{"id":186880,"date":"2024-11-11T09:36:41","date_gmt":"2024-11-11T01:36:41","guid":{"rendered":"https:\/\/server.hk\/cnblog\/186880\/"},"modified":"2024-11-11T09:36:42","modified_gmt":"2024-11-11T01:36:42","slug":"%e6%95%b8%e6%93%9a%e5%ba%ab%e8%81%af%e5%90%88%e6%9f%a5%e8%a9%a2%e7%b3%bb%e7%b5%b1%e7%a0%94%e7%a9%b6%ef%bc%9a%e4%b8%89%e6%ac%be%e8%a7%a3%e6%b1%ba%e6%96%b9%e6%a1%88%e4%bb%8b%e7%b4%b9-%e4%b8%89%e5%80%8b","status":"publish","type":"post","link":"https:\/\/server.hk\/cnblog\/186880\/","title":{"rendered":"\u6578\u64da\u5eab\u806f\u5408\u67e5\u8a62\u7cfb\u7d71\u7814\u7a76\uff1a\u4e09\u6b3e\u89e3\u6c7a\u65b9\u6848\u4ecb\u7d39 (\u4e09\u500b\u6578\u64da\u5eab\u806f\u5408\u67e5\u8a62\u7cfb\u7d71)"},"content":{"rendered":"<h1 id=\"%e6%95%b8%e6%93%9a%e5%ba%ab%e8%81%af%e5%90%88%e6%9f%a5%e8%a9%a2%e7%b3%bb%e7%b5%b1%e7%a0%94%e7%a9%b6%ef%bc%9a%e4%b8%89%e6%ac%be%e8%a7%a3%e6%b1%ba%e6%96%b9%e6%a1%88%e4%bb%8b%e7%b4%b9-VXMyKsOscj\">\u6578\u64da\u5eab\u806f\u5408\u67e5\u8a62\u7cfb\u7d71\u7814\u7a76\uff1a\u4e09\u6b3e\u89e3\u6c7a\u65b9\u6848\u4ecb\u7d39<\/h1>\n<p>\u5728\u7576\u4eca\u6578\u64da\u9a45\u52d5\u7684\u4e16\u754c\u4e2d\uff0c\u6578\u64da\u5eab\u806f\u5408\u67e5\u8a62\u7cfb\u7d71\u7684\u9700\u6c42\u65e5\u76ca\u589e\u52a0\u3002\u9019\u4e9b\u7cfb\u7d71\u5141\u8a31\u7528\u6236\u5f9e\u591a\u500b\u6578\u64da\u5eab\u4e2d\u63d0\u53d6\u548c\u6574\u5408\u6578\u64da\uff0c\u5f9e\u800c\u63d0\u9ad8\u6578\u64da\u5206\u6790\u7684\u6548\u7387\u548c\u6e96\u78ba\u6027\u3002\u672c\u6587\u5c07\u4ecb\u7d39\u4e09\u6b3e\u6d41\u884c\u7684\u6578\u64da\u5eab\u806f\u5408\u67e5\u8a62\u89e3\u6c7a\u65b9\u6848\uff0c\u5e6b\u52a9\u8b80\u8005\u4e86\u89e3\u5b83\u5011\u7684\u7279\u9ede\u548c\u9069\u7528\u5834\u666f\u3002<\/p>\n<h2 id=\"1-apache-drill-VXMyKsOscj\">1. Apache Drill<\/h2>\n<p>Apache Drill \u662f\u4e00\u500b\u958b\u6e90\u7684\u5206\u4f48\u5f0f\u67e5\u8a62\u5f15\u64ce\uff0c\u5c08\u70ba\u5927\u6578\u64da\u74b0\u5883\u8a2d\u8a08\u3002\u5b83\u652f\u6301\u591a\u7a2e\u6578\u64da\u6e90\uff0c\u5305\u62ec\u95dc\u4fc2\u578b\u6578\u64da\u5eab\u3001NoSQL \u6578\u64da\u5eab\u548c\u6587\u4ef6\u7cfb\u7d71\u3002Drill \u7684\u4e00\u5927\u7279\u9ede\u662f\u5176\u9748\u6d3b\u6027\uff0c\u5141\u8a31\u7528\u6236\u4f7f\u7528 SQL \u8a9e\u8a00\u67e5\u8a62\u4e0d\u540c\u985e\u578b\u7684\u6578\u64da\u3002<\/p>\n<h3 id=\"%e7%89%b9%e9%bb%9e-VXMyKsOscj\">\u7279\u9ede<\/h3>\n<ul>\n<li><strong>\u7121\u9700 ETL\uff1a<\/strong>\u7528\u6236\u53ef\u4ee5\u76f4\u63a5\u67e5\u8a62\u539f\u59cb\u6578\u64da\uff0c\u7121\u9700\u9032\u884c\u6578\u64da\u8f49\u63db\u3002<\/li>\n<li><strong>\u5373\u6642\u67e5\u8a62\uff1a<\/strong>\u652f\u6301\u5373\u6642\u67e5\u8a62\uff0c\u9069\u5408\u9700\u8981\u5feb\u901f\u53cd\u61c9\u7684\u696d\u52d9\u5834\u666f\u3002<\/li>\n<li><strong>\u591a\u6578\u64da\u6e90\u652f\u6301\uff1a<\/strong>\u80fd\u5920\u9023\u63a5\u591a\u7a2e\u6578\u64da\u6e90\uff0c\u63d0\u4f9b\u7d71\u4e00\u7684\u67e5\u8a62\u63a5\u53e3\u3002<\/li>\n<\/ul>\n<h3 id=\"%e4%bd%bf%e7%94%a8%e7%af%84%e4%be%8b-VXMyKsOscj\">\u4f7f\u7528\u7bc4\u4f8b<\/h3>\n<pre><code>SELECT * FROM dfs.`\/path\/to\/data.json` WHERE age &gt; 30;<\/code><\/pre>\n<p>\u9019\u6bb5 SQL \u67e5\u8a62\u5c07\u5f9e\u6307\u5b9a\u7684 JSON \u6587\u4ef6\u4e2d\u63d0\u53d6\u5e74\u9f61\u5927\u65bc 30 \u7684\u8a18\u9304\uff0c\u5c55\u793a\u4e86 Drill \u7684\u9748\u6d3b\u6027\u548c\u5f37\u5927\u529f\u80fd\u3002<\/p>\n<h2 id=\"2-presto-VXMyKsOscj\">2. Presto<\/h2>\n<p>Presto \u662f\u7531 Facebook \u958b\u767c\u7684\u4e00\u500b\u5206\u4f48\u5f0f SQL \u67e5\u8a62\u5f15\u64ce\uff0c\u5c08\u9580\u7528\u65bc\u5927\u6578\u64da\u5206\u6790\u3002\u5b83\u80fd\u5920\u5728\u591a\u500b\u6578\u64da\u6e90\u4e0a\u9032\u884c\u67e5\u8a62\uff0c\u5305\u62ec Hadoop\u3001Cassandra \u548c\u95dc\u4fc2\u578b\u6578\u64da\u5eab\u3002Presto \u7684\u8a2d\u8a08\u76ee\u7684\u662f\u63d0\u4f9b\u9ad8\u6548\u7684\u67e5\u8a62\u6027\u80fd\uff0c\u7279\u5225\u662f\u5728\u8655\u7406\u5927\u898f\u6a21\u6578\u64da\u96c6\u6642\u3002<\/p>\n<h3 id=\"%e7%89%b9%e9%bb%9e-VXMyKsOscj\">\u7279\u9ede<\/h3>\n<ul>\n<li><strong>\u9ad8\u6548\u6027\u80fd\uff1a<\/strong>Presto \u80fd\u5920\u5728\u6578\u79d2\u5167\u5b8c\u6210\u67e5\u8a62\uff0c\u9069\u5408\u9700\u8981\u5feb\u901f\u6578\u64da\u5206\u6790\u7684\u5834\u666f\u3002<\/li>\n<li><strong>\u652f\u6301\u591a\u7a2e\u6578\u64da\u683c\u5f0f\uff1a<\/strong>\u80fd\u5920\u8655\u7406\u591a\u7a2e\u6578\u64da\u683c\u5f0f\uff0c\u5982 Parquet\u3001ORC \u548c JSON\u3002<\/li>\n<li><strong>\u6613\u65bc\u64f4\u5c55\uff1a<\/strong>\u652f\u6301\u6c34\u5e73\u64f4\u5c55\uff0c\u80fd\u5920\u8f15\u9b06\u61c9\u5c0d\u4e0d\u65b7\u589e\u9577\u7684\u6578\u64da\u9700\u6c42\u3002<\/li>\n<\/ul>\n<h3 id=\"%e4%bd%bf%e7%94%a8%e7%af%84%e4%be%8b-VXMyKsOscj\">\u4f7f\u7528\u7bc4\u4f8b<\/h3>\n<pre><code>SELECT customer_id, COUNT(*) FROM orders GROUP BY customer_id;<\/code><\/pre>\n<p>\u9019\u6bb5\u67e5\u8a62\u5c07\u7d71\u8a08\u6bcf\u4f4d\u5ba2\u6236\u7684\u8a02\u55ae\u6578\u91cf\uff0c\u5c55\u793a\u4e86 Presto \u5728\u6578\u64da\u5206\u6790\u4e2d\u7684\u61c9\u7528\u3002<\/p>\n<h2 id=\"3-apache-spark-sql-VXMyKsOscj\">3. Apache Spark SQL<\/h2>\n<p>Apache Spark SQL \u662f\u4e00\u500b\u5f37\u5927\u7684\u6578\u64da\u8655\u7406\u5f15\u64ce\uff0c\u652f\u6301 SQL \u67e5\u8a62\u548c\u6578\u64da\u6d41\u8655\u7406\u3002\u5b83\u80fd\u5920\u8655\u7406\u7d50\u69cb\u5316\u548c\u534a\u7d50\u69cb\u5316\u6578\u64da\uff0c\u4e26\u4e14\u53ef\u4ee5\u8207\u591a\u7a2e\u6578\u64da\u6e90\u96c6\u6210\uff0c\u5982 HDFS\u3001Hive \u548c JDBC \u6578\u64da\u5eab\u3002Spark SQL \u7684\u512a\u52e2\u5728\u65bc\u5176\u9ad8\u6548\u7684\u8a08\u7b97\u80fd\u529b\u548c\u9748\u6d3b\u7684\u6578\u64da\u8655\u7406\u65b9\u5f0f\u3002<\/p>\n<h3 id=\"%e7%89%b9%e9%bb%9e-VXMyKsOscj\">\u7279\u9ede<\/h3>\n<ul>\n<li><strong>\u9ad8\u6548\u8a08\u7b97\uff1a<\/strong>\u5229\u7528\u5167\u5b58\u8a08\u7b97\u6280\u8853\uff0c\u986f\u8457\u63d0\u9ad8\u67e5\u8a62\u6027\u80fd\u3002<\/li>\n<li><strong>\u652f\u6301\u591a\u7a2e\u6578\u64da\u6e90\uff1a<\/strong>\u80fd\u5920\u8207\u591a\u7a2e\u6578\u64da\u6e90\u7121\u7e2b\u96c6\u6210\uff0c\u63d0\u4f9b\u9748\u6d3b\u7684\u67e5\u8a62\u9078\u64c7\u3002<\/li>\n<li><strong>\u5f37\u5927\u7684\u6578\u64da\u8655\u7406\u80fd\u529b\uff1a<\/strong>\u652f\u6301\u6279\u8655\u7406\u548c\u6d41\u8655\u7406\uff0c\u9069\u5408\u5404\u7a2e\u6578\u64da\u8655\u7406\u9700\u6c42\u3002<\/li>\n<\/ul>\n<h3 id=\"%e4%bd%bf%e7%94%a8%e7%af%84%e4%be%8b-VXMyKsOscj\">\u4f7f\u7528\u7bc4\u4f8b<\/h3>\n<pre><code>val df = spark.sql(\"SELECT * FROM sales WHERE amount &gt; 1000\")<\/code><\/pre>\n<p>\u9019\u6bb5\u4ee3\u78bc\u5c55\u793a\u4e86\u5982\u4f55\u4f7f\u7528 Spark SQL \u67e5\u8a62\u92b7\u552e\u984d\u5927\u65bc 1000 \u7684\u8a18\u9304\uff0c\u986f\u793a\u4e86\u5176\u5728\u5927\u6578\u64da\u74b0\u5883\u4e2d\u7684\u61c9\u7528\u6f5b\u529b\u3002<\/p>\n<h2 id=\"%e7%b8%bd%e7%b5%90-VXMyKsOscj\">\u7e3d\u7d50<\/h2>\n<p>\u6578\u64da\u5eab\u806f\u5408\u67e5\u8a62\u7cfb\u7d71\u5728\u7576\u4eca\u7684\u6578\u64da\u5206\u6790\u4e2d\u626e\u6f14\u8457\u91cd\u8981\u89d2\u8272\u3002\u7121\u8ad6\u662f Apache Drill\u3001Presto \u9084\u662f Apache Spark SQL\uff0c\u5b83\u5011\u5404\u81ea\u90fd\u6709\u7368\u7279\u7684\u512a\u52e2\u548c\u9069\u7528\u5834\u666f\u3002\u9078\u64c7\u5408\u9069\u7684\u89e3\u6c7a\u65b9\u6848\u53ef\u4ee5\u5e6b\u52a9\u4f01\u696d\u66f4\u9ad8\u6548\u5730\u8655\u7406\u548c\u5206\u6790\u6578\u64da\uff0c\u5f9e\u800c\u63d0\u5347\u696d\u52d9\u6c7a\u7b56\u7684\u6e96\u78ba\u6027\u3002<\/p>\n<p>\u5982\u679c\u60a8\u6b63\u5728\u5c0b\u627e\u9ad8\u6548\u7684 <a href=\"https:\/\/server.hk\">VPS<\/a> \u89e3\u6c7a\u65b9\u6848\u4f86\u652f\u6301\u60a8\u7684\u6578\u64da\u5eab\u806f\u5408\u67e5\u8a62\u7cfb\u7d71\uff0cServer.HK \u63d0\u4f9b\u591a\u7a2e\u9078\u64c7\uff0c\u6eff\u8db3\u4e0d\u540c\u9700\u6c42\u7684\u5ba2\u6236\u3002\u7121\u8ad6\u662f <a href=\"https:\/\/server.hk\">\u9999\u6e2fVPS<\/a> \u9084\u662f\u5176\u4ed6\u670d\u52d9\uff0c\u6211\u5011\u90fd\u80fd\u70ba\u60a8\u63d0\u4f9b\u7a69\u5b9a\u53ef\u9760\u7684\u652f\u6301\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u63a2\u7d22\u4e09\u6b3e\u6578\u64da\u5eab\u806f\u5408\u67e5\u8a62\u7cfb\u7d71\u7684\u89e3\u6c7a\u65b9\u6848\uff0c\u6df1\u5165\u7814\u7a76\u5176\u529f\u80fd\u8207\u61c9\u7528\uff0c\u63d0\u5347\u6578\u64da\u6574\u5408\u8207\u67e5\u8a62\u6548\u7387\u3002<\/p>\n","protected":false},"author":0,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[101],"tags":[],"class_list":["post-186880","post","type-post","status-publish","format-standard","hentry","category-database"],"_links":{"self":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/186880","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/comments?post=186880"}],"version-history":[{"count":1,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/186880\/revisions"}],"predecessor-version":[{"id":186881,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/186880\/revisions\/186881"}],"wp:attachment":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/media?parent=186880"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/categories?post=186880"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/tags?post=186880"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}