Job ... 弱弱的問一下：台灣有多少企業 Cluster 有這麼大？Task 有這麼 多？ 11 / 74 我們對 Hadoop 的期許： Batch Job Interactive Query Real-Time Processing Graph Processing Iterative Modeling 人心不足蛇吞象 Hadoop 的體質 (Batch Processing) 問題： Batch 應用變成 Data Operating System： 透過 MapReduce 進行 Batch Processing 透過 Hive 與 Tez 進行 Interactive SQL Query ... 15 / 74 MapReduce 改造前 Hadoop 原來的架構，MapReduce 是一切應用的基礎 所有 Job 都得轉換成 MapReduce 16 / 74 MapReduce Level Language for Data Analysis (2010-09 成為 Top-Level Project) Hive：Data Warehousing and SQL-Like Query (2010-09 成為 Top-Level Project) Sqoop：Data Migration Tool Between HDFS and RDBMS Hadoop Ecosystem

Oracle 白皮书 — 通过 Oracle 并行处理集成 Hadoop 数据 String query = "declare dopt dbms_aq.enqueue_options_t; mprop dbms_aq.message_properties_t; msgid raw(100); begin ), msgid); commit; end;"; CallableStatement pstmt = null; try { pstmt = conn.prepareCall(query); } catch (Exception e){ System.out.println("Got exception " + e); if (rset != null) rset MR_QUEUE', 'HADOOP_MR_QUEUE'); execute DBMS_AQADM.START_QUEUE ('HADOOP_MR_QUEUE'); -- Query being executed by an end user or BI tool -- Note the hint is not a real hint, but a comment -- to

Indexing – Page Rank Machine Learning – Bayesian Classification – K-Means Clustering Analytical Query HiBench 1.0 paper (“The HiBench Suite: Characterization of the MapReduce-Based Data Analysis”) published

（2）执行均衡计划 hdfs diskbalancer -execute hadoop103.plan.json （3）查看当前均衡任务的执行情况 hdfs diskbalancer -query hadoop103 （4）取消均衡任务 hdfs diskbalancer -cancel hadoop103.plan.json 第 4 章 HDFS—集群扩容及缩容 4.1 添加白名单