{"id":142529,"date":"2020-08-04T00:58:29","date_gmt":"2020-08-03T16:58:29","guid":{"rendered":"http:\/\/4563.org\/?p=142529"},"modified":"2020-08-04T00:58:29","modified_gmt":"2020-08-03T16:58:29","slug":"spark-rdd%e6%8c%81%e4%b9%85%e5%8c%96%e7%bc%93%e5%ad%98%e6%9c%ba%e5%88%b6","status":"publish","type":"post","link":"http:\/\/4563.org\/?p=142529","title":{"rendered":"Spark RDD\u6301\u4e45\u5316\u7f13\u5b58\u673a\u5236"},"content":{"rendered":"<h2><a href=\"https:\/\/www.studytime.xin\/article\/#RDD-\u6301\u4e45\u5316\" title=\"RDD \u6301\u4e45\u5316\"><\/a>RDD \u6301\u4e45\u5316<\/h2>\n<h3><a href=\"https:\/\/www.studytime.xin\/article\/#\u4ec0\u4e48\u4e8bRDD\u6301\u4e45\u5316\u7f13\u5b58\u673a\u5236\" title=\"\u4ec0\u4e48\u4e8bRDD\u6301\u4e45\u5316\u7f13\u5b58\u673a\u5236\"><\/a>\u4ec0\u4e48\u4e8bRDD\u6301\u4e45\u5316\u7f13\u5b58\u673a\u5236<\/h3>\n<p>RDD \u6301\u4e45\u5316\u662f Spark \u975e\u5e38\u91cd\u8981\u7684\u7279\u6027\u4e4b\u4e00\u3002\u7528\u6237\u53ef\u663e\u5f0f\u5c06\u4e00\u4e2a RDD \u6301\u4e45\u5316\u5230\u5185\u5b58\u6216\u78c1\u76d8\u4e2d\uff0c\u4ee5\u4fbf\u91cd\u7528\u8be5RDD\u3002RDD \u6301\u4e45\u5316\u662f\u4e00\u4e2a\u5206\u5e03\u5f0f\u7684\u8fc7\u7a0b\uff0c\u5176\u5185\u90e8\u7684\u6bcf\u4e2a Partition \u5404\u81ea\u7f13\u5b58\u5230\u6240\u5728\u7684\u8ba1\u7b97\u8282\u70b9\u4e0a\u3002RDD \u6301\u4e45\u5316\u5b58\u50a8\u80fd\u5927\u5927\u52a0\u5feb\u6570\u636e\u8ba1\u7b97\u6548\u7387\uff0c\u5c24\u5176\u9002\u5408\u8fed\u4ee3\u5f0f\u8ba1\u7b97\u548c\u4ea4\u4e92\u5f0f\u8ba1\u7b97\u3002<\/p>\n<h3><a href=\"https:\/\/www.studytime.xin\/article\/#\u5982\u4f55\u5bf9rdd\u8bbe\u7f6e\u7f13\u5b58\" title=\"\u5982\u4f55\u5bf9rdd\u8bbe\u7f6e\u7f13\u5b58\"><\/a>\u5982\u4f55\u5bf9rdd\u8bbe\u7f6e\u7f13\u5b58<\/h3>\n<p>Spark \u63d0\u4f9b\u4e86 persist \u548c cache \u4e24\u4e2a\u6301\u4e45\u5316\u51fd\u6570\uff0c\u5176\u4e2d cache \u5c06 RDD \u6301\u4e45\u5316\u5230\u5185\u5b58\u4e2d\uff0c\u800c persist \u5219\u652f\u6301\u591a\u79cd\u5b58\u50a8\u7ea7\u522b\u3002<\/p>\n<p>persist RDD \u5b58\u50a8\u7ea7\u522b\uff1a<\/p>\n<table>\n<thead>\n<tr>\n<th>\u6301\u4e45\u5316\u7ea7\u522b<\/th>\n<th>\u542b\u4e49<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>MEMORY_ONLY<\/td>\n<td>\u4ee5\u975e\u5e8f\u5217\u5316\u7684Java\u5bf9\u8c61\u7684\u65b9\u5f0f\u6301\u4e45\u5316\u5728JVM\u5185\u5b58\u4e2d\u3002\u5982\u679c\u5185\u5b58\u65e0\u6cd5\u5b8c\u5168\u5b58\u50a8RDD\u6240\u6709\u7684partition\uff0c\u90a3\u4e48\u90a3\u4e9b\u6ca1\u6709\u6301\u4e45\u5316\u7684partition\u5c31\u4f1a\u5728\u4e0b\u4e00\u6b21\u9700\u8981\u4f7f\u7528\u5b83\u7684\u65f6\u5019\uff0c\u91cd\u65b0\u88ab\u8ba1\u7b97\u3002<\/td>\n<\/tr>\n<tr>\n<td>MEMORY_AND_DISK<\/td>\n<td>\u540c\u4e0a\uff0c\u4f46\u662f\u5f53\u67d0\u4e9bpartition\u65e0\u6cd5\u5b58\u50a8\u5728\u5185\u5b58\u4e2d\u65f6\uff0c\u4f1a\u6301\u4e45\u5316\u5230\u78c1\u76d8\u4e2d\u3002\u4e0b\u6b21\u9700\u8981\u4f7f\u7528\u8fd9\u4e9bpartition\u65f6\uff0c\u9700\u8981\u4ece\u78c1\u76d8\u4e0a\u8bfb\u53d6\u3002<\/td>\n<\/tr>\n<tr>\n<td><\/td>\n<td><\/td>\n<\/tr>\n<tr>\n<td>MEMORY_ONLY_SER<\/td>\n<td>\u540cMEMORY_ONLY\uff0c\u4f46\u662f\u4f1a\u4f7f\u7528Java\u5e8f\u5217\u5316\u65b9\u5f0f\uff0c\u5c06Java\u5bf9\u8c61\u5e8f\u5217\u5316\u540e\u8fdb\u884c\u6301\u4e45\u5316\u3002\u53ef\u4ee5\u51cf\u5c11\u5185\u5b58\u5f00\u9500\uff0c\u4f46\u662f\u9700\u8981\u8fdb\u884c\u53cd\u5e8f\u5217\u5316\uff0c\u56e0\u6b64\u4f1a\u52a0\u5927CPU\u5f00\u9500<\/td>\n<\/tr>\n<tr>\n<td>MEMORY_AND_DSK_SER<\/td>\n<td>\u540cMEMORY_AND_DSK\u3002\u4f46\u662f\u4f7f\u7528\u5e8f\u5217\u5316\u65b9\u5f0f\u6301\u4e45\u5316Java\u5bf9\u8c61\u3002<\/td>\n<\/tr>\n<tr>\n<td>DISK_ONLY<\/td>\n<td>\u4f7f\u7528\u975e\u5e8f\u5217\u5316Java\u5bf9\u8c61\u7684\u65b9\u5f0f\u6301\u4e45\u5316\uff0c\u5b8c\u5168\u5b58\u50a8\u5230\u78c1\u76d8\u4e0a\u3002<\/td>\n<\/tr>\n<tr>\n<td>MEMORY_ONLY_2<\/td>\n<td><\/td>\n<\/tr>\n<tr>\n<td>MEMORY_AND_DISK_2<\/td>\n<td>\u5982\u679c\u662f\u5c3e\u90e8\u52a0\u4e862\u7684\u6301\u4e45\u5316\u7ea7\u522b\uff0c\u8868\u793a\u4f1a\u5c06\u6301\u4e45\u5316\u6570\u636e\u590d\u7528\u4e00\u4efd\uff0c\u4fdd\u5b58\u5230\u5176\u4ed6\u8282\u70b9\uff0c\u4ece\u800c\u5728\u6570\u636e\u4e22\u5931\u65f6\uff0c\u4e0d\u9700\u8981\u518d\u6b21\u8ba1\u7b97\uff0c\u53ea\u9700\u8981\u4f7f\u7528\u5907\u4efd\u6570\u636e\u5373\u53ef\u3002<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>\u662f\u5e76\u4e0d\u662f\u8fd9\u4e24\u4e2a\u65b9\u6cd5\u88ab\u8c03\u7528\u65f6\u7acb\u5373\u7f13\u5b58\uff0c\u800c\u662f\u89e6\u53d1\u540e\u9762\u7684action\u65f6\uff0c\u8be5RDD\u5c06\u4f1a\u88ab\u7f13\u5b58\u5728\u8ba1\u7b97\u8282\u70b9\u7684\u5185\u5b58\u4e2d\uff0c\u5e76\u4f9b\u540e\u9762\u91cd\u7528\u3002<br \/>\u901a\u8fc7\u8fc7\u67e5\u770b\u6e90\u7801\u53d1\u73b0cache\u6700\u7ec8\u4e5f\u662f\u8c03\u7528\u4e86persist\u65b9\u6cd5\uff0c\u9ed8\u8ba4\u7684\u5b58\u50a8\u7ea7\u522b\u90fd\u662f\u4ec5\u5728\u5185\u5b58\u5b58\u50a8\u4e00\u4efd\uff0cSpark\u7684\u5b58\u50a8\u7ea7\u522b\u8fd8\u6709\u597d\u591a\u79cd\uff0c\u5b58\u50a8\u7ea7\u522b\u5728object StorageLevel\u4e2d\u5b9a\u4e49\u7684\u3002<\/p>\n<h3><a href=\"https:\/\/www.studytime.xin\/article\/#\u4ee3\u7801\u6f14\u793a\" title=\"\u4ee3\u7801\u6f14\u793a\"><\/a>\u4ee3\u7801\u6f14\u793a<\/h3>\n<figure>\n<table>\n<tr>\n<td>\n<pre><span>1<\/span><br><span>2<\/span><br><span>3<\/span><br><span>4<\/span><br><span>5<\/span><br><span>6<\/span><br><span>7<\/span><br><span>8<\/span><br><\/pre>\n<\/td>\n<td>\n<pre><span><span>val<\/span> rdd1=sc.textFile(<span>\"\/words.txt\"<\/span>)<\/span><br><span><span>val<\/span> rdd2=rdd1.flatMap(_.split(<span>\" \"<\/span>))<\/span><br><span><span>val<\/span> rdd3=rdd2.cache<\/span><br><span>rdd3.collect<\/span><br><span><\/span><br><span><span>val<\/span> rdd4=rdd3.map((_,<span>1<\/span>))<\/span><br><span><span>val<\/span> rdd5=rdd4.persist(\u7f13\u5b58\u7ea7\u522b)<\/span><br><span>rdd5.collect<\/span><br><\/pre>\n<\/td>\n<\/tr>\n<\/table>\n<\/figure>\n<h3><a href=\"https:\/\/www.studytime.xin\/article\/#\u5982\u4f55\u9009\u62e9RDD\u6301\u4e45\u5316\u7b56\u7565\uff1a\" title=\"\u5982\u4f55\u9009\u62e9RDD\u6301\u4e45\u5316\u7b56\u7565\uff1a\"><\/a>\u5982\u4f55\u9009\u62e9RDD\u6301\u4e45\u5316\u7b56\u7565\uff1a<\/h3>\n<p>Spark \u63d0\u4f9b\u7684\u591a\u79cd\u6301\u4e45\u5316\u7ea7\u522b\uff0c\u4e3b\u8981\u662f\u4e3a\u4e86\u5728 CPU \u548c\u5185\u5b58\u6d88\u8017\u4e4b\u95f4\u8fdb\u884c\u53d6\u820d\u3002\u4e0b\u9762\u662f\u4e00\u4e9b\u901a\u7528\u7684\u6301\u4e45\u5316\u7ea7\u522b\u7684\u9009\u62e9\u5efa\u8bae\uff1a<\/p>\n<ul>\n<li>\u4f18\u5148\u4f7f\u7528 MEMORY_ONLY\uff0c\u5982\u679c\u53ef\u4ee5\u7f13\u5b58\u6240\u6709\u6570\u636e\u7684\u8bdd\uff0c\u90a3\u4e48\u5c31\u4f7f\u7528\u8fd9\u79cd\u7b56\u7565\u3002\u56e0\u4e3a\u7eaf\u5185\u5b58\u901f\u5ea6\u6700\u5feb\uff0c\u800c\u4e14\u6ca1\u6709\u5e8f\u5217\u5316\uff0c\u4e0d\u9700\u8981\u6d88\u8017CPU\u8fdb\u884c\u53cd\u5e8f\u5217\u5316\u64cd\u4f5c\u3002<\/li>\n<li>\u5982\u679cMEMORY_ONLY\u7b56\u7565\uff0c\u65e0\u6cd5\u5b58\u50a8\u7684\u4e0b\u6240\u6709\u6570\u636e\u7684\u8bdd\uff0c\u90a3\u4e48\u4f7f\u7528MEMORY_ONLY_SER\uff0c\u5c06\u6570\u636e\u8fdb\u884c\u5e8f\u5217\u5316\u8fdb\u884c\u5b58\u50a8\uff0c\u7eaf\u5185\u5b58\u64cd\u4f5c\u8fd8\u662f\u975e\u5e38\u5feb\uff0c\u53ea\u662f\u8981\u6d88\u8017CPU\u8fdb\u884c\u53cd\u5e8f\u5217\u5316\u3002<\/li>\n<li>\u5982\u679c\u9700\u8981\u8fdb\u884c\u5feb\u901f\u7684\u5931\u8d25\u6062\u590d\uff0c\u90a3\u4e48\u5c31\u9009\u62e9\u5e26\u540e\u7f00\u4e3a_2\u7684\u7b56\u7565\uff0c\u8fdb\u884c\u6570\u636e\u7684\u5907\u4efd\uff0c\u8fd9\u6837\u5728\u5931\u8d25\u65f6\uff0c\u5c31\u4e0d\u9700\u8981\u91cd\u65b0\u8ba1\u7b97\u4e86\u3002<\/li>\n<li>\u80fd\u4e0d\u4f7f\u7528DISK\u76f8\u5173\u7684\u7b56\u7565\uff0c\u5c31\u4e0d\u7528\u4f7f\u7528\uff0c\u6709\u7684\u65f6\u5019\uff0c\u4ece\u78c1\u76d8\u8bfb\u53d6\u6570\u636e\uff0c\u8fd8\u4e0d\u5982\u91cd\u65b0\u8ba1\u7b97\u4e00\u6b21\u3002<\/li>\n<\/ul>\n<h3><a href=\"https:\/\/www.studytime.xin\/article\/#\u4ec0\u4e48\u65f6\u5019\u8bbe\u7f6e\u7f13\u5b58\" title=\"\u4ec0\u4e48\u65f6\u5019\u8bbe\u7f6e\u7f13\u5b58\"><\/a>\u4ec0\u4e48\u65f6\u5019\u8bbe\u7f6e\u7f13\u5b58<\/h3>\n<h4><a href=\"https:\/\/www.studytime.xin\/article\/#\u67d0\u4e2ardd\u7684\u6570\u636e\u540e\u671f\u88ab\u4f7f\u7528\u4e86\u591a\u6b21\" title=\"\u67d0\u4e2ardd\u7684\u6570\u636e\u540e\u671f\u88ab\u4f7f\u7528\u4e86\u591a\u6b21\"><\/a>\u67d0\u4e2ardd\u7684\u6570\u636e\u540e\u671f\u88ab\u4f7f\u7528\u4e86\u591a\u6b21<\/h4>\n<p><img decoding=\"async\" src=\"http:\/\/4563.org\/wp-content\/uploads\/2020\/08\/20200803_5f28424332a10.png\" alt=\"Spark RDD\u6301\u4e45\u5316\u7f13\u5b58\u673a\u5236\"><\/p>\n<p>\u5982\u4e0a\u56fe\u6240\u793a\u7684\u8ba1\u7b97\u903b\u8f91\uff1a <\/p>\n<ul>\n<li>\u5f53\u7b2c\u4e00\u6b21\u4f7f\u7528rdd2\u505a\u76f8\u5e94\u7684\u7b97\u5b50\u64cd\u4f5c\u5f97\u5230rdd3\u7684\u65f6\u5019\uff0c\u5c31\u4f1a\u4ecerdd1\u5f00\u59cb\u8ba1\u7b97\uff0c\u5148\u8bfb\u53d6HDFS\u4e0a\u7684\u6587\u4ef6\uff0c\u7136\u540e\u5bf9rdd1 \u505a\u5bf9\u5e94\u7684\u7b97\u5b50\u64cd\u4f5c\u5f97\u5230rdd2,\u518d\u7531rdd2\u8ba1\u7b97\u4e4b\u540e\u5f97\u5230rdd3\u3002\u540c\u6837\u4e3a\u4e86\u8ba1\u7b97\u5f97\u5230rdd4\uff0c\u524d\u9762\u7684\u903b\u8f91\u4f1a\u88ab\u91cd\u65b0\u8ba1\u7b97\u3002<\/li>\n<li>\u9ed8\u8ba4\u60c5\u51b5\u4e0b\u591a\u6b21\u5bf9\u4e00\u4e2ardd\u6267\u884c\u7b97\u5b50\u64cd\u4f5c\uff0c rdd\u90fd\u4f1a\u5bf9\u8fd9\u4e2ardd\u53ca\u4e4b\u524d\u7684\u7236rdd\u5168\u90e8\u91cd\u65b0\u8ba1\u7b97\u4e00\u6b21\u3002 \u8fd9\u79cd\u60c5\u51b5\u5728\u5b9e\u9645\u5f00\u53d1\u4ee3\u7801\u7684\u65f6\u5019\u4f1a\u7ecf\u5e38\u9047\u5230\uff0c\u4f46\u662f\u6211\u4eec\u4e00\u5b9a\u8981\u907f\u514d\u4e00\u4e2ardd\u91cd\u590d\u8ba1\u7b97\u591a\u6b21\uff0c\u5426\u5219\u4f1a\u5bfc\u81f4\u6027\u80fd\u6025\u5267\u964d\u4f4e\u3002   <\/li>\n<\/ul>\n<p>\u603b\u7ed3\uff1a<br \/>\u53ef\u4ee5\u628a\u591a\u6b21\u4f7f\u7528\u5230\u7684rdd\uff0c\u4e5f\u5c31\u662f\u516c\u5171rdd\u8fdb\u884c\u6301\u4e45\u5316\uff0c\u907f\u514d\u540e\u7eed\u9700\u8981\uff0c\u518d\u6b21\u91cd\u65b0\u8ba1\u7b97\uff0c\u63d0\u5347\u6548\u7387\u3002<\/p>\n<h4><a href=\"https:\/\/www.studytime.xin\/article\/#\u4e3a\u4e86\u83b7\u53d6\u5f97\u5230\u4e00\u4e2ardd\u7684\u7ed3\u679c\u6570\u636e\uff0c\u7ecf\u8fc7\u4e86\u5927\u91cf\u7684\u7b97\u5b50\u64cd\u4f5c\u6216\u8005\u662f\u8ba1\u7b97\u903b\u8f91\u6bd4\u8f83\u590d\u6742\" title=\"\u4e3a\u4e86\u83b7\u53d6\u5f97\u5230\u4e00\u4e2ardd\u7684\u7ed3\u679c\u6570\u636e\uff0c\u7ecf\u8fc7\u4e86\u5927\u91cf\u7684\u7b97\u5b50\u64cd\u4f5c\u6216\u8005\u662f\u8ba1\u7b97\u903b\u8f91\u6bd4\u8f83\u590d\u6742\"><\/a>\u4e3a\u4e86\u83b7\u53d6\u5f97\u5230\u4e00\u4e2ardd\u7684\u7ed3\u679c\u6570\u636e\uff0c\u7ecf\u8fc7\u4e86\u5927\u91cf\u7684\u7b97\u5b50\u64cd\u4f5c\u6216\u8005\u662f\u8ba1\u7b97\u903b\u8f91\u6bd4\u8f83\u590d\u6742<\/h4>\n<p><img decoding=\"async\" src=\"http:\/\/4563.org\/wp-content\/uploads\/2020\/08\/20200803_5f2842485fe78.png\" alt=\"Spark RDD\u6301\u4e45\u5316\u7f13\u5b58\u673a\u5236\"><\/p>\n<figure>\n<table>\n<tr>\n<td>\n<pre><span>1<\/span><br><\/pre>\n<\/td>\n<td>\n<pre><span>val rdd2&#x3D;rdd1.flatMap(\u51fd\u6570).map(\u51fd\u6570).reduceByKey(\u51fd\u6570).xxx.xxx.xxx.xxx.xxx<\/span><br><\/pre>\n<\/td>\n<\/tr>\n<\/table>\n<\/figure>\n<h3><a href=\"https:\/\/www.studytime.xin\/article\/#\u6e05\u9664\u7f13\u5b58\u6570\u636e\" title=\"\u6e05\u9664\u7f13\u5b58\u6570\u636e\"><\/a>\u6e05\u9664\u7f13\u5b58\u6570\u636e<\/h3>\n<h4><a href=\"https:\/\/www.studytime.xin\/article\/#\u81ea\u52a8\u6e05\u9664\" title=\"\u81ea\u52a8\u6e05\u9664\"><\/a>\u81ea\u52a8\u6e05\u9664<\/h4>\n<p>\u4e00\u4e2aapplication\u5e94\u7528\u7a0b\u5e8f\u7ed3\u675f\u4e4b\u540e\uff0c\u5bf9\u5e94\u7684\u7f13\u5b58\u6570\u636e\u4e5f\u5c31\u81ea\u52a8\u6e05\u9664<\/p>\n<h4><a href=\"https:\/\/www.studytime.xin\/article\/#\u624b\u52a8\u6e05\u9664\" title=\"\u624b\u52a8\u6e05\u9664\"><\/a>\u624b\u52a8\u6e05\u9664<\/h4>\n<figure>\n<table>\n<tr>\n<td>\n<pre><span>1<\/span><br><\/pre>\n<\/td>\n<td>\n<pre><span>\u8c03\u7528rdd\u7684unpersist\u65b9\u6cd5<\/span><br><\/pre>\n<\/td>\n<\/tr>\n<\/table>\n<\/figure>\n<h2><a href=\"https:\/\/www.studytime.xin\/article\/#RDD\u7684checkpoint\u673a\u5236\" title=\"RDD\u7684checkpoint\u673a\u5236\"><\/a>RDD\u7684checkpoint\u673a\u5236<\/h2>\n<p>\u9664\u4e86 cache \u548c persist \u4e4b\u5916\uff0cSpark \u8fd8\u63d0\u4f9b\u4e86\u53e6\u5916\u4e00\u79cd\u6301\u4e45\u5316\uff1acheckpoint, \u5b83\u80fd\u5c06 RDD \u5199\u5165\u5206\u5e03\u5f0f\u6587\u4ef6\u7cfb\u7edf\uff0c\u63d0\u4f9b\u7c7b\u4f3c\u4e8e\u6570\u636e\u5e93\u5feb\u7167\u7684\u529f\u80fd\u3002<\/p>\n<p>\u5b83\u662f\u63d0\u4f9b\u4e86\u4e00\u79cd\u76f8\u5bf9\u800c\u8a00\u66f4\u52a0\u53ef\u9760\u7684\u6570\u636e\u6301\u4e45\u5316\u65b9\u5f0f\u3002\u5b83\u662f\u628a\u6570\u636e\u4fdd\u5b58\u5728\u5206\u5e03\u5f0f\u6587\u4ef6\u7cfb\u7edf\uff0c<br \/>\u6bd4\u5982HDFS\u4e0a\u3002\u8fd9\u91cc\u5c31\u662f\u5229\u7528\u4e86HDFS\u9ad8\u53ef\u7528\u6027\uff0c\u9ad8\u5bb9\u9519\u6027\uff08\u591a\u526f\u672c\uff09\u6765\u6700\u5927\u7a0b\u5ea6\u4fdd\u8bc1\u6570\u636e\u7684\u5b89\u5168\u6027\u3002<\/p>\n<h3><a href=\"https:\/\/www.studytime.xin\/article\/#\u5982\u4f55\u8bbe\u7f6echeckpoint\" title=\"\u5982\u4f55\u8bbe\u7f6echeckpoint\"><\/a>\u5982\u4f55\u8bbe\u7f6echeckpoint<\/h3>\n<h4><a href=\"https:\/\/www.studytime.xin\/article\/#\u5728hdfs\u4e0a\u8bbe\u7f6e\u4e00\u4e2acheckpoint\u76ee\u5f55\" title=\"\u5728hdfs\u4e0a\u8bbe\u7f6e\u4e00\u4e2acheckpoint\u76ee\u5f55\"><\/a>\u5728hdfs\u4e0a\u8bbe\u7f6e\u4e00\u4e2acheckpoint\u76ee\u5f55<\/h4>\n<figure>\n<table>\n<tr>\n<td>\n<pre><span>1<\/span><br><\/pre>\n<\/td>\n<td>\n<pre><span>sc.setCheckpointDir(<span>\"hdfs:\/\/node01:8020\/checkpoint\"<\/span>)<\/span><br><\/pre>\n<\/td>\n<\/tr>\n<\/table>\n<\/figure>\n<h4><a href=\"https:\/\/www.studytime.xin\/article\/#\u5bf9\u9700\u8981\u505acheckpoint\u64cd\u4f5c\u7684rdd\u8c03\u7528checkpoint\u65b9\u6cd5\" title=\"\u5bf9\u9700\u8981\u505acheckpoint\u64cd\u4f5c\u7684rdd\u8c03\u7528checkpoint\u65b9\u6cd5\"><\/a>\u5bf9\u9700\u8981\u505acheckpoint\u64cd\u4f5c\u7684rdd\u8c03\u7528checkpoint\u65b9\u6cd5<\/h4>\n<figure>\n<table>\n<tr>\n<td>\n<pre><span>1<\/span><br><span>2<\/span><br><span>3<\/span><br><\/pre>\n<\/td>\n<td>\n<pre><span><span>val<\/span> rdd1=sc.textFile(<span>\"\/words.txt\"<\/span>)<\/span><br><span>rdd1.checkpoint<\/span><br><span><span>val<\/span> rdd2=rdd1.flatMap(_.split(<span>\" \"<\/span>))<\/span><br><\/pre>\n<\/td>\n<\/tr>\n<\/table>\n<\/figure>\n<h4><a href=\"https:\/\/www.studytime.xin\/article\/#\u6700\u540e\u9700\u8981\u6709\u4e00\u4e2aaction\u64cd\u4f5c\u53bb\u89e6\u53d1\u4efb\u52a1\u7684\u8fd0\u884c\" title=\"\u6700\u540e\u9700\u8981\u6709\u4e00\u4e2aaction\u64cd\u4f5c\u53bb\u89e6\u53d1\u4efb\u52a1\u7684\u8fd0\u884c\"><\/a>\u6700\u540e\u9700\u8981\u6709\u4e00\u4e2aaction\u64cd\u4f5c\u53bb\u89e6\u53d1\u4efb\u52a1\u7684\u8fd0\u884c<\/h4>\n<figure>\n<table>\n<tr>\n<td>\n<pre><span>1<\/span><br><\/pre>\n<\/td>\n<td>\n<pre><span>rdd2.collect<\/span><br><\/pre>\n<\/td>\n<\/tr>\n<\/table>\n<\/figure>\n<h2><a href=\"https:\/\/www.studytime.xin\/article\/#cache\u3001persist\u3001checkpoint\u4e09\u8005\u533a\u522b\" title=\"cache\u3001persist\u3001checkpoint\u4e09\u8005\u533a\u522b\"><\/a>cache\u3001persist\u3001checkpoint\u4e09\u8005\u533a\u522b<\/h2>\n<h3><a href=\"https:\/\/www.studytime.xin\/article\/#cache\u548cpersis\" title=\"cache\u548cpersis\"><\/a>cache\u548cpersis<\/h3>\n<ul>\n<li>cache\u9ed8\u8ba4\u6570\u636e\u7f13\u5b58\u5728\u5185\u5b58\u4e2d<\/li>\n<li>persist\u53ef\u4ee5\u628a\u6570\u636e\u4fdd\u5b58\u5728\u5185\u5b58\u6216\u8005\u78c1\u76d8\u4e2d<\/li>\n<li>\u540e\u7eed\u8981\u89e6\u53d1 cache \u548c persist \u6301\u4e45\u5316\u64cd\u4f5c\uff0c\u9700\u8981\u6709\u4e00\u4e2aaction\u64cd\u4f5c<\/li>\n<li>\u5b83\u4e0d\u4f1a\u5f00\u542f\u5176\u4ed6\u65b0\u7684\u4efb\u52a1\uff0c\u4e00\u4e2aaction\u64cd\u4f5c\u5c31\u5bf9\u5e94\u4e00\u4e2ajob <\/li>\n<li>\u5b83\u4e0d\u4f1a\u6539\u53d8rdd\u7684\u4f9d\u8d56\u5173\u7cfb\uff0c\u7a0b\u5e8f\u8fd0\u884c\u5b8c\u6210\u540e\u5bf9\u5e94\u7684\u7f13\u5b58\u6570\u636e\u5c31\u81ea\u52a8\u6d88\u5931<\/li>\n<\/ul>\n<h3><a href=\"https:\/\/www.studytime.xin\/article\/#checkpoint\" title=\"checkpoint\"><\/a>checkpoint<\/h3>\n<ul>\n<li>\u53ef\u4ee5\u628a\u6570\u636e\u6301\u4e45\u5316\u5199\u5165\u5230hdfs\u4e0a<\/li>\n<li>\u540e\u7eed\u8981\u89e6\u53d1checkpoint\u6301\u4e45\u5316\u64cd\u4f5c\uff0c\u9700\u8981\u6709\u4e00\u4e2aaction\u64cd\u4f5c\uff0c\u540e\u7eed\u4f1a\u5f00\u542f\u65b0\u7684job\u6267\u884ccheckpoint\u64cd\u4f5c<\/li>\n<li>\u5b83\u4f1a\u6539\u53d8rdd\u7684\u4f9d\u8d56\u5173\u7cfb\uff0c\u540e\u7eed\u6570\u636e\u4e22\u5931\u4e86\u4e0d\u80fd\u591f\u5728\u901a\u8fc7\u8840\u7edf\u8fdb\u884c\u6570\u636e\u7684\u6062\u590d\u3002<\/li>\n<li>\u7a0b\u5e8f\u8fd0\u884c\u5b8c\u6210\u540e\u5bf9\u5e94\u7684checkpoint\u6570\u636e\u5c31\u4e0d\u4f1a\u6d88\u5931<\/li>\n<\/ul>\n<figure>\n<table>\n<tr>\n<td>\n<pre><span>1<\/span><br><span>2<\/span><br><span>3<\/span><br><span>4<\/span><br><span>5<\/span><br><span>6<\/span><br><\/pre>\n<\/td>\n<td>\n<pre><span>sc.setCheckpointDir(<span>\"\/checkpoint\"<\/span>)<\/span><br><span><span>val<\/span> rdd1=sc.textFile(<span>\"\/words.txt\"<\/span>)<\/span><br><span><span>val<\/span> rdd2=rdd1.cache<\/span><br><span>rdd2.checkpoint<\/span><br><span><span>val<\/span> rdd3=rdd2.flatMap(_.split(<span>\" \"<\/span>))<\/span><br><span>rdd3.collect<\/span><br><\/pre>\n<\/td>\n<\/tr>\n<\/table>\n<\/figure>\n<p>checkpoint\u64cd\u4f5c\u8981\u6267\u884c\u9700\u8981\u6709\u4e00\u4e2aaction\u64cd\u4f5c\uff0c\u4e00\u4e2aaction\u64cd\u4f5c\u5bf9\u5e94\u540e\u7eed\u7684\u4e00\u4e2ajob\u3002\u8be5job\u6267\u884c\u5b8c\u6210\u4e4b\u540e\uff0c\u5b83\u4f1a\u518d\u6b21\u5355\u72ec\u5f00\u542f\u53e6\u5916\u4e00\u4e2ajob\u6765\u6267\u884c rdd1.checkpoint\u64cd\u4f5c\u3002<\/p>\n<p>\u5bf9checkpoint\u5728\u4f7f\u7528\u7684\u65f6\u5019\u8fdb\u884c\u4f18\u5316\uff0c\u5728\u8c03\u7528checkpoint\u64cd\u4f5c\u4e4b\u524d\uff0c\u53ef\u4ee5\u5148\u6765\u505a\u4e00\u4e2acache\u64cd\u4f5c\uff0c\u7f13\u5b58\u5bf9\u5e94rdd\u7684\u7ed3\u679c\u6570\u636e\uff0c\u540e\u7eed\u5c31\u53ef\u4ee5\u76f4\u63a5\u4ececache\u4e2d\u83b7\u53d6\u5230rdd\u7684\u6570\u636e\u5199\u5165\u5230\u6307\u5b9acheckpoint\u76ee\u5f55\u4e2d<\/p>\n<h3><a href=\"https:\/\/www.studytime.xin\/article\/#checkpoint-\u4e8e-cache-\u548c-persist\u53bb\u533a\u522b\" title=\"checkpoint \u4e8e cache \u548c persist\u53bb\u533a\u522b\"><\/a>checkpoint \u4e8e cache \u548c persist\u53bb\u533a\u522b<\/h3>\n<ul>\n<li>Spark \u81ea\u52a8\u7ba1\u7406\uff08\u521b\u5efa\u548c\u56de\u6536\uff09cache \u548c persist \u6301\u4e45\u5316\u7684\u6570\u636e\uff0c\u800ccheckpoint\u6301\u4e45\u5316\u7684\u6570\u636e\u9700\u8981\u6709\u7531\u6237\u81ea\u5df1\u7ba1\u7406<\/li>\n<li>checkpoint \u4f1a\u6e05\u9664 RDD \u7684\u8840\u7edf\uff0c\u907f\u514d\u8840\u7edf\u8fc7\u957f\u5bfc\u81f4\u5e8f\u5217\u5316\u5f00\u9500\u589e\u5927\uff0c\u800c cache \u548c persist \u4e0d\u4f1a\u6e05\u695a RDD \u7684\u8840\u7edf<\/li>\n<\/ul>\n<p>\u4ee3\u7801\u5b9e\u4f8b\uff1a<\/p>\n<figure>\n<table>\n<tr>\n<td>\n<pre><span>1<\/span><br><span>2<\/span><br><span>3<\/span><br><span>4<\/span><br><span>5<\/span><br><span>6<\/span><br><\/pre>\n<\/td>\n<td>\n<pre><span>sc.checkpoint(<span>\"hdfs:\/\/spark\/rdd\"<\/span>);<\/span><br><span><span>val<\/span> data = sc.testFile(<span>\"hdfs:\/\/node01:8020\/input\"<\/span>);<\/span><br><span><span>val<\/span> rdd = data.map(..).reduceByKey(...)<\/span><br><span><\/span><br><span>rdd.checkpoint<\/span><br><span>rdd.count()<\/span><br><\/pre>\n<\/td>\n<\/tr>\n<\/table>\n<\/figure>\n","protected":false},"excerpt":{"rendered":"<p>RDD \u6301\u4e45\u5316 \u4ec0\u4e48\u4e8bRDD\u6301\u4e45\u5316&hellip;<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[],"tags":[],"_links":{"self":[{"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/posts\/142529"}],"collection":[{"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=142529"}],"version-history":[{"count":0,"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/posts\/142529\/revisions"}],"wp:attachment":[{"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=142529"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=142529"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=142529"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}