Phoenix优化

hbase-site.xml： <property> <name>hbase.master.maxclockskew</name> <value>45000000</value> </property> <property>    <name>hbase.rpc.timeout</name> <value>36000000</value>    </property> <property>    <name>hbase.client.scanner.timeout.period</name> <value>36000000</value>    </property> <!--控制超时的属性--> <property>    <name>mapreduce.task.timeout</name> <value>1200000</value>    </property> <property>    <name>zookeeper.session.timeout</name> <value>1200000</value>    </property> <!--写缓存大小--> <property> <name>hbase.client.write.buffer</name> <value>20971520</value> </property> <!--hbase.balancer.period--> <property> <name>hbase.balancer.period</name> <value>300000</value> </property> <!--二级索引--> <property> <name>hbase.regionserver.wal.codec</name> <value>org.apache.hadoop.hbase.regionserver.wal.IndexedWALEditCodec</value> </property> 组合主键: create table "test_keys2" ( "V_1" decimal(24,8), "V_2" varchar, "YEAR" INTEGER not null , "PERIOD" INTEGER not null ,"ACCOUNT" INTEGER not null , "ENTITY" INTEGER not null , "SCENARIO" INTEGER not null , "CURRENCY" INTEGER not null , "VERSION" INTEGER not null , "CST_DIM_02217" INTEGER not null, "CST_DIM_30453" INTEGER not null, "CST_DIM_47894" INTEGER not null , "CST_DIM_61310" INTEGER  not null , "CST_DIM_81981" INTEGER not null , "CST_DIM_01216" INTEGER not null, "CST_DIM_25287" INTEGER  not null, "CST_DIM_41183" INTEGER not null constraint pk primary key("YEAR" ,  "PERIOD" , "ACCOUNT" ,"ENTITY" , "SCENARIO" , "CURRENCY" , "VERSION","CST_DIM_02217" ,"CST_DIM_30453" ,"CST_DIM_47894" , "CST_DIM_61310","CST_DIM_81981" ,"CST_DIM_01216" , "CST_DIM_25287" ,"CST_DIM_41183")); upsert插入数据有问题 二级索引： 同步创建索引 CREATE INDEX ifact1 ON C1_FACT("diminfo".YEAR) INCLUDE("diminfo"."V_1","diminfo".V_2 ,  "diminfo".PERIOD ,  "diminfo".ACCOUNT , "diminfo".ENTITY , "diminfo".SCENARIO , "diminfo".CURRENCY , "diminfo".VERSION ,"diminfo"."CST_DIM_02217" , "diminfo"."CST_DIM_30453" , "diminfo"."CST_DIM_47894" , "diminfo"."CST_DIM_61310", "diminfo"."CST_DIM_81981" , "diminfo"."CST_DIM_01216" , "diminfo"."CST_DIM_25287" , "diminfo"."CST_DIM_41183") 当执行create index的时候，索引表会直接与源数据表进行同步。但是，有时候我们的源表数据量很大，同步创建索引会抛出异常。 异步创建索引 create index ifact1 on C1_FACT ("diminfo".YEAR) include("diminfo"."V_1","diminfo".V_2 ,  "diminfo".PERIOD ,  "diminfo".ACCOUNT , "diminfo".ENTITY , "diminfo".SCENARIO , "diminfo".CURRENCY , "diminfo".VERSION ,"diminfo"."CST_DIM_02217" , "diminfo"."CST_DIM_30453" , "diminfo"."CST_DIM_47894" , "diminfo"."CST_DIM_61310", "diminfo"."CST_DIM_81981" , "diminfo"."CST_DIM_01216" , "diminfo"."CST_DIM_25287" , "diminfo"."CST_DIM_41183") ASYNC 通过create index的时候指定 ASYNC 关键字来指定异步创建索引。执行这个命令之后并不会引起索引表与源表的直接同步。这个时候查询并不会使用这个索引表。那么索引数据的导入还需要采用phoenix提供的索引同步工具类 IndexTool ， 这是一个mapreduce工具类，使用方式如下： $HBASE_HOME/bin/hbase org.apache.phoenix.mapreduce.index.IndexTool --data-table C1_FACT --index-table ifact10   --output-path  hdfs:/phoenixindex 数据量大，报异常 加上--direct  如果指定，避免批量加载（可选）