Logstash学习之路(四)使用Logstash将mysql数据导入elasticsearch(单表同步、多表同步、全量同步、增量同步)

一、使用Logstash将mysql数据导入elasticsearch

1、在mysql中准备数据:

mysql> show tables;
+----------------+
| Tables_in_yang |
+----------------+
| im             |
+----------------+
1 row in set (0.00 sec)

mysql> select * from im;
+----+------+
| id | name |
+----+------+
|  2 | MSN  |
|  3 | QQ   |
+----+------+
2 rows in set (0.00 sec)

2、简单实例配置文件准备:

[root@master bin]# cat mysqles.conf 
input {
        stdin {}
        jdbc {
                type => "jdbc"
                jdbc_connection_string => "jdbc:mysql://192.168.200.100:3306/yang?characterEncoding=UTF-8&autoReconnect=true"
                 # 数据库连接账号密码;
                jdbc_user => "root"
                jdbc_password => "010209"
                 # MySQL依赖包路径;
                jdbc_driver_library => "/mnt/mysql-connector-java-5.1.38.jar"
                 # the name of the driver class for mysql
                jdbc_driver_class => "com.mysql.jdbc.Driver"
                statement => "SELECT * FROM `im`"
        }
}
output {
        elasticsearch {
                 # 配置ES集群地址
                hosts => ["192.168.200.100:9200"]
                 # 索引名字,必须小写
                index => "im"
        }
        stdout {
        }
}

3、实例结果:

[root@master bin]# ./logstash -f mysqles.conf

4、更多选项配置如下(单表同步):

input {
    stdin {}
    jdbc {
        type => "jdbc"
         # 数据库连接地址
        jdbc_connection_string => "jdbc:mysql://192.168.1.1:3306/TestDB?characterEncoding=UTF-8&autoReconnect=true""
         # 数据库连接账号密码;
        jdbc_user => "username"
        jdbc_password => "pwd"
         # MySQL依赖包路径;
        jdbc_driver_library => "mysql/mysql-connector-java-5.1.34.jar"
         # the name of the driver class for mysql
        jdbc_driver_class => "com.mysql.jdbc.Driver"
         # 数据库重连尝试次数
        connection_retry_attempts => "3"
         # 判断数据库连接是否可用,默认false不开启
        jdbc_validate_connection => "true"
         # 数据库连接可用校验超时时间,默认3600S
        jdbc_validation_timeout => "3600"
         # 开启分页查询(默认false不开启);
        jdbc_paging_enabled => "true"
         # 单次分页查询条数(默认100000,若字段较多且更新频率较高,建议调低此值);
        jdbc_page_size => "500"
         # statement为查询数据sql,如果sql较复杂,建议配通过statement_filepath配置sql文件的存放路径;
         # sql_last_value为内置的变量,存放上次查询结果中最后一条数据tracking_column的值,此处即为ModifyTime;
         # statement_filepath => "mysql/jdbc.sql"
        statement => "SELECT KeyId,TradeTime,OrderUserName,ModifyTime FROM `DetailTab` WHERE ModifyTime>= :sql_last_value order by ModifyTime asc"
         # 是否将字段名转换为小写,默认true(如果有数据序列化、反序列化需求,建议改为false);
        lowercase_column_names => false
         # Value can be any of: fatal,error,warn,info,debug,默认info;
        sql_log_level => warn
         #
         # 是否记录上次执行结果,true表示会将上次执行结果的tracking_column字段的值保存到last_run_metadata_path指定的文件中;
        record_last_run => true
         # 需要记录查询结果某字段的值时,此字段为true,否则默认tracking_column为timestamp的值;
        use_column_value => true
         # 需要记录的字段,用于增量同步,需是数据库字段
        tracking_column => "ModifyTime"
         # Value can be any of: numeric,timestamp,Default value is "numeric"
        tracking_column_type => timestamp
         # record_last_run上次数据存放位置;
        last_run_metadata_path => "mysql/last_id.txt"
         # 是否清除last_run_metadata_path的记录,需要增量同步时此字段必须为false;
        clean_run => false
         #
         # 同步频率(分 时 天 月 年),默认每分钟同步一次;
        schedule => "* * * * *"
    }
}
filter {
    json {
        source => "message"
        remove_field => ["message"]
    }
    # convert 字段类型转换,将字段TotalMoney数据类型改为float;
    mutate {
        convert => {
            "TotalMoney" => "float"
        }
    }
}
output {
    elasticsearch {
         # 配置ES集群地址
        hosts => ["192.168.1.1:9200", "192.168.1.2:9200", "192.168.1.3:9200"]
         # 索引名字,必须小写
        index => "consumption"
    }
    stdout {
        codec => json_lines
    }
}

5、多表同步:

多表配置和单表配置的区别在于input模块的jdbc模块有几个type,output模块就需对应有几个type;

input {
    stdin {}
    jdbc {
         # 多表同步时,表类型区分,建议命名为“库名_表名”,每个jdbc模块需对应一个type;
        type => "TestDB_DetailTab"
        
         # 其他配置此处省略,参考单表配置
         # ...
         # ...
         # record_last_run上次数据存放位置;
        last_run_metadata_path => "mysql\last_id.txt"
         # 是否清除last_run_metadata_path的记录,需要增量同步时此字段必须为false;
        clean_run => false
         #
         # 同步频率(分 时 天 月 年),默认每分钟同步一次;
        schedule => "* * * * *"
    }
    jdbc {
         # 多表同步时,表类型区分,建议命名为“库名_表名”,每个jdbc模块需对应一个type;
        type => "TestDB_Tab2"
        # 多表同步时,last_run_metadata_path配置的路径应不一致,避免有影响;
         # 其他配置此处省略
         # ...
         # ...
    }
}
 
filter {
    json {
        source => "message"
        remove_field => ["message"]
    }
}
 
output {
    # output模块的type需和jdbc模块的type一致
    if [type] == "TestDB_DetailTab" {
        elasticsearch {
             # host => "192.168.1.1"
             # port => "9200"
             # 配置ES集群地址
            hosts => ["192.168.1.1:9200", "192.168.1.2:9200", "192.168.1.3:9200"]
             # 索引名字,必须小写
            index => "detailtab1"
             # 数据唯一索引(建议使用数据库KeyID)
            document_id => "%{KeyId}"
        }
    }
    if [type] == "TestDB_Tab2" {
        elasticsearch {
            # host => "192.168.1.1"
            # port => "9200"
            # 配置ES集群地址
            hosts => ["192.168.1.1:9200", "192.168.1.2:9200", "192.168.1.3:9200"]
            # 索引名字,必须小写
            index => "detailtab2"
            # 数据唯一索引(建议使用数据库KeyID)
            document_id => "%{KeyId}"
        }
    }
    stdout {
        codec => json_lines
    }
}

 

二、使用logstash全量同步(1分钟同步一次)mysql数据导入到elasticsearch

配置如下:

input {
        stdin {}
        jdbc {
                type => "jdbc"
                jdbc_connection_string => "jdbc:mysql://192.168.200.100:3306/yang?characterEncoding=UTF-8&autoReconnect=true"
                 # 数据库连接账号密码;
                jdbc_user => "root"
                jdbc_password => "010209"
                 # MySQL依赖包路径;
                jdbc_driver_library => "/mnt/mysql-connector-java-5.1.38.jar"
                 # the name of the driver class for mysql
                jdbc_driver_class => "com.mysql.jdbc.Driver"
                statement => "SELECT * FROM `im`"
                schedule => "* * * * *"
        }
}
output {
        elasticsearch {
                 # 配置ES集群地址
                hosts => ["192.168.200.100:9200"]
                 # 索引名字,必须小写
                index => "im"
        }
        stdout {
        }
}

第一次同步结果:

[2019-04-25T14:39:03,194][INFO ][logstash.inputs.jdbc     ] (0.100064s) SELECT * FROM `im`
{
      "@version" => "1",
    "@timestamp" => 2019-04-25T06:39:03.338Z,
          "type" => "jdbc",
            "id" => 3,
          "name" => "QQ"
}
{
      "@version" => "1",
    "@timestamp" => 2019-04-25T06:39:03.309Z,
          "type" => "jdbc",
            "id" => 2,
          "name" => "MSN"
}

向mysql插入数据后第二次同步:

[2019-04-25T14:40:00,295][INFO ][logstash.inputs.jdbc     ] (0.001956s) SELECT * FROM `im`
{
      "@version" => "1",
    "@timestamp" => 2019-04-25T06:40:00.310Z,
          "type" => "jdbc",
            "id" => 2,
          "name" => "MSN"
}
{
      "@version" => "1",
    "@timestamp" => 2019-04-25T06:40:00.316Z,
          "type" => "jdbc",
            "id" => 3,
          "name" => "QQ"
}
{
      "@version" => "1",
    "@timestamp" => 2019-04-25T06:40:00.317Z,
          "type" => "jdbc",
            "id" => 4,
          "name" => "dfs"
}
{
      "@version" => "1",
    "@timestamp" => 2019-04-25T06:40:00.317Z,
          "type" => "jdbc",
            "id" => 5,
          "name" => "fdf"
}

三、使用logstash增量同步(1分钟同步一次)mysql数据导入到elasticsearch

 

input {
        stdin {}
        jdbc {
                type => "jdbc"
                jdbc_connection_string => "jdbc:mysql://192.168.200.100:3306/yang?characterEncoding=UTF-8&autoReconnect=true"
                # 数据库连接账号密码;
                jdbc_user => "root"
                jdbc_password => "010209"
                # MySQL依赖包路径;
                jdbc_driver_library => "/mnt/mysql-connector-java-5.1.38.jar"
                # the name of the driver class for mysql
                jdbc_driver_class => "com.mysql.jdbc.Driver"
                #是否开启分页
                jdbc_paging_enabled => "true"
                #分页条数
                jdbc_page_size => "50000"
                # 执行的sql 文件路径+名称
                #statement_filepath => "/data/my_sql2.sql"
                #SQL语句,也可以使用statement_filepath来指定想要执行的SQL
                statement => "SELECT * FROM `im` where id > :sql_last_value"
                #每一分钟做一次同步
                schedule => "* * * * *"
                #是否将字段名转换为小写,默认true(如果有数据序列化、反序列化需求,建议改为false)
                lowercase_column_names => false
                # 是否记录上次执行结果,true表示会将上次执行结果的tracking_column字段的值保存到last_run_metadata_path指定的文件中;
                record_last_run => true
                # 需要记录查询结果某字段的值时,此字段为true,否则默认tracking_column为timestamp的值;
                use_column_value => true
                # 需要记录的字段,用于增量同步,需是数据库字段
                tracking_column => "id"
                # record_last_run上次数据存放位置;
                last_run_metadata_path => "/mnt/sql_last_value"
                #是否将字段名转换为小写,默认true(如果有数据序列化、反序列化需求,建议改为false)
                clean_run => false
        }
}
output {
        elasticsearch {
                 # 配置ES集群地址
                hosts => ["192.168.200.100:9200"]
                 # 索引名字,必须小写
                index => "im"
        }
        stdout {
        }
}
注意标红色的部分:这些配置是为了达到增量同步的目的,每次同步结束之后会记录最后一条数据的tracking_column列,比如我们这设置的是id,就会将这个值记录在last_run_metadata_path中。
下次在执行同步的时候会将这个值,赋给sql_last_value

说明:

由于我上一次最后sql_last_value文件中记录的id为5,当向mysql插入id=6的值时,结果:

插入id=8,7时;

因为我插入的顺序,先插入id 为8,后插入id为7,因此最后一次记录的id为7,当我下一次插入id=9,10时,会重新导入id为8的值。

当我插入id=10的值后,结束,观察sql_last_value文件的最后记录:

结果:

 

posted @ 2019-04-25 11:52  xiaolaotou  阅读(2617)  评论(0编辑  收藏  举报