使用logstash同步mysql數據到elasticsearch實現

# 下載
wget https://repo.huaweicloud.com/logstash/7.14.2/logstash-7.14.2-linux-x86_64.tar.gz
# 解壓
tar -zxvf logstash-7.14.2-linux-x86_64.tar.gz
# 需要mysql-connector-java-5.1.40.jar，隨便放到比如目錄
# /var/lib/hadoop-hdfs/logstash-7.14.2/lib/mysql-connector-java-5.1.40.jar

curl -u elastic:changeme -X PUT  http://192.168.20.130:9200/test -H 'Content-Type: application/json' -d'
{
  "settings" : {
      "number_of_shards" : 1,
      "number_of_replicas" : 1
   },
    "mappings" : {
        "properties": {
          "id": {
            "type" : "long"
          }, 
          "type": {
            "type": "keyword"
          }, 
          "keyword_1": {
            "type": "text",
            "analyzer" : "ik_smart"
          }, 
          "keyword_2": {
            "type": "text",
            "analyzer" : "ik_smart"
          },
          "keyword_3": {
            "type": "text",
            "analyzer" : "ik_smart"
          },
          "data": {
            "type": "keyword"
          },
          "created_at": {
            "type": "date",
            "format": "yyyy-MM-dd HH:mm:ss||yyyy-MM-dd"
          }, 
          "updated_at": {
            "type": "date",
            "format": "yyyy-MM-dd HH:mm:ss||yyyy-MM-dd"
          }
      }
    }
}'

input {
  stdin{
  }
  jdbc{
    # 連接的數據庫地址和數據庫，指定編碼格式，禁用ssl協議，設定自動重連
    # 此處10.112.103.2為MySQL所在IP地址，也是elastic search所在IP地址
    jdbc_connection_string => "jdbc:mysql://192.168.13.28:3306/test?characterEncoding=UTF-8&useSSL=FALSE&autoReconnect=true"
    #數據庫用戶名
    jdbc_user => "root"
    # 數據庫用戶名對應的密碼
    jdbc_password => "root"
    # jar包存放位置
    jdbc_driver_library => "/var/lib/hadoop-hdfs/logstash-7.14.2/lib/mysql-connector-java-5.1.40.jar"
    jdbc_driver_class => "com.mysql.jdbc.Driver"
    jdbc_default_timezone => "Asia/Shanghai"
    jdbc_paging_enabled => "true"
    jdbc_page_size => "320000"
    lowercase_column_names => false
    statement => "select id, type, tags, title from test"
  }
}
filter {
    # 移除無關的字段
    mutate {
        remove_field => ["@version", "@timestamp"]
    }
}
output {
  elasticsearch {
    hosts => ["http://192.168.20.130:9200"]
    user => "elastic"
    password => "changeme"
    index => "test"
    document_type => "_doc"
	# 將字段type和id作為文檔id
    document_id => "%{type}_%{id}"
  }
  stdout {
    codec => json_lines
  }
}

./logstash-7.14.2/bin/logstash -f script/logstash/logstash_mysql2es.conf