{"id":13917,"date":"2025-03-11T15:54:58","date_gmt":"2025-03-11T07:54:58","guid":{"rendered":"https:\/\/nj.transwarp.cn:8180\/?p=13917"},"modified":"2025-06-05T11:44:29","modified_gmt":"2025-06-05T03:44:29","slug":"bzip2%e5%8e%8b%e7%bc%a9%e7%bc%93%e8%a7%a3text%e8%a1%a8%e6%96%87%e4%bb%b6%e5%8d%a0%e7%94%a8%e8%bf%87%e5%a4%a7%e9%97%ae%e9%a2%98","status":"publish","type":"post","link":"https:\/\/kbwp.transwarp.cn\/?p=13917","title":{"rendered":"bzip2\u538b\u7f29\u7f13\u89e3text\u8868\u6587\u4ef6\u5360\u7528\u8fc7\u5927\u95ee\u9898"},"content":{"rendered":"<h3>\u6982\u8981\u63cf\u8ff0<\/h3>\n<hr \/>\n<p>\u5ba2\u6237\u53cd\u9988\uff0c\u96c6\u7fa4\u4e2d\u6709\u4e00\u4e9btextfile\u8868\u6587\u4ef6\u8fc7\u5927\uff0c\u5360\u7528\u5927\u91cfhdfs\u5b58\u50a8\u7a7a\u95f4\uff0c\u672c\u6587\u4e3b\u8981\u4ecb\u7ecd\u5982\u4f55\u901a\u8fc7bzip2\u538b\u7f29\u65b9\u5f0f\u51cf\u5c11hdfs\u5360\u7528\u3002<\/p>\n<p>\u6807\u51c6\u7684textfile\u662f\u65e0\u538b\u7f29\u683c\u5f0f\uff0c\u5b58\u50a8\u5360\u7528\u7a7a\u95f4\u6bd4\u8f83\u5927\uff0c\u800cBzip2\u683c\u5f0f\u538b\u7f29\u7387\u8f83\u9ad8\uff0c\u53ef\u4ee5\u5c1d\u8bd5\u901a\u8fc7\u8fd9\u79cd\u65b9\u5f0f\u51cf\u5c11\u7a7a\u95f4\u5360\u7528\u3002<\/p>\n<blockquote>\n<p>\u4e3a\u4f55\u4e0d\u8003\u8651gzip\u538b\u7f29\u683c\u5f0f\uff1f<br \/>\n\u57fa\u4e8egzip\u683c\u5f0f\u4e0b\u4e0d\u652f\u6301\u5207\u5206\u7684\u7279\u6027\uff0c\u4f1a\u5bfc\u81f4\u8bfb\u8868stage\u62a5\u9519\uff08\u6bd4\u5982 bucket size is too large\uff09\u3002\u800cbzip2\u7684\u538b\u7f29\u683c\u5f0f\uff0c\u652f\u6301\u5207\u5206\uff0c\u80fd\u591f\u6b63\u5e38\u8bfb\u53d6\u3002<\/p>\n<\/blockquote>\n<h3>\u8be6\u7ec6\u8bf4\u660e<\/h3>\n<hr \/>\n<p>\u8fd9\u91cc\u6709\u4e00\u5f20120m\u5927\u5c0f\u7684people\u8868\uff0chdfs\u5360\u7528120m.<\/p>\n<pre><code class=\"language-shell\">> dfs -du -s -h hdfs:\/\/nameservice1\/tmp\/people\/\n120.1 M  360.2 M  hdfs:\/\/nameservice1\/tmp\/people<\/code><\/pre>\n<p>\u6211\u4eec\u521b\u5efa\u4e00\u5f20\u65b0\u8868<\/p>\n<pre><code class=\"language-sql\">--\u521b\u5efa\u65b0\u8868\nDROP TABLE IF EXISTS people_text_bzip2_N;\nCREATE  TABLE people_text_bzip2_N(\n  name string DEFAULT NULL,\n  sex string DEFAULT NULL,\n  nation string DEFAULT NULL,\n  id string DEFAULT NULL,\n  borndate string DEFAULT NULL,\n  phonenumber string DEFAULT NULL,\n  email string DEFAULT NULL,\n  homeaddress string DEFAULT NULL\n)STORED AS TEXTFILE;<\/code><\/pre>\n<p>\u5c06\u672a\u538b\u7f29\u7684\u8868\uff0c\u901a\u8fc7\u5f00\u542f\u538b\u7f29\u53c2\u6570\uff0c\u5c06\u6570\u636e\u5199\u5165\u5230\u65b0\u8868<\/p>\n<pre><code class=\"language-sql\">--\u8bbe\u7f6ebzip2\u538b\u7f29\u65b9\u5f0f\uff0c\u63d2\u5165\u6570\u636e\n--\u5f00\u542fhive\u6700\u7ec8\u8f93\u51fa\u6570\u636e\u538b\u7f29\u529f\u80fd\nset hive.exec.compress.output=true;\n--\u5f00\u542fmapreduce\u6700\u7ec8\u8f93\u51fa\u6570\u636e\u538b\u7f29\nset mapreduce.output.fileoutputformat.compress=true;\n--\u5141\u8bb8\u7528\u6237\u6307\u5b9a\u8981\u4f7f\u7528\u7684\u538b\u7f29\u7f16\u89e3\u7801\u5668\u7684\u7c7b\u540d\nset mapreduce.output.fileoutputformat.compress.codec=org.apache.hadoop.io.compress.BZip2Codec;\nINSERT INTO people_text_bzip2_N SELECT * FROM test.people_external_text;\n\nSHOW CREATE TABLE people_text_bzip2_N;\ndfs -du -s -h  hdfs:\/\/nameservice1\/quark1\/user\/hive\/warehouse\/default.db\/hive\/people_text_bzip2_n\n29.1 M  87.4 M  hdfs:\/\/nameservice1\/quark1\/user\/hive\/warehouse\/default.db\/hive\/people_text_bzip2_n<\/code><\/pre>\n<p>\u53ef\u4ee5\u770b\u5230\u538b\u7f29\u8fc7\u540e\uff0c29.1m\uff0c\u538b\u7f29\u6bd4\u8fd14:1<\/p>\n<h4>FAQ:<\/h4>\n<p><strong>1. \u53ef\u4ee5\u76f4\u63a5\u5199\u51fa\u5230\u4e00\u4e2ahdfs\u8def\u5f84\u4e0b\uff0c\u5b9e\u73b0\u538b\u7f29\u6570\u636e\u7684\u76ee\u7684\uff1a<\/strong><\/p>\n<pre><code class=\"language-sql\">--\u8bbe\u7f6ebzip2\u538b\u7f29\u65b9\u5f0f\uff0c\u63d2\u5165\u6570\u636e\nset hive.exec.compress.output=true;\nset mapreduce.output.fileoutputformat.compress=true;\nset mapreduce.output.fileoutputformat.compress.codec=org.apache.hadoop.io.compress.BZip2Codec;\nINSERT OVERWRITE DIRECTORY '\/tmp\/people_bzip2' SELECT * FROM test.people_external_text;\ndfs -du -s -h \/tmp\/people_bzip2<\/code><\/pre>\n<p><strong>2. linux\u81ea\u5e26\u7684bzip2\u538b\u7f29\/\u89e3\u538b\u7f29\u547d\u4ee4<\/strong><\/p>\n<p>\u53ef\u4ee5\u5bf9\u539f\u59cb\u6587\u4ef6\u8fdb\u884c\u538b\u7f29\uff0c\u518d\u4e0a\u4f20\u5230hdfs\uff0c\u901a\u8fc7textfile\u6765\u8bfb\u53d6\u3002<\/p>\n<pre><code class=\"language-shell\">#\u538b\u7f29\uff1a\nbzip2 -zkv all_people\n#\u89e3\u538b\uff1a\nbzip2 -d all_people.bz2<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"<p>\u6982\u8981\u63cf\u8ff0 \u5ba2\u6237\u53cd\u9988\uff0c\u96c6\u7fa4\u4e2d\u6709\u4e00\u4e9btextfile\u8868\u6587\u4ef6\u8fc7\u5927\uff0c\u5360\u7528\u5927\u91cfhdfs\u5b58\u50a8\u7a7a\u95f4\uff0c\u672c\u6587\u4e3b\u8981\u4ecb\u7ecd\u5982\u4f55\u901a\u8fc7bz ..<\/p>\n<div class=\"clear-fix\"><\/div>\n<p><a href=\"https:\/\/kbwp.transwarp.cn\/?p=13917\" title=\"read more...\">Read more<\/a><\/p>\n","protected":false},"author":12,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[40],"tags":[],"class_list":["post-13917","post","type-post","status-publish","format-standard","hentry","category-sql_issue"],"acf":[],"_links":{"self":[{"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=\/wp\/v2\/posts\/13917","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\/12"}],"replies":[{"embeddable":true,"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=13917"}],"version-history":[{"count":3,"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=\/wp\/v2\/posts\/13917\/revisions"}],"predecessor-version":[{"id":16681,"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=\/wp\/v2\/posts\/13917\/revisions\/16681"}],"wp:attachment":[{"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=13917"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=13917"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=13917"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}