{"id":135075,"date":"2024-10-31T07:27:38","date_gmt":"2024-10-30T23:27:38","guid":{"rendered":"https:\/\/server.hk\/cnblog\/135075\/"},"modified":"2024-10-31T07:27:39","modified_gmt":"2024-10-30T23:27:39","slug":"spark%ef%bc%9a%e7%82%ba%e5%a4%a7%e6%95%b8%e6%93%9a%e8%99%95%e7%90%86%e9%bb%9e%e4%ba%ae%e4%b8%80%e7%9b%9e%e6%98%8e%e7%87%88","status":"publish","type":"post","link":"https:\/\/server.hk\/cnblog\/135075\/","title":{"rendered":"Spark\uff1a\u70ba\u5927\u6578\u64da\u8655\u7406\u9ede\u4eae\u4e00\u76de\u660e\u71c8"},"content":{"rendered":"<h1 id=\"spark%ef%bc%9a%e7%82%ba%e5%a4%a7%e6%95%b8%e6%93%9a%e8%99%95%e7%90%86%e9%bb%9e%e4%ba%ae%e4%b8%80%e7%9b%9e%e6%98%8e%e7%87%88-zusOUBbImo\">Spark\uff1a\u70ba\u5927\u6578\u64da\u8655\u7406\u9ede\u4eae\u4e00\u76de\u660e\u71c8<\/h1>\n<p>\u5728\u7576\u4eca\u6578\u64da\u9a45\u52d5\u7684\u6642\u4ee3\uff0c\u5927\u6578\u64da\u7684\u8655\u7406\u548c\u5206\u6790\u5df2\u6210\u70ba\u4f01\u696d\u6210\u529f\u7684\u95dc\u9375\u3002Apache Spark \u4f5c\u70ba\u4e00\u500b\u5f37\u5927\u7684\u958b\u6e90\u5927\u6578\u64da\u8655\u7406\u6846\u67b6\uff0c\u56e0\u5176\u9ad8\u6548\u7684\u8a08\u7b97\u80fd\u529b\u548c\u9748\u6d3b\u7684\u6578\u64da\u8655\u7406\u65b9\u5f0f\uff0c\u9010\u6f38\u6210\u70ba\u696d\u754c\u7684\u9996\u9078\u5de5\u5177\u3002\u672c\u6587\u5c07\u6df1\u5165\u63a2\u8a0e Spark \u7684\u7279\u9ede\u3001\u67b6\u69cb\u53ca\u5176\u5728\u5927\u6578\u64da\u8655\u7406\u4e2d\u7684\u61c9\u7528\u3002<\/p>\n<h2 id=\"spark-%e7%9a%84%e7%89%b9%e9%bb%9e-zusOUBbImo\">Spark \u7684\u7279\u9ede<\/h2>\n<ul>\n<li><strong>\u9ad8\u901f\u8655\u7406\uff1a<\/strong>Spark \u7684\u5167\u5b58\u8a08\u7b97\u80fd\u529b\u4f7f\u5176\u5728\u8655\u7406\u5927\u6578\u64da\u6642\u6bd4\u50b3\u7d71\u7684 MapReduce \u5feb\u4e0a\u6578\u5341\u500d\u3002\u9019\u662f\u56e0\u70ba Spark \u80fd\u5920\u5c07\u6578\u64da\u5b58\u5132\u5728\u5167\u5b58\u4e2d\uff0c\u6e1b\u5c11\u4e86\u78c1\u789f I\/O \u7684\u9700\u6c42\u3002<\/li>\n<li><strong>\u6613\u65bc\u4f7f\u7528\uff1a<\/strong>Spark \u63d0\u4f9b\u4e86\u591a\u7a2e\u9ad8\u7d1a API\uff0c\u5305\u62ec Java\u3001Scala\u3001Python \u548c R\uff0c\u9019\u4f7f\u5f97\u958b\u767c\u8005\u53ef\u4ee5\u4f7f\u7528\u719f\u6089\u7684\u8a9e\u8a00\u9032\u884c\u6578\u64da\u8655\u7406\u3002<\/li>\n<li><strong>\u591a\u6a23\u5316\u7684\u6578\u64da\u8655\u7406\uff1a<\/strong>Spark \u652f\u6301\u6279\u8655\u7406\u3001\u6d41\u8655\u7406\u548c\u4ea4\u4e92\u5f0f\u67e5\u8a62\uff0c\u80fd\u5920\u6eff\u8db3\u4e0d\u540c\u5834\u666f\u4e0b\u7684\u6578\u64da\u8655\u7406\u9700\u6c42\u3002<\/li>\n<li><strong>\u5f37\u5927\u7684\u751f\u614b\u7cfb\u7d71\uff1a<\/strong>Spark \u64c1\u6709\u8c50\u5bcc\u7684\u5eab\u548c\u5de5\u5177\uff0c\u5982 Spark SQL\u3001MLlib\uff08\u6a5f\u5668\u5b78\u7fd2\u5eab\uff09\u3001GraphX\uff08\u5716\u8a08\u7b97\u5eab\uff09\u7b49\uff0c\u9019\u4e9b\u5de5\u5177\u4f7f\u5f97\u6578\u64da\u5206\u6790\u548c\u6a5f\u5668\u5b78\u7fd2\u8b8a\u5f97\u66f4\u52a0\u7c21\u55ae\u3002<\/li>\n<\/ul>\n<h2 id=\"spark-%e7%9a%84%e6%9e%b6%e6%a7%8b-zusOUBbImo\">Spark \u7684\u67b6\u69cb<\/h2>\n<p>Spark \u7684\u67b6\u69cb\u4e3b\u8981\u7531\u4ee5\u4e0b\u5e7e\u500b\u7d44\u4ef6\u7d44\u6210\uff1a<\/p>\n<ul>\n<li><strong>Driver Program\uff1a<\/strong>\u8ca0\u8cac\u5354\u8abf Spark \u61c9\u7528\u7684\u57f7\u884c\uff0c\u4e26\u5c07\u4efb\u52d9\u5206\u914d\u7d66\u96c6\u7fa4\u4e2d\u7684\u5de5\u4f5c\u7bc0\u9ede\u3002<\/li>\n<li><strong>Cluster Manager\uff1a<\/strong>\u8ca0\u8cac\u7ba1\u7406\u96c6\u7fa4\u8cc7\u6e90\uff0cSpark \u652f\u6301\u591a\u7a2e\u96c6\u7fa4\u7ba1\u7406\u5668\uff0c\u5982 Standalone\u3001Apache Mesos \u548c Hadoop YARN\u3002<\/li>\n<li><strong>Worker Nodes\uff1a<\/strong>\u57f7\u884c\u5be6\u969b\u7684\u8a08\u7b97\u4efb\u52d9\uff0c\u4e26\u5c07\u7d50\u679c\u8fd4\u56de\u7d66 Driver\u3002<\/li>\n<li><strong>Resilient Distributed Dataset (RDD)\uff1a<\/strong>Spark \u7684\u6838\u5fc3\u6578\u64da\u7d50\u69cb\uff0c\u652f\u6301\u5206\u4f48\u5f0f\u8a08\u7b97\u548c\u5bb9\u932f\u3002<\/li>\n<\/ul>\n<h2 id=\"spark-%e5%9c%a8%e5%a4%a7%e6%95%b8%e6%93%9a%e8%99%95%e7%90%86%e4%b8%ad%e7%9a%84%e6%87%89%e7%94%a8-zusOUBbImo\">Spark \u5728\u5927\u6578\u64da\u8655\u7406\u4e2d\u7684\u61c9\u7528<\/h2>\n<p>Spark \u5728\u5404\u884c\u5404\u696d\u7684\u61c9\u7528\u8d8a\u4f86\u8d8a\u5ee3\u6cdb\uff0c\u4ee5\u4e0b\u662f\u5e7e\u500b\u5177\u9ad4\u7684\u4f8b\u5b50\uff1a<\/p>\n<h3 id=\"1-%e6%95%b8%e6%93%9a%e5%88%86%e6%9e%90-zusOUBbImo\">1. \u6578\u64da\u5206\u6790<\/h3>\n<p>\u8a31\u591a\u4f01\u696d\u5229\u7528 Spark \u9032\u884c\u5be6\u6642\u6578\u64da\u5206\u6790\u3002\u4f8b\u5982\uff0c\u91d1\u878d\u6a5f\u69cb\u53ef\u4ee5\u4f7f\u7528 Spark \u4f86\u5206\u6790\u4ea4\u6613\u6578\u64da\uff0c\u53ca\u6642\u767c\u73fe\u7570\u5e38\u884c\u70ba\uff0c\u5f9e\u800c\u9632\u6b62\u8a50\u9a19\u3002<\/p>\n<h3 id=\"2-%e6%a9%9f%e5%99%a8%e5%ad%b8%e7%bf%92-zusOUBbImo\">2. \u6a5f\u5668\u5b78\u7fd2<\/h3>\n<p>Spark \u7684 MLlib \u63d0\u4f9b\u4e86\u591a\u7a2e\u6a5f\u5668\u5b78\u7fd2\u7b97\u6cd5\uff0c\u4f01\u696d\u53ef\u4ee5\u5229\u7528\u9019\u4e9b\u7b97\u6cd5\u9032\u884c\u9810\u6e2c\u5206\u6790\u3002\u4f8b\u5982\uff0c\u96f6\u552e\u5546\u53ef\u4ee5\u6839\u64da\u9867\u5ba2\u7684\u8cfc\u8cb7\u884c\u70ba\u9032\u884c\u500b\u6027\u5316\u63a8\u85a6\u3002<\/p>\n<h3 id=\"3-%e6%b5%81%e8%99%95%e7%90%86-zusOUBbImo\">3. \u6d41\u8655\u7406<\/h3>\n<p>Spark Streaming \u4f7f\u5f97\u5be6\u6642\u6578\u64da\u8655\u7406\u8b8a\u5f97\u53ef\u884c\u3002\u793e\u4ea4\u5a92\u9ad4\u5e73\u53f0\u53ef\u4ee5\u4f7f\u7528 Spark Streaming \u4f86\u5206\u6790\u7528\u6236\u7684\u5373\u6642\u53cd\u994b\uff0c\u5f9e\u800c\u5feb\u901f\u8abf\u6574\u71df\u92b7\u7b56\u7565\u3002<\/p>\n<h2 id=\"%e7%b5%90%e8%ab%96-zusOUBbImo\">\u7d50\u8ad6<\/h2>\n<p>Apache Spark \u4f5c\u70ba\u4e00\u500b\u9ad8\u6548\u7684\u5927\u6578\u64da\u8655\u7406\u6846\u67b6\uff0c\u70ba\u4f01\u696d\u63d0\u4f9b\u4e86\u5f37\u5927\u7684\u6578\u64da\u8655\u7406\u80fd\u529b\u3002\u7121\u8ad6\u662f\u5728\u6578\u64da\u5206\u6790\u3001\u6a5f\u5668\u5b78\u7fd2\u9084\u662f\u6d41\u8655\u7406\u65b9\u9762\uff0cSpark \u90fd\u5c55\u73fe\u4e86\u5176\u5353\u8d8a\u7684\u6027\u80fd\u548c\u9748\u6d3b\u6027\u3002\u96a8\u8457\u5927\u6578\u64da\u6280\u8853\u7684\u6301\u7e8c\u767c\u5c55\uff0cSpark \u5c07\u5728\u672a\u4f86\u7684\u6578\u64da\u8655\u7406\u4e2d\u626e\u6f14\u8d8a\u4f86\u8d8a\u91cd\u8981\u7684\u89d2\u8272\u3002<\/p>\n<p>\u5982\u679c\u60a8\u5c0d\u65bc\u5927\u6578\u64da\u8655\u7406\u6709\u8208\u8da3\uff0c\u4e26\u5e0c\u671b\u5c0b\u627e\u5408\u9069\u7684 <a href=\"https:\/\/server.hk\">VPS<\/a> \u89e3\u6c7a\u65b9\u6848\u4f86\u652f\u6301\u60a8\u7684\u9805\u76ee\uff0cServer.HK \u63d0\u4f9b\u591a\u7a2e\u9078\u64c7\uff0c\u52a9\u60a8\u8f15\u9b06\u61c9\u5c0d\u5404\u7a2e\u6578\u64da\u6311\u6230\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u63a2\u7d22Spark\u5982\u4f55\u70ba\u5927\u6578\u64da\u8655\u7406\u63d0\u4f9b\u9ad8\u6548\u89e3\u6c7a\u65b9\u6848\uff0c\u52a9\u529b\u4f01\u696d\u6d1e\u5bdf\u6578\u64da\uff0c\u63d0\u5347\u6c7a\u7b56\u80fd\u529b\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-135075","post","type-post","status-publish","format-standard","hentry","category-database"],"_links":{"self":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/135075","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=135075"}],"version-history":[{"count":1,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/135075\/revisions"}],"predecessor-version":[{"id":135076,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/135075\/revisions\/135076"}],"wp:attachment":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/media?parent=135075"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/categories?post=135075"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/tags?post=135075"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}