这篇文章主要给大家介绍max_result_window参数及其对性能影响。

Part1 背景描述

当前某个业务xxxdb单个索引值较大，每日单个索引大小在二三百G，当前索引保留15天，如果拉取一个15天的范围周期，会查询到几个T的数据量，并且该索引未做副本，这种大查询会导致ES负载较高，严重影响性能。

单日索引大小

检查发现xxx_access_xxx_xxx 索引使用的索引模版xxx_xxx_access_xxx_template 有个参数max_result_window 比较异常，设置值较大。

-- 查询xxx_xxxx_access_xxx_template索引模版信息

GET /_template/xxx_xxx_access_xxx_template
-- 上述命令执行结果如下：
{
  "xxx_xxx_access_xxx_template" : {
    "order" : 8,
    "index_patterns" : [
      "xxx_xxx_access_xxx_*"
    ],
    "settings" : {
      "index" : {
        "lifecycle" : {
          "name" : "5d_cold_15d_delete_policy"
        },
        "refresh_interval" : "30s",
        "number_of_shards" : "10",
        "translog" : {
          "sync_interval" : "60s"
        },
        "merge" : {
          "scheduler" : {
            "max_thread_count" : "1"
          },
          "policy" : {
            "max_merged_segment" : "500m"
          }
        },
        "max_result_window" : "1000000",
        "analysis" : {
          "analyzer" : {
            "comma_analyzer" : {
              "filter" : [
                "lowercase"
              ],
              "char_filter" : [
                "replace_comma"
              ],
              "type" : "custom",
              "tokenizer" : "standard"
            },
            "file_analyzer" : {
              "filter" : [
                "lowercase"
              ],
              "char_filter" : [
                "file_sep"
              ],
              "type" : "custom",
              "tokenizer" : "standard"
            }
          },
          "char_filter" : {
            "file_sep" : {
              "type" : "mapping",
              "mappings" : [
                "/ => ' '",
                ". => ' '"
              ]
            },
            "replace_comma" : {
              "type" : "mapping",
              "mappings" : [
                ". => ' '",
                ", => ' '",
                "# => ' '",
                "$ => ' '",
                "% => ' '",
                "' => ' '",
                "( => ' '",
                ") => ' '",
                "* => ' '",
                "+ => ' '",
                "- => ' '",
                "/ => ' '",
                ": => ' '",
                "; => ' '",
                "< => ' '",
                "= => ' '",
                "> => ' '",
                "? => ' '",
                "@ => ' '",
                "[ => ' '",
                "] => ' '",
                "^ => ' '",
                "{ => ' '",
                "} => ' '",
                "~ => ' '",
                "` => ' '",
                "| => ' '",
                "& => ' '",
                "! => ' '",
                "\" => ' '",
                "_ => ' '"
              ]
            }
          }
        },
        "number_of_replicas" : "0"
      }
    },
    "mappings" : {
      "properties" : {
        "schema" : {
          "type" : "text"
        },
        "netSendTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "checkLengthTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "routeTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "type" : {
          "type" : "text"
        },
        "databaseTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "resultSetSize" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "sql" : {
          "analyzer" : "comma_analyzer",
          "type" : "text"
        },
        "minNodeTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "dbExeTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "host" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "ignore_above" : 256,
              "type" : "keyword"
            }
          }
        },
        "startTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "sqlRows" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "mergeTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "sqlStartTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "dataNodeNum" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "funcDbTime" : {
          "ignore_malformed" : true,
          "type" : "integer"
        },
        "dataNode" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "ignore_above" : 256,
              "type" : "keyword"
            }
          }
        },
        "maxReceiveNodeResultsTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "MaxNodeTime" : {
          "ignore_malformed" : true,
          "type" : "integer"
        },
        "allTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "funcRedisTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "selectRowTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "fddbTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "sqlType" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "calcTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "endTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "minReceiveNodeResultsTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "extern1" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "user" : {
          "type" : "text"
        },
        "executeTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        }
      }
    },
    "aliases" : { }
  }
}

1 max_result_window 解释

通过上面命令可以看到 max_result_window 值设置过大，当前设置为 1000000 (一百万)。

max_result_window 这个参数是什么意思，是用来做什么的呢？

max_result_window 是 Elasticsearch 中的一个参数，它决定了可以从单个查询中请求的最大结果窗口的大小。换句话说，它控制了可以通过 from 和 size 参数获取的最大文档数量。这对于防止过度内存使用和性能问题非常重要，因为请求大量数据会消耗大量内存并影响集群性能。

示例：
如果有一个索引并希望从该索引中检索文档，可以使用 from 和 size 参数来控制分页：
GET /index_name/_search

{

“from”: 0,

“size”: 100

}
这将返回前 100 个文档。from 参数指定要跳过的文档数，size 参数指定要返回的文档数。
但如果尝试执行如下操作：
GET /index_name/_search

{

“from”: 10000,

“size”: 100

}
在默认配置下，这将返回一个错误，因为 from + size 超过了 max_result_window 的限制。
如果希望更改更大的结果窗口，可以在索引中调整 max_result_window 参数，比如：
PUT /index_name/_settings

{

“index”: {

“max_result_window”: 50000

}

}
这将 max_result_window 设置为 50,000。

在 Elasticsearch 7.12.1 版本中，max_result_window 的默认值是 10,000。这意味着默认情况下，您可以请求的结果窗口最大为 10,000 个文档。如果尝试请求超过这个限制的结果窗口，Elasticsearch 会返回一个错误。

max_result_window 支持的最大返回数是 2^31-1，也就是2147483647，生产不建议对 max_result_window 设置过大的值，过大的max_result_window值会对ES带来性能问题，可能会因为值设置过大导致ES内存问题和性能下降。

可以通过设置 from 和 size 参数可以进行分页查询。例如：from=num_a, size=num_b，则获取的结果是从第 num_a + 1 条到第 num_a + num_b 条数据。

2 参数调整

根据对上面max_result_window 参数的分析，计划对 max_result_window值进行调整，将其调整为默认大小。

最简单的方法是通过修改索引模版json信息，将该参数从索引模版删除，调整为默认值，执行如下修改命令：

PUT /_template/xxx_xxx_access_xxx_template
{
    "order" : 8,
    "index_patterns" : [
      "xxx_xxx_access_xxx_*"
    ],
    "settings" : {
      "index" : {
        "lifecycle" : {
          "name" : "5d_cold_15d_delete_policy"
        },
        "refresh_interval" : "30s",
        "number_of_shards" : "10",
        "translog" : {
          "sync_interval" : "60s"
        },
        "merge" : {
          "scheduler" : {
            "max_thread_count" : "1"
          },
          "policy" : {
            "max_merged_segment" : "500m"
          }
        },
        "analysis" : {
          "analyzer" : {
            "comma_analyzer" : {
              "filter" : [
                "lowercase"
              ],
              "char_filter" : [
                "replace_comma"
              ],
              "type" : "custom",
              "tokenizer" : "standard"
            },
            "file_analyzer" : {
              "filter" : [
                "lowercase"
              ],
              "char_filter" : [
                "file_sep"
              ],
              "type" : "custom",
              "tokenizer" : "standard"
            }
          },
          "char_filter" : {
            "file_sep" : {
              "type" : "mapping",
              "mappings" : [
                "/ => ' '",
                ". => ' '"
              ]
            },
            "replace_comma" : {
              "type" : "mapping",
              "mappings" : [
                ". => ' '",
                ", => ' '",
                "# => ' '",
                "$ => ' '",
                "% => ' '",
                "' => ' '",
                "( => ' '",
                ") => ' '",
                "* => ' '",
                "+ => ' '",
                "- => ' '",
                "/ => ' '",
                ": => ' '",
                "; => ' '",
                "< => ' '",
                "= => ' '",
                "> => ' '",
                "? => ' '",
                "@ => ' '",
                "[ => ' '",
                "] => ' '",
                "^ => ' '",
                "{ => ' '",
                "} => ' '",
                "~ => ' '",
                "` => ' '",
                "| => ' '",
                "& => ' '",
                "! => ' '",
                "\" => ' '",
                "_ => ' '"
              ]
            }
          }
        },
        "number_of_replicas" : "0"
      }
    },
    "mappings" : {
      "properties" : {
        "schema" : {
          "type" : "text"
        },
        "netSendTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "checkLengthTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "routeTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "type" : {
          "type" : "text"
        },
        "databaseTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "resultSetSize" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "sql" : {
          "analyzer" : "comma_analyzer",
          "type" : "text"
        },
        "minNodeTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "dbExeTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "host" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "ignore_above" : 256,
              "type" : "keyword"
            }
          }
        },
        "startTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "sqlRows" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "mergeTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "sqlStartTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "dataNodeNum" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "funcDbTime" : {
          "ignore_malformed" : true,
          "type" : "integer"
        },
        "dataNode" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "ignore_above" : 256,
              "type" : "keyword"
            }
          }
        },
        "maxReceiveNodeResultsTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "MaxNodeTime" : {
          "ignore_malformed" : true,
          "type" : "integer"
        },
        "allTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "funcRedisTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "selectRowTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "fddbTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "sqlType" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "calcTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "endTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "minReceiveNodeResultsTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "extern1" : {
          "ignore_malformed" : true,
          "type" : "long"
        },
        "user" : {
          "type" : "text"
        },
        "executeTime" : {
          "ignore_malformed" : true,
          "type" : "long"
        }
      }
    },
    "aliases" : { }
  }

除了以上方法，还可以通过使用 PUT Template API在操作系统上执行。 今天带大家分享了max_result_window参数含义，后续将会给大家带来更多分享。