Elasticsearch 7 : doc_values 属性

字段的 doc_values 属性有两个值， true、false。默认为 true ，即开启。

当 doc_values 为 fasle 时，无法基于该字段排序、聚合、在脚本中访问字段值。

当 doc_values 为 true 时，ES 会增加一个相应的正排索引，这增加的磁盘占用，也会导致索引数据速度慢一些。

示例1: 关闭 doc_values 属性

创建索引

PUT student
{
  "mappings" : {
    "properties" : {
      "name" : {
        "type" : "keyword",
        "doc_values": false
      },
      "age" : {
        "type" : "integer",
        "doc_values": false
      }
    }
  }
}

插入数据

POST _bulk
{ "index" : { "_index" : "student", "_id" : "1" } }
{ "name" : "张三", "age": 12 }
{ "index" : { "_index" : "student", "_id" : "2" } }
{ "name" : "李四", "age": 10 }
{ "index" : { "_index" : "student", "_id" : "3" } }
{ "name" : "王五", "age": 11 }

查询数据

POST student/_search
{
  "query": {
    "match_all": {}
  }
}

执行结果：

{
  "took" : 2,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 3,
      "relation" : "eq"
    },
    "max_score" : 1.0,
    "hits" : [
      {
        "_index" : "student",
        "_type" : "_doc",
        "_id" : "1",
        "_score" : 1.0,
        "_source" : {
          "name" : "张三",
          "age" : 12
        }
      },
      {
        "_index" : "student",
        "_type" : "_doc",
        "_id" : "2",
        "_score" : 1.0,
        "_source" : {
          "name" : "李四",
          "age" : 10
        }
      },
      {
        "_index" : "student",
        "_type" : "_doc",
        "_id" : "3",
        "_score" : 1.0,
        "_source" : {
          "name" : "王五",
          "age" : 11
        }
      }
    ]
  }
}

查询数据并按照age排序，会报错

POST student/_search
{
  "query": {
    "match_all": {}
  },
  "sort" : [
    {"age": {"order": "desc"}}
  ],
  "from": 0,
  "size": 1
}

报错如下：

{
  "error": {
    "root_cause": [
      {
        "type": "illegal_argument_exception",
        "reason": "Can't load fielddata on [age] because fielddata is unsupported on fields of type [integer]. Use doc values instead."
      }
    ],
    "type": "search_phase_execution_exception",
    "reason": "all shards failed",
    "phase": "query",
    "grouped": true,
    "failed_shards": [
      {
        "shard": 0,
        "index": "student",
        "node": "wFhSfuLwR3OX21eldbRIHg",
        "reason": {
          "type": "illegal_argument_exception",
          "reason": "Can't load fielddata on [age] because fielddata is unsupported on fields of type [integer]. Use doc values instead."
        }
      }
    ],
    "caused_by": {
      "type": "illegal_argument_exception",
      "reason": "Can't load fielddata on [age] because fielddata is unsupported on fields of type [integer]. Use doc values instead.",
      "caused_by": {
        "type": "illegal_argument_exception",
        "reason": "Can't load fielddata on [age] because fielddata is unsupported on fields of type [integer]. Use doc values instead."
      }
    }
  },
  "status": 400
}

查询数据并按照 name 排序，会报错

和基于 age 的排序报错类似。

获取 age 平均值，会报错

POST student/_search
{
  "aggs":{
    "age_stat": {
      "avg": {"field": "age"}
    }
  },
  "from": 0
}

和上面的排序报错类似。

示例2: 开启 doc_values 属性

创建索引

PUT student
{
  "mappings" : {
    "properties" : {
      "name" : {
        "type" : "keyword",
        "doc_values": true
      },
      "age" : {
        "type" : "integer",
        "doc_values": true
      }
    }
  }
}

插入数据

POST _bulk
{ "index" : { "_index" : "student", "_id" : "1" } }
{ "name" : "张三", "age": 12 }
{ "index" : { "_index" : "student", "_id" : "2" } }
{ "name" : "李四", "age": 10 }
{ "index" : { "_index" : "student", "_id" : "3" } }
{ "name" : "王五", "age": 11 }

查询数据

POST student/_search
{
  "query": {
    "match_all": {}
  }
}

执行结果：

{
  "took" : 2,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 3,
      "relation" : "eq"
    },
    "max_score" : 1.0,
    "hits" : [
      {
        "_index" : "student",
        "_type" : "_doc",
        "_id" : "1",
        "_score" : 1.0,
        "_source" : {
          "name" : "张三",
          "age" : 12
        }
      },
      {
        "_index" : "student",
        "_type" : "_doc",
        "_id" : "2",
        "_score" : 1.0,
        "_source" : {
          "name" : "李四",
          "age" : 10
        }
      },
      {
        "_index" : "student",
        "_type" : "_doc",
        "_id" : "3",
        "_score" : 1.0,
        "_source" : {
          "name" : "王五",
          "age" : 11
        }
      }
    ]
  }
}

查询数据并按照age排序，正常执行

POST student/_search
{
  "query": {
    "match_all": {}
  },
  "sort" : [
    {"age": {"order": "desc"}}
  ],
  "from": 0,
  "size": 1
}

响应：

{
  "took" : 1,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 3,
      "relation" : "eq"
    },
    "max_score" : null,
    "hits" : [
      {
        "_index" : "student",
        "_type" : "_doc",
        "_id" : "1",
        "_score" : null,
        "_source" : {
          "name" : "张三",
          "age" : 12
        },
        "sort" : [
          12
        ]
      }
    ]
  }
}

查询数据并按照 name 排序，正常执行

POST student/_search
{
  "query": {
    "match_all": {}
  },
  "sort" : [
    {"name": {"order": "desc"}}
  ],
  "from": 0,
  "size": 1
}

响应:

{
  "took" : 1,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 3,
      "relation" : "eq"
    },
    "max_score" : null,
    "hits" : [
      {
        "_index" : "student",
        "_type" : "_doc",
        "_id" : "3",
        "_score" : null,
        "_source" : {
          "name" : "王五",
          "age" : 11
        },
        "sort" : [
          "王五"
        ]
      }
    ]
  }
}

获取 age 平均值，正常执行

POST student/_search
{
  "aggs":{
    "age_stat": {
      "avg": {"field": "age"}
    }
  },
  "from": 0,
  "size": 0
}

响应：

{
  "took" : 1,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 3,
      "relation" : "eq"
    },
    "max_score" : null,
    "hits" : [ ]
  },
  "aggregations" : {
    "age_stat" : {
      "value" : 11.0
    }
  }
}

 

原文链接:https://www.letianbiji.com/elasticsearch/es7-doc-values.html