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}");
}
}
private static void LinearizeDatabase(Args arguments)
{
// and a couple of checks here
Contract.Requires(arguments.InputDirectory != null, "You must specify an input directory");
Contract.Requires(Directory.Exists(arguments.InputDirectory), "The input directory must exist");
var collectedArtifacts = new MultiValueDictionary <int, MLArtifact>();
var currentTicks = Environment.TickCount;
var linearFile = $"{Path.Combine(arguments.InputDirectory, $"{Convert.ToString(currentTicks)}.csv")}";
var linearOutput = TextWriter.Synchronized(new StreamWriter(linearFile));
s_logger.Info($"Linearizing to [{linearFile}]");
// write the headers
MLArtifact.WriteColumnsToStream(linearOutput);
// so now we are ready to linearize
var linearizeBlock = new TransformBlock <LinearizeArtifactsInput, TimedActionResult <LinearizeArtifactsOutput> >(i =>
{
var action = new LinearizeArtifacts(linearOutput);
return(action.PerformAction(i));
},
new ExecutionDataflowBlockOptions()
{
MaxDegreeOfParallelism = arguments.AppConfig.ConcurrencyConfig.MaxArtifactLinearizationTasks
}
);
var collectLinearResultsBlock = new ActionBlock <TimedActionResult <LinearizeArtifactsOutput> >(i =>
{
if (i.ExecutionStatus)
{
collectedArtifacts.Add(i.Result.NumQueues, i.Result.Linear);
}
},
// enforce serial
new ExecutionDataflowBlockOptions()
{
MaxDegreeOfParallelism = 1
}
);
// connect
linearizeBlock.LinkTo(collectLinearResultsBlock, new DataflowLinkOptions {
PropagateCompletion = true
});
// and post the tasks
var posted = 0;
foreach (var hashDir in Directory.EnumerateDirectories(arguments.InputDirectory))
{
linearizeBlock.Post(new LinearizeArtifactsInput(hashDir));
++posted;
}
s_logger.Info($"Posted {posted} linearizing tasks, waiting...");
linearizeBlock.Complete();
// and wait
collectLinearResultsBlock.Completion.Wait();
// and close...
linearOutput.Close();
// now, scale to create the samples...
s_logger.Info($"Creating {arguments.NumSamples} samples of size {arguments.SampleSize}");
var scale = new Dictionary <int, int>();
foreach (var entry in collectedArtifacts)
{
var queueCount = entry.Key;
var entryCount = entry.Value.Count;
var proportion = 1.0 * Math.BigMul(entryCount, arguments.SampleSize) / (1.0 * posted);
scale[queueCount] = (int)Math.Ceiling(proportion);
}
// we have the scale, lets post tasks here
var createSampleBlocks = new ActionBlock <SampleArtifactsInput>(i =>
{
var action = new SampleArtifacts();
action.PerformAction(i);
},
// one per each sample
new ExecutionDataflowBlockOptions()
{
MaxDegreeOfParallelism = arguments.NumSamples
}
);
// post some tasks in here
for (var i = 0; i < arguments.NumSamples; ++i)
{
createSampleBlocks.Post(new SampleArtifactsInput($"{Path.Combine(arguments.InputDirectory, $"{Convert.ToString(currentTicks)}-sample{i}.csv")}", scale, collectedArtifacts));
}
// and wait...
createSampleBlocks.Complete();
createSampleBlocks.Completion.Wait();
// done...
}
