{"id":50418,"date":"2023-03-01T11:57:08","date_gmt":"2024-02-13T17:48:24","guid":{"rendered":"https:\/\/www.silicloud.com\/zh\/blog\/spark%e5%86%85%e9%83%a8%e7%bb%93%e6%9e%84%e8%a7%a3%e9%87%8a%e6%96%87%e6%a1%a3%e9%93%be%e6%8e%a5%e5%90%88%e9%9b%86\/"},"modified":"2024-04-29T16:51:06","modified_gmt":"2024-04-29T08:51:06","slug":"spark%e5%86%85%e9%83%a8%e7%bb%93%e6%9e%84%e8%a7%a3%e9%87%8a%e6%96%87%e6%a1%a3%e9%93%be%e6%8e%a5%e5%90%88%e9%9b%86","status":"publish","type":"post","link":"https:\/\/www.silicloud.com\/zh\/blog\/spark%e5%86%85%e9%83%a8%e7%bb%93%e6%9e%84%e8%a7%a3%e9%87%8a%e6%96%87%e6%a1%a3%e9%93%be%e6%8e%a5%e5%90%88%e9%9b%86\/","title":{"rendered":"Spark\u5185\u90e8\u7ed3\u6784\u89e3\u91ca\u6587\u6863\u94fe\u63a5\u5408\u96c6"},"content":{"rendered":"<p>\u4ee5\u4e0b\u662f\u4e00\u4e9b\u4ecb\u7ecdApache Spark\u5185\u90e8\u7ed3\u6784\u548c\u5de5\u4f5c\u539f\u7406\u7684\u4fe1\u606f\u6765\u6e90\uff08\u6211\u5c06\u968f\u65f6\u66f4\u65b0\uff0c\u5982\u679c\u6709\u9519\u8bef\u6216\u5176\u4ed6\u4fe1\u606f\u6765\u6e90\uff0c\u8bf7\u544a\u77e5\uff09\u3002<br \/>\n\u6240\u6709\u7684\u5e7b\u706f\u7247\u548c\u6587\u6863\u90fd\u662f\u7528\u82f1\u6587\u64b0\u5199\u7684\uff0c\u4f46\u662f\u957f\u7bc7\u6587\u6bb5\u8f83\u5c11\uff0c\u6240\u4ee5\u5e94\u8be5\u53ef\u4ee5\u7406\u89e3\u3002<\/p>\n<h1>\u6574\u4f53\u7684\u5f62\u8c61<\/h1>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">A Deeper Understanding of Spark\u2019s Internals<\/ul>\n<\/li>\n<\/ul>\n<p>https:\/\/spark-summit.org\/2014\/wp-content\/uploads\/2014\/07\/A-Deeper-Understanding-of-Spark-Internals-Aaron-Davidson.pdf<br \/>\nExecution model\u3068Shuffle\u306b\u7d5e\u3063\u3066\u89e3\u8aac\u3057\u3066\u3044\u307e\u3059\uff08Caching\u306b\u3064\u3044\u3066\u306f\u8aac\u660e\u3057\u3066\u3044\u307e\u305b\u3093\uff09<\/p>\n<p>Spark Architecture<\/p>\n<p>http:\/\/0x0fff.com\/spark-architecture\/<br \/>\n\u65e5\u672c\u8a9e\u8a33\u306f\u3053\u3061\u3089<\/p>\n<p>http:\/\/qiita.com\/kimutansk\/items\/3496e5b139959e362f02<\/p>\n<p>Master&amp;worker, Java heap\u306e\u4f7f\u308f\u308c\u65b9\u3001RDD\u306epartition\u3001\u306b\u3064\u3044\u3066\u8aac\u660e\u3057\u3066\u3044\u307e\u3059<br \/>\n1.6\u304b\u3089\u306e\u65b0\u3057\u3044Memory\u7ba1\u7406\u306b\u3064\u3044\u3066\u306f\u3001\u3053\u3061\u3089<br \/>\nhttp:\/\/0x0fff.com\/spark-memory-management\/<br \/>\n\u65e5\u672c\u8a9e\u8a33\u306f\u3053\u3061\u3089<\/p>\n<p>http:\/\/qiita.com\/giwa\/items\/96cc6cc9ea74aae83e2e<\/p>\n<p>Apache Spark Architecture (Nov 7, 2015)<\/p>\n<p><iframe loading=\"lazy\" title=\"Apache Spark Architecture\" src=\"https:\/\/www.slideshare.net\/slideshow\/embed_code\/key\/igfluRtWHYElyT\" width=\"427\" height=\"356\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" style=\"border:1px solid #CCC; border-width:1px; margin-bottom:5px; max-width: 100%;\" allowfullscreen> <\/iframe> <\/p>\n<div style=\"margin-bottom:5px\"> <strong> <a href=\"https:\/\/www.slideshare.net\/AGrishchenko\/apache-spark-architecture\" title=\"Apache Spark Architecture\" target=\"_blank\">Apache Spark Architecture<\/a> <\/strong> from <strong><a href=\"https:\/\/www.slideshare.net\/AGrishchenko\" target=\"_blank\">Alexey Grishchenko<\/a><\/strong> <\/div>\n<p>114\u30da\u30fc\u30b8\u3068\u9577\u3044\u3067\u3059\u304c\u3001Spark\u5168\u4f53\u306e\u30b3\u30f3\u30dd\u30fc\u30cd\u30f3\u30c8\u3092\u7db2\u7f85\u3057\u3066\u3044\u307e\u3059\u3002<br \/>\nSpark\u3067\u30d7\u30ed\u30b0\u30e9\u30e0\u3092\u5b9f\u884c\u3057\u305f\u3053\u3068\u304c\u3042\u308b\u4eba\u304c\u3001\u5185\u90e8\u69cb\u9020\u3092\u7406\u89e3\u3057\u3088\u3046\u3068\u3059\u308b\u3068\u304d\u3001\u6700\u521d\u306b\u773a\u3081\u308b\u306e\u306b\u6700\u9069\u306a\u30b9\u30e9\u30a4\u30c9\u3060\u3068\u601d\u3044\u307e\u3059\u3002<\/p>\n<p>Introduction to Apache Spark Internal (May 19, 2015)<\/p>\n<p><iframe loading=\"lazy\" title=\"Introduction to Spark Internals\" src=\"https:\/\/www.slideshare.net\/slideshow\/embed_code\/key\/72Z6QsfUaZbVKQ\" width=\"427\" height=\"356\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" style=\"border:1px solid #CCC; border-width:1px; margin-bottom:5px; max-width: 100%;\" allowfullscreen> <\/iframe> <\/p>\n<div style=\"margin-bottom:5px\"> <strong> <a href=\"https:\/\/www.slideshare.net\/michiard\/introduction-to-spark-internals\" title=\"Introduction to Spark Internals\" target=\"_blank\">Introduction to Spark Internals<\/a> <\/strong> from <strong><a href=\"https:\/\/www.slideshare.net\/michiard\" target=\"_blank\">Pietro Michiardi<\/a><\/strong> <\/div>\n<p>DAG scheduler, Task scheduler, Executor, RDD, Block Manager, Shuffle\u3068\u3044\u3063\u305f\u69cb\u6210\u8981\u7d20\u306b\u3064\u3044\u3066\u8aac\u660e\u3055\u308c\u3066\u3044\u307e\u3059<\/p>\n<p>Shuffle\u306f\u3001Hash-based\u3068Sort-based\u3092\u8aac\u660e\u3057\u3066\u3044\u307e\u3059<\/p>\n<p>RDD\u306e\u8aac\u660e\u304c\u6bd4\u8f03\u7684\u8a73\u3057\u3044<\/p>\n<p>Mastering Apache Spark<\/p>\n<p>https:\/\/jaceklaskowski.gitbooks.io\/mastering-apache-spark\/content\/<br \/>\nSpark\u5168\u4f53\u306e\u30b3\u30f3\u30dd\u30fc\u30cd\u30f3\u30c8\u3092\u7db2\u7f85\u3057\u3066\u3044\u307e\u3059\u3002<br \/>\nSpark\u306e\u30d7\u30ed\u30b0\u30e9\u30e0\u306b\u305d\u3063\u3066\u3001RDD\u306a\u3069\u3092\u8aac\u660e\u3057\u3066\u304f\u308c\u3066\u3044\u308b\u7ae0\uff08Section 2\uff09\u3082\u3042\u308a\u307e\u3059\u3002<br \/>\n\u30b9\u30e9\u30a4\u30c9\u3067\u306f\u306a\u3044\u306e\u3067\u3001\u4ed6\u306b\u6bd4\u3079\u3066\u6587\u7ae0\u304c\u591a\u3081\u3067\u3059\u3002\u305d\u308c\u3067\u3082\u3001\u30af\u30e9\u30b9\u9593\u306e\u95a2\u4fc2\u3084\u3001\u5b9f\u969b\u306e\u5b9f\u884c\u6642\u306e\u753b\u9762\u30ad\u30e3\u30d7\u30c1\u30e3\u306a\u3069\u3001\u56f3\u7d75\u304c\u591a\u304f\u4f7f\u308f\u308c\u3066\u304a\u308a\u3001\u308f\u304b\u308a\u3084\u3059\u3044\u3068\u601d\u3044\u307e\u3059\u3002<\/p>\n<p>Spark Internals (May 29, 2014)<\/p>\n<p><iframe loading=\"lazy\" title=\"Spark Internals - Hadoop Source Code Reading #16 in Japan\" src=\"https:\/\/www.slideshare.net\/slideshow\/embed_code\/key\/2wk4nwO4BE02UQ\" width=\"427\" height=\"356\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" style=\"border:1px solid #CCC; border-width:1px; margin-bottom:5px; max-width: 100%;\" allowfullscreen> <\/iframe> <\/p>\n<div style=\"margin-bottom:5px\"> <strong> <a href=\"https:\/\/www.slideshare.net\/taroleo\/spark-internal-hadoop-source-code-reading-16-in-japan\" title=\"Spark Internals - Hadoop Source Code Reading #16 in Japan\" target=\"_blank\">Spark Internals &#8211; Hadoop Source Code Reading #16 in Japan<\/a> <\/strong> from <strong><a href=\"https:\/\/www.slideshare.net\/taroleo\" target=\"_blank\">Taro L. Saito<\/a><\/strong> <\/div>\n<p>RDD\u3084Task\u306a\u3069\u3001\u8981\u6240\u306e\u30b3\u30f3\u30dd\u30fc\u30cd\u30f3\u30c8\u306e\u30bd\u30fc\u30b9\u306e\u4e00\u90e8\u304c\u7d39\u4ecb\u3055\u308c\u3066\u3044\u307e\u3059<br \/>\n\u5168\u4f53\u50cf\u3092\u63b4\u307e\u308c\u305f\u3042\u3068\u306b\u3053\u308c\u3092\u8aad\u3080\u3068\u3001\u30bd\u30fc\u30b9\u304c\u7d39\u4ecb\u3055\u308c\u3066\u3044\u308b\u306e\u3067\u3001\u3053\u3046\u3044\u3046\u5b9f\u88c5\u306b\u306a\u3063\u3066\u3044\u308b\u306e\u304b\u3001\u3068\u7406\u89e3\u3067\u304d\u308b\u304b\u3068\u601d\u3044\u307e\u3059\uff08\u305f\u3060\u3057\u30012014\u5e74\u306e\u8cc7\u6599\u306a\u306e\u3067\u3001\u30b3\u30fc\u30c9\u304c\u53e4\u3044\u90e8\u5206\u3082\u3042\u308a\u307e\u3059\uff09<br \/>\nClosureSerializer\u306b\u3064\u3044\u3066\u89e6\u308c\u3066\u3044\u308b\u6570\u5c11\u306a\u3044\u8cc7\u6599\u306e\uff11\u3064\u3067\u3059<\/p>\n<p>Spark Internals<\/p>\n<p>https:\/\/github.com\/JerryLead\/SparkInternals\/<br \/>\n\u65e5\u672c\u8a9e\u8a33\u306f\u3053\u3061\u3089<\/p>\n<p>http:\/\/qiita.com\/kimutansk\/items\/f47c2a28eda6817db531<br \/>\nhttp:\/\/qiita.com\/kimutansk\/items\/3496e5b139959e362f02<br \/>\nhttp:\/\/qiita.com\/kimutansk\/items\/be5a29c539061ad5a634<br \/>\nhttp:\/\/qiita.com\/kimutansk\/items\/e36db0f22893ee4c428d<\/p>\n<p>Overview, Job logical plan, Job physical plan, shuffle, Master&amp;worker coordination, cache and check point, broad cast,\u306b\u3064\u3044\u3066\u8a73\u3057\u304f\u66f8\u304b\u308c\u3066\u3044\u307e\u3059<br \/>\n\u5b9f\u88c5\u306b\u3064\u3044\u3066\u3001\u30bd\u30fc\u30b9\u30b3\u30fc\u30c9\u3084\u30c7\u30fc\u30bf\u69cb\u9020\u306e\u7d75\u3092\u4f7f\u3063\u3066\u8aac\u660e\u3057\u3066\u3044\u308b\u306e\u3067\u3001\u7d30\u304b\u3044\u70b9\u3082\u308f\u304b\u308a\u3084\u3059\u3044\u3067\u3059<br \/>\n\u8a73\u7d30\u3092\u628a\u63e1\u3057\u305f\u3044\u4eba\u306f\u304a\u3059\u3059\u3081\u3067\u3059\u3002<\/p>\n<h1>\u5d4c\u5165\u5f0f\u5206\u5e03\u5f0f\u6570\u636e\u5e93 (RDD)<\/h1>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">Anatomy of RDD<\/ul>\n<\/li>\n<\/ul>\n<p>\u30b9\u30e9\u30a4\u30c9\u3000http:\/\/www.slideshare.net\/datamantra\/anatomy-of-rdd<\/p>\n<p>\u30d3\u30c7\u30aa\u3000http:\/\/blog.madhukaraphatak.com\/anatomy-of-rdd\/<\/p>\n<p>\u30c7\u30fc\u30bf\u306e\u6301\u3061\u65b9\u3001\u8a08\u7b97\u306e\u3055\u308c\u304b\u305f\u3001\u30ad\u30e3\u30c3\u30b7\u30e5\u306e\u65b9\u6cd5\u3001\u306a\u3069\u8aac\u660e\u3057\u3066\u3044\u307e\u3059<br \/>\n\u3042\u308b\u7a0b\u5ea6\u3001\u30bd\u30fc\u30b9\u30b3\u30fc\u30c9\u3092\u8aad\u3093\u3067\u304b\u3089\u3067\u306a\u3044\u3068\u3001\u8aac\u660e\u304c\u30d4\u30f3\u3068\u3053\u306a\u3044\u304b\u3082\u3057\u308c\u307e\u305b\u3093\u3002<\/p>\n<p>caching and checkpoint<\/p>\n<p>https:\/\/github.com\/JerryLead\/SparkInternals\/blob\/master\/markdown\/english\/6-CacheAndCheckpoint.md<br \/>\n\u5168\u4f53\u50cf\u3001\u306e\u6700\u5f8c\u3067\u7d39\u4ecb\u3057\u305f\u8cc7\u6599\u306e6\u7ae0\u3067\u3059\u304c\u3001cache\u306b\u3064\u3044\u3066\u3001\u6982\u5ff5\u30fb\u5b9f\u88c5\u3092\u30c7\u30fc\u30bf\u69cb\u9020\u306e\u7d75\u3068\u3068\u3082\u306b\u308f\u304b\u308a\u3084\u3059\u304f\u8aac\u660e\u3057\u3066\u3044\u307e\u3059<\/p>\n<p>Cache\u3055\u308c\u306a\u3044RDD\u306epartition\u306b\u95a2\u3059\u308b\u8aac\u660e<\/p>\n<p>https:\/\/www.quora.com\/In-Spark-Where-is-one-RDD-which-hasnt-called-its-cache-or-persist-method-deleted<br \/>\nCache\u3055\u308c\u306a\u3044RDD\u306epartition\u306f\u3001\u305f\u3060\u306eiterator\u3068\u305d\u306eSeq\u306a\u306e\u3067\u3001\u4f7f\u3044\u7d42\u308f\u3063\u305f\u3089\u3069\u3053\u304b\u3089\u3082\u53c2\u7167\u304c\u306a\u304f\u306a\u3063\u3066GC\u3067\u56de\u53ce\u3055\u308c\u308b<\/p>\n<p>Controlling Parallelism in Spark<\/p>\n<p>http:\/\/www.bigsynapse.com\/spark-input-output<br \/>\nlocal\u30d5\u30a1\u30a4\u30eb\u304b\u3089\u3001\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u3060\u3057\u305f\u969b\u306b\u751f\u6210\u3055\u308c\u308b\u3001\u30d1\u30fc\u30c6\u30a3\u30b7\u30e7\u30f3\u6570\u306e\u8a08\u7b97\u65b9\u6cd5\u306e\u8aac\u660e\u3067\u3059<\/p>\n<p>Glom in Spark<\/p>\n<p>http:\/\/blog.madhukaraphatak.com\/glom-in-spark\/<br \/>\nRDD\u306e\u5404\u30d1\u30fc\u30c6\u30a3\u30b7\u30e7\u30f3\u306e\u30c7\u30fc\u30bf\u3092\u914d\u5217\u5316\u3059\u308b\u3001RDD.glom()\u306e\u8aac\u660e<\/p>\n<p>Extending Spark API<\/p>\n<p>http:\/\/blog.madhukaraphatak.com\/extending-spark-api\/<br \/>\n\u30ab\u30b9\u30bf\u30e0RDD\u306e\u4f5c\u308a\u65b9<\/p>\n<p>Succinct Spark: Queries on Compressed RDDs<\/p>\n<p>https:\/\/amplab.cs.berkeley.edu\/succinct-spark-queries-on-compressed-rdds\/ (Succinct Spark)<br \/>\nhttps:\/\/github.com\/amplab\/succinct<br \/>\n(RDD\u306e\u69cb\u9020\u306e\u8aac\u660e\u3068\u306f\u7570\u306a\u308a\u307e\u3059\u304c)\u7c21\u6f54\u30c7\u30fc\u30bf\u69cb\u9020\u3092\u7528\u3044\u3066\u3001\u5727\u7e2e\u3057\u305f\u5f62\u3067RDD\u5185\u306b\u30c7\u30fc\u30bf\u3092\u6301\u3061\u3001\u5c55\u958b\u3059\u308b\u3053\u3068\u306a\u304f\u6f14\u7b97\u3092\u884c\u3046\u305f\u3081\u306e\u30ab\u30b9\u30bf\u30e0RDD\u30d1\u30c3\u30b1\u30fc\u30b8\u306e\u8aac\u660e\u3068\u30bd\u30fc\u30b9\u30b3\u30fc\u30c9<\/p>\n<h1>\u6d17\u724c<\/h1>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">How Spark Beat Hadoop @ 100 TB Daytona GraySort Challenge<\/ul>\n<\/li>\n<\/ul>\n<p><iframe loading=\"lazy\" title=\"Advanced Apache Spark Meetup:  How Spark Beat Hadoop @ 100 TB Daytona GraySort Challenge\" src=\"https:\/\/www.slideshare.net\/slideshow\/embed_code\/key\/CwRGb5lzV5JpTv\" width=\"427\" height=\"356\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" style=\"border:1px solid #CCC; border-width:1px; margin-bottom:5px; max-width: 100%;\" allowfullscreen> <\/iframe> <\/p>\n<div style=\"margin-bottom:5px\"> <strong> <a href=\"https:\/\/www.slideshare.net\/cfregly\/advanced-apache-spark-meetup-how-spark-beat-hadoop-100-tb-daytona-graysort-challenge\" title=\"Advanced Apache Spark Meetup: How Spark Beat Hadoop @ 100 TB Daytona GraySort Challenge\" target=\"_blank\">Advanced Apache Spark Meetup: How Spark Beat Hadoop @ 100 TB Daytona GraySort Challenge<\/a> <\/strong> from <strong><a href=\"https:\/\/www.slideshare.net\/cfregly\" target=\"_blank\">Chris Fregly<\/a><\/strong> <\/div>\n<p>P.22-34\u306b\u3001\u30b7\u30e3\u30c3\u30d5\u30eb\u306e\u6982\u8981\u3001\u8a2d\u5b9a\u3067\u304d\u308b\u30aa\u30d7\u30b7\u30e7\u30f3\u306b\u3064\u3044\u3066\u89e6\u308c\u3066\u3044\u307e\u3059<\/p>\n<p>Spark Architecture: Shuffle<\/p>\n<p>http:\/\/0x0fff.com\/spark-architecture-shuffle\/<br \/>\n\u65e5\u672c\u8a9e\u8a33\u306f\u3053\u3061\u3089<\/p>\n<p>http:\/\/qiita.com\/giwa\/items\/08ac5bda1eabb8c597b3<br \/>\nhttp:\/\/qiita.com\/kimutansk\/items\/3496e5b139959e362f02<\/p>\n<p>\u7d75\u3092\u7528\u3044\u3066\u52d5\u4f5c\u3092\u8aac\u660e\u3057\u3066\u3044\u307e\u3059<br \/>\nHash, Sort, Tungsten-sort\u306e\uff13\u3064\u306e\u52d5\u4f5c\u3092\u305d\u308c\u305e\u308c\u8aac\u660e\u3057\u3066\u3044\u308b\u8cc7\u6599\u3067\u3059<\/p>\n<p>Shuffle Process<\/p>\n<p>https:\/\/github.com\/JerryLead\/SparkInternals\/blob\/master\/markdown\/english\/4-shuffleDetails.md<br \/>\n\u5168\u4f53\u50cf\u3001\u306e\u6700\u5f8c\u3067\u7d39\u4ecb\u3057\u305f\u8cc7\u6599\u306e4\u7ae0\u3067\u3059\u304c\u3001shuffle\u306b\u3064\u3044\u3066\u3001\u6982\u5ff5\u30fb\u52d5\u4f5c\u3092\u30c7\u30fc\u30bf\u69cb\u9020\u306e\u7d75\u3068\u3068\u3082\u306b\u308f\u304b\u308a\u3084\u3059\u304f\u8aac\u660e\u3057\u3066\u3044\u307e\u3059<br \/>\nhash\u306e\u307f\u3092\u8aac\u660e\u3057\u3066\u3044\u307e\u3059<\/p>\n<p>Optimizing Shuffle Performance in Spark<\/p>\n<p>http:\/\/www.cs.berkeley.edu\/~kubitron\/courses\/cs262a-F13\/projects\/reports\/project16_report.pdf<br \/>\nSpark\u306e(Hash) shuffle\u306e\u554f\u984c\u70b9\u3092\u3042\u3052\u3001\u6539\u5584\u65b9\u6cd5\u3068\u3057\u3066column\u65b9\u5411\u306e\u30c7\u30fc\u30bf\u5727\u7e2e\u3001\u9001\u4fe1\u5074\u304c\u30d5\u30a1\u30a4\u30eb\u306b\u5404\u5185\u5bb9\u3092\u307e\u3068\u3081\u3066\u30d5\u30a1\u30a4\u30eb\u6570\u3092\u6e1b\u3089\u3059\u3001\u3092\u63d0\u6848\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n<p>Everyday I&#8217;m Shuffling &#8211; Tips for Writing Better Spark Programs<\/p>\n<p><iframe loading=\"lazy\" title=\"Everyday I&#039;m Shuffling - Tips for Writing Better Spark Programs, Strata San Jose 2015\" src=\"https:\/\/www.slideshare.net\/slideshow\/embed_code\/key\/m5ot6FTIwXX8ba\" width=\"427\" height=\"356\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" style=\"border:1px solid #CCC; border-width:1px; margin-bottom:5px; max-width: 100%;\" allowfullscreen> <\/iframe> <\/p>\n<div style=\"margin-bottom:5px\"> <strong> <a href=\"https:\/\/www.slideshare.net\/slideshow\/strata-sj-everyday-im-shuffling-tips-for-writing-better-spark-programs\/45030392\" title=\"Everyday I&#39;m Shuffling - Tips for Writing Better Spark Programs, Strata San Jose 2015\" target=\"_blank\">Everyday I&#39;m Shuffling &#8211; Tips for Writing Better Spark Programs, Strata San Jose 2015<\/a> <\/strong> from <strong><a href=\"https:\/\/www.slideshare.net\/databricks\" target=\"_blank\">Databricks<\/a><\/strong> <\/div>\n<p>Shuffle\u3092\u4f7f\u3046\u30b3\u30fc\u30c9\u3092\u66f8\u304f\u3068\u304d\u306b\u3001\u6027\u80fd\u3092\u4f4e\u4e0b\u3055\u305b\u306a\u3044\u305f\u3081\u306etips\u304c\u66f8\u304b\u308c\u3066\u3044\u307e\u3059<\/p>\n<p>A simplified sequence diagram of Spark Shuffle Write<\/p>\n<p>https:\/\/www.linkedin.com\/groups\/7403611\/7403611-6103074141341044737<br \/>\nShuffle\u306e\u52d5\u4f5c\u306e\u30b7\u30fc\u30b1\u30f3\u30b9\u56f3\u3067\u3059<\/p>\n<h1>\u6570\u636e\u6846\u67b6<\/h1>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">Anatomy of Data Frame API<\/ul>\n<\/li>\n<\/ul>\n<p>\u30b9\u30e9\u30a4\u30c9\u3000http:\/\/www.slideshare.net\/datamantra\/anatomy-of-data-frame-api<\/p>\n<p>\u30d3\u30c7\u30aa\u3000http:\/\/blog.madhukaraphatak.com\/anatomy-of-spark-dataframe-api\/<\/p>\n<p>SQL\u306eData Frame API\u306b\u7d5e\u3063\u3066\u3001\u3069\u306e\u3088\u3046\u306b\u6700\u9069\u5316\u3055\u308c\u308b\u304b\u3092\u8aac\u660e\u3057\u3066\u3044\u307e\u3059<\/p>\n<h1>\u94a8<\/h1>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">Project Tungsten Nov 12 2015<\/ul>\n<\/li>\n<\/ul>\n<p><iframe loading=\"lazy\" title=\"Advanced Apache Spark Meetup Project Tungsten Nov 12 2015\" src=\"https:\/\/www.slideshare.net\/slideshow\/embed_code\/key\/5SXuMSujJFUVHn\" width=\"427\" height=\"356\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" style=\"border:1px solid #CCC; border-width:1px; margin-bottom:5px; max-width: 100%;\" allowfullscreen> <\/iframe> <\/p>\n<div style=\"margin-bottom:5px\"> <strong> <a href=\"https:\/\/www.slideshare.net\/cfregly\/advanced-apache-spark-meetup-project-tungsten-nov-12-2015\" title=\"Advanced Apache Spark Meetup Project Tungsten Nov 12 2015\" target=\"_blank\">Advanced Apache Spark Meetup Project Tungsten Nov 12 2015<\/a> <\/strong> from <strong><a href=\"https:\/\/www.slideshare.net\/cfregly\" target=\"_blank\">Chris Fregly<\/a><\/strong> <\/div>\n<p>P.37\u304b\u3089\u3001Tungsten\u306e\uff13\u3064\u306e\u30a2\u30a4\u30c7\u30a2\u306e\u3046\u3061\u3001\u30c7\u30fc\u30bf\u69cb\u9020\u306e\u6700\u9069\u5316\u3001\u30b3\u30fc\u30c9\u751f\u6210\u3001\u306b\u3064\u3044\u3066\u3088\u308a\u5177\u4f53\u7684\u306b\u8aac\u660e\u3057\u3066\u3044\u307e\u3059<\/p>\n<p>\u30ea\u30f3\u30af\u304a\u304d\u3070<\/p>\n<p><iframe loading=\"lazy\" title=\"Anatomy of in memory processing in Spark\" src=\"https:\/\/www.slideshare.net\/slideshow\/embed_code\/key\/uSCsTiT1jf1toN\" width=\"427\" height=\"356\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" style=\"border:1px solid #CCC; border-width:1px; margin-bottom:5px; max-width: 100%;\" allowfullscreen> <\/iframe> <\/p>\n<div style=\"margin-bottom:5px\"> <strong> <a href=\"https:\/\/www.slideshare.net\/datamantra\/anatomy-of-in-memory-processing-in-spark\" title=\"Anatomy of in memory processing in Spark\" target=\"_blank\">Anatomy of in memory processing in Spark<\/a> <\/strong> from <strong><a href=\"https:\/\/www.slideshare.net\/datamantra\" target=\"_blank\">datamantra<\/a><\/strong> <\/div>\n<p>\uff08\u8aac\u660e\u306f\u5f8c\u65e5\uff09<\/p>\n<h1>\u50ac\u5316\u5242 (catalyst)<\/h1>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">Data Sources API Cassandra Spark Connector Spark 1.5.1 Zeppelin 0.6.0<\/ul>\n<\/li>\n<\/ul>\n<p><iframe loading=\"lazy\" title=\"Advanced Apache Spark Meetup Data Sources API Cassandra Spark Connector Spark 1.5.1 Zeppelin 0.6.0\" src=\"https:\/\/www.slideshare.net\/slideshow\/embed_code\/key\/6zxFJKWBErid2t\" width=\"427\" height=\"356\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" style=\"border:1px solid #CCC; border-width:1px; margin-bottom:5px; max-width: 100%;\" allowfullscreen> <\/iframe> <\/p>\n<div style=\"margin-bottom:5px\"> <strong> <a href=\"https:\/\/www.slideshare.net\/cfregly\/advanced-apache-spark-meetup-data-sources-api-cassandra-spark-connector-spark-151-zeppelin-060\" title=\"Advanced Apache Spark Meetup Data Sources API Cassandra Spark Connector Spark 1.5.1 Zeppelin 0.6.0\" target=\"_blank\">Advanced Apache Spark Meetup Data Sources API Cassandra Spark Connector Spark 1.5.1 Zeppelin 0.6.0<\/a> <\/strong> from <strong><a href=\"https:\/\/www.slideshare.net\/cfregly\" target=\"_blank\">Chris Fregly<\/a><\/strong> <\/div>\n<p>P.15-18\u306b\u3001\u7c21\u5358\u306bPlan optimizer\u306b\u3064\u3044\u3066\u89e6\u308c\u3066\u3044\u307e\u3059<\/p>\n<p>SparkSQLInternal<\/p>\n<p>http:\/\/www.trongkhoanguyen.com\/2014\/11\/introduction-to-sparksql.html<br \/>\nSparkSQL\u304c\u3069\u306e\u3088\u3046\u306bRDD\u306e\u30aa\u30da\u30ec\u30fc\u30b7\u30e7\u30f3\u3068\u306a\u3063\u3066\u6700\u9069\u5316\u3055\u308c\u5b9f\u884c\u3055\u308c\u308b\u304b\u8aac\u660e\u3057\u3066\u3044\u307e\u3059\u3002<br \/>\nhttp:\/\/www.trongkhoanguyen.com\/2015\/08\/sparksql-internals.html<br \/>\n\uff08\u8aac\u660e\u306f\u5f8c\u65e5\uff09<br \/>\nhttps:\/\/hxquangnhat.com\/2015\/04\/10\/sparksql-internals-part-1-sqlcontext\/<br \/>\n\uff08\u8aac\u660e\u306f\u5f8c\u65e5\uff09<br \/>\nhttps:\/\/hxquangnhat.com\/2015\/04\/14\/arch-sparksql-internals-part-2-sparksql-data-flow\/<br \/>\n\uff08\u8aac\u660e\u306f\u5f8c\u65e5\uff09<br \/>\n<iframe loading=\"lazy\" title=\"Deep Dive : Spark Data Frames, SQL and Catalyst Optimizer\" src=\"https:\/\/www.slideshare.net\/slideshow\/embed_code\/key\/1dO7NneZohdluf\" width=\"427\" height=\"356\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" style=\"border:1px solid #CCC; border-width:1px; margin-bottom:5px; max-width: 100%;\" allowfullscreen> <\/iframe> <\/p>\n<div style=\"margin-bottom:5px\"> <strong> <a href=\"https:\/\/www.slideshare.net\/sachinparmarss\/deep-dive-spark-data-frames-sql-and-catalyst-optimizer\" title=\"Deep Dive : Spark Data Frames, SQL and Catalyst Optimizer\" target=\"_blank\">Deep Dive : Spark Data Frames, SQL and Catalyst Optimizer<\/a> <\/strong> from <strong><a href=\"https:\/\/www.slideshare.net\/sachinparmarss\" target=\"_blank\">Sachin Parmar<\/a><\/strong> <\/div>\n<p>\uff08\u8aac\u660e\u306f\u5f8c\u65e5\uff09<\/p>\n<p>\u30ea\u30f3\u30af\u304a\u304d\u3070<\/p>\n<p>http:\/\/www.slideshare.net\/maropu0804\/20160322-bdi<br \/>\n\u304a\u3059\u3059\u3081<br \/>\n<iframe loading=\"lazy\" title=\"Enhancements on Spark SQL optimizer by Min Qiu\" src=\"https:\/\/www.slideshare.net\/slideshow\/embed_code\/key\/zvslBhfij4F0LH\" width=\"427\" height=\"356\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" style=\"border:1px solid #CCC; border-width:1px; margin-bottom:5px; max-width: 100%;\" allowfullscreen> <\/iframe> <\/p>\n<div style=\"margin-bottom:5px\"> <strong> <a href=\"https:\/\/www.slideshare.net\/slideshow\/enhancements-on-spark-sql-optimizer-by-min-qiu\/58639642\" title=\"Enhancements on Spark SQL optimizer by Min Qiu\" target=\"_blank\">Enhancements on Spark SQL optimizer by Min Qiu<\/a> <\/strong> from <strong><a href=\"https:\/\/www.slideshare.net\/SparkSummit\" target=\"_blank\">Spark Summit<\/a><\/strong> <\/div>\n<p>\uff08\u8aac\u660e\u306f\u5f8c\u65e5\uff09<br \/>\n<iframe loading=\"lazy\" title=\"Introduction to Spark SQL &amp; Catalyst\" src=\"https:\/\/www.slideshare.net\/slideshow\/embed_code\/key\/b4LnyW9IUFBA4H\" width=\"427\" height=\"356\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" style=\"border:1px solid #CCC; border-width:1px; margin-bottom:5px; max-width: 100%;\" allowfullscreen> <\/iframe> <\/p>\n<div style=\"margin-bottom:5px\"> <strong> <a href=\"https:\/\/www.slideshare.net\/ueshin\/introduction-to-spark-sql-catalyst\" title=\"Introduction to Spark SQL &amp; Catalyst\" target=\"_blank\">Introduction to Spark SQL &amp; Catalyst<\/a> <\/strong> from <strong><a href=\"https:\/\/www.slideshare.net\/ueshin\" target=\"_blank\">Takuya UESHIN<\/a><\/strong> <\/div>\n<p>\uff08\u8aac\u660e\u306f\u5f8c\u65e5\uff09<br \/>\nhttp:\/\/igm.univ-mlv.fr\/~ocure\/LIGM_LIKE\/Teaching\/m2Log\/sparkSQLDF.pdf<br \/>\n\uff08\u8aac\u660e\u306f\u5f8c\u65e5\uff09<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u4ee5\u4e0b\u662f\u4e00\u4e9b\u4ecb\u7ecdApache Spark\u5185\u90e8\u7ed3\u6784\u548c\u5de5\u4f5c\u539f\u7406\u7684\u4fe1\u606f\u6765\u6e90\uff08\u6211\u5c06\u968f\u65f6\u66f4\u65b0\uff0c\u5982\u679c\u6709\u9519\u8bef\u6216\u5176\u4ed6\u4fe1\u606f\u6765\u6e90\uff0c\u8bf7 [&hellip;]<\/p>\n","protected":false},"author":9,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-50418","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>Spark\u5185\u90e8\u7ed3\u6784\u89e3\u91ca\u6587\u6863\u94fe\u63a5\u5408\u96c6 - 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\/spark\u5185\u90e8\u7ed3\u6784\u89e3\u91ca\u6587\u6863\u94fe\u63a5\u5408\u96c6\/\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Spark\u5185\u90e8\u7ed3\u6784\u89e3\u91ca\u6587\u6863\u94fe\u63a5\u5408\u96c6\" \/>\n<meta property=\"og:description\" content=\"\u4ee5\u4e0b\u662f\u4e00\u4e9b\u4ecb\u7ecdApache Spark\u5185\u90e8\u7ed3\u6784\u548c\u5de5\u4f5c\u539f\u7406\u7684\u4fe1\u606f\u6765\u6e90\uff08\u6211\u5c06\u968f\u65f6\u66f4\u65b0\uff0c\u5982\u679c\u6709\u9519\u8bef\u6216\u5176\u4ed6\u4fe1\u606f\u6765\u6e90\uff0c\u8bf7 [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.silicloud.com\/zh\/blog\/spark\u5185\u90e8\u7ed3\u6784\u89e3\u91ca\u6587\u6863\u94fe\u63a5\u5408\u96c6\/\" \/>\n<meta property=\"og:site_name\" content=\"Blog - Silicon Cloud\" \/>\n<meta property=\"article:published_time\" content=\"2024-02-13T17:48:24+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-04-29T08:51:06+00:00\" \/>\n<meta name=\"author\" content=\"\u6e05, \u626c\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"\u6e05, \u626c\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 \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\/spark%e5%86%85%e9%83%a8%e7%bb%93%e6%9e%84%e8%a7%a3%e9%87%8a%e6%96%87%e6%a1%a3%e9%93%be%e6%8e%a5%e5%90%88%e9%9b%86\/\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/spark%e5%86%85%e9%83%a8%e7%bb%93%e6%9e%84%e8%a7%a3%e9%87%8a%e6%96%87%e6%a1%a3%e9%93%be%e6%8e%a5%e5%90%88%e9%9b%86\/\",\"name\":\"Spark\u5185\u90e8\u7ed3\u6784\u89e3\u91ca\u6587\u6863\u94fe\u63a5\u5408\u96c6 - Blog - Silicon Cloud\",\"isPartOf\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\"},\"datePublished\":\"2024-02-13T17:48:24+00:00\",\"dateModified\":\"2024-04-29T08:51:06+00:00\",\"author\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/cb5556d2501da73d864cac945e8d9461\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/spark%e5%86%85%e9%83%a8%e7%bb%93%e6%9e%84%e8%a7%a3%e9%87%8a%e6%96%87%e6%a1%a3%e9%93%be%e6%8e%a5%e5%90%88%e9%9b%86\/#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.silicloud.com\/zh\/blog\/spark%e5%86%85%e9%83%a8%e7%bb%93%e6%9e%84%e8%a7%a3%e9%87%8a%e6%96%87%e6%a1%a3%e9%93%be%e6%8e%a5%e5%90%88%e9%9b%86\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/spark%e5%86%85%e9%83%a8%e7%bb%93%e6%9e%84%e8%a7%a3%e9%87%8a%e6%96%87%e6%a1%a3%e9%93%be%e6%8e%a5%e5%90%88%e9%9b%86\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.silicloud.com\/zh\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Spark\u5185\u90e8\u7ed3\u6784\u89e3\u91ca\u6587\u6863\u94fe\u63a5\u5408\u96c6\"}]},{\"@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\/cb5556d2501da73d864cac945e8d9461\",\"name\":\"\u6e05, \u626c\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/32a4239de8ff29adace466261d309424a1e5fe9f7e3036bf89fe03f2e3dbe717?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/32a4239de8ff29adace466261d309424a1e5fe9f7e3036bf89fe03f2e3dbe717?s=96&d=mm&r=g\",\"caption\":\"\u6e05, \u626c\"},\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/author\/qingyang\/\"},{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/spark%e5%86%85%e9%83%a8%e7%bb%93%e6%9e%84%e8%a7%a3%e9%87%8a%e6%96%87%e6%a1%a3%e9%93%be%e6%8e%a5%e5%90%88%e9%9b%86\/#local-main-organization-logo\",\"url\":\"\",\"contentUrl\":\"\",\"caption\":\"Blog - Silicon Cloud\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Spark\u5185\u90e8\u7ed3\u6784\u89e3\u91ca\u6587\u6863\u94fe\u63a5\u5408\u96c6 - 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\/spark\u5185\u90e8\u7ed3\u6784\u89e3\u91ca\u6587\u6863\u94fe\u63a5\u5408\u96c6\/","og_locale":"zh_CN","og_type":"article","og_title":"Spark\u5185\u90e8\u7ed3\u6784\u89e3\u91ca\u6587\u6863\u94fe\u63a5\u5408\u96c6","og_description":"\u4ee5\u4e0b\u662f\u4e00\u4e9b\u4ecb\u7ecdApache Spark\u5185\u90e8\u7ed3\u6784\u548c\u5de5\u4f5c\u539f\u7406\u7684\u4fe1\u606f\u6765\u6e90\uff08\u6211\u5c06\u968f\u65f6\u66f4\u65b0\uff0c\u5982\u679c\u6709\u9519\u8bef\u6216\u5176\u4ed6\u4fe1\u606f\u6765\u6e90\uff0c\u8bf7 [&hellip;]","og_url":"https:\/\/www.silicloud.com\/zh\/blog\/spark\u5185\u90e8\u7ed3\u6784\u89e3\u91ca\u6587\u6863\u94fe\u63a5\u5408\u96c6\/","og_site_name":"Blog - Silicon Cloud","article_published_time":"2024-02-13T17:48:24+00:00","article_modified_time":"2024-04-29T08:51:06+00:00","author":"\u6e05, \u626c","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"\u6e05, \u626c","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"3 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.silicloud.com\/zh\/blog\/spark%e5%86%85%e9%83%a8%e7%bb%93%e6%9e%84%e8%a7%a3%e9%87%8a%e6%96%87%e6%a1%a3%e9%93%be%e6%8e%a5%e5%90%88%e9%9b%86\/","url":"https:\/\/www.silicloud.com\/zh\/blog\/spark%e5%86%85%e9%83%a8%e7%bb%93%e6%9e%84%e8%a7%a3%e9%87%8a%e6%96%87%e6%a1%a3%e9%93%be%e6%8e%a5%e5%90%88%e9%9b%86\/","name":"Spark\u5185\u90e8\u7ed3\u6784\u89e3\u91ca\u6587\u6863\u94fe\u63a5\u5408\u96c6 - Blog - Silicon Cloud","isPartOf":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website"},"datePublished":"2024-02-13T17:48:24+00:00","dateModified":"2024-04-29T08:51:06+00:00","author":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/cb5556d2501da73d864cac945e8d9461"},"breadcrumb":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/spark%e5%86%85%e9%83%a8%e7%bb%93%e6%9e%84%e8%a7%a3%e9%87%8a%e6%96%87%e6%a1%a3%e9%93%be%e6%8e%a5%e5%90%88%e9%9b%86\/#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.silicloud.com\/zh\/blog\/spark%e5%86%85%e9%83%a8%e7%bb%93%e6%9e%84%e8%a7%a3%e9%87%8a%e6%96%87%e6%a1%a3%e9%93%be%e6%8e%a5%e5%90%88%e9%9b%86\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.silicloud.com\/zh\/blog\/spark%e5%86%85%e9%83%a8%e7%bb%93%e6%9e%84%e8%a7%a3%e9%87%8a%e6%96%87%e6%a1%a3%e9%93%be%e6%8e%a5%e5%90%88%e9%9b%86\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.silicloud.com\/zh\/blog\/"},{"@type":"ListItem","position":2,"name":"Spark\u5185\u90e8\u7ed3\u6784\u89e3\u91ca\u6587\u6863\u94fe\u63a5\u5408\u96c6"}]},{"@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\/cb5556d2501da73d864cac945e8d9461","name":"\u6e05, \u626c","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/32a4239de8ff29adace466261d309424a1e5fe9f7e3036bf89fe03f2e3dbe717?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/32a4239de8ff29adace466261d309424a1e5fe9f7e3036bf89fe03f2e3dbe717?s=96&d=mm&r=g","caption":"\u6e05, \u626c"},"url":"https:\/\/www.silicloud.com\/zh\/blog\/author\/qingyang\/"},{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/spark%e5%86%85%e9%83%a8%e7%bb%93%e6%9e%84%e8%a7%a3%e9%87%8a%e6%96%87%e6%a1%a3%e9%93%be%e6%8e%a5%e5%90%88%e9%9b%86\/#local-main-organization-logo","url":"","contentUrl":"","caption":"Blog - Silicon Cloud"}]}},"_links":{"self":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/50418","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\/9"}],"replies":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/comments?post=50418"}],"version-history":[{"count":2,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/50418\/revisions"}],"predecessor-version":[{"id":86469,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/50418\/revisions\/86469"}],"wp:attachment":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/media?parent=50418"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/categories?post=50418"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/tags?post=50418"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}