{"id":1447,"date":"2020-05-28T02:19:16","date_gmt":"2020-05-27T18:19:16","guid":{"rendered":"http:\/\/39.97.231.10\/?p=1447"},"modified":"2020-05-28T02:19:16","modified_gmt":"2020-05-27T18:19:16","slug":"hudi%e9%85%8d%e7%bd%ae%e8%bf%9e%e6%8e%a5%e4%ba%91%e5%b9%b3%e5%8f%b0%e5%ad%98%e5%82%a8%e7%b3%bb%e7%bb%9f","status":"publish","type":"post","link":"http:\/\/www.weijing.co\/?p=1447","title":{"rendered":"Hudi\u914d\u7f6e\u8fde\u63a5\u4e91\u5e73\u53f0\u5b58\u50a8\u7cfb\u7edf"},"content":{"rendered":"<p>\u65e0\u8bba\u4f7f\u7528RDD\/WriteClient API\u8fd8\u662f\u6570\u636e\u6e90\uff0c\u8bf7\u53c2\u8003\u4ee5\u4e0b\u4e91\u5b58\u50a8\u5e73\u53f0\u914d\u7f6e\u5bf9\u4e91\u5b58\u50a8\u7684\u8bbf\u95ee\u3002<\/p>\n<header>\n<h3 id=\\\"page-title\\\" class=\\\"page__title\\\"><span>S3\u6587\u4ef6\u7cfb\u7edf<\/span><\/h3>\n<\/header>\n<section class=\\\"page__content\\\"><span>\u5728\u6b64\u9875\u9762\u4e2d\uff0c\u6211\u4eec\u5c06\u8bf4\u660e\u5982\u4f55\u5c06Hudi Spark\u4f5c\u4e1a\u5b58\u50a8\u5230AWS S3\u4e2d\u3002<\/span><br \/>\n<span>Hudi-S3\u517c\u5bb9\u6027\u9700\u8981\u4e24\u79cd\u914d\u7f6e\uff1a<\/span><\/p>\n<ul>\n<li><span><span class=\\\"\\\">\u4e3aHudi\u6dfb\u52a0AWS\u51ed\u8bc1<\/span><\/span><\/li>\n<li><span>\u5c06\u6240\u9700\u7684Jar\u6dfb\u52a0\u5230\u5bf9\u5e94\u7684\u7c7b\u8def\u5f84\u4e0b<\/span><\/li>\n<\/ul>\n<h5 id=\\\"aws-credentials\\\"><span>AWS\u51ed\u8bc1<\/span><\/h5>\n<p>\u5c06Hudi\u4e0eS3\u4e00\u8d77\u4f7f\u7528\u7684\u6700\u7b80\u5355\u65b9\u6cd5\u662f\u914d\u7f6e\u60a8\u7684\u51ed\u636eSparkSession\u6216SparkContext\u4f7f\u7528S3\u51ed\u636e\u3002Hudi\u4f1a\u81ea\u52a8\u63a5\u542c\u5e76\u4e0eS3\u901a\u8bdd\u3002<br \/>\n\u6216\u5c06\u5fc5\u9700\u7684\u914d\u7f6e\u6dfb\u52a0\u5230\u60a8\u7684core-site.xml\u4e2d\uff0cHudi\u53ef\u4ece\u4e2d\u83b7\u53d6\u5b83\u4eec\u3002\u5c06fs.defaultFSS3\u5b58\u50a8\u6876\u540d\u79f0\u66ff\u6362\u4e3a\uff0cHudi\u5e94\u8be5\u80fd\u591f\u4ece\u5b58\u50a8\u6876\u4e2d\u8fdb\u884c\u8bfb\u53d6\/\u5199\u5165\u3002<\/p>\n<div>\n<div>\n<pre>  &lt;property&gt;\n      &lt;name&gt;fs.defaultFS&lt;\/name&gt;\n      &lt;value&gt;s3:\/\/ysharma&lt;\/value&gt;\n  &lt;\/property&gt;\n  &lt;property&gt;\n      &lt;name&gt;fs.s3.impl&lt;\/name&gt;\n      &lt;value&gt;org.apache.hadoop.fs.s3native.NativeS3FileSystem&lt;\/value&gt;\n  &lt;\/property&gt;\n  &lt;property&gt;\n      &lt;name&gt;fs.s3.awsAccessKeyId&lt;\/name&gt;\n      &lt;value&gt;AWS_KEY&lt;\/value&gt;\n  &lt;\/property&gt;\n  &lt;property&gt;\n       &lt;name&gt;fs.s3.awsSecretAccessKey&lt;\/name&gt;\n       &lt;value&gt;AWS_SECRET&lt;\/value&gt;\n  &lt;\/property&gt;\n  &lt;property&gt;\n       &lt;name&gt;fs.s3n.awsAccessKeyId&lt;\/name&gt;\n       &lt;value&gt;AWS_KEY&lt;\/value&gt;\n  &lt;\/property&gt;\n  &lt;property&gt;\n       &lt;name&gt;fs.s3n.awsSecretAccessKey&lt;\/name&gt;\n       &lt;value&gt;AWS_SECRET&lt;\/value&gt;\n  &lt;\/property&gt;\n<\/pre>\n<\/div>\n<\/div>\n<p>\u8bf8\u5982hudi-cli\u6216deltastreamer\u5de5\u5177\u4e4b\u7c7b\u7684\u5b9e\u7528\u7a0b\u5e8f\u53ef\u4ee5\u901a\u8fc7\u4ee5\u5f00\u5934\u7684\u73af\u5883\u53d8\u91cf\u6765\u83b7\u53d6s3\u51ed\u636eHOODIE_ENV_\u3002\u4f8b\u5982\uff0c\u4e0b\u9762\u662f\u4e00\u4e2abash\u7247\u6bb5\uff0c\u7528\u4e8e\u8bbe\u7f6e\u6b64\u7c7b\u53d8\u91cf\uff0c\u7136\u540e\u4f7f\u5176\u80fd\u591f\u5904\u7406s3\u4e2d\u5b58\u50a8\u7684\u6570\u636e\u96c6\u3002<\/p>\n<div>\n<div>\n<pre>export HOODIE_ENV_fs_DOT_s3a_DOT_access_DOT_key=$accessKey\nexport HOODIE_ENV_fs_DOT_s3a_DOT_secret_DOT_key=$secretKey\nexport HOODIE_ENV_fs_DOT_s3_DOT_awsAccessKeyId=$accessKey\nexport HOODIE_ENV_fs_DOT_s3_DOT_awsSecretAccessKey=$secretKey\nexport HOODIE_ENV_fs_DOT_s3n_DOT_awsAccessKeyId=$accessKey\nexport HOODIE_ENV_fs_DOT_s3n_DOT_awsSecretAccessKey=$secretKey\nexport HOODIE_ENV_fs_DOT_s3n_DOT_impl=org.apache.hadoop.fs.s3a.S3AFileSystem\n<\/pre>\n<\/div>\n<\/div>\n<h5 id=\\\"aws-libs\\\"><span>AWS\u5e93<\/span><\/h5>\n<p><span>AWS hadoop\u5e93\u6dfb\u52a0\u5230\u6211\u4eec\u7684\u7c7b\u8def\u5f84<\/span><\/p>\n<ul>\n<li><span>com.amazonaws\uff1aaws-java-sdk\uff1a1.10.34<\/span><\/li>\n<li><span>org.apache.hadoop\uff1ahadoop-aws\uff1a2.7.3<\/span><\/li>\n<\/ul>\n<p><span>\u5982\u679c\u4f7f\u7528AWS Glue \u6570\u636e \uff0c\u5219\u9700\u914d\u7f6e\u3002<\/span><\/p>\n<ul>\n<li><span>com.amazonaws.glue\uff1aaws-glue-datacatalog-hive2-client\uff1a1.11.0<\/span><\/li>\n<li><span>com.amazonaws\uff1aaws-java-sdk-glue\uff1a1.11.475<\/span><\/li>\n<\/ul>\n<\/section>\n<h3><\/h3>\n<h3>Google Cloud Storage<\/h3>\n<p>GCS\u548cHudi\u534f\u540c\u5de5\u4f5c\u6240\u9700\u7684\u914d\u7f6e\u3002<span style=\\\"font-size: 16px;\\\">\u5bf9\u4e8eGCS\u4e0a\u7684Hudi\u5b58\u50a8\uff0c<\/span><span style=\\\"font-size: 16px;\\\">\u533a\u57df<\/span><span style=\\\"font-size: 16px;\\\">\u5b58\u50a8\u6876\u63d0\u4f9b\u4e86\u5177\u6709\u9ad8\u5ea6\u4e00\u81f4\u6027\u7684DFS API\u3002<\/span><\/p>\n<section>\n<h2 id=\\\"gcs-configs\\\">GCS\u914d\u7f6e<\/h2>\n<p>Hudi GCS\u517c\u5bb9\u6027\u9700\u8981\u4e24\u79cd\u914d\u7f6e\uff1a<\/p>\n<ul>\n<li>\u4e3aHudi\u6dfb\u52a0GCS\u51ed\u636e<\/li>\n<li>\u5c06\u6240\u9700\u7684jar\u6dfb\u52a0\u5230\u7c7b\u8def\u5f84\u4e0b<\/li>\n<\/ul>\n<h3 id=\\\"gcs-credentials\\\">GCS\u51ed\u8bc1<\/h3>\n<p>\u5728Hudi\u53ef\u4ee5\u4ece\u4e2d\u83b7\u53d6\u6240\u9700\u914d\u7f6e\u7684core-site.xml\u4e2d\u6dfb\u52a0\u6240\u9700\u914d\u7f6e\u3002fs.defaultFS\u7528\u60a8\u7684GCS\u5b58\u50a8\u6876\u540d\u79f0\u66ff\u6362\uff0cHudi\u5e94\u8be5\u80fd\u591f\u4ece\u5b58\u50a8\u6876\u4e2d\u8fdb\u884c\u8bfb\u53d6\/\u5199\u5165\u3002<\/p>\n<div>\n<div>\n<pre>  &lt;property&gt;\n    &lt;name&gt;fs.defaultFS&lt;\/name&gt;\n    &lt;value&gt;gs:\/\/hudi-bucket&lt;\/value&gt;\n  &lt;\/property&gt;\n  &lt;property&gt;\n    &lt;name&gt;fs.gs.impl&lt;\/name&gt;\n    &lt;value&gt;com.google.cloud.hadoop.fs.gcs.GoogleHadoopFileSystem&lt;\/value&gt;\n    &lt;description&gt;The FileSystem for gs: (GCS) uris.&lt;\/description&gt;\n  &lt;\/property&gt;\n  &lt;property&gt;\n    &lt;name&gt;fs.AbstractFileSystem.gs.impl&lt;\/name&gt;\n    &lt;value&gt;com.google.cloud.hadoop.fs.gcs.GoogleHadoopFS&lt;\/value&gt;\n    &lt;description&gt;The AbstractFileSystem for gs: (GCS) uris.&lt;\/description&gt;\n  &lt;\/property&gt;\n  &lt;property&gt;\n    &lt;name&gt;fs.gs.project.id&lt;\/name&gt;\n    &lt;value&gt;GCS_PROJECT_ID&lt;\/value&gt;\n  &lt;\/property&gt;\n  &lt;property&gt;\n    &lt;name&gt;google.cloud.auth.service.account.enable&lt;\/name&gt;\n    &lt;value&gt;true&lt;\/value&gt;\n  &lt;\/property&gt;\n  &lt;property&gt;\n    &lt;name&gt;google.cloud.auth.service.account.email&lt;\/name&gt;\n    &lt;value&gt;GCS_SERVICE_ACCOUNT_EMAIL&lt;\/value&gt;\n  &lt;\/property&gt;\n  &lt;property&gt;\n    &lt;name&gt;google.cloud.auth.service.account.keyfile&lt;\/name&gt;\n    &lt;value&gt;GCS_SERVICE_ACCOUNT_KEYFILE&lt;\/value&gt;\n  &lt;\/property&gt;\n<\/pre>\n<\/div>\n<\/div>\n<h3 id=\\\"gcs-libs\\\">GCS\u5e93<\/h3>\n<p>GCS hadoop\u5e93\u6dfb\u52a0\u5230\u6211\u4eec\u7684\u7c7b\u8def\u5f84\u4e2d<\/p>\n<ul>\n<li>com.google.cloud.bigdataoss\uff1agcs-connector\uff1a1.6.0-hadoop2<\/li>\n<\/ul>\n<\/section>\n<p>&nbsp;<\/p>\n<h3>Microsoft Azure<\/h3>\n<p>Azure\u548cHudi\u534f\u540c\u5de5\u4f5c\u6240\u9700\u7684\u914d\u7f6e\u3002\u652f\u6301\u7684\u5b58\u50a8\u7cfb\u7edf\u3002<br \/>\n\u6709\u4e24\u4e2a\u652f\u6301Hudi\u7684\u5b58\u50a8\u7cfb\u7edf\u3002<\/p>\n<ul>\n<li>Azure Blob\u5b58\u50a8<\/li>\n<li>\u7b2c2\u4ee3Azure Data Lake<\/li>\n<\/ul>\n<p id=\\\"verified-combination-of-spark-and-storage-system\\\">\u5df2\u9a8c\u8bc1Spark\u548c\u5b58\u50a8\u7cfb\u7edf\u7684\u7ec4\u5408\uff0cAzure Data Lake Storage Gen 2\u4e0a\u7684HDInsight Spark2.4\uff0c\u6b64\u7ec4\u5408\u5f00\u7bb1\u5373\u7528\u3002\u65e0\u9700\u989d\u5916\u7684\u914d\u7f6e\u3002<\/p>\n<p id=\\\"databricks-spark24-on-azure-data-lake-storage-gen-2\\\">\n<ul>\n<li>\u5c06Hudi jar\u5bfc\u5165databricks\u5de5\u4f5c\u533a<\/li>\n<li>\u5c06\u6587\u4ef6\u7cfb\u7edf\u6302\u8f7d\u5230dbutils\u3002\n<div>\n<div>\n<pre>dbutils.fs.mount(\n  source = \\\"abfss:\/\/xxx@xxx.dfs.core.windows.net\\\",\n  mountPoint = \\\"\/mountpoint\\\",\n  extraConfigs = configs)\n<\/pre>\n<\/div>\n<\/div>\n<\/li>\n<li>\u7f16\u5199Hudi\u6570\u636e\u96c6\u65f6\uff0c\u8bf7\u4f7f\u7528abfss URL\n<div>\n<div>\n<pre>inputDF.write\n  .format(\\\"org.apache.hudi\\\")\n  .options(opts)\n  .mode(SaveMode.Append)\n  .save(\\\"abfss:\/\/&lt;&lt;storage-account&gt;&gt;.dfs.core.windows.net\/hudi-tables\/customer\\\")\n<\/pre>\n<\/div>\n<\/div>\n<\/li>\n<li>\u8bfb\u53d6Hudi\u6570\u636e\u96c6\u65f6\uff0c\u8bf7\u4f7f\u7528\u5b89\u88c5\u70b9\n<div>\n<div>\n<pre>spark.read\n  .format(\\\"org.apache.hudi\\\")\n  .load(\\\"\/mountpoint\/hudi-tables\/customer\\\")<\/pre>\n<\/div>\n<\/div>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h3 id=\\\"aliyun-oss-\u90e8\u7f72\\\">Aliyun OSS \u90e8\u7f72<i class=\\\"fa fa-link\\\"><\/i><\/h3>\n<p>\u4e3a\u4e86\u8ba9Hudi\u4f7f\u7528OSS\uff0c\u9700\u8981\u589e\u52a0\u4e24\u90e8\u5206\u7684\u914d\u7f6e:<\/p>\n<ul>\n<li>\u4e3aHidi\u589e\u52a0Aliyun OSS\u7684\u76f8\u5173\u914d\u7f6e<\/li>\n<li>\u589e\u52a0Jar\u5305\u7684MVN\u4f9d\u8d56<\/li>\n<\/ul>\n<h5 id=\\\"aliyun-oss-\u76f8\u5173\u7684\u914d\u7f6e\\\">Aliyun OSS \u76f8\u5173\u7684\u914d\u7f6e<\/h5>\n<p>\u65b0\u589e\u4e0b\u9762\u7684\u914d\u7f6e\u5230\u4f60\u7684Hudi\u80fd\u8bbf\u95ee\u7684core-site.xml\u6587\u4ef6\u3002\u4f7f\u7528\u4f60\u7684OSS bucket name\u66ff\u6362\u6389fs.defaultFS\uff0c\u4f7f\u7528OSS endpoint\u5730\u5740\u66ff\u6362fs.oss.endpoint\uff0c\u4f7f\u7528OSS\u7684key\u548csecret\u5206\u522b\u66ff\u6362fs.oss.accessKeyId\u548cfs.oss.accessKeySecret\u3002\u4e3b\u8981Hudi\u5c31\u80fd\u8bfb\u5199\u76f8\u5e94\u7684bucket\u3002<\/p>\n<div>\n<div>\n<pre>    &lt;property&gt;\n        &lt;name&gt;fs.defaultFS&lt;\/name&gt;\n        &lt;value&gt;oss:\/\/bucketname\/&lt;\/value&gt;\n    &lt;\/property&gt;\n    &lt;property&gt;\n      &lt;name&gt;fs.oss.endpoint&lt;\/name&gt;\n      &lt;value&gt;oss-endpoint-address&lt;\/value&gt;\n      &lt;description&gt;Aliyun OSS endpoint to connect to.&lt;\/description&gt;\n    &lt;\/property&gt;\n    &lt;property&gt;\n      &lt;name&gt;fs.oss.accessKeyId&lt;\/name&gt;\n      &lt;value&gt;oss_key&lt;\/value&gt;\n      &lt;description&gt;Aliyun access key ID&lt;\/description&gt;\n    &lt;\/property&gt;\n    &lt;property&gt;\n      &lt;name&gt;fs.oss.accessKeySecret&lt;\/name&gt;\n      &lt;value&gt;oss-secret&lt;\/value&gt;\n      &lt;description&gt;Aliyun access key secret&lt;\/description&gt;\n    &lt;\/property&gt;\n    &lt;property&gt;\n      &lt;name&gt;fs.oss.impl&lt;\/name&gt;\n      &lt;value&gt;org.apache.hadoop.fs.aliyun.oss.AliyunOSSFileSystem&lt;\/value&gt;\n    &lt;\/property&gt;\n<\/pre>\n<\/div>\n<\/div>\n<h5 id=\\\"aliyun-oss-libs\\\">Aliyun OSS Libs<\/h5>\n<p>\u65b0\u589eAliyun hadoop\u7684jar\u5305\u7684MVN\u4f9d\u8d56\u5230pom.xml\u6587\u4ef6\u3002\u7531\u4e8ehadoop-aliyun\u4f9d\u8d56hadoop 2.9.1+\uff0c\u56e0\u6b64\u4f60\u9700\u8981\u4f7f\u7528hadoop 2.9.1\u6216\u66f4\u65b0\u7684\u7248\u672c\u3002<\/p>\n<div>\n<div>\n<pre>&lt;dependency&gt;\n    &lt;groupId&gt;org.apache.hadoop&lt;\/groupId&gt;\n    &lt;artifactId&gt;hadoop-aliyun&lt;\/artifactId&gt;\n    &lt;version&gt;3.2.1&lt;\/version&gt;\n&lt;\/dependency&gt;\n&lt;dependency&gt;\n    &lt;groupId&gt;com.aliyun.oss&lt;\/groupId&gt;\n    &lt;artifactId&gt;aliyun-sdk-oss&lt;\/artifactId&gt;\n    &lt;version&gt;3.8.1&lt;\/version&gt;\n&lt;\/dependency&gt;\n&lt;dependency&gt;\n    &lt;groupId&gt;org.jdom&lt;\/groupId&gt;\n    &lt;artifactId&gt;jdom&lt;\/artifactId&gt;\n    &lt;version&gt;1.1&lt;\/version&gt;\n&lt;\/dependency&gt;<\/pre>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>\u65e0\u8bba\u4f7f\u7528RDD\/WriteClient API\u8fd8\u662f\u6570\u636e\u6e90\uff0c\u8bf7\u53c2\u8003\u4ee5\u4e0b\u4e91\u5b58\u50a8\u5e73\u53f0\u914d\u7f6e\u5bf9\u4e91\u5b58\u50a8\u7684\u8bbf\u95ee\u3002 S3\u6587\u4ef6\u7cfb &hellip;<\/p>\n<p class=\"read-more\"> <a class=\"\" href=\"http:\/\/www.weijing.co\/?p=1447\"> <span class=\"screen-reader-text\">Hudi\u914d\u7f6e\u8fde\u63a5\u4e91\u5e73\u53f0\u5b58\u50a8\u7cfb\u7edf<\/span> \u67e5\u770b\u5168\u6587 &raquo;<\/a><\/p>\n","protected":false},"author":4,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"default","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"default","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":""},"categories":[116],"tags":[],"uagb_featured_image_src":{"full":false,"thumbnail":false,"medium":false,"medium_large":false,"large":false,"1536x1536":false,"2048x2048":false,"mailpoet_newsletter_max":false,"woocommerce_thumbnail":false,"woocommerce_single":false,"woocommerce_gallery_thumbnail":false,"shop_catalog":false,"shop_single":false,"shop_thumbnail":false},"uagb_author_info":{"display_name":"weijing","author_link":"http:\/\/www.weijing.co\/?author=4"},"uagb_comment_info":0,"uagb_excerpt":"\u65e0\u8bba\u4f7f\u7528RDD\/WriteClient API\u8fd8\u662f\u6570\u636e\u6e90\uff0c\u8bf7\u53c2\u8003\u4ee5\u4e0b\u4e91\u5b58\u50a8\u5e73\u53f0\u914d\u7f6e\u5bf9\u4e91\u5b58\u50a8\u7684\u8bbf\u95ee\u3002 S3\u6587\u4ef6\u7cfb&hellip;","_links":{"self":[{"href":"http:\/\/www.weijing.co\/index.php?rest_route=\/wp\/v2\/posts\/1447"}],"collection":[{"href":"http:\/\/www.weijing.co\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.weijing.co\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.weijing.co\/index.php?rest_route=\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"http:\/\/www.weijing.co\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1447"}],"version-history":[{"count":0,"href":"http:\/\/www.weijing.co\/index.php?rest_route=\/wp\/v2\/posts\/1447\/revisions"}],"wp:attachment":[{"href":"http:\/\/www.weijing.co\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1447"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.weijing.co\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1447"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.weijing.co\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1447"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}