264 lines
10 KiB
C#
264 lines
10 KiB
C#
using System.Text.Json;
|
|
using Confluent.Kafka;
|
|
using Microsoft.Extensions.Options;
|
|
using Minio.DataModel.Args;
|
|
|
|
public sealed class DataLakeWriterService : BackgroundService
|
|
{
|
|
private readonly KafkaOptions _kafkaOptions;
|
|
private readonly DataLakeOptions _opts;
|
|
private readonly MinioOptions _minioOpts;
|
|
private readonly ILogger<DataLakeWriterService> _logger;
|
|
|
|
// Buffer key: identifies one Parquet file-to-be.
|
|
// Events sharing a topic, date, and Kafka partition land in the same file.
|
|
private record BufferKey(string Topic, string DatePath, int Partition);
|
|
|
|
private record BufferedEvent(string Payload, long Offset);
|
|
|
|
private readonly Dictionary<BufferKey, List<BufferedEvent>> _buffer = new();
|
|
// Track the highest offset per topic-partition for post-flush commit.
|
|
private readonly Dictionary<TopicPartition, TopicPartitionOffset> _highWatermarks = new();
|
|
|
|
public DataLakeWriterService(
|
|
IOptions<KafkaOptions> kafkaOptions,
|
|
IOptions<DataLakeOptions> opts,
|
|
IOptions<MinioOptions> minioOpts,
|
|
ILogger<DataLakeWriterService> logger)
|
|
{
|
|
_kafkaOptions = kafkaOptions.Value;
|
|
_opts = opts.Value;
|
|
_minioOpts = minioOpts.Value;
|
|
_logger = logger;
|
|
}
|
|
|
|
protected override async Task ExecuteAsync(CancellationToken ct)
|
|
{
|
|
var consumerConfig = new ConsumerConfig
|
|
{
|
|
BootstrapServers = _kafkaOptions.BootstrapServers,
|
|
GroupId = "data-lake-writer",
|
|
AutoOffsetReset = AutoOffsetReset.Earliest,
|
|
EnableAutoCommit = false,
|
|
}.ApplySecurity(_kafkaOptions);
|
|
|
|
using var consumer = new ConsumerBuilder<string, string>(consumerConfig).Build();
|
|
consumer.Subscribe(new[]
|
|
{
|
|
_kafkaOptions.Topics.ObservationRecorded,
|
|
_kafkaOptions.Topics.AlertGenerated,
|
|
_kafkaOptions.Topics.EncounterStatusChanged,
|
|
});
|
|
|
|
_logger.LogInformation(
|
|
"DataLakeWriterService started. FlushCount={FlushCount} FlushIntervalSeconds={FlushInterval}",
|
|
_opts.FlushCount, _opts.FlushIntervalSeconds);
|
|
|
|
var lastFlush = DateTimeOffset.UtcNow;
|
|
|
|
try
|
|
{
|
|
while (!ct.IsCancellationRequested)
|
|
{
|
|
ConsumeResult<string, string>? result;
|
|
try
|
|
{
|
|
result = consumer.Consume(TimeSpan.FromMilliseconds(500));
|
|
}
|
|
catch (ConsumeException ex)
|
|
{
|
|
_logger.LogError(ex, "DataLakeWriter consume error");
|
|
continue;
|
|
}
|
|
|
|
if (result is not null)
|
|
AddToBuffer(result);
|
|
|
|
var totalBuffered = _buffer.Values.Sum(v => v.Count);
|
|
var shouldFlushCount = totalBuffered >= _opts.FlushCount;
|
|
var shouldFlushTime = DateTimeOffset.UtcNow - lastFlush
|
|
>= TimeSpan.FromSeconds(_opts.FlushIntervalSeconds);
|
|
|
|
if ((shouldFlushCount || shouldFlushTime) && totalBuffered > 0)
|
|
{
|
|
await FlushAsync(consumer, ct);
|
|
lastFlush = DateTimeOffset.UtcNow;
|
|
}
|
|
}
|
|
}
|
|
finally
|
|
{
|
|
// Final flush on shutdown so buffered events are not lost.
|
|
// Use CancellationToken.None — host shutdown cancels the execute token before
|
|
// MinIO uploads finish, which surfaces as TaskCanceledException noise.
|
|
if (_buffer.Values.Sum(v => v.Count) > 0)
|
|
{
|
|
try { await FlushAsync(consumer, CancellationToken.None); }
|
|
catch (Exception ex)
|
|
{
|
|
_logger.LogError(ex, "DataLakeWriter shutdown flush failed — some events may be re-read on next start");
|
|
}
|
|
}
|
|
consumer.Close();
|
|
}
|
|
}
|
|
|
|
private void AddToBuffer(ConsumeResult<string, string> result)
|
|
{
|
|
var datePath = ExtractDatePath(result.Topic, result.Message.Value);
|
|
var key = new BufferKey(result.Topic, datePath, result.Partition.Value);
|
|
|
|
if (!_buffer.TryGetValue(key, out var list))
|
|
{
|
|
list = new List<BufferedEvent>();
|
|
_buffer[key] = list;
|
|
}
|
|
list.Add(new BufferedEvent(result.Message.Value, result.Offset.Value));
|
|
|
|
// Track highest offset per topic-partition for post-flush commit.
|
|
var tp = new TopicPartition(result.Topic, result.Partition);
|
|
_highWatermarks[tp] = new TopicPartitionOffset(tp, result.Offset + 1);
|
|
}
|
|
|
|
private async Task FlushAsync(IConsumer<string, string> consumer, CancellationToken ct)
|
|
{
|
|
var flushedKeys = new HashSet<BufferKey>();
|
|
var failedPartitions = new HashSet<int>();
|
|
|
|
foreach (var (key, events) in _buffer)
|
|
{
|
|
if (events.Count == 0) continue;
|
|
|
|
try
|
|
{
|
|
var firstOffset = events.Min(e => e.Offset);
|
|
var objectKey = BuildObjectKey(key, firstOffset);
|
|
var bytes = await BuildParquetAsync(key.Topic, events, key.Partition);
|
|
|
|
await UploadToMinioAsync(objectKey, bytes, ct);
|
|
flushedKeys.Add(key);
|
|
|
|
_logger.LogInformation(
|
|
"[DATA-LAKE] Wrote {Count} events → {ObjectKey} ({Bytes} bytes)",
|
|
events.Count, objectKey, bytes.Length);
|
|
}
|
|
catch (Exception ex)
|
|
{
|
|
failedPartitions.Add(key.Partition);
|
|
|
|
if (ex is OperationCanceledException && ct.IsCancellationRequested)
|
|
{
|
|
_logger.LogInformation(
|
|
"[DATA-LAKE] Flush canceled for key {Key} during shutdown", key);
|
|
}
|
|
else
|
|
{
|
|
_logger.LogError(ex, "[DATA-LAKE] Failed to write file for key {Key}", key);
|
|
}
|
|
}
|
|
}
|
|
|
|
// Only commit offsets for topic-partitions that had no failures.
|
|
var safeOffsets = _highWatermarks
|
|
.Where(kv => !failedPartitions.Contains(kv.Key.Partition))
|
|
.Select(kv => kv.Value)
|
|
.ToList();
|
|
|
|
if (safeOffsets.Count > 0)
|
|
{
|
|
consumer.Commit(safeOffsets);
|
|
_logger.LogInformation(
|
|
"[DATA-LAKE] Committed offsets for {PartitionCount} partitions after flushing {FileCount} files",
|
|
safeOffsets.Count, flushedKeys.Count);
|
|
}
|
|
|
|
if (failedPartitions.Count > 0)
|
|
{
|
|
_logger.LogWarning(
|
|
"[DATA-LAKE] Retained buffers for {FailedCount} failed partitions — will retry next flush",
|
|
failedPartitions.Count);
|
|
}
|
|
|
|
// Clear only successfully flushed keys; retain failed ones for retry.
|
|
foreach (var key in flushedKeys)
|
|
_buffer.Remove(key);
|
|
|
|
// Clear watermarks only for partitions with no failures.
|
|
foreach (var tp in _highWatermarks.Keys.ToList())
|
|
{
|
|
if (!failedPartitions.Contains(tp.Partition))
|
|
_highWatermarks.Remove(tp);
|
|
}
|
|
}
|
|
|
|
private string ExtractDatePath(string topic, string payload) =>
|
|
DataLakeEventParser.ExtractDatePath(topic, payload, _kafkaOptions.Topics);
|
|
|
|
private async Task<byte[]> BuildParquetAsync(
|
|
string topic, List<BufferedEvent> events, int partition)
|
|
{
|
|
if (topic == _kafkaOptions.Topics.ObservationRecorded)
|
|
{
|
|
var rows = events.Select(e => DataLakeEventParser.ParseObservationRow(
|
|
e.Payload, e.Offset, partition)).ToList();
|
|
return await ParquetFileBuilder.BuildObservationsAsync(rows);
|
|
}
|
|
if (topic == _kafkaOptions.Topics.AlertGenerated)
|
|
{
|
|
var rows = events.Select(e => DataLakeEventParser.ParseAlertRow(
|
|
e.Payload, e.Offset, partition)).ToList();
|
|
return await ParquetFileBuilder.BuildAlertsAsync(rows);
|
|
}
|
|
if (topic == _kafkaOptions.Topics.EncounterStatusChanged)
|
|
{
|
|
var rows = events.Select(e => DataLakeEventParser.ParseEncounterRow(
|
|
e.Payload, e.Offset, partition)).ToList();
|
|
return await ParquetFileBuilder.BuildEncountersAsync(rows);
|
|
}
|
|
throw new InvalidOperationException($"Unknown topic: {topic}");
|
|
}
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Object key and date partition helpers
|
|
// ---------------------------------------------------------------------------
|
|
|
|
// File path: observations/2025/01/15/partition-0-offset-0000001000.parquet
|
|
// The date comes from the event timestamp, not the wall clock.
|
|
// Events from the same encounter that cross midnight are written into the date
|
|
// bucket matching their recorded_at timestamp — consistent with how Athena and
|
|
// Spark partition-prune by event time, not ingest time.
|
|
private string BuildObjectKey(BufferKey key, long firstOffset)
|
|
{
|
|
var folder = key.Topic switch
|
|
{
|
|
var t when t == _kafkaOptions.Topics.ObservationRecorded => "observations",
|
|
var t when t == _kafkaOptions.Topics.AlertGenerated => "alerts",
|
|
var t when t == _kafkaOptions.Topics.EncounterStatusChanged => "encounters",
|
|
_ => "unknown",
|
|
};
|
|
return $"{folder}/{key.DatePath}/partition-{key.Partition}-offset-{firstOffset:D10}.parquet";
|
|
}
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// MinIO upload
|
|
// ---------------------------------------------------------------------------
|
|
|
|
private async Task UploadToMinioAsync(string objectKey, byte[] bytes, CancellationToken ct)
|
|
{
|
|
var client = MinioClientFactory.Build(_minioOpts);
|
|
var bucket = _opts.BucketName;
|
|
|
|
var exists = await client.BucketExistsAsync(
|
|
new BucketExistsArgs().WithBucket(bucket), ct);
|
|
if (!exists)
|
|
await client.MakeBucketAsync(new MakeBucketArgs().WithBucket(bucket), ct);
|
|
|
|
await client.PutObjectAsync(new PutObjectArgs()
|
|
.WithBucket(bucket)
|
|
.WithObject(objectKey)
|
|
.WithStreamData(new MemoryStream(bytes))
|
|
.WithObjectSize(bytes.Length)
|
|
.WithContentType("application/octet-stream"),
|
|
ct);
|
|
}
|
|
} |