关于 Elasticsearch 不同分片设置的压测报告

原创

已于 2023-07-17 17:14:24 修改 · 380 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#elasticsearch #大数据 #搜索引擎

于 2023-07-17 11:12:25 首次发布

通过对Elasticsearch集群进行模拟线上环境的压测，分析850个分片和减半后的索引在不同并发、批次大小下的写入性能。发现大分片索引在低并发时就可能出现请求拒绝，而较小分片的索引具有更高的吞吐量。建议根据业务需求将大索引拆分为更小的子索引，以提高写入效率和系统稳定性。

QQ图片20230715153931.png

摘要

为了验证当前集群经常出现索引超时以及请求拒绝的问题，现模拟线上集群环境及索引设置，通过压测工具随机生成测试数据，针对当前的 850 个分片的索引，以及减半之后的索引，以及更小分片索引的写入进行压测，使用不同的并发、不同的批次大小来观察索引的吞吐情况，并记录写入队列的堆积情况，用来分析分片数、批次数对写入的影响，从而确定后续的优化方案。

压测场景

Elasticsearch 版本 v7.7.1, 共有 57 个节点，其中 3 个独立 Master，3 个协调节点，31GB JVM。

压测流程

单索引 850 分片

索引定义

PUT idx-xxxx-xxxxxx
{
    "aliases" : {
      "alias-xxxx-xxxxxx" : { }
    },
    "mappings" : {
      "dynamic" : "strict",
      "_routing" : {
        "required" : true
      },
      "_source" : {
        "excludes" : [
          "isExtract*",
          "batchNo"
        ]
      },
      "properties" : {
        "addxxxx" : {
          "type" : "text",
          "term_vector" : "with_positions_offsets"
        },
        "clxxxx" : {
          "type" : "byte"
        },
        "contxxxx" : {
          "type" : "text",
          "boost" : 4.0,
          "term_vector" : "with_positions_offsets"
        },
        "conxxxx" : {
          "type" : "keyword",
          "doc_values" : false
        },
        "con1xxxx" : {
          "type" : "text",
          "boost" : 16.0,
          "term_vector" : "with_positions_offsets",
          "fields" : {
            "keyword" : {
              "type" : "keyword",
              "normalizer" : "keyword_normalizer"
            }
          },
          "analyzer" : "name_analyzer",
          "search_analyzer" : "keyword_analyzer"
        },
        "contSxxxx" : {
          "type" : "long",
          "index" : false,
          "doc_values" : false
        },
        "contSxxxxx" : {
          "type" : "keyword",
          "doc_values" : false
        },
        "contTxxxx" : {
          "type" : "short"
        },
        "crtxxxx" : {
          "type" : "date",
          "ignore_malformed" : true,
          "format" : "yyyyMMddHHmmss"
        },
        "duration" : {
          "type" : "long",
          "index" : false,
          "doc_values" : false
        },
        "largeTxxxx" : {
          "type" : "keyword",
          "boost" : 8.0,
          "index" : false,
          "doc_values" : false
        },
        "md5" : {
          "type" : "keyword",
          "index" : false,
          "doc_values" : false
        },
        "orderxxxx" : {
          "type" : "alias",
          "path" : "contName.keyword"
        },
        "ownxxxxxx" : {
          "type" : "keyword",
          "doc_values" : false
        },
        "ownxxxxxxxxxx" : {
          "type" : "keyword",
          "doc_values" : false
        },
        "ownxxxxxxxxxxx" : {
          "type" : "keyword",
          "doc_values" : false
        },
        "ownxxxxxxxxxxx" : {
          "type" : "keyword",
          "doc_values" : false
        },
        "parenxxxxxxxxxx" : {
          "type" : "keyword"
        },
        "pathxx" : {
          "type" : "text",
          "boost" : 8.0,
          "term_vector" : "with_positions_offsets",
          "fields" : {
            "keyword" : {
              "type" : "keyword"
            }
          },
          "analyzer" : "path_analyzer"
        },
        "presexxxxx" : {
          "type" : "keyword",
          "boost" : 8.0,
          "index" : false,
          "doc_values" : false
        },
        "presexxxxx" : {
          "type" : "keyword",
          "boost" : 8.0,
          "index" : false,
          "doc_values" : false
        },
        "presxxxxxx" : {
          "type" : "keyword",
          "boost" : 8.0,
          "index" : false,
          "doc_values" : false
        },
        "prixxxxxx" : {
          "type" : "short",
          "index" : false
        },
        "search_xxxxxx" : {
          "type" : "alias",
          "path" : "contName"
        },
        "servixxxxxx" : {
          "type" : "byte"
        },
        "shotxxxxxx" : {
          "type" : "date",
          "ignore_malformed" : true,
          "format" : "yyyyMMddHHmmss"
        },
        "xxxxxxlThuxxxxxx" : {
          "type" : "keyword",
          "boost" : 8.0,
          "index" : false,
          "doc_values" : false
        },
        "tagxxxxxx" : {
          "type" : "text",
          "term_vector" : "with_positions_offsets"
        },
        "thumxxxxxx" : {
          "type" : "keyword",
          "boost" : 8.0,
          "index" : false,
          "doc_values" : false
        },
        "xxxxxxpdxxxxxx" : {
          "type" : "date",
          "ignore_malformed" : true,
          "format" : "yyyyMMddHHmmss"
        },
        "xxxxxxderAcxxxxxx" : {
          "type" : "keyword",
          "doc_values" : false
        },
        "xxxxxxerAccouxxxxxx" : {
          "type" : "keyword",
          "doc_values" : false
        },
        "xxxxxxerxxxxxxID" : {
          "type" : "keyword",
          "doc_values" : false
        },
        "xxxxxxderNxxxxxx" : {
          "type" : "keyword",
          "doc_values" : false
        }
      }
    },
    "settings" : {
      "index" : {
        "max_ngram_diff" : "50",
        "refresh_interval" : "1s",
        "number_of_shards" : "850",

        "analysis" : {
          "normalizer" : {
            "keyword_normalizer" : {
              "filter" : [
                "lowercase"
              ],
              "type" : "custom"
            }
          },
          "analyzer" : {
            "keyword_analyzer" : {
              "filter" : [
                "lowercase"
              ],
              "type" : "custom",
              "tokenizer" : "keyword"
            },
            "name_analyzer" : {
              "filter" : [
                "lowercase"
              ],
              "type" : "custom",
              "tokenizer" : "name_tokenizer"
            },
            "path_analyzer" : {
              "filter" : [
                "lowercase"
              ],

最低0.47元/天解锁文章