Requires(arguments.OutputDirectory != null, "You must specify an output directory");
Contract.Requires(arguments.InputDirectory != null, "You must specify an input directory");
Contract.Requires(Directory.Exists(arguments.OutputDirectory), "The output directory must exist");
Contract.Requires(Directory.Exists(arguments.InputDirectory), "The input directory must exist");
var sharedCount = 0;
var nonSharedCount = 0;
try
{
// load the classifier first
s_logger.Info("Loading classifier...");
// work on the content store
s_logger.Info($"Initializing store at [{arguments.OutputDirectory}]");
var store = new RocksDbContentPlacementPredictionStore(arguments.OutputDirectory, true);
var opContext = new OperationContext(new Context(new LogWrapper(s_logger)));
// init it
var initialized = store.StartupAsync(opContext);
initialized.Wait();
// and check
if (!initialized.Result)
{
s_logger.Error($"Could not initialize RocksDbContentPlacementPredictionStore at [{arguments.OutputDirectory}]");
}
var classifier = new ContentPlacementClassifier(arguments.AppConfig.ClassifierConfiguration);
// create the pipeline. The first step here is to parse the input files, and we can do this in parallel
var buildArtifactParsingBlock = new TransformManyBlock <ParseBuildArtifactsInput, KeyValuePair <string, IReadOnlyList <ArtifactWithBuildMeta> > >(i =>
{
var action = new ParseBuildArtifacts();
var result = action.PerformAction(i);
if (result.ExecutionStatus)
{
return(result.Result.ArtifactsByHash.ToList());
}
else
{
s_logger.Error(result.Exception, $"Error when parsing [{i.BuildArtifactsFile}]");
throw result.Exception;
}
},
new ExecutionDataflowBlockOptions()
{
MaxDegreeOfParallelism = arguments.AppConfig.ConcurrencyConfig.MaxBuildParsingTasks
}
);
// then, when we have one, we linearize it
var linearizeBlock = new TransformBlock <KeyValuePair <string, IReadOnlyList <ArtifactWithBuildMeta> >, TimedActionResult <LinearizeArtifactsOutput> >(i =>
{
var action = new LinearizeArtifacts();
return(action.PerformAction(new LinearizeArtifactsInput(i.Key, i.Value)));
},
new ExecutionDataflowBlockOptions()
{
MaxDegreeOfParallelism = arguments.AppConfig.ConcurrencyConfig.MaxArtifactLinearizationTasks
}
);
// and we classify them
var classifyBlock = new ActionBlock <TimedActionResult <LinearizeArtifactsOutput> >(i =>
{
// i have an ml instance here
if (i.ExecutionStatus)
{
var cpInstance = new ContentPlacementInstance()
{
Artifact = i.Result.Linear.AsInstance(), // using the default utility method
QueueName = i.Result.Linear.Queues.First() // the first here is enough, since its always one!
};
var result = classifier.Classify(cpInstance);
if (result.Succeeded)
{
var selectedMachines = result.Value;
foreach (var path in i.Result.Linear.ReportedPaths)
{
store.StoreResult(opContext, path, selectedMachines);
Interlocked.Add(ref sharedCount, 1);
}
}
else
{
Interlocked.Add(ref nonSharedCount, 1);
}
}
},
new ExecutionDataflowBlockOptions()
{
MaxDegreeOfParallelism = arguments.AppConfig.ConcurrencyConfig.MaxArtifactClassificationTasks
}
);
// link them
var numParsingTasks = 0;
buildArtifactParsingBlock.LinkTo(linearizeBlock, new DataflowLinkOptions {
PropagateCompletion = true
});
linearizeBlock.LinkTo(classifyBlock, new DataflowLinkOptions {
PropagateCompletion = true
});
// do now we can post to the initial queue
foreach (var file in Directory.EnumerateFiles(arguments.InputDirectory, "*.json"))
{
buildArtifactParsingBlock.Post(new ParseBuildArtifactsInput(file));
++numParsingTasks;
}
s_logger.Info($"Posted {numParsingTasks} parsing tasks, processing");
// now wait
buildArtifactParsingBlock.Complete();
classifyBlock.Completion.Wait();
// and now we should snapshot
var snapshotDir = Path.Combine(arguments.OutputDirectory, "Snap");
Directory.CreateDirectory(snapshotDir);
s_logger.Info($"Done, snapshoting to [{snapshotDir}]");
var result = store.CreateSnapshot(opContext, snapshotDir);
// done
}
finally
{
var total = 1.0 * (sharedCount + nonSharedCount);
var percentage = (1.0 * sharedCount) / total;
s_logger.Info($"Stats: shared={sharedCount} ({percentage}), nonShared={nonSharedCount}, total={total}");
}
}