{"id":325,"date":"2013-01-12T17:11:23","date_gmt":"2013-01-12T09:11:23","guid":{"rendered":"http:\/\/www.yallonking.com\/?p=325"},"modified":"2013-01-12T18:05:06","modified_gmt":"2013-01-12T10:05:06","slug":"hive%e7%9a%84%e7%ae%80%e5%8d%95%e6%93%8d%e4%bd%9c","status":"publish","type":"post","link":"http:\/\/www.yallonking.com\/?p=325","title":{"rendered":"hive\u7684\u7b80\u5355\u64cd\u4f5c"},"content":{"rendered":"

hive\u7684\u7b80\u5355\u64cd\u4f5c
\n\u73af\u5883\u8bf4\u660e\uff1a
\n\u4e00\u822c\u53f0\u5f0f\u673a+vmware8.0+orcel enterprise linux6.0+hadoop-0.20.2+hive-0.7.1
\n
\n--\u521b\u5efa\u6d4b\u8bd5\u8868 test_hive2[\u6d4b\u8bd5\u8868 test_hive3 \u540c\u7406]
\nhive> create table test_hive2 (id int,id2 int,name string)
\n > row format delimited
\n > fields terminated by '\\t';
\nOK
\nTime taken: 0.055 seconds
\nhive> load data local inpath '\/root\/tmp001.txt'
\n > overwrite into table test_hive2;
\nCopying data from file:\/root\/tmp001.txt
\nCopying file: file:\/root\/tmp001.txt
\nLoading data to table default.test_hive2
\nDeleted file:\/user\/hive\/warehouse\/test_hive2
\nOK
\nTime taken: 0.342 seconds<\/p>\n

--\u6d4b\u8bd5\u5168\u8868\u626b\u63cf\u6548\u7387
\nhive> select count(*) from test_hive2;
\nTotal MapReduce jobs = 1
\nLaunching Job 1 out of 1
\nNumber of reduce tasks determined at compile time: 1
\nIn order to change the average load for a reducer (in bytes):
\n set hive.exec.reducers.bytes.per.reducer=
\nIn order to limit the maximum number of reducers:
\n set hive.exec.reducers.max=
\nIn order to set a constant number of reducers:
\n set mapred.reduce.tasks=
\nExecution log at: \/tmp\/root\/root_20120331160606_9f242fd6-e321-4413-92a7-b4d92207f14e.log
\nJob running in-process (local Hadoop)
\n2012-03-31 16:06:10,931 null map = 100%, reduce = 100%
\nEnded Job = job_local_0001
\nOK
\n65535
\nTime taken: 2.36 seconds<\/p>\n

--\u6d4b\u8bd52\u4e2a\u884c\u5b58\u50a8\u8868\u7684\u7b49\u503c\u8fde\u63a5\u6548\u7387
\nhive> select test_hive2.*,test_hive3.name from test_hive2 join test_hive3 on ( test_hive2.id=test_hive3.id);<\/p>\n

Time taken: 27.749 seconds<\/p>\n

--\u5217\u5b58\u50a82\u8868\u7b49\u503c\u8fde\u63a5\u6d4b\u8bd5\u5982\u4e0b
\n[root@oraking ~]# hive
\nHive history file=\/tmp\/root\/hive_job_log_root_201203311553_471153629.txt<\/p>\n

--\u521b\u5efa\u6d4b\u8bd5\u8868 test_hive
\nhive> create table test_hive (id int,id2 int,name string)
\n > row format serde 'org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe'
\n > STORED AS RCFILE;
\nOK
\nTime taken: 2.944 seconds<\/p>\n

--\u63d2\u5165\u6570\u636e
\nhive> insert overwrite table test_hive
\n > select id,id2,name
\n > from test_hive2;
\nTotal MapReduce jobs = 2
\nLaunching Job 1 out of 2
\nNumber of reduce tasks is set to 0 since there's no reduce operator
\nExecution log at: \/tmp\/root\/root_20120331164444_44ac1bdb-f603-45e2-b50a-4681e69d330f.log
\nJob running in-process (local Hadoop)
\n2012-03-31 16:44:31,709 null map = 100%, reduce = 0%
\nEnded Job = job_local_0001
\nEnded Job = 171641075, job is filtered out (removed at runtime).
\nMoving data to: file:\/tmp\/hive-root\/hive_2012-03-31_16-44-28_048_8584030323247636747\/-ext-10000
\nLoading data to table default.test_hive
\nDeleted file:\/user\/hive\/warehouse\/test_hive
\nTable default.test_hive stats: [num_partitions: 0, num_files: 1, num_rows: 65535, total_size: 961048]
\nOK
\nTime taken: 3.946 seconds<\/p>\n

--\u521b\u5efa\u6d4b\u8bd5\u8868 test_hive4
\nhive> create table test_hive4 (id int,id2 int,name string)
\n > row format serde 'org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe'
\n > STORED AS RCFILE;
\nOK
\nTime taken: 0.019 seconds<\/p>\n

--\u63d2\u5165\u6570\u636e
\nhive> insert overwrite table test_hive4
\n > select id,id2,name
\n > from test_hive2;
\nTotal MapReduce jobs = 2
\nLaunching Job 1 out of 2
\nNumber of reduce tasks is set to 0 since there's no reduce operator
\nExecution log at: \/tmp\/root\/root_20120331165555_13476cce-d845-4277-9505-38e6441e8e77.log
\nJob running in-process (local Hadoop)
\n2012-03-31 16:55:11,786 null map = 100%, reduce = 0%
\nEnded Job = job_local_0001
\nEnded Job = -1613004717, job is filtered out (removed at runtime).
\nMoving data to: file:\/tmp\/hive-root\/hive_2012-03-31_16-55-09_157_510206187744689585\/-ext-10000
\nLoading data to table default.test_hive4
\nDeleted file:\/user\/hive\/warehouse\/test_hive4
\nTable default.test_hive4 stats: [num_partitions: 0, num_files: 1, num_rows: 65535, total_size: 961048]
\nOK
\nTime taken: 2.863 seconds<\/p>\n

--\u5168\u8868\u626b\u63cf\u6548\u7387
\nhive> select count(*) from test_hive;
\nTotal MapReduce jobs = 1
\nLaunching Job 1 out of 1
\nNumber of reduce tasks determined at compile time: 1
\nIn order to change the average load for a reducer (in bytes):
\n set hive.exec.reducers.bytes.per.reducer=
\nIn order to limit the maximum number of reducers:
\n set hive.exec.reducers.max=
\nIn order to set a constant number of reducers:
\n set mapred.reduce.tasks=
\nExecution log at: \/tmp\/root\/root_20120331164848_c82b81f6-ee21-48fa-bbb8-c5a52b5c01bb.log
\nJob running in-process (local Hadoop)
\n2012-03-31 16:48:45,111 null map = 100%, reduce = 100%
\nEnded Job = job_local_0001
\nOK
\n65535
\nTime taken: 2.357 seconds<\/p>\n

hive> select count(*) from test_hive4;
\nTotal MapReduce jobs = 1
\nLaunching Job 1 out of 1
\nNumber of reduce tasks determined at compile time: 1
\nIn order to change the average load for a reducer (in bytes):
\n set hive.exec.reducers.bytes.per.reducer=
\nIn order to limit the maximum number of reducers:
\n set hive.exec.reducers.max=
\nIn order to set a constant number of reducers:
\n set mapred.reduce.tasks=
\nExecution log at: \/tmp\/root\/root_20120331165555_0e89d023-1969-4272-8ab5-a68c48db7073.log
\nJob running in-process (local Hadoop)
\n2012-03-31 16:55:45,199 null map = 100%, reduce = 100%
\nEnded Job = job_local_0001
\nOK
\n65535
\nTime taken: 2.377 seconds<\/p>\n

--2\u8868\u7b49\u503c\u8fde\u63a5\u6548\u7387
\nhive> select test_hive.*,test_hive4.name from test_hive join test_hive4 on (test_hive.id=test_hive4.id); <\/p>\n

Time taken: 28.306 seconds<\/p>\n

<\/coolcode><\/p>\n","protected":false},"excerpt":{"rendered":"

hive\u7684\u7b80\u5355\u64cd\u4f5c \u73af\u5883\u8bf4\u660e\uff1a \u4e00\u822c\u53f0\u5f0f\u673a+vmware8.0+orcel enterprise linux6 […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[8],"tags":[],"_links":{"self":[{"href":"http:\/\/www.yallonking.com\/index.php?rest_route=\/wp\/v2\/posts\/325"}],"collection":[{"href":"http:\/\/www.yallonking.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.yallonking.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.yallonking.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www.yallonking.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=325"}],"version-history":[{"count":2,"href":"http:\/\/www.yallonking.com\/index.php?rest_route=\/wp\/v2\/posts\/325\/revisions"}],"predecessor-version":[{"id":369,"href":"http:\/\/www.yallonking.com\/index.php?rest_route=\/wp\/v2\/posts\/325\/revisions\/369"}],"wp:attachment":[{"href":"http:\/\/www.yallonking.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=325"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.yallonking.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=325"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.yallonking.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=325"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}