{"id":1648,"date":"2011-05-17T08:10:45","date_gmt":"2011-05-17T08:10:45","guid":{"rendered":"http:\/\/www.msinterdev.org\/wp\/2011\/05\/17\/pig-cassandra-hadoop-%ec%84%a4%ec%a0%95\/"},"modified":"2011-05-17T08:10:45","modified_gmt":"2011-05-17T08:10:45","slug":"pig-cassandra-hadoop-%ec%84%a4%ec%a0%95","status":"publish","type":"post","link":"http:\/\/www.msinterdev.org\/wp\/2011\/05\/17\/pig-cassandra-hadoop-%ec%84%a4%ec%a0%95\/","title":{"rendered":"PIG Cassandra HADOOP \uc124\uc815"},"content":{"rendered":"<p>PIG\ub97c \ud1b5\ud574 \uce74\uc0b0\ub4dc\ub77c(Cassandra) \uc640 \uc5f0\uacb0\uc5d0 \uc131\uacf5\ud55c \uc124\uc815\uc785\ub2c8\ub2e4. <\/p>\n<p>==========================================================================================<br \/><span style=\"color: rgb(0, 128, 0); font-weight: bold;\">core-site.xml<\/span> <span style=\"font-weight: bold; color: rgb(255, 0, 0);\">on HADOOP<\/span><br \/>==========================================================================================<br \/>&lt;configuration&gt;<br \/>&nbsp; &lt;property&gt;<br \/>&nbsp; &nbsp; &lt;name&gt;fs.default.name&lt;\/name&gt;<br \/>&nbsp; &nbsp; &lt;value&gt;hdfs:\/\/localhost:54310&lt;\/value&gt;<br \/>&nbsp; &lt;\/property&gt;<\/p>\n<p>&nbsp; &lt;property&gt;<br \/>&nbsp; &nbsp;&nbsp; &lt;name&gt;hadoop.tmp.dir&lt;\/name&gt;<br \/>&nbsp; &nbsp;&nbsp; &lt;value&gt;\/usr\/lib64\/hadoop\/tmp&lt;\/value&gt;<br \/>&nbsp; &lt;\/property&gt;<br \/>&nbsp; &lt;property&gt;<br \/>&nbsp; &nbsp; &nbsp; &lt;name&gt;cassandra.thrift.address&lt;\/name&gt;<br \/>&nbsp; &nbsp; &nbsp; &lt;value&gt;localhost&lt;\/value&gt;<br \/>&nbsp; &lt;\/property&gt;<br \/>&nbsp; &lt;property&gt;<br \/>&nbsp; &nbsp; &nbsp; &lt;name&gt;cassandra.thrift.port&lt;\/name&gt;<br \/>&nbsp; &nbsp; &nbsp; &lt;value&gt;9160&lt;\/value&gt;<br \/>&nbsp; &lt;\/property&gt;<br \/>&nbsp; &lt;property&gt;<br \/>&nbsp; &nbsp; &nbsp; &lt;name&gt;cassandra.partitioner.class&lt;\/name&gt;<br \/>&nbsp; &nbsp; &nbsp; &lt;value&gt;org.apache.cassandra.dht.RandomPartitioner&lt;\/value&gt;<br \/>&nbsp; &lt;\/property&gt;<br \/>&lt;\/configuration&gt;<br \/>==========================================================================================<\/p>\n<p>==========================================================================================<br \/>system environment(<span style=\"font-weight: bold; color: rgb(0, 128, 0);\">\/etc\/profile<\/span>) for<span style=\"color: rgb(255, 0, 0); font-weight: bold;\"> HADDOP, PIG and CASSANDRA<\/span><br \/>==========================================================================================<br \/>export JAVA_HOME=\/usr\/lib64\/jvm\/java-6-sun<\/p>\n<p>export HADOOP_HOME=\/usr\/lib64\/hadoop<br \/>export HADOOPDIR=$HADOOP_HOME\/conf<br \/>export HADOOP_CONF_DIR=$HADOOPDIR<br \/>export HADOOP_CONF=$HADOOPDIR<br \/>export HADOOPDIR=$HADOOP_CONF<br \/>export HADOOP_CLASSPATH=$HADOOP_CONF:$CASSANDRA_LIB<\/p>\n<p>export PIG_HOME=\/usr\/lib64\/pig<br \/>export PIG_CLASSPATH=$HADOOPDIR<br \/>export PIG_CONF=$HADOOPDIR<br \/>export PIG_CONF_DIR=$HADOOPDIR<br \/>export PIG_RPC_PORT=9160<br \/>export PIG_INITIAL_ADDRESS=localhost<\/p>\n<p>export cassandra_home=\/usr\/share\/cassandra<br \/>export CASSANDRA_HOME=$cassandra_home<br \/>export CASSANDRA_LIB=\/usr\/share\/cassandra<br \/>export CASSANDRA_CLASSPATH=$cassandra_home<\/p>\n<p>export PATH=$PATH:$HADOOP_HOME\/bin:$PIG_HOME\/bin<br \/>================================================================================================<\/p>\n<p>================================================================================================<br \/><span style=\"font-weight: bold; color: rgb(255, 0, 0);\">HADOOP_CLASSPATH<\/span><br \/>================================================================================================<\/p>\n<p class=\"line862\">One configuration note on getting the task trackers to be able to perform queries over Cassandra:  you&#8217;ll want to update your <tt class=\"backtick\">HADOOP_CLASSPATH<\/tt> in your <tt style=\"font-weight: bold; color: rgb(212, 26, 1);\" class=\"backtick\">&lt;hadoop&gt;\/conf\/hadoop-env.sh<\/tt> to include the Cassandra lib libraries.  For example you&#8217;ll want to do something like this in the <tt class=\"backtick\">hadoop-env.sh<\/tt> on each of your task trackers: <\/p>\n<pre style=\"background-color: rgb(193, 193, 193);\">export HADOOP_CLASSPATH=\/opt\/cassandra\/lib\/*:$HADOOP_CLASSPATH<\/pre>\n<p>================================================================================================<\/p>\n<p>PIG\ub97c \uc0ac\uc6a9\ud558\uc9c0 \uc54a\uace0&nbsp; HADOOP\uc5d0\uc11c CASSANDRA\ub97c \uc5f0\uacb0\ud558\uae30 \uc704\ud574\uc11c\ub294 \uba87 \uac00\uc9c0 \uc124\uc815\uc774 \ud544\uc694\ud558\uc9c0 \uc548\uc2b5\ub2c8\ub2e4.<br \/>PIG \uc5d0\uc11c \uc9c1\uc811 Cassandra \uc5d0\uc11c \uc811\uadfc\ud558\uc9c0 \uc54a\uc744 \uacbd\uc6b0 Java\uc5d0\uc11c \ub4dc\ub77c\uc774\ubc84\ub97c \uc774\uc6a9\ud574\uc11c \uc9c1\uc811 \uc811\uadfc \ud560 \uc218 \uc788\uc73c\ub9ac\ub77c \ud310\ub2e8 \ub429\ub2c8\ub2e4. <\/p>\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>PIG\ub97c \ud1b5\ud574 \uce74\uc0b0\ub4dc\ub77c(Cassandra) \uc640 \uc5f0\uacb0\uc5d0 \uc131\uacf5\ud55c \uc124\uc815\uc785\ub2c8\ub2e4. ==========================================================================================core-site.xml on HADOOP==========================================================================================&lt;configuration&gt;&nbsp; &lt;property&gt;&nbsp; &nbsp; &lt;name&gt;fs.default.name&lt;\/name&gt;&nbsp; &nbsp; &lt;value&gt;hdfs:\/\/localhost:54310&lt;\/value&gt;&nbsp; &lt;\/property&gt; &nbsp; &lt;property&gt;&nbsp; &nbsp;&nbsp; &lt;name&gt;hadoop.tmp.dir&lt;\/name&gt;&nbsp; &nbsp;&nbsp; &lt;value&gt;\/usr\/lib64\/hadoop\/tmp&lt;\/value&gt;&nbsp; &lt;\/property&gt;&nbsp; &lt;property&gt;&nbsp; &nbsp; &nbsp; &lt;name&gt;cassandra.thrift.address&lt;\/name&gt;&nbsp; &nbsp; &nbsp; &lt;value&gt;localhost&lt;\/value&gt;&nbsp; &lt;\/property&gt;&nbsp; &lt;property&gt;&nbsp; &nbsp; &nbsp; &lt;name&gt;cassandra.thrift.port&lt;\/name&gt;&nbsp; &nbsp; &nbsp; &lt;value&gt;9160&lt;\/value&gt;&nbsp; &lt;\/property&gt;&nbsp; &lt;property&gt;&nbsp; &nbsp; &nbsp; &lt;name&gt;cassandra.partitioner.class&lt;\/name&gt;&nbsp; &nbsp; &nbsp; &lt;value&gt;org.apache.cassandra.dht.RandomPartitioner&lt;\/value&gt;&nbsp; &lt;\/property&gt;&lt;\/configuration&gt;========================================================================================== ==========================================================================================system environment(\/etc\/profile) for HADDOP, PIG and CASSANDRA==========================================================================================export JAVA_HOME=\/usr\/lib64\/jvm\/java-6-sun [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2948],"tags":[2979,2980,2981,2926,2982,2983,844,2984,2985,2927,2986,2987,2988],"class_list":["post-1648","post","type-post","status-publish","format-standard","hentry","category-about-knowledge-system_apache_hadoop","tag-etc-profile","tag-cassandra","tag-core-site-xml","tag-hadoop","tag-pig","tag-profile","tag-844","tag-2984","tag-2985","tag-2927","tag-2986","tag-2987","tag-2988"],"_links":{"self":[{"href":"http:\/\/www.msinterdev.org\/wp\/wp-json\/wp\/v2\/posts\/1648","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/www.msinterdev.org\/wp\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.msinterdev.org\/wp\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.msinterdev.org\/wp\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www.msinterdev.org\/wp\/wp-json\/wp\/v2\/comments?post=1648"}],"version-history":[{"count":0,"href":"http:\/\/www.msinterdev.org\/wp\/wp-json\/wp\/v2\/posts\/1648\/revisions"}],"wp:attachment":[{"href":"http:\/\/www.msinterdev.org\/wp\/wp-json\/wp\/v2\/media?parent=1648"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.msinterdev.org\/wp\/wp-json\/wp\/v2\/categories?post=1648"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.msinterdev.org\/wp\/wp-json\/wp\/v2\/tags?post=1648"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}