基于logstash同步mysql数据到elasticsearch

基于logstash同步mysql数据到elasticsearch

• 去官网https://www.elastic.co/cn/downloads/past-releases#logstash下载与elasticsearch同版本的安装包

  wget https://artifacts.elastic.co/downloads/logstash/logstash-6.4.3.tar.gz

• 解压 tar -zxvf logstash-6.4.3.tar.gz

• 下载一个mysql驱动包mysql-connector-java-5.1.41.jar可以从本地maven库上传

• 创建一个配置文件如下

  input {
      jdbc {
          # 设置 MySql/MariaDB 数据库url以及数据库名称
          jdbc_connection_string => "jdbc:mysql://192.168.31.29:3306/foodie-shop?useUnicode=true&characterEncoding=UTF-8&autoReconnect&useSSL=false"
          # 用户名和密码
          jdbc_user => "root"
          jdbc_password => "root1234"
          # 数据库驱动所在位置，可以是绝对路径或者相对路径
          jdbc_driver_library => "/usr/local/logstash-6.4.3/sync/mysql-connector-java-5.1.41.jar"
          # 驱动类名
          jdbc_driver_class => "com.mysql.jdbc.Driver"
          # 开启分页
          jdbc_paging_enabled => "true"
          # 分页每页数量，可以自定义
          jdbc_page_size => "1000"
          # 执行的sql文件路径
          statement_filepath => "/usr/local/logstash-6.4.3/sync/foodie-items.sql"
          # 设置定时任务间隔  含义：分、时、天、月、年，全部为*默认含义为每分钟跑一次任务
          schedule => "* * * * *"
          # 索引类型
          type => "_doc"
          # 是否开启记录上次追踪的结果，也就是上次更新的时间，这个会记录到 last_run_metadata_path 的文件
          use_column_value => true
          # 记录上一次追踪的结果值
          last_run_metadata_path => "/usr/local/logstash-6.4.3/sync/track_time"
          # 如果 use_column_value 为true， 配置本参数，追踪的 column 名，可以是自增id或者时间
          tracking_column => "updated_time"
          # tracking_column 对应字段的类型
          tracking_column_type => "timestamp"
          # 是否清除 last_run_metadata_path 的记录，true则每次都从头开始查询所有的数据库记录
          clean_run => false
          # 数据库字段名称大写转小写
          lowercase_column_names => false
      }
  }
  
  output {
      elasticsearch {
          # es地址
          hosts => ["192.168.31.226:9200"]
          # 同步的索引名
          index => "foodie-items"
          # 设置_docID和数据相同
          # document_id => "%{id}"
          document_id => "%{itemId}"
  
  		# 定义模板名称
  		template_name => "myik"
  		# 模板所在位置
  		template => "/usr/local/logstash-6.4.3/sync/logstash-ik.json"
  		# 重写模板
  		template_overwrite => true
  		# 默认为true, false关闭logstas 自动管理模板功能,如果自定义模板,则设置为false
  		manage_template => false
      }
  
      # 日志输出
      stdout {
          codec => json_lines
      }
  }
  

• 参照配置文件中路径创建待执行的sql脚本

  SELECT
  	i.item_name AS itemName,
  	i.id AS itemId,
  	i.sell_counts AS sellCounts,
  	ii.url AS imgUrl,
  	tempSpec.priceDiscount as price,
  			i.updated_time 
    FROM
  	items i
  	  LEFT JOIN items_img ii ON i.id = ii.item_id
  	  LEFT JOIN (
  		SELECT item_id, MIN(price_discount) AS priceDiscount FROM items_spec GROUP BY item_id
  	  ) tempSpec on i.id = tempSpec.item_id
    WHERE
  	ii.is_main = 1
  	## :sql_last_value 是logstash维护的上次更新时间
      and i.updated_time  >= :sql_last_value
  

• 自定义模板配置(配置中文分词) logstash-ik.json

  {
  	"order": 0,
  	"version": 1,
  	"index_patterns": ["*"],
  	"settings": {
  		"index": {
  			"refresh_interval": "5s"
  		}
  	},
  	"mappings": {
  		"_default_": {
  			"dynamic_templates": [
  				{
  					"message_field": {
  						"path_match": "message",
  						"match_mapping_type": "string",
  						"mapping": {
  							"type": "text",
  							"norms": false
  						}
  					}
  				},
  				{
  					"string_fields": {
  						"match": "*",
  						"match_mapping_type": "string",
  						"mapping": {
  							"type": "text",
  							"norms": false,
  							"analyzer": "ik_max_word",
  							"fields": {
  								"keyword": {
  									"type": "keyword",
  									"ignore_above": 256
  								}
  							}
  						}
  					}
  				}
  			],
  			"properties": {
  				"@timestamp": {
  					"type": "date"
  				},
  				"@version": {
  					"type": "keyword"
  				},
  				"geoip": {
  					"dynamic": true,
  					"properties": {
  						"ip": {
  							"type": "ip"
  						},
  						"location": {
  							"type": "geo_point"
  						},
  						"latitude": {
  							"type": "half_float"
  						},
  						"longitude": {
  							"type": "half_float"
  						}
  					}
  				}
  			}
  		}
  	},
  	"aliases": {}
  }
  

• logstash启动命令./logstash -f /usr/local/logstash-6.4.3/sync/logstatsh-db-sync.conf