{"id":47033,"date":"2022-11-20T19:45:15","date_gmt":"2024-02-25T10:34:49","guid":{"rendered":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e8%bd%ac%e7%a7%bb%e5%88%b0%e7%94%9f%e4%ba%a7%e7%8e%af%e5%a2%83%e4%b8%ad\/"},"modified":"2024-04-29T01:40:07","modified_gmt":"2024-04-28T17:40:07","slug":"%e5%b0%86spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e8%bd%ac%e7%a7%bb%e5%88%b0%e7%94%9f%e4%ba%a7%e7%8e%af%e5%a2%83%e4%b8%ad","status":"publish","type":"post","link":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e8%bd%ac%e7%a7%bb%e5%88%b0%e7%94%9f%e4%ba%a7%e7%8e%af%e5%a2%83%e4%b8%ad\/","title":{"rendered":"\u5c06Spark\u7ed3\u6784\u5316\u6d41\u8f6c\u79fb\u5230\u751f\u4ea7\u73af\u5883\u4e2d"},"content":{"rendered":"<p>\u5c06Apache Spark\u7684\u7ed3\u6784\u5316\u6d41\u5f0f\u5904\u7406\u5e26\u5165\u751f\u4ea7\u73af\u5883 &#8211; Databricks\u535a\u5ba2\u7684\u7ffb\u8bd1\u8bf4\u660e\u3002<\/p>\n<div>\u8fd9\u672c\u4e66\u662f\u8282\u9009\u8bd1\uff0c\u4e0d\u4fdd\u8bc1\u5185\u5bb9\u7684\u51c6\u786e\u6027\u3002\u6709\u5173\u51c6\u786e\u5185\u5bb9\uff0c\u8bf7\u53c2\u8003\u539f\u6587\u3002<\/div>\n<div>\u8bf7\u6ce8\u610f\uff0c\u8fd9\u662f\u4e00\u7bc72017\u5e74\u7684\u6587\u7ae0\u3002<\/div>\n<p>\u9019\u662f\u4e00\u7cfb\u5217\u95dc\u65bc\u5982\u4f55\u4f7f\u7528Apache Spark\u9032\u884c\u8907\u96dc\u7684\u6d41\u5f0f\u5206\u6790\u7684\u7b2c\u4e94\u7bc7\u6587\u7ae0\u3002<\/p>\n<p>\u5728Databricks\u4e2d\uff0c\u6211\u4eec\u5728\u8fc7\u53bb\u51e0\u4e2a\u6708\u91cc\u9010\u6e10\u5c06\u751f\u4ea7\u6d41\u7a0b\u8f6c\u79fb\u5230\u4e86\u7ed3\u6784\u5316\u6d41\u5904\u7406\u3002\u4e3a\u4e86\u8ba9\u5ba2\u6237\u80fd\u591f\u5728Databricks\u4e0a\u5feb\u901f\u5efa\u7acb\u751f\u4ea7\u6d41\u7a0b\uff0c\u6211\u4eec\u5e0c\u671b\u63d0\u4f9b\u4e00\u79cd\u5373\u53ef\u7528\u7684\u90e8\u7f72\u6a21\u578b\u3002<\/p>\n<p>\u5728\u4ea7\u54c1\u5e94\u7528\u4e2d\uff0c\u81ea\u52a8\u5316\uff08\u4e91\u539f\u751f\uff09\u65b9\u6cd5\u5bf9\u4e8e\u76d1\u63a7\u3001\u8b66\u62a5\u548c\u6545\u969c\u6062\u590d\u662f\u5fc5\u4e0d\u53ef\u5c11\u7684\u3002\u672c\u4e66\u4e0d\u4ec5\u63d0\u4f9b\u4e86\u53ef\u7528\u4e8e\u5e94\u5bf9\u8fd9\u4e9b\u6311\u6218\u7684API\u7684\u8be6\u7ec6\u89e3\u91ca\uff0c\u8fd8\u89e3\u91ca\u4e86Databricks\u5982\u4f55\u7b80\u5316\u751f\u4ea7\u73af\u5883\u4e2d\u7684\u7ed3\u6784\u5316\u6d41\u5904\u7406\u3002<\/p>\n<h1>\u6307\u6807\u548c\u76d1\u63a7<\/h1>\n<p>\u5728Apache Spark\u7684\u7ed3\u6784\u5316\u6d41\u5904\u7406\u4e2d\uff0c\u6211\u4eec\u63d0\u4f9b\u4e86\u4e00\u4e2a\u7b80\u5355\u7684\u7a0b\u5e8fAPI\uff0c\u7528\u4e8e\u83b7\u53d6\u6709\u5173\u5f53\u524d\u6b63\u5728\u6267\u884c\u7684\u6d41\u7684\u4fe1\u606f\u3002\u4e3a\u4e86\u83b7\u53d6\u4e0e\u5f53\u524d\u6d3b\u52a8\u6d41\u6709\u5173\u7684\u9002\u5f53\u4fe1\u606f\uff0c\u5b58\u5728\u4e24\u4e2a\u4e3b\u8981\u547d\u4ee4\u53ef\u4ee5\u5bf9\u5f53\u524d\u67e5\u8be2\u8fdb\u884c\u6267\u884c\u3002\u4e00\u4e2a\u662f\u7528\u4e8e\u83b7\u53d6\u5f53\u524d\u72b6\u6001\u7684\u547d\u4ee4\uff0c\u53e6\u4e00\u4e2a\u662f\u7528\u4e8e\u83b7\u53d6\u67e5\u8be2\u7684\u6700\u65b0\u8fdb\u5c55\u7684\u547d\u4ee4\u3002<\/p>\n<h2>\u72b6\u51b5<\/h2>\n<p>\u53ef\u80fd\u7684\u6c49\u8bed\u7ffb\u8bd1\uff1a<br \/>\n\u4e5f\u8bb8\u7b2c\u4e00\u4e2a\u95ee\u9898\u662f\u201c\u6211\u7684\u6d41\u6b63\u5728\u6267\u884c\u4ec0\u4e48\u5904\u7406\uff1f\u201d\u3002\u72b6\u6001\u4fdd\u7559\u4e86\u4e0e\u6d41\u7684\u5f53\u524d\u72b6\u6001\u76f8\u5173\u7684\u4fe1\u606f\uff0c\u5e76\u4e14\u53ef\u4ee5\u901a\u8fc7\u8fd4\u56de\u7684\u5bf9\u8c61\u6765\u8bbf\u95ee\u67e5\u8be2\u5f00\u5934\u3002\u4f8b\u5982\uff0c\u5047\u8bbe\u6709\u4e00\u4e2a\u7b80\u5355\u7684\u8ba1\u6570\u6d41\uff0c\u901a\u8fc7\u4e0b\u9762\u7684\u67e5\u8be2\u5b9a\u4e49\u63d0\u4f9bIOT\u8bbe\u5907\u7684\u8ba1\u6570\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"n\">query<\/span> <span class=\"o\">=<\/span> <span class=\"n\">streamingCountsDF<\/span> \\\r\n    <span class=\"p\">.<\/span><span class=\"n\">writeStream<\/span> \\\r\n    <span class=\"p\">.<\/span><span class=\"nf\">format<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">memory<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span> \\\r\n    <span class=\"p\">.<\/span><span class=\"nf\">queryName<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">counts<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span> \\\r\n    <span class=\"p\">.<\/span><span class=\"nf\">outputMode<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">complete<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span> \\\r\n    <span class=\"p\">.<\/span><span class=\"nf\">start<\/span><span class=\"p\">()<\/span>\r\n<\/code><\/pre>\n<p>\u901a\u8fc7\u6267\u884c query.status \uff0c\u53ef\u4ee5\u83b7\u53d6\u6d41\u7684\u5f53\u524d\u72b6\u6001\u3002\u8fd9\u6837\u53ef\u4ee5\u8be6\u7ec6\u4e86\u89e3\u6d41\u4e2d\u76ee\u524d\u53d1\u751f\u7684\u4e8b\u60c5\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"p\">{<\/span>\r\n  <span class=\"nl\">\"message\"<\/span> <span class=\"p\">:<\/span> <span class=\"s2\">\"Getting offsets from FileStreamSource[dbfs:\/databricks-datasets\/structured-streaming\/events]\"<\/span><span class=\"p\">,<\/span>\r\n  <span class=\"nl\">\"isDataAvailable\"<\/span> <span class=\"p\">:<\/span> <span class=\"kc\">true<\/span><span class=\"p\">,<\/span>\r\n  <span class=\"nl\">\"isTriggerActive\"<\/span> <span class=\"p\">:<\/span> <span class=\"kc\">true<\/span>\r\n<span class=\"p\">}<\/span>\r\n<\/code><\/pre>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d7c1c913a08637a69b460\/13-1.png\" alt=\"\" \/><\/div>\n<h2>\u6700\u65b0\u7684\u8fdb\u5c55<\/h2>\n<p>\u67e5\u8be2\u7684\u72b6\u6001\u65e0\u7591\u975e\u5e38\u91cd\u8981\uff0c\u4f46\u80fd\u591f\u53c2\u8003\u67e5\u8be2\u7684\u5386\u53f2\u8fdb\u5c55\u540c\u6837\u91cd\u8981\u3002\u901a\u8fc7\u4f7f\u7528\u8fdb\u5c55\u5143\u6570\u636e\uff0c\u6211\u4eec\u53ef\u4ee5\u56de\u7b54\u8bf8\u5982\u201c\u4ee5\u591a\u5feb\u7684\u901f\u5ea6\u5904\u7406\u5143\u7ec4\uff1f\u201d\u6216\u201c\u4ece\u6e90\u5934\u4ee5\u591a\u5feb\u7684\u901f\u5ea6\u5230\u8fbe\u5143\u7ec4\uff1f\u201d\u7b49\u95ee\u9898\u3002<\/p>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d7c1c913a08637a69b460\/16-0.png\" alt=\"\" \/><\/div>\n<p>\u8ba9\u6211\u4eec\u63a2\u7d22\u4e3a\u4ec0\u4e48\u9009\u62e9\u8fd9\u4e9b\u6307\u6807\uff0c\u4ee5\u53ca\u4e3a\u4ec0\u4e48\u7406\u89e3\u5b83\u4eec\u7684\u91cd\u8981\u6027\u3002<\/p>\n<h2>\u8f93\u5165\u901f\u7387\u548c\u5904\u7406\u901f\u7387<\/h2>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d7c1c913a08637a69b460\/19-0.png\" alt=\"\" \/><\/div>\n<h2>\u6279\u5904\u7406\u5468\u671f<\/h2>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d7c1c913a08637a69b460\/21-0.png\" alt=\"\" \/><\/div>\n<h1>\u5728\u6d41\u5a92\u4f53\u4f5c\u4e1a\u4e2d\u7684\u751f\u4ea7\u8b66\u62a5\u3002<\/h1>\n<p>\u6307\u6807\u548c\u76d1\u63a7\u662f\u4e0d\u9519\u7684\u5de5\u5177\uff0c\u4f46\u4e3a\u4e86\u80fd\u5feb\u901f\u54cd\u5e94\u4efb\u4f55\u51fa\u73b0\u7684\u95ee\u9898\uff0c\u800c\u4e0d\u7528\u6574\u5929\u5b88\u7740\u6d41\u5f0f\u4f5c\u4e1a\uff0c\u5c31\u9700\u8981\u4e00\u4e2a\u5f3a\u5927\u7684\u62a5\u8b66\u673a\u5236\u3002\u5728Databricks\u4e0a\uff0c\u6211\u4eec\u53ef\u4ee5\u5c06\u7ed3\u6784\u5316\u6d41\u4f5c\u4e3a\u751f\u4ea7\u7ba1\u9053\u6765\u8fd0\u884c\uff0c\u4ece\u800c\u4f7f\u62a5\u8b66\u53d8\u5f97\u7b80\u5355\u3002<\/p>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d7c1c913a08637a69b460\/24-0.png\" alt=\"\" \/><\/div>\n<p>\u8bf7\u6ce8\u610f\u6307\u5b9a\u7528\u4e8e\u89e6\u53d1PagerDuty\u8b66\u62a5\u7684\u7535\u5b50\u90ae\u4ef6\u5730\u5740\u3002\u5f53\u4f5c\u4e1a\u5931\u8d25\u65f6\uff0c\u5c06\u89e6\u53d1\u4ea7\u54c1\u7684\u8b66\u62a5\uff08\u6216\u6307\u5b9a\u7ea7\u522b\u7684\u8b66\u62a5\uff09\u3002<\/p>\n<h1>\u81ea\u52a8\u5316\u6545\u969c\u6062\u590d<\/h1>\n<p>\u5c3d\u7ba1\u8b66\u62a5\u5f88\u65b9\u4fbf\uff0c\u4f46\u5373\u4f7f\u5728\u6700\u4f73\u60c5\u51b5\u4e0b\uff0c\u4ecd\u7136\u9700\u8981\u4eba\u7c7b\u6765\u5904\u7406\u969c\u788d\uff0c\u5e76\u4e14\u5728\u6700\u7cdf\u7cd5\u7684\u60c5\u51b5\u4e0b\uff0c\u5904\u7406\u672c\u8eab\u53ef\u80fd\u662f\u4e0d\u53ef\u80fd\u7684\u3002\u4e3a\u4e86\u771f\u6b63\u5c06\u7ed3\u6784\u5316\u6d41\u5f0f\u5904\u7406\u8fc7\u6e21\u5230\u751f\u4ea7\u73af\u5883\uff0c\u60a8\u53ef\u80fd\u5e0c\u671b\u5728\u4fdd\u6301\u6570\u636e\u4e00\u81f4\u6027\u5e76\u4e14\u6ca1\u6709\u6570\u636e\u4e22\u5931\u7684\u60c5\u51b5\u4e0b\uff0c\u5c3d\u5feb\u4ece\u969c\u788d\u4e2d\u81ea\u52a8\u6062\u590d\u3002Databricks\u53ef\u4ee5\u65e0\u7f1d\u5b9e\u73b0\u8fd9\u4e00\u70b9\u3002\u53ea\u9700\u7b80\u5355\u8bbe\u7f6e\u65e0\u6cd5\u6062\u590d\u7684\u6545\u969c\u4e4b\u524d\u7684\u91cd\u8bd5\u6b21\u6570\uff0cDatabricks\u5c06\u5c1d\u8bd5\u81ea\u52a8\u6062\u590d\u60a8\u7684\u6d41\u5f0f\u5904\u7406\u4f5c\u4e1a\u3002\u60a8\u8fd8\u53ef\u4ee5\u9009\u62e9\u5728\u6bcf\u6b21\u5931\u8d25\u65f6\u89e6\u53d1\u901a\u77e5\u4f5c\u4e3a\u751f\u4ea7\u969c\u788d\u3002<\/p>\n<p>\u53ef\u4ee5\u540c\u65f6\u83b7\u5f97\u4e24\u4e2a\u4e16\u754c\u4e2d\u6700\u597d\u7684\u4e1c\u897f\u3002\u7cfb\u7edf\u4f1a\u4e0d\u65ad\u5c1d\u8bd5\u81ea\u6211\u4fee\u590d\uff0c\u5e76\u4e0e\u5458\u5de5\u548c\u5f00\u53d1\u8005\u4fdd\u6301\u6c9f\u901a\u3002<\/p>\n<h1>\u66f4\u65b0\u5e94\u7528<\/h1>\n<p>\u60a8\u9700\u8981\u66f4\u65b0\u6d41\u5a92\u4f53\u5e94\u7528\u7a0b\u5e8f\u7684\u4e24\u79cd\u5e38\u89c1\u60c5\u51b5\u4f1a\u4ea7\u751f\u5145\u5206\u7684\u7406\u7531\u3002(\u4f8b\u5982\uff0c\u8f93\u51fa\u6a21\u5f0f\u7b49)\u5728\u8bb8\u591a\u60c5\u51b5\u4e0b\uff0c\u5982\u679c\u4e0d\u66f4\u6539\u91cd\u8981\u7684\u4e1a\u52a1\u903b\u8f91\uff0c\u5219\u53ef\u4ee5\u7b80\u5355\u5730\u91cd\u65b0\u542f\u52a8\u6d41\u5a92\u4f53\u4f5c\u4e1a\uff0c\u5e76\u6307\u5b9a\u76f8\u540c\u7684\u68c0\u67e5\u70b9\u76ee\u5f55\u3002\u66f4\u65b0\u540e\u7684\u65b0\u6d41\u5a92\u4f53\u5e94\u7528\u7a0b\u5e8f\u5c06\u4ece\u4e0a\u6b21\u7684\u68c0\u67e5\u70b9\u4f4d\u7f6e\u7ee7\u7eed\uff0c\u5e76\u7ee7\u7eed\u8fd0\u884c\u3002<\/p>\n<p>\u7136\u800c\uff0c\u5982\u679c\u8981\u66f4\u6539\u6709\u72b6\u6001\u7684\u64cd\u4f5c\uff08\u5982\u805a\u5408\u548c\u8f93\u51fa\u6a21\u5f0f\uff09\uff0c\u5c06\u9700\u8981\u66f4\u591a\u7684\u66f4\u65b0\u64cd\u4f5c\u3002\u60a8\u9700\u8981\u6307\u5b9a\u4e00\u4e2a\u65b0\u7684\u68c0\u67e5\u70b9\u76ee\u5f55\uff0c\u5e76\u542f\u52a8\u4e00\u4e2a\u5168\u65b0\u7684\u6d41\u6765\u5b8c\u6210\u6b64\u64cd\u4f5c\u3002\u5e78\u8fd0\u7684\u662f\uff0c\u5728Databricks\u4e2d\uff0c\u60a8\u53ef\u4ee5\u8f7b\u677e\u5730\u542f\u52a8\u53e6\u4e00\u4e2a\u6d41\uff0c\u540c\u65f6\u8fdb\u884c\u8fc1\u79fb\u5230\u65b0\u6d41\u7684\u64cd\u4f5c\u3002<\/p>\n<h1>\u9ad8\u7ea7\u8b66\u62a5\u548c\u76d1\u6d4b<\/h1>\n<p>\u8fd8\u6709\u5176\u4ed6\u6570\u636e\u5206\u6790\u4e5f\u652f\u6301\u7684\u884c\u4e3a\u76d1\u63a7\u6280\u672f\u3002\u4f8b\u5982\uff0c\u53ef\u4ee5\u4f7f\u7528Datadog\u3001Apache Kafka\u3001Coda Hale Metrics\u7b49\u7cfb\u7edf\u6765\u8f93\u51fa\u901a\u77e5\u3002\u8fd9\u4e9b\u9ad8\u7ea7\u6280\u672f\u53ef\u4ee5\u7528\u4e8e\u5916\u90e8\u76d1\u63a7\u548c\u8b66\u62a5\u7cfb\u7edf\u7684\u5b9e\u65bd\u3002<\/p>\n<p>\u6211\u4eec\u5c06\u5728\u4ee5\u4e0b\u793a\u4f8b\u4e2d\u521b\u5efa\u4e00\u4e2aStreamingQueryListener\uff0c\u5c06\u6240\u6709\u67e5\u8be2\u7684\u8fdb\u5ea6\u4fe1\u606f\u4f20\u9001\u5230Kafka\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"k\">class<\/span> <span class=\"nc\">KafkaMetrics<\/span><span class=\"o\">(<\/span><span class=\"n\">servers<\/span><span class=\"k\">:<\/span> <span class=\"kt\">String<\/span><span class=\"o\">)<\/span> <span class=\"k\">extends<\/span> <span class=\"nc\">StreamingQueryListener<\/span> <span class=\"o\">{<\/span>\r\n  <span class=\"k\">val<\/span> <span class=\"nv\">kafkaProperties<\/span> <span class=\"k\">=<\/span> <span class=\"k\">new<\/span> <span class=\"nc\">Properties<\/span><span class=\"o\">()<\/span>\r\n  <span class=\"nv\">kafkaProperties<\/span><span class=\"o\">.<\/span><span class=\"py\">put<\/span><span class=\"o\">(<\/span><span class=\"s\">\"bootstrap.servers\"<\/span><span class=\"o\">,<\/span> <span class=\"n\">servers<\/span><span class=\"o\">)<\/span>\r\n  <span class=\"nv\">kafkaProperties<\/span><span class=\"o\">.<\/span><span class=\"py\">put<\/span><span class=\"o\">(<\/span><span class=\"s\">\"key.serializer\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"kafkashaded.org.apache.kafka.common.serialization.StringSerializer\"<\/span><span class=\"o\">)<\/span>\r\n  <span class=\"nv\">kafkaProperties<\/span><span class=\"o\">.<\/span><span class=\"py\">put<\/span><span class=\"o\">(<\/span><span class=\"s\">\"value.serializer\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"kafkashaded.org.apache.kafka.common.serialization.StringSerializer\"<\/span><span class=\"o\">)<\/span>\r\n\r\n  <span class=\"k\">val<\/span> <span class=\"nv\">producer<\/span> <span class=\"k\">=<\/span> <span class=\"k\">new<\/span> <span class=\"nc\">KafkaProducer<\/span><span class=\"o\">[<\/span><span class=\"kt\">String<\/span>, <span class=\"kt\">String<\/span><span class=\"o\">](<\/span><span class=\"n\">kafkaProperties<\/span><span class=\"o\">)<\/span>\r\n\r\n  <span class=\"k\">def<\/span> <span class=\"nf\">onQueryProgress<\/span><span class=\"o\">(<\/span><span class=\"n\">event<\/span><span class=\"k\">:<\/span> <span class=\"kt\">org.apache.spark.sql.streaming.StreamingQueryListener.QueryProgressEvent<\/span><span class=\"o\">)<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Unit<\/span> <span class=\"o\">=<\/span> <span class=\"o\">{<\/span>\r\n    <span class=\"nv\">producer<\/span><span class=\"o\">.<\/span><span class=\"py\">send<\/span><span class=\"o\">(<\/span><span class=\"k\">new<\/span> <span class=\"nc\">ProducerRecord<\/span><span class=\"o\">(<\/span><span class=\"s\">\"streaming-metrics\"<\/span><span class=\"o\">,<\/span> <span class=\"nv\">event<\/span><span class=\"o\">.<\/span><span class=\"py\">progress<\/span><span class=\"o\">.<\/span><span class=\"py\">json<\/span><span class=\"o\">))<\/span>\r\n  <span class=\"o\">}<\/span>\r\n  <span class=\"k\">def<\/span> <span class=\"nf\">onQueryStarted<\/span><span class=\"o\">(<\/span><span class=\"n\">event<\/span><span class=\"k\">:<\/span> <span class=\"kt\">org.apache.spark.sql.streaming.StreamingQueryListener.QueryStartedEvent<\/span><span class=\"o\">)<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Unit<\/span> <span class=\"o\">=<\/span> <span class=\"o\">{}<\/span>\r\n  <span class=\"k\">def<\/span> <span class=\"nf\">onQueryTerminated<\/span><span class=\"o\">(<\/span><span class=\"n\">event<\/span><span class=\"k\">:<\/span> <span class=\"kt\">org.apache.spark.sql.streaming.StreamingQueryListener.QueryTerminatedEvent<\/span><span class=\"o\">)<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Unit<\/span> <span class=\"o\">=<\/span> <span class=\"o\">{}<\/span>\r\n<span class=\"o\">}<\/span>\r\n<\/code><\/pre>\n<div>\u7ffb\u8bd1\u6ce8\uff1a\u73b0\u5728PySpark\u4e5f\u652f\u6301\u6d41\u67e5\u8be2\u7684\u76d1\u542c\u5668\u3002<\/div>\n<h1>\u6574\u7406<\/h1>\n<p>\u5728\u8fd9\u7bc7\u6587\u7ae0\u4e2d\uff0c\u6211\u4eec\u901a\u8fc7\u4f7f\u7528Databricks\u6765\u89e3\u91ca\u4e86\u4ece\u7ed3\u6784\u5316\u6d41\u7684\u539f\u578b\u5230\u751f\u4ea7\u73af\u5883\u7684\u8f6c\u53d8\u6709\u591a\u7b80\u5355\u3002\u5982\u679c\u4f60\u60f3\u4e86\u89e3\u5173\u4e8e\u7ed3\u6784\u5316\u6d41\u7684\u5176\u4ed6\u65b9\u9762\uff0c\u8bf7\u67e5\u770b\u6211\u4eec\u7684\u535a\u5ba2\u7cfb\u5217\u3002<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">Spark\u306e\u69cb\u9020\u5316\u30b9\u30c8\u30ea\u30fc\u30df\u30f3\u30b0<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">Real-time Streaming ETL with Structured Streaming in Apache Spark 2.1<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">Working with Complex Data Formats with Structured Streaming in Apache Spark 2.1<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">Processing Data in Apache Kafka with Structured Streaming in Apache Spark 2.2<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">Event-time Aggregation and Watermarking in Apache Spark\u2019s Structured Streaming<\/ul>\n<p>\u4f60\u53ef\u4ee5\u5728Databricks\u7684\u6587\u6863\u4e2d\u5b66\u4e60\u5982\u4f55\u4f7f\u7528\u6d41\u5f0f\u64cd\u4f5c\uff0c\u4e5f\u53ef\u4ee5\u6ce8\u518c\u8fdb\u884c\u514d\u8d39\u8bd5\u7528\u3002<\/p>\n<h3>Databricks \u514d\u8d39\u8bd5\u7528\u7248<\/h3>\n<p>\u6570\u636e\u5149\u8f89\u514d\u8d39\u8bd5\u7528<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u5c06Apache Spark\u7684\u7ed3\u6784\u5316\u6d41\u5f0f\u5904\u7406\u5e26\u5165\u751f\u4ea7\u73af\u5883 &#8211; Databricks\u535a\u5ba2\u7684\u7ffb\u8bd1\u8bf4\u660e\u3002  [&hellip;]<\/p>\n","protected":false},"author":12,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-47033","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v21.5 (Yoast SEO v21.5) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>\u5c06Spark\u7ed3\u6784\u5316\u6d41\u8f6c\u79fb\u5230\u751f\u4ea7\u73af\u5883\u4e2d - Blog - Silicon Cloud<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.silicloud.com\/zh\/blog\/\u5c06spark\u7ed3\u6784\u5316\u6d41\u8f6c\u79fb\u5230\u751f\u4ea7\u73af\u5883\u4e2d\/\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u5c06Spark\u7ed3\u6784\u5316\u6d41\u8f6c\u79fb\u5230\u751f\u4ea7\u73af\u5883\u4e2d\" \/>\n<meta property=\"og:description\" content=\"\u5c06Apache Spark\u7684\u7ed3\u6784\u5316\u6d41\u5f0f\u5904\u7406\u5e26\u5165\u751f\u4ea7\u73af\u5883 &#8211; Databricks\u535a\u5ba2\u7684\u7ffb\u8bd1\u8bf4\u660e\u3002 [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.silicloud.com\/zh\/blog\/\u5c06spark\u7ed3\u6784\u5316\u6d41\u8f6c\u79fb\u5230\u751f\u4ea7\u73af\u5883\u4e2d\/\" \/>\n<meta property=\"og:site_name\" content=\"Blog - Silicon Cloud\" \/>\n<meta property=\"article:published_time\" content=\"2024-02-25T10:34:49+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-04-28T17:40:07+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d7c1c913a08637a69b460\/13-1.png\" \/>\n<meta name=\"author\" content=\"\u9038, \u79d1\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"\u9038, \u79d1\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"1 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e8%bd%ac%e7%a7%bb%e5%88%b0%e7%94%9f%e4%ba%a7%e7%8e%af%e5%a2%83%e4%b8%ad\/\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e8%bd%ac%e7%a7%bb%e5%88%b0%e7%94%9f%e4%ba%a7%e7%8e%af%e5%a2%83%e4%b8%ad\/\",\"name\":\"\u5c06Spark\u7ed3\u6784\u5316\u6d41\u8f6c\u79fb\u5230\u751f\u4ea7\u73af\u5883\u4e2d - Blog - Silicon Cloud\",\"isPartOf\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\"},\"datePublished\":\"2024-02-25T10:34:49+00:00\",\"dateModified\":\"2024-04-28T17:40:07+00:00\",\"author\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/85c1dae56e6ea1e695c73d33c684d487\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e8%bd%ac%e7%a7%bb%e5%88%b0%e7%94%9f%e4%ba%a7%e7%8e%af%e5%a2%83%e4%b8%ad\/#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e8%bd%ac%e7%a7%bb%e5%88%b0%e7%94%9f%e4%ba%a7%e7%8e%af%e5%a2%83%e4%b8%ad\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e8%bd%ac%e7%a7%bb%e5%88%b0%e7%94%9f%e4%ba%a7%e7%8e%af%e5%a2%83%e4%b8%ad\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.silicloud.com\/zh\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u5c06Spark\u7ed3\u6784\u5316\u6d41\u8f6c\u79fb\u5230\u751f\u4ea7\u73af\u5883\u4e2d\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/\",\"name\":\"Blog - Silicon Cloud\",\"description\":\"\",\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/85c1dae56e6ea1e695c73d33c684d487\",\"name\":\"\u9038, \u79d1\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/c94f6d9cbbfbca863fab309840bd690c153c95f8490c290ad2ed54dd693dad16?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/c94f6d9cbbfbca863fab309840bd690c153c95f8490c290ad2ed54dd693dad16?s=96&d=mm&r=g\",\"caption\":\"\u9038, \u79d1\"},\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/author\/keyi\/\"},{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e8%bd%ac%e7%a7%bb%e5%88%b0%e7%94%9f%e4%ba%a7%e7%8e%af%e5%a2%83%e4%b8%ad\/#local-main-organization-logo\",\"url\":\"\",\"contentUrl\":\"\",\"caption\":\"Blog - Silicon Cloud\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"\u5c06Spark\u7ed3\u6784\u5316\u6d41\u8f6c\u79fb\u5230\u751f\u4ea7\u73af\u5883\u4e2d - Blog - Silicon Cloud","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.silicloud.com\/zh\/blog\/\u5c06spark\u7ed3\u6784\u5316\u6d41\u8f6c\u79fb\u5230\u751f\u4ea7\u73af\u5883\u4e2d\/","og_locale":"zh_CN","og_type":"article","og_title":"\u5c06Spark\u7ed3\u6784\u5316\u6d41\u8f6c\u79fb\u5230\u751f\u4ea7\u73af\u5883\u4e2d","og_description":"\u5c06Apache Spark\u7684\u7ed3\u6784\u5316\u6d41\u5f0f\u5904\u7406\u5e26\u5165\u751f\u4ea7\u73af\u5883 &#8211; Databricks\u535a\u5ba2\u7684\u7ffb\u8bd1\u8bf4\u660e\u3002 [&hellip;]","og_url":"https:\/\/www.silicloud.com\/zh\/blog\/\u5c06spark\u7ed3\u6784\u5316\u6d41\u8f6c\u79fb\u5230\u751f\u4ea7\u73af\u5883\u4e2d\/","og_site_name":"Blog - Silicon Cloud","article_published_time":"2024-02-25T10:34:49+00:00","article_modified_time":"2024-04-28T17:40:07+00:00","og_image":[{"url":"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d7c1c913a08637a69b460\/13-1.png"}],"author":"\u9038, \u79d1","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"\u9038, \u79d1","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"1 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e8%bd%ac%e7%a7%bb%e5%88%b0%e7%94%9f%e4%ba%a7%e7%8e%af%e5%a2%83%e4%b8%ad\/","url":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e8%bd%ac%e7%a7%bb%e5%88%b0%e7%94%9f%e4%ba%a7%e7%8e%af%e5%a2%83%e4%b8%ad\/","name":"\u5c06Spark\u7ed3\u6784\u5316\u6d41\u8f6c\u79fb\u5230\u751f\u4ea7\u73af\u5883\u4e2d - Blog - Silicon Cloud","isPartOf":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website"},"datePublished":"2024-02-25T10:34:49+00:00","dateModified":"2024-04-28T17:40:07+00:00","author":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/85c1dae56e6ea1e695c73d33c684d487"},"breadcrumb":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e8%bd%ac%e7%a7%bb%e5%88%b0%e7%94%9f%e4%ba%a7%e7%8e%af%e5%a2%83%e4%b8%ad\/#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e8%bd%ac%e7%a7%bb%e5%88%b0%e7%94%9f%e4%ba%a7%e7%8e%af%e5%a2%83%e4%b8%ad\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e8%bd%ac%e7%a7%bb%e5%88%b0%e7%94%9f%e4%ba%a7%e7%8e%af%e5%a2%83%e4%b8%ad\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.silicloud.com\/zh\/blog\/"},{"@type":"ListItem","position":2,"name":"\u5c06Spark\u7ed3\u6784\u5316\u6d41\u8f6c\u79fb\u5230\u751f\u4ea7\u73af\u5883\u4e2d"}]},{"@type":"WebSite","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website","url":"https:\/\/www.silicloud.com\/zh\/blog\/","name":"Blog - Silicon Cloud","description":"","inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/85c1dae56e6ea1e695c73d33c684d487","name":"\u9038, \u79d1","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/c94f6d9cbbfbca863fab309840bd690c153c95f8490c290ad2ed54dd693dad16?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/c94f6d9cbbfbca863fab309840bd690c153c95f8490c290ad2ed54dd693dad16?s=96&d=mm&r=g","caption":"\u9038, \u79d1"},"url":"https:\/\/www.silicloud.com\/zh\/blog\/author\/keyi\/"},{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e8%bd%ac%e7%a7%bb%e5%88%b0%e7%94%9f%e4%ba%a7%e7%8e%af%e5%a2%83%e4%b8%ad\/#local-main-organization-logo","url":"","contentUrl":"","caption":"Blog - Silicon Cloud"}]}},"_links":{"self":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/47033","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/users\/12"}],"replies":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/comments?post=47033"}],"version-history":[{"count":2,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/47033\/revisions"}],"predecessor-version":[{"id":72335,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/47033\/revisions\/72335"}],"wp:attachment":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/media?parent=47033"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/categories?post=47033"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/tags?post=47033"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}