我正在阅读一个大小为30MB的json文件，该文件用于创建列族和键值。然后创建put对象，将rowkey和值插入其中。创建此类put对象的列表并调用table.batch（）并传递此列表。当我的arraylist大小为50000时，我称之为此。然后清除列表并调用下一批。然而，处理最终有800000个条目的while文件需要300秒。我也累了，但它更慢。我正在使用hbase 1.1。我从Kafka那里得到了json。如有任何改进性能的建议，我们将不胜感激。我查了那么多论坛，但没什么帮助。如果你想看的话，我会和你分享代码。
当做
拉格哈文德拉

public static void processData(String jsonData)
{
    if (jsonData == null || jsonData.isEmpty())
    {
        System.out.println("JSON data is null or empty. Nothing to process");
        return;
    }

    long startTime = System.currentTimeMillis();

    Table table = null;
    try
    {
        table = HBaseConfigUtil.getInstance().getConnection().getTable(TableName.valueOf("MYTABLE"));
    }
    catch (IOException e1)
    {
        System.out.println(e1);
    }

    Put processData = null;
    List<Put> bulkData = new ArrayList<Put>();

    try
    {

        //Read the json and generate the model into a class    
        //ProcessExecutions is List<ProcessExecution>
        ProcessExecutions peData = JsonToColumnData.gson.fromJson(jsonData, ProcessExecutions.class);

        if (peData != null)
        {
            //Read the data and pass it to Hbase
            for (ProcessExecution pe : peData.processExecutions)
            {
                //Class Header stores some header information
                Header headerData = pe.getHeader();   

                String rowKey = headerData.getRowKey();
                processData = new Put(Bytes.toBytes(JsonToColumnData.rowKey));
                processData.addColumn(Bytes.toBytes("Data"),
                                Bytes.toBytes("Time"),
                                Bytes.toBytes("value"));

                //Add to list
                bulkData.add(processData);            
                if (bulkData.size() >= 50000) //hardcoded for demo
                {
                    long tmpTime = System.currentTimeMillis();
                    Object[] results = null;
                    table.batch(bulkData, results);                     
                    bulkData.clear();
                    System.gc();
                }
            } //end for
            //Complete the remaining write operation
            if (bulkData.size() > 0)
            {
                Object[] results = null;
                table.batch(bulkData, results);
                bulkData.clear();
                //Try to free memory
                System.gc();
            }
    }
    catch (Exception e)
    {
        System.out.println(e);
        e.printStackTrace();
    }
    finally
    {
        try
        {
            table.close();
        }
        catch (IOException e)
        {
            System.out.println("Error closing table " + e);
            e.printStackTrace();
        }
    }

}

//This function is added here to show the connection
 /*public Connection getConnection()
{

    try
    {
        if (this.connection == null)
        {
            ExecutorService executor = Executors.newFixedThreadPool(HBaseConfigUtil.THREADCOUNT);
            this.connection = ConnectionFactory.createConnection(this.getHBaseConfiguration(), executor);
        }
    }
    catch (IOException e)
    {
        e.printStackTrace();
        System.out.println("Error in getting connection " + e.getMessage());
    }

    return this.connection;
}*/