Question

我有一个spark kafka流媒体工作。下面是主要的作业处理逻辑。

val processedStream = rawStream.transform(x => {
var offsetRanges = x.asInstanceOf[HasOffsetRanges].offsetRanges;
val spark = SparkSession.builder.config(x.sparkContext.getConf).getOrCreate();
val parsedRDD = x.map(cr => cr.value());

var df = spark.sqlContext.read.schema(KafkaRawEvent.getStructure()).json(parsedRDD);

// Explode Events array as individual Event
if (DFUtils.hasColumn(df, "events")) {
    // Rename the dow and hour
    if (DFUtils.hasColumn(df, "dow"))
        df = df.withColumnRenamed("dow", "hit-dow");
    if (DFUtils.hasColumn(df, "hour"))
        df = df.withColumnRenamed("hour", "hit-hour");

    df = df
        .withColumn("event", explode(col("events")))
        .drop("events");

    if (DFUtils.hasColumn(df, "event.key")) {
        df = df.select(
            "*", "event.key",
            "event.count", "event.hour",
            "event.dow", "event.sum",
            "event.timestamp",
            "event.segmentation");
    }

    if (DFUtils.hasColumn(df, "key")) {
        df = df.filter("key != '[CLY]_view'");
    }

    df = df.select("*", "segmentation.*")
        .drop("segmentation")
        .drop("event");

    if (DFUtils.hasColumn(df, "metrics")) {
        df = df.select("*", "metrics.*").drop("metrics");
    }

    df = df.withColumnRenamed("timestamp", "eventTimeString");
    df = df.withColumn("eventtimestamp", df("eventTimeString").cast(LongType).divide(1000).cast(TimestampType).cast(DateType))
        .withColumn("date", current_date());


    if (DFUtils.hasColumn(df, "restID")) {
        df = df.join(broadcast(restroCached), df.col("restID") === restro.col("main_r_id"), "left_outer");
    }

    val SAVE_PATH = Conf.getSavePath();

    //Write dataframe to file
    df.write.partitionBy("date").mode("append").parquet(SAVE_PATH);

    // filter out app launch events and group by adId and push to kafka
    val columbiaDf = df.filter(col("adId").isNotNull)
        .select(col("adId")).distinct().toDF("cui").toJSON;

    // push columbia df to kafka for further processing
    columbiaDf.foreachPartition(partitionOfRecords => {
        val factory = columbiaProducerPool.value;
        val producer = factory.getOrCreateProducer();
        partitionOfRecords.foreach(record => {
            producer.send(record);
        });
    });

    df.toJSON
        .foreachPartition(partitionOfRecords => {
            val factory = producerPool.value;
            val producer = factory.getOrCreateProducer();
            partitionOfRecords.foreach(record => {
                producer.send(record);
            });
        });
}
rawStream.asInstanceOf[CanCommitOffsets].commitAsync(offsetRanges);
df.toJSON.rdd;
});

val windowOneHourEveryMinute = processedStream.window(Minutes(60), Seconds(60));

windowOneHourEveryMinute.foreachRDD(windowRDD => ({
val prefix = Conf.getAnalyticsPrefixesProperties().getProperty("view.all.last.3.hours");

val viewCount = spark.sqlContext.read.schema(ProcessedEvent.getStructure()).json(windowRDD)
    .filter("key == 'RestaurantView'")
    .groupBy("restID")
    .count()
    .rdd.map(r => (prefix + String.valueOf(r.get(0)), String.valueOf(r.get(1))));
spark.sparkContext.toRedisKV(viewCount, Conf.getRedisKeysTTL());
}));

streamingContext.start();
streamingContext.awaitTermination();

这项工作已经运行了近一个月没有一次失败现在突然处理时间开始呈指数增长，尽管没有事件被处理。

我无法弄清楚它为什么会发生。下面我附上了应用程序大师的截图。