我正在使用spark插入hbase，但速度很慢。60000张唱片需要2-3分钟。我要保存大约一千万张唱片。

object WriteToHbase extends Serializable {
    def main(args: Array[String]) {
        val csvRows: RDD[Array[String] = ...
        val dateFormatter = DateTimeFormat.forPattern("yyyy-MM-dd HH:mm:ss")
        val usersRDD = csvRows.map(row => {
            new UserTable(row(0), row(1), row(2), row(9), row(10), row(11))
        })
        processUsers(sc: SparkContext, usersRDD, dateFormatter)
    })
}

def processUsers(sc: SparkContext, usersRDD: RDD[UserTable], dateFormatter: DateTimeFormatter): Unit = {

    usersRDD.foreachPartition(part => {
        val conf = HBaseConfiguration.create()
        val table = new HTable(conf, tablename)

        part.foreach(userRow => {
            val id = userRow.id
            val name = userRow.name
            val date1 = dateFormatter.parseDateTime(userRow.date1)
            val hRow = new Put(Bytes.toBytes(id))
            hRow.add(cf, q, Bytes.toBytes(date1))
            hRow.add(cf, q, Bytes.toBytes(name))
            ...
            table.put(hRow)
        })
        table.flushCommits()
        table.close()
    })
}

我在spark submit中使用这个：

--num-executors 2 --driver-memory 2G --executor-memory 2G --executor-cores 2