Apache Flink 2026: Xu ly Stream, Event Time va Cau hoi Phong van

// Basic Flink streaming application setup
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

// Enable checkpointing every 10 seconds for fault tolerance
env.enableCheckpointing(10000, CheckpointingMode.EXACTLY_ONCE);

// Configure state backend for large state
env.setStateBackend(new EmbeddedRocksDBStateBackend());

// Define the data source - Kafka in production scenarios
DataStream<String> rawStream = env.addSource(
    new FlinkKafkaConsumer<>("events", new SimpleStringSchema(), kafkaProps)
);

// Parse and transform the stream
DataStream<Event> events = rawStream
    .map(json -> objectMapper.readValue(json, Event.class))
    .assignTimestampsAndWatermarks(
        WatermarkStrategy.<Event>forBoundedOutOfOrderness(Duration.ofSeconds(5))
            .withTimestampAssigner((event, timestamp) -> event.getTimestamp())
    );

// Configuring event time with watermarks
public class EventTimeProcessor {
    
    public DataStream<AggregatedMetric> processWithEventTime(
            DataStream<SensorReading> readings) {
        
        return readings
            // Extract timestamp from the event payload
            .assignTimestampsAndWatermarks(
                WatermarkStrategy
                    .<SensorReading>forBoundedOutOfOrderness(Duration.ofMinutes(2))
                    .withTimestampAssigner((reading, ts) -> reading.getEventTime())
                    .withIdleness(Duration.ofMinutes(5)) // Handle idle partitions
            )
            // Window by event time, not wall clock
            .keyBy(SensorReading::getSensorId)
            .window(TumblingEventTimeWindows.of(Time.minutes(1)))
            .aggregate(new AverageAggregator());
    }
}

// Different windowing approaches for stream processing
public class WindowingStrategies {

    // Tumbling windows: fixed-size, non-overlapping
    // Use case: hourly aggregations, daily summaries
    public DataStream<Summary> tumblingAggregation(DataStream<Transaction> txns) {
        return txns
            .keyBy(Transaction::getAccountId)
            .window(TumblingEventTimeWindows.of(Time.hours(1)))
            .sum("amount");
    }

    // Sliding windows: fixed-size, overlapping
    // Use case: moving averages, rolling metrics
    public DataStream<Double> slidingAverage(DataStream<Metric> metrics) {
        return metrics
            .keyBy(Metric::getCategory)
            .window(SlidingEventTimeWindows.of(Time.minutes(10), Time.minutes(1)))
            .aggregate(new AverageAggregator());
    }

    // Session windows: activity-based, variable size
    // Use case: user sessions, conversation analysis
    public DataStream<Session> sessionAnalysis(DataStream<ClickEvent> clicks) {
        return clicks
            .keyBy(ClickEvent::getUserId)
            .window(EventTimeSessionWindows.withGap(Time.minutes(30)))
            .process(new SessionBuilder());
    }
}

// Managing state in a Flink KeyedProcessFunction
public class FraudDetector extends KeyedProcessFunction<String, Transaction, Alert> {
    
    // Keyed state: one value per key (account)
    private ValueState<Double> lastAmountState;
    private ValueState<Long> lastTransactionTimeState;
    private MapState<String, Integer> merchantCountState;
    
    @Override
    public void open(Configuration parameters) {
        // Initialize state descriptors
        lastAmountState = getRuntimeContext().getState(
            new ValueStateDescriptor<>("lastAmount", Double.class));
        lastTransactionTimeState = getRuntimeContext().getState(
            new ValueStateDescriptor<>("lastTime", Long.class));
        merchantCountState = getRuntimeContext().getMapState(
            new MapStateDescriptor<>("merchantCounts", String.class, Integer.class));
    }
    
    @Override
    public void processElement(Transaction txn, Context ctx, Collector<Alert> out) 
            throws Exception {
        Double lastAmount = lastAmountState.value();
        Long lastTime = lastTransactionTimeState.value();
        
        // Detect suspicious patterns
        if (lastAmount != null && lastTime != null) {
            long timeDelta = txn.getTimestamp() - lastTime;
            // Flag transactions 10x larger than previous within 1 minute
            if (txn.getAmount() > lastAmount * 10 && timeDelta < 60000) {
                out.collect(new Alert(txn.getAccountId(), "SUSPICIOUS_SPIKE", txn));
            }
        }
        
        // Update state for next transaction
        lastAmountState.update(txn.getAmount());
        lastTransactionTimeState.update(txn.getTimestamp());
        
        // Track merchant frequency
        Integer count = merchantCountState.get(txn.getMerchantId());
        merchantCountState.put(txn.getMerchantId(), (count == null ? 0 : count) + 1);
    }
}

-- flink_sql_streaming.sql
-- Create a streaming source table from Kafka
CREATE TABLE orders (
    order_id STRING,
    customer_id STRING,
    product_id STRING,
    amount DECIMAL(10, 2),
    order_time TIMESTAMP(3),
    -- Define watermark for event time processing
    WATERMARK FOR order_time AS order_time - INTERVAL '5' SECOND
) WITH (
    'connector' = 'kafka',
    'topic' = 'orders',
    'properties.bootstrap.servers' = 'kafka:9092',
    'format' = 'json',
    'scan.startup.mode' = 'earliest-offset'
);

-- Streaming aggregation with tumbling window
SELECT 
    customer_id,
    TUMBLE_START(order_time, INTERVAL '1' HOUR) AS window_start,
    COUNT(*) AS order_count,
    SUM(amount) AS total_amount
FROM orders
GROUP BY 
    customer_id,
    TUMBLE(order_time, INTERVAL '1' HOUR);

# flink-deployment.yaml
# Kubernetes deployment for a Flink application
apiVersion: flink.apache.org/v1beta1
kind: FlinkDeployment
metadata:
  name: fraud-detection-job
spec:
  image: flink:1.20
  flinkVersion: v1_20
  flinkConfiguration:
    taskmanager.numberOfTaskSlots: "4"
    state.backend.type: rocksdb
    state.checkpoints.dir: s3://flink-checkpoints/fraud-detection
    execution.checkpointing.interval: "30s"
  serviceAccount: flink
  jobManager:
    resource:
      memory: "2048m"
      cpu: 1
  taskManager:
    resource:
      memory: "4096m"
      cpu: 2
    replicas: 3
  job:
    jarURI: s3://flink-artifacts/fraud-detection-1.0.jar
    entryClass: com.example.FraudDetectionJob
    parallelism: 12
    upgradeMode: savepoint

// Production-ready Flink configuration
public class ProductionConfig {
    
    public static void configureForProduction(StreamExecutionEnvironment env) {
        // Checkpoint configuration
        CheckpointConfig checkpointConfig = env.getCheckpointConfig();
        checkpointConfig.setCheckpointingMode(CheckpointingMode.EXACTLY_ONCE);
        checkpointConfig.setMinPauseBetweenCheckpoints(30000); // 30 seconds
        checkpointConfig.setCheckpointTimeout(600000); // 10 minutes
        checkpointConfig.setMaxConcurrentCheckpoints(1);
        checkpointConfig.setExternalizedCheckpointRetention(
            ExternalizedCheckpointRetention.RETAIN_ON_CANCELLATION);
        
        // State backend with incremental checkpoints
        EmbeddedRocksDBStateBackend rocksDB = new EmbeddedRocksDBStateBackend(true);
        rocksDB.setDbStoragePath("/tmp/rocksdb");
        env.setStateBackend(rocksDB);
        
        // Restart strategy with exponential backoff
        env.setRestartStrategy(RestartStrategies.exponentialDelayRestart(
            Duration.ofSeconds(1),  // Initial delay
            Duration.ofMinutes(5),  // Max delay
            2.0,                    // Backoff multiplier
            Duration.ofHours(1),    // Reset backoff after
            0.1                     // Jitter
        ));
    }
}