{"id":3382,"date":"2020-12-29T11:48:34","date_gmt":"2020-12-29T03:48:34","guid":{"rendered":"https:\/\/nj.transwarp.cn:8180\/?p=3382"},"modified":"2020-12-29T11:48:34","modified_gmt":"2020-12-29T03:48:34","slug":"spark-%e8%bf%9e%e6%8e%a5-inceptor-%e7%9a%84%e6%96%b9%e6%b3%95","status":"publish","type":"post","link":"https:\/\/kbwp.transwarp.cn\/?p=3382","title":{"rendered":"spark \u8fde\u63a5 inceptor \u7684\u65b9\u6cd5"},"content":{"rendered":"<h3>\u6982\u8981\u63cf\u8ff0<\/h3>\n<hr \/>\n<p>Spark \u5e94\u7528\u8fc1\u79fb\u5230 TDH \u96c6\u7fa4\u540e\u4f1a\u6709\u5bf9\u63a5\u95ee\u9898\uff0c\u672c\u6587\u6863\u4ecb\u63d0\u4f9b\u51e0\u79cd spark \u8fde\u63a5 inceptor \u7684\u65b9\u6cd5\u4ee5\u53ca\u793a\u4f8b\u4ee3\u7801\uff1b<\/p>\n<h3>\u8be6\u7ec6\u8bf4\u660e<\/h3>\n<hr \/>\n<ol>\n<li>JDBC\u65b9\u5f0f\n<ol>\n<li>LDAP<\/li>\n<li>Kerberos<\/li>\n<\/ol>\n<\/li>\n<li>Spark\u7a0b\u5e8fschema\u8d70jdbc\uff0c\u6570\u636e\u4e0d\u8d70jdbc\u7684\u65b9\u5f0f\u8bbf\u95eeInceptor\uff1a<\/li>\n<\/ol>\n<h4>\u64cd\u4f5c\u4ee5\u53ca\u5b9e\u4f8b\u4ee3\u7801<\/h4>\n<h5>JDBC\u65b9\u5f0f<\/h5>\n<h6>Inceptor \u5f00\u542f LDAP \u8ba4\u8bc1\u65b9\u5f0f<\/h6>\n<p>1\u3001export SPARK_CONF_DIR=\/etc\/discover1\/conf\/spark<br \/>\n2\u3001cd \/usr\/lib\/discover\/bin<br \/>\n\u8fdb\u5165spark-shell\u4e2d\u6267\u884c\u4e0b\u5217\u547d\u4ee4\uff1a<\/p>\n<pre><code class=\"language-scala\">import org.apache.spark.sql.SparkSession\n\/\/\u521d\u59cb\u5316SparkSession\nval spark = SparkSession.builder().master(\"yarn\").appName(\"discover test\").getOrCreate()\n\/\/\u521b\u5efajdbc\u8fde\u63a5\uff0c\u914d\u7f6e\u9879\u5206\u522b\u4e3a inceptor\u8282\u70b9ip\uff0c\u662f\u5426\u542f\u7528Kerberos\uff0c\u662f\u5426hiveServer2\u6a21\u5f0f\uff0cinceptor\u7528\u6237\u540d\uff0cinceptor\u7528\u6237\u5bc6\u7801\uff0c\u5e93\u540d\nval jdbc=io.transwarp.discover.source.InceptorJDBC.getInceptorJDBC(\"172.22.24.66\",false,true,\"discover\",\"123456\",\"default\")\n\/\/\u83b7\u53d6table\u6570\u636e\n\/\/text\nval table = jdbc.getDataTable(\"SELECT * FROM emp_text\",spark)\n\/\/varchar\uff0c\u9ed8\u8ba4\u4e0d\u80fd\u8bfb\u53d6varchar\u7c7b\u578b\u6570\u636e\uff0c\u9700\u8981\u4f7f\u7528\u7c7b\u578b\u8f6c\u6362\u51fd\u6570\uff08\u6bd4\u5982\uff1ato_char()\u51fd\u6570\uff09\u8f6c\u6362\u6210\u5176\u4ed6\u7c7b\u578b\nval table = jdbc.getDataTable(\"SELECT to_char(address) FROM emp_varchar LIMIT 10\",spark)\n\/\/orc-transaction\nval table = jdbc.getDataTable(\"SELECT * FROM emp_torc LIMIT 10\",spark)\n\/\/view\nval table = jdbc.getDataTable(\"SELECT * FROM emp_v LIMIT 10\",spark)\n\n\/\/\u67e5\u770b\u6570\u636e\nval df = table.dataFrame\ndf.collect()\ndf.show()<\/code><\/pre>\n<p><strong>\u5907\u6ce8\uff1a\u9ed8\u8ba4\u4e0d\u80fd\u8bfb\u53d6varchar\u7c7b\u578b\u6570\u636e\uff0c\u9700\u8981\u4f7f\u7528\u7c7b\u578b\u8f6c\u6362\u51fd\u6570\uff08\u6bd4\u5982\uff1ato_char()\u51fd\u6570\uff09\u8f6c\u6362\u6210\u5176\u4ed6\u7c7b\u578b<\/strong><\/p>\n<h6>Inceptor \u5f00\u542f Kerberos \u8ba4\u8bc1\u65b9\u5f0f<\/h6>\n<p>1\u3001export SPARK_CONF_DIR=\/etc\/discover1\/conf\/spark<br \/>\n2\u3001export INCEPTOR_KEYTAB=&quot;\/etc\/discover1\/conf\/discover.keytab&quot;<br \/>\n3\u3001export RUSER=&quot;discover&quot;<br \/>\n4\u3001cd \/usr\/lib\/discover\/bin<\/p>\n<p>\u8fdb\u5165spark-shell\u4e2d\u6267\u884c\u4e0b\u5217\u547d\u4ee4\uff1a<\/p>\n<pre><code class=\"language-scala\">import org.apache.spark.sql.SparkSession\n\/\/\u521d\u59cb\u5316SparkSession\nval spark = SparkSession.builder().master(\"yarn\").appName(\"discover test\").getOrCreate()\n\/\/\u521b\u5efajdbc\u8fde\u63a5\uff0c\u914d\u7f6e\u9879\u5206\u522b\u4e3a inceptor\u8282\u70b9ip\uff0c\u662f\u5426\u542f\u7528Kerberos\uff0c\u662f\u5426hiveServer2\u6a21\u5f0f\uff0cinceptor\u7528\u6237\u540d\uff0cinceptor\u7528\u6237\u5bc6\u7801\uff0c\u5e93\u540d\uff1b\u5f53\u4f7f\u7528kerberos \u8ba4\u8bc1\u65f6\uff0cInceptor\u7528\u6237\u540d\u548cInceptor\u7528\u6237\u9762\u53ef\u4ee5\u4f7f\u7528\u7a7a\u5b57\u7b26\u4e32\uff1b\nval jdbc=io.transwarp.discover.source.InceptorJDBC.getInceptorJDBC(\"172.22.24.66\",true,true,\"\",\"\",\"default\")\n\/\/\u83b7\u53d6table\u6570\u636e\n\/\/text\nval table = jdbc.getDataTable(\"SELECT * FROM emp_text\",spark)\n\/\/varchar\uff0c\u9ed8\u8ba4\u4e0d\u80fd\u8bfb\u53d6varchar\u7c7b\u578b\u6570\u636e\uff0c\u9700\u8981\u4f7f\u7528\u7c7b\u578b\u8f6c\u6362\u51fd\u6570\uff08\u6bd4\u5982\uff1ato_char()\u51fd\u6570\uff09\u8f6c\u6362\u6210\u5176\u4ed6\u7c7b\u578b\nval table = jdbc.getDataTable(\"SELECT to_char(address) FROM emp_varchar LIMIT 10\",spark)\n\/\/orc-transaction\nval table = jdbc.getDataTable(\"SELECT * FROM emp_torc LIMIT 10\",spark)\n\/\/view\nval table = jdbc.getDataTable(\"SELECT * FROM emp_v LIMIT 10\",spark)\n\n\/\/\u67e5\u770b\u6570\u636e\nval df = table.dataFrame\ndf.collect()\ndf.show()<\/code><\/pre>\n<p><strong>\u5907\u6ce8\uff1a\u9ed8\u8ba4\u4e0d\u80fd\u8bfb\u53d6varchar\u7c7b\u578b\u6570\u636e\uff0c\u9700\u8981\u4f7f\u7528\u7c7b\u578b\u8f6c\u6362\u51fd\u6570\uff08\u6bd4\u5982\uff1ato_char()\u51fd\u6570\uff09\u8f6c\u6362\u6210\u5176\u4ed6\u7c7b\u578b<\/strong><\/p>\n<h5>Spark\u7a0b\u5e8fschema\u8d70jdbc\uff0c\u6570\u636e\u4e0d\u8d70jdbc\u7684\u65b9\u5f0f\u8bbf\u95eeInceptor<\/h5>\n<pre><code class=\"language-scala\">\/\/\u5bfc\u5165\u6240\u9700\u5305\nimport org.apache.spark.sql.SQLContext\n\/\/\u521d\u59cb\u5316sqlcontext\nval sqlContext = new org.apache.spark.sql.SQLContext(sc)\n\/\/\u521b\u5efajdbc\u8fde\u63a5,\u914d\u7f6e\u9879\u6839\u636e\u81ea\u8eab\u4fee\u6539\uff0c\u4ee5\u4e0b\u9762\u4e3a\u4f8b\uff1ainceptor\u6570\u636e\u5e93\u5730\u5740\u4e0e\u6570\u636e\u5e93\u540d\uff0cinceptor\u9a71\u52a8\uff0c\u8bfb\u53d6\u7684\u8868\u540d\uff0cinceptor\u7528\u6237\u540d\uff0cinceptor\u7528\u6237\u5bc6\u7801\u3002\n\nval jdbcDF = sqlContext.read.format(\"jdbc\").options(Map(\"url\" -> \"jdbc:hive2:\/\/172.22.24.66:10000\/default\", \"driver\" -> \"org.apache.hive.jdbc.HiveDriver\", \"dbtable\" -> \" emp_table \", \"user\" -> \"admin\", \"password\" -> \"123456\")).load()\njdbcDF.collect()\n\nval jdbcDF = sqlContext.read.format(\"jdbc\").options(Map(\"url\" -> \"jdbc:hive2:\/\/172.22.24.66:10000\/default\", \"driver\" -> \"org.apache.hive.jdbc.HiveDriver\", \"dbtable\" -> \" emp_table \", \"user\" -> \"admin\", \"password\" -> \"123456\")).load()\njdbcDF.collect()\n\n\/\/\u67e5\u770b\u6570\u636e\njdbcDF.show()<\/code><\/pre>\n<h4>\u5e38\u89c1\u95ee\u9898\uff1a<\/h4>\n<ol>\n<li>\n<p>kerberos \u8ba4\u8bc1\u9700\u8981\u6307\u5b9a\u4e24\u4e2a\u73af\u5883\u53d8\u91cf\uff0c<strong><code>export INCEPTOR_KEYTAB=&quot;\/etc\/discover1\/conf\/discover.keytab&quot; <\/code>\u548c <code>export RUSER=&quot;discover&quot;<\/code><\/strong><\/p>\n<\/li>\n<li>\n<p>\u5f53\u4f7f\u7528\u7684\u662f\u666e\u901a\u7528\u6237\u8ba4\u8bc1\u7684\u65f6\u5019\uff0c\u9700\u8981\u6709 Inceptor \u7684 discover \u6570\u636e\u5e93\u7684 select \u548c create \u6743\u9650\uff1b<\/p>\n<pre><code class=\"language-java\">20\/07\/15 08:42:48 ERROR io.transwarp.discover.source.InceptorJDBC: COMPILE FAILED: \nInternal error HiveAccessControlException: [Error 20388] Permission denied: \nPrincipal [name=discover, type=USER] does not have following privileges for operation CREATETABLE_AS_SELECT [[CREATE] on Object [type=DATABASE, name=discover]]<\/code><\/pre>\n<\/li>\n<li>\n<p>JDBC \u65b9\u5f0f\u9ed8\u8ba4\u4e0d\u80fd\u8bfb\u53d6varchar\u7c7b\u578b\u6570\u636e\uff0c\u9700\u8981\u4f7f\u7528\u7c7b\u578b\u8f6c\u6362\u51fd\u6570\uff08\u6bd4\u5982\uff1ato_char()\u51fd\u6570\uff09\u8f6c\u6362\u6210\u5176\u4ed6\u7c7b\u578b\uff1b<\/p>\n<pre><code class=\"language-java\">20\/07\/15 08:53:45 ERROR io.transwarp.discover.source.InceptorJDBC: org.apache.spark.sql.catalyst.parser.ParseException:\nDataType varchar is not supported.(line 1, pos 0)\n== SQL ==\nvarchar\n^^^<\/code><\/pre>\n<\/li>\n<li>\n<p>spark-shell \u6216\u8005 spark-submit \u63d0\u4ea4\u7684\u5e94\u7528\u53ef\u4ee5\u5728 \/var\/log\/discover1\/spark.log \u91cc\u9762\u67e5\u770b\u8fd0\u884c\u60c5\u51b5\uff0c\u6839\u636e\u5177\u4f53\u62a5\u9519\u67e5\u627e\u5177\u4f53\u539f\u56e0\u3002<\/p>\n<\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"<p>\u6982\u8981\u63cf\u8ff0 Spark \u5e94\u7528\u8fc1\u79fb\u5230 TDH \u96c6\u7fa4\u540e\u4f1a\u6709\u5bf9\u63a5\u95ee\u9898\uff0c\u672c\u6587\u6863\u4ecb\u63d0\u4f9b\u51e0\u79cd spark \u8fde\u63a5 incept ..<\/p>\n<div class=\"clear-fix\"><\/div>\n<p><a href=\"https:\/\/kbwp.transwarp.cn\/?p=3382\" title=\"read more...\">Read more<\/a><\/p>\n","protected":false},"author":11,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[47],"tags":[],"class_list":["post-3382","post","type-post","status-publish","format-standard","hentry","category-third_part"],"acf":[],"_links":{"self":[{"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=\/wp\/v2\/posts\/3382","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=\/wp\/v2\/users\/11"}],"replies":[{"embeddable":true,"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=3382"}],"version-history":[{"count":0,"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=\/wp\/v2\/posts\/3382\/revisions"}],"wp:attachment":[{"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3382"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3382"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3382"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}