{"id":1024,"date":"2019-01-30T19:05:20","date_gmt":"2019-01-30T11:05:20","guid":{"rendered":"http:\/\/www.rain1024.com\/?p=1024"},"modified":"2023-08-07T20:57:25","modified_gmt":"2023-08-07T12:57:25","slug":"article142","status":"publish","type":"post","link":"http:\/\/rain1024.com\/index.php\/2019\/01\/30\/article142\/","title":{"rendered":"Kafka connect\u5feb\u901f\u6784\u5efa\u6570\u636eETL\u901a\u9053"},"content":{"rendered":"

\u4e00.\u80cc\u666f\u4ecb\u7ecd<\/strong><\/span><\/p>\n

Kafka connect\u662fConfluent\u516c\u53f8(\u5f53\u65f6\u5f00\u53d1\u51faApache Kafka\u7684\u6838\u5fc3\u56e2\u961f\u6210\u5458\u51fa\u6765\u521b\u7acb\u7684\u65b0\u516c\u53f8)\u5f00\u53d1\u7684confluent platform\u7684\u6838\u5fc3\u529f\u80fd.<\/p>\n

\u5927\u5bb6\u90fd\u77e5\u9053\u73b0\u5728\u6570\u636e\u7684ETL\u8fc7\u7a0b\u7ecf\u5e38\u4f1a\u9009\u62e9kafka\u4f5c\u4e3a\u6d88\u606f\u4e2d\u95f4\u4ef6\u5e94\u7528\u5728\u79bb\u7ebf\u548c\u5b9e\u65f6\u7684\u4f7f\u7528\u573a\u666f\u4e2d,\u800ckafka\u7684\u6570\u636e\u4e0a\u6e38\u548c\u4e0b\u6e38\u4e00\u76f4\u6ca1\u6709\u4e00\u4e2a<\/p>\n

\u65e0\u7f1d\u8854\u63a5\u7684pipeline\u6765\u5b9e\u73b0\u7edf\u4e00,\u6bd4\u5982\u4f1a\u9009\u62e9flume\u6216\u8005logstash\u91c7\u96c6\u6570\u636e\u5230kafka,\u7136\u540ekafka\u53c8\u901a\u8fc7\u5176\u4ed6\u65b9\u5f0fpull\u6216\u8005push\u6570\u636e\u5230\u76ee\u6807\u5b58\u50a8.<\/p>\n

\u800ckafka connect\u65e8\u5728\u56f4\u7ed5kafka\u6784\u5efa\u4e00\u4e2a\u53ef\u4f38\u7f29\u7684\uff0c\u53ef\u9760\u7684\u6570\u636e\u6d41\u901a\u9053\uff0c\u901a\u8fc7kafka connect\u53ef\u4ee5\u5feb\u901f\u5b9e\u73b0\u5927\u91cf\u6570\u636e\u8fdb\u51fakafka\u4ece\u800c\u548c\u5176<\/p>\n

\u4ed6\u6e90\u6570\u636e\u6e90\u6216\u8005\u76ee\u6807\u6570\u636e\u6e90\u8fdb\u884c\u4ea4\u4e92\u6784\u9020\u4e00\u4e2a\u4f4e\u5ef6\u8fdf\u7684\u6570\u636epipeline.\u7ed9\u4e2a\u56fe\u66f4\u76f4\u89c2\u70b9\uff0c\u5927\u5bb6\u611f\u53d7\u4e0b.<\/p>\n

\"0\"<\/a><\/p>\n

\u4e8c.Kafka-connect\u5feb\u901f\u914d\u7f6e<\/strong><\/span><\/p>\n

\u8fd9\u91ccConfluent\u5b98\u65b9\u5f88\u8d34\u5fc3\u7684\u63d0\u4f9b\u4e86\u4e00\u4e2a\u96c6\u6210\u7684\u955c\u50cf\u4ee5\u4fbfquickstart,\u5982\u4e0b\u94fe\u63a5<\/p>\n

https:\/\/s3-us-west-2.amazonaws.com\/confluent-files\/kafka_connect_blog.ova<\/a><\/p>\n

\u8fd9\u662f\u5b58\u50a8\u5728Amazon S3\u4e0a\u7684\uff0c\u76f4\u63a5\u70b9\u51fb\u5373\u53ef\u4e0b\u8f7d.\u8fd9\u91cc\u6211\u4f7f\u7528VMWare\u76f4\u63a5\u6253\u5f00,\u521a\u5f00\u59cb\u4f1a\u63d0\u793a\u4e00\u4e2a\u9519\u8bef\uff0c\u4e0d\u7528\u7ba1\u5b83\u76f4\u63a5\u70b9\u51fb\u91cd\u8bd5\u5373\u53ef<\/p>\n

\u7cfb\u7edf\u52a0\u8f7d\u7684\u8fc7\u7a0b\u4e2d\u4f1a\u9ed8\u8ba4\u521d\u59cb\u5316\u865a\u62df\u673a\u7684\u7f51\u7edc\u914d\u7f6e\uff0c\u8fd9\u91cc\u6211\u5efa\u8bae\u63d0\u524d\u8bbe\u7f6e\u597d\u6865\u63a5\u7f51\u7edc\uff0c\u8ba9\u8be5\u865a\u62df\u673a\u4f7f\u7528\u6865\u63a5\u7f51\u7edc\u521d\u59cb\u5316.<\/p>\n

\u52a0\u8f7d\u6210\u529f\u540e\uff0c\u767b\u5f55\u8fdb\u5165\u8be5Ubuntu\u7cfb\u7edf,\u9ed8\u8ba4\u7684\u7528\u6237\u540d\u548c\u5bc6\u7801\u90fd\u662f:vagrant.<\/p>\n

\u7136\u540els\u67e5\u770bvagrant\u7528\u6237\u76ee\u5f55\uff0c\u67e5\u770b\u51e0\u4e2a\u5173\u952e\u7684\u811a\u672c\u5185\u5bb9\u540e,\u6211\u5206\u522b\u4ecb\u7ecd\u5b83\u4eec\u7684\u529f\u80fd<\/p>\n

1>setup.sh:\u81ea\u52a8\u4e0b\u8f7dmysql,mysql jdbc driver,\u914d\u7f6e\u597dmysql\u4ee5\u53ca\u505a\u4e3ahive\u7684metastore<\/p>\n

2>start.sh:\u542f\u52a8confluent platform,kafka,hadoop,hive\u76f8\u5173\u670d\u52a1<\/p>\n

3>clean_up.sh:\u548cstart.sh\u76f8\u53cd\u7684\uff0c\u4f1a\u5173\u95ed\u6389\u6240\u6709\u7684\u670d\u52a1\uff0c\u800c\u4e14\u8fd8\u4f1a\u5220\u9664\u6389\u6240\u6709\u7684\u6570\u636e(\u4f8b\u5982hdfs namenode\u548c datanode\u7684\u6570\u636e\uff0c\u5176\u5b9e\u76f8\u5f53\u4e8efs format\u4e86)<\/p>\n

\u90a3\u4e48\u5f88\u660e\u663e\uff0c\u7b2c\u4e00\u6b65\u80af\u5b9a\u662f\u6267\u884csetup.sh,\u8fd9\u91cc\u6267\u884c\u540e\u4f1a\u62a5\u9519\u5982\u4e0b<\/p>\n

\"setupFailed\"<\/a><\/p>\n

\u8fd9\u91cc\u65e0\u6cd5\u4e0b\u8f7d\u76f8\u5173\u7684\u8f6f\u4ef6\u5305\uff0c\u597d\u5427\uff0c\u90a3\u4e48\u6211\u4eec\u9700\u8981\u66f4\u65b0\u4e00\u4e0b\u4e0b\u8f7d\u6e90\u7684\u7d22\u5f15\uff0c\u6267\u884c\u5982\u4e0b\u547d\u4ee4<\/p>\n

sudo apt-get update<\/p>\n

\u66f4\u65b0\u5b8c\u6bd5\u540e\u518d\u6b21\u6267\u884csetup.sh\u5b89\u88c5\u597dmysql,hive\u7b49\u670d\u52a1<\/p>\n

\u7d27\u63a5\u7740\u6267\u884cstart.sh\u6765\u542f\u52a8\u4e0a\u8ff0\u670d\u52a1\uff0c\u542f\u52a8\u540e\u5e94\u8be5\u6709\u5982\u4e0b\u8fdb\u7a0b\uff0c\u8fd9\u662f\u4e00\u4e2a\u4f2a\u5206\u5e03\u5f0f\u8282\u70b9<\/p>\n

\"jpsService\"<\/a><\/p>\n

\u5bf9\u4e86\uff0c\u865a\u62df\u673a\u5404\u4e2a\u670d\u52a1(\u4f8b\u5982hive,zookeeper\u7b49),\u914d\u7f6e\u6587\u4ef6\u548c\u65e5\u5fd7\u6587\u4ef6\u5728\u8def\u5f84\/mnt\/\u4e0b,\u7ec4\u4ef6\u7684\u5b89\u88c5\u4f4d\u7f6e\u4f4d\u4e8e\/opt\u4e0b<\/p>\n

\u4e09.Kafka connect\u5feb\u901f\u4f7f\u7528<\/strong><\/span><\/p>\n

\u914d\u7f6e\u5b8c\u4ee5\u540e\u5c31\u53ef\u4ee5\u51c6\u5907\u4f7f\u7528kafka-connect\u6765\u5feb\u901f\u6784\u5efa\u4e00\u4e2a\u6570\u636epipeline\u4e86\uff0c\u5982\u4e0b\u56fe\u6240\u793a<\/p>\n

\"wholePic\"<\/a><\/p>\n

\u6574\u4e2a\u8fc7\u7a0b\u662f\u5c06\u6570\u636e\u4ee5mysql\u4f5c\u4e3a\u6570\u636e\u6e90\uff0c\u5c06\u6570\u636e\u901a\u8fc7kafka connect\u5feb\u901fETL\u5230hive\u4e2d\u53bb.\u6ce8\u610f\u8fd9\u91cc\u56fe\u4e2d\u6ca1\u753bkafka<\/p>\n

\u4f46\u662f\u5b9e\u9645\u4e0a\u662f\u5305\u542b\u5728kafka connect\u91cc\u9762\u7684,\u8bdd\u4e0d\u591a\u8bf4\uff0c\u5f00\u59cb\u4f7f\u7528<\/p>\n

1>Mysql\u6570\u636e\u51c6\u5907<\/span><\/p>\n

\u6267\u884c\u5982\u4e0b\u547d\u4ee4<\/p>\n

\n
\"\u590d\u5236\u4ee3\u7801\"<\/a><\/span><\/div>\n
$ mysql -u root --password=\"mypassword\"\nmysql> CREATE DATABASE demo;\nmysql> USE demo;\nmysql> CREATE TABLE users (\n    ->   id serial NOT NULL PRIMARY KEY,\n    ->   name varchar(100),\n    ->   email varchar(200),\n    ->   department varchar(200),\n    ->   modified timestamp default CURRENT_TIMESTAMP NOT NULL,\n    ->   INDEX `modified_index` (`modified`)\n    -> );\nmysql> INSERT INTO users (name, email, department) VALUES ('alice', 'alice@abc.com', 'engineering');\nmysql> INSERT INTO users (name, email, department) VALUES ('bob', 'bob@abc.com', 'sales');\nmysql> exit;<\/pre>\n
\"\u590d\u5236\u4ee3\u7801\"<\/a><\/span><\/div>\n<\/div>\n
\u6ce8\u610f\u4e0a\u9762\u7b2c\u4e00\u884c\uff0c--password=\"mypassword\"\u00a0,\u5bf9\uff0c\u4f60\u6ca1\u770b\u9519\uff0c\u8fd9\u91cc\u865a\u62df\u673amysql\u7684root\u9ed8\u8ba4\u5bc6\u7801\u5c31\u662fmypassword,<\/p>\n
\u5f3a\u8feb\u75c7\u60a3\u8005\u8bf7\u81ea\u884c\u66f4\u6539.\u968f\u540e\u5efa\u5e93\uff0c\u5efa\u8868\uff0c\u63d2\u5165\u6570\u636e.<\/p>\n
2>\u5173\u952e\u6982\u5ff5\u51c6\u5907<\/span><\/p>\n
\u8fd9\u91cc\u6211\u5feb\u901f\u666e\u53ca\u4e00\u4e0b\u53c2\u8003\u5b98\u65b9\u6587\u6863\u7406\u89e3\u7684\u4e00\u4e9b\u5173\u952e\u6982\u5ff5.<\/span><\/p>\n
kafka connector<\/span>:kafka connector\u662fkafka connect\u7684\u5173\u952e\u7ec4\u6210\u90e8\u5206\uff0c\u5b83\u662f\u4e00\u4e2a\u903b\u8f91\u4e0a\u7684job,\u7528\u4e8e\u5728kafka\u548c\u5176\u4ed6\u7cfb\u7edf\u4e4b\u95f4\u62f7\u8d1d\u6570\u636e,\u6bd4\u5982<\/p>\n
\u4ece\u4e0a\u6e38\u7cfb\u7edf\u62f7\u8d1d\u6570\u636e\u5230kafka,\u6216\u8005\u4ecekafka\u62f7\u8d1d\u6570\u636e\u5230\u4e0b\u6e38\u7cfb\u7edf<\/p>\n
Tasks<\/span>:\u6bcf\u4e2akafka connector\u53ef\u4ee5\u521d\u59cb\u5316\u4e00\u7ec4task\u8fdb\u884c\u6570\u636e\u7684\u62f7\u8d1d<\/p>\n
Workers<\/span>:\u903b\u8f91\u4e0a\u5305\u542bkafka connector\u548ctasks\u7528\u6765\u8c03\u5ea6\u6267\u884c\u5177\u4f53\u4efb\u52a1\u7684\u8fdb\u7a0b,\u5177\u4f53\u6267\u884c\u65f6\u5206\u4e3astandalone\u6a21\u5f0f\u548cdistributed\u6a21\u5f0f<\/p>\n
\u89c1\u4e0b\u56fe\uff0c\u8fd9\u4e2a\u662fkafka\u4e0a\u6e38\u7684\u6570\u636estream\u8fc7\u6765\u540e\uff0c\u5b9a\u4e49\u597d\u5bf9\u5e94\u7684kafka connector\u540e\uff0c\u5206\u89e3\u4e3a\u4e00\u7ec4tasks\u7136\u540epush\u6570\u636e\u5230kafka\u7684\u4e0d\u540ctopic<\/p>\n
\"kafkaConnectors\"<\/a><\/p>\n
3>\u5229\u7528Kafka-connect\u6444\u53d6\u6570\u636e<\/span><\/p>\n
\u4e3b\u8981\u662f\u901a\u8fc7\u914d\u7f6e\u6765\u5b9e\u73b0\u4ecemysql\u6444\u53d6\u6570\u636e\u5230kafka,\u7136\u540e\u6309\u7167topic\u6765\u83b7\u53d6\u6570\u636e\u5199\u5165hdfs,\u547d\u4ee4\u5982\u4e0b<\/p>\n
\n
connect-standalone \/mnt\/etc\/connect-avro-standalone.properties \\\n \/mnt\/etc\/mysql.properties \/mnt\/etc\/hdfs.properties &<\/pre>\n<\/div>\n
\u6ce8\u610f\u4e0a\u9762\u8fd9\u4e9bproperties\u6587\u4ef6\u662f\u865a\u62df\u673a\u5df2\u7ecf\u4e8b\u5148\u914d\u7f6e\u597d\u7684\uff0c\u53ef\u4ee5\u76f4\u63a5\u6267\u884c\u5b9e\u73b0\u6570\u636e\u7684\u6444\u53d6<\/p>\n
\u5f53\u524d\u4f7f\u7528\u7684kafka connect\u7684standalone\u6a21\u5f0f\uff0c\u5f53\u7136\u8fd8\u6709distributed\u6a21\u5f0f\u540e\u7eed\u53ef\u4ee5\u5c1d\u8bd5<\/p>\n
\u4e0a\u9762\u7684\u90a3\u6761\u547d\u4ee4\u7684\u683c\u5f0f\u662f\u8fd9\u6837:<\/p>\n
connect-standalone worker.properties connector1.properties [connector2.properties connector3.properties ...]<\/span><\/pre>\n
\u4e3b\u8981\u89e3\u91ca\u4e00\u4e0bconnect-standalone\u540e\u9762\u7684\u53c2\u6570<\/p>\n
worker.properties:\u5c31\u662f\u4e0a\u9762\u63d0\u5230\u8fc7\u7684worker\u8fdb\u7a0b\u7684\u914d\u7f6e\u6587\u4ef6,\u53ef\u4ee5\u5b9a\u4e49kafka cluster\u7684\u76f8\u5173\u4fe1\u606f\u4ee5\u53ca\u6570\u636e\u5e8f\u5217\u5316\u7684\u683c\u5f0f.<\/p>\n
\u968f\u540e\u7684\u4e00\u4e9b\u53c2\u6570\u5c31\u662fkafka connector\u7684\u914d\u7f6e\u53c2\u6570\u4e86,\u6bd4\u5982\u4e0a\u9762\u7684mysql.properties\u5b9a\u4e49\u4e86\u4e00\u4e2akafka jdbc connector,\u7528\u6765\u540c\u6b65mysql\u6570\u636e\u5230kafka<\/p>\n
\u6700\u540e\u4e00\u4e2ahdfs.properties\u662fkafka hdfs connector\u7684\u914d\u7f6e\u6587\u4ef6,\u7528\u6765\u6d88\u8d39kafka topic\u6570\u636epush\u5230hdfs.<\/p>\n
\u90a3\u4e48\u6267\u884c\u8fd9\u6761\u547d\u4ee4\u540e\u5c31\u53ef\u4ee5\u5c06mysql\u7684\u6570\u636e\u901a\u8fc7kafka connect\u5feb\u901fETL\u5230hdfs\u4e86.<\/p>\n
\u6700\u540e\u53ef\u4ee5\u901a\u8fc7hive\u521b\u5efa\u5916\u8868\u6620\u5c04hdfs\u4e0a\u7684\u6570\u636e\u6587\u4ef6,\u7136\u540e\u5728hive\u4e2d\u67e5\u770b\u5bf9\u5e94\u6570\u636e,\u5982\u4e0b<\/p>\n
\n
\"\u590d\u5236\u4ee3\u7801\"<\/a><\/span><\/div>\n
$ hive\nhive> SHOW TABLES;\nOK\ntest_jdbc_users\nhive> SELECT * FROM test_jdbc_users;\nOK\n1 alice alice@abc.com engineering 1450305345000\n2 bob   bob@abc.com   sales       1450305346000<\/pre>\n
\"\u590d\u5236\u4ee3\u7801\"<\/a><\/span><\/div>\n<\/div>\n
\u56db.Kafka connect\u4f7f\u7528\u603b\u7ed3<\/strong><\/span><\/p>\n
1>Kafka connect\u7684\u4f7f\u7528\u5176\u5b9e\u5c31\u662f\u914d\u7f6e\u4e0d\u540c\u7684kafka connectors,\u8fd9\u91cc\u5927\u5bb6\u53ef\u4ee5\u628akafka\u4f5c\u4e3a\u4e2d\u95f4\u7ec4\u4ef6\uff0c\u7136\u540e\u53ef\u4ee5\u7c7b\u6bd4flume\u7406\u89e3,kafka\u4e0a\u6e38\u7684<\/p>\n
connector\u5176\u5b9e\u5c31\u662ffllume\u7684source\u4ece\u4e0a\u6e38\u6570\u636e\u6e90sink\u5230kafka,kafka\u7684\u4e0b\u6e38connector\u5176\u5b9e\u5c31\u662fflume\u7684source\u662fkafka,sink\u5230\u4e0b\u6e38\u7cfb\u7edf.<\/p>\n
2>Kafka connect\u7684\u6570\u636epipeline\u8981\u6253\u901a\uff0c\u5b83\u8981\u6c42\u6570\u636e\u9075\u5b88confluent\u81ea\u5df1\u7684\u4e00\u5957\u901a\u7528\u7684schema\u673a\u5236\uff0c\u7ec6\u5fc3\u7684\u540c\u5b66\u4f1a\u53d1\u73b0\u4e0a\u9762jps\u540e\u4f1a\u6709\u4e2a\u8fdb\u7a0b\u540d<\/p>\n
SchemaRegistryMain,\u8fd9\u91cc\u5b98\u65b9\u9ed8\u8ba4\u4f7f\u7528Avro\u683c\u5f0f\u8fdb\u51faKafka,\u6240\u4ee5\u8981\u7559\u610fworker.properties\u6587\u4ef6\u7684\u914d\u7f6e\u4fe1\u606f.<\/p>\n
3>\u6211\u5728\u4f7f\u7528\u4e2d\u6ca1\u6709\u53d1\u73b0Flume \u76f8\u5173\u7684connector,\u56e0\u6b64\u5f88\u597d\u5947\u5b83\u5e94\u8be5\u662f\u6ca1\u6709\u5b9e\u73b0\u4e0a\u6e38flume conector\u7684\u5c5e\u6027\u914d\u7f6e\u3002\u95ee\u9898\u5e94\u8be5\u51fa\u5728Flume\u7684\u6570\u636e\u662f\u57fa<\/p>\n
\u4e8eevent\u7684,\u800c\u548c\u4e0a\u97622\u4e2d\u6240\u8bf4\u7684schema\u5b9a\u4e49\u683c\u5f0f\u6ca1\u6709\u5f88\u597d\u7684\u517c\u5bb9.<\/p>\n
4>kafka connect\u7684distributed\u6a21\u5f0f\u5e94\u8be5\u66f4\u5b9e\u7528\uff0c\u968f\u540e\u4f1a\u5c1d\u8bd5\uff0c\u4ee5\u53caconfluent\u6240\u652f\u6301\u7684\u5b9e\u65f6\u5904\u7406\u6d41kafka streams.<\/p>\n","protected":false},"excerpt":{"rendered":"
\u4e00.\u80cc\u666f\u4ecb\u7ecd Kafka connect\u662fConfluent\u516c\u53f8(\u5f53\u65f6\u5f00\u53d1\u51faApache Kafka\u7684\u6838\u5fc3\u56e2\u961f\u2026 Read More »<\/a><\/span><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[7],"tags":[52],"class_list":["post-1024","post","type-post","status-publish","format-standard","hentry","category-kafka-hadoop","tag-kafka"],"_links":{"self":[{"href":"http:\/\/rain1024.com\/index.php\/wp-json\/wp\/v2\/posts\/1024","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/rain1024.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/rain1024.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/rain1024.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/rain1024.com\/index.php\/wp-json\/wp\/v2\/comments?post=1024"}],"version-history":[{"count":1,"href":"http:\/\/rain1024.com\/index.php\/wp-json\/wp\/v2\/posts\/1024\/revisions"}],"predecessor-version":[{"id":1390,"href":"http:\/\/rain1024.com\/index.php\/wp-json\/wp\/v2\/posts\/1024\/revisions\/1390"}],"wp:attachment":[{"href":"http:\/\/rain1024.com\/index.php\/wp-json\/wp\/v2\/media?parent=1024"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/rain1024.com\/index.php\/wp-json\/wp\/v2\/categories?post=1024"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/rain1024.com\/index.php\/wp-json\/wp\/v2\/tags?post=1024"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}