performance - 在多个过滤器上优化聚合查询

Question

我有13,000个网页，其中收录了他们的正文。目标是获得一个单词，两个单词，三个单词...最多八个单词短语的前200个词组频率。

这些网页中有超过1.5亿个单词需要标记。

问题是查询大约需要15分钟，此后它用完堆空间，无法完成。

我正在4 CPU核心，8GB RAM，SSD Ubuntu服务器上对此进行测试。 6GB的RAM被分配为堆。交换已禁用。

现在，我可以通过将其分为8个不同的索引来做到这一点，查询/设置/映射组合适用于单字词组。也就是说，我可以在一个单词词组，两个单词词组等上单独运行此命令，从而获得期望的结果(尽管每个结果仍然需要5分钟左右)。我想知道是否有一种方法可以调整此完整聚合，使其与我的硬件一起使用一个索引和查询。

设置和映射:

{
   "settings":{
      "index":{
         "number_of_shards" : 1,
         "number_of_replicas" : 0,
         "analysis":{
            "analyzer":{
               "analyzer_shingle_2":{
                  "tokenizer":"standard",
                  "filter":["standard", "lowercase", "filter_shingle_2"]
               },
               "analyzer_shingle_3":{
                  "tokenizer":"standard",
                  "filter":["standard", "lowercase", "filter_shingle_3"]
               },
               "analyzer_shingle_4":{
                  "tokenizer":"standard",
                  "filter":["standard", "lowercase", "filter_shingle_4"]
               },
               "analyzer_shingle_5":{
                  "tokenizer":"standard",
                  "filter":["standard", "lowercase", "filter_shingle_5"]
               },
               "analyzer_shingle_6":{
                  "tokenizer":"standard",
                  "filter":["standard", "lowercase", "filter_shingle_6"]
               },
               "analyzer_shingle_7":{
                  "tokenizer":"standard",
                  "filter":["standard", "lowercase", "filter_shingle_7"]
               },
               "analyzer_shingle_8":{
                  "tokenizer":"standard",
                  "filter":["standard", "lowercase", "filter_shingle_8"]
               }
            },
            "filter":{
               "filter_shingle_2":{
                  "type":"shingle",
                  "max_shingle_size":2,
                  "min_shingle_size":2,
                  "output_unigrams":"false"
               },
               "filter_shingle_3":{
                  "type":"shingle",
                  "max_shingle_size":3,
                  "min_shingle_size":3,
                  "output_unigrams":"false"
               },
               "filter_shingle_4":{
                  "type":"shingle",
                  "max_shingle_size":4,
                  "min_shingle_size":4,
                  "output_unigrams":"false"
               },
               "filter_shingle_5":{
                  "type":"shingle",
                  "max_shingle_size":5,
                  "min_shingle_size":5,
                  "output_unigrams":"false"
               },
               "filter_shingle_6":{
                  "type":"shingle",
                  "max_shingle_size":6,
                  "min_shingle_size":6,
                  "output_unigrams":"false"
               },
               "filter_shingle_7":{
                  "type":"shingle",
                  "max_shingle_size":7,
                  "min_shingle_size":7,
                  "output_unigrams":"false"
               },
               "filter_shingle_8":{
                  "type":"shingle",
                  "max_shingle_size":8,
                  "min_shingle_size":8,
                  "output_unigrams":"false"
               }
            }
         }
      }
   },
   "mappings":{
      "items":{
         "properties":{
            "body":{
               "type": "multi_field",
               "fields": {
                  "two-word-phrases": {
                     "analyzer":"analyzer_shingle_2",
                     "type":"string"
                  },
                  "three-word-phrases": {
                     "analyzer":"analyzer_shingle_3",
                     "type":"string"
                  },
                  "four-word-phrases": {
                     "analyzer":"analyzer_shingle_4",
                     "type":"string"
                  },
                  "five-word-phrases": {
                     "analyzer":"analyzer_shingle_5",
                     "type":"string"
                  },
                  "six-word-phrases": {
                     "analyzer":"analyzer_shingle_6",
                     "type":"string"
                  },
                  "seven-word-phrases": {
                     "analyzer":"analyzer_shingle_7",
                     "type":"string"
                  },
                  "eight-word-phrases": {
                     "analyzer":"analyzer_shingle_8",
                     "type":"string"
                  }
               }
            }
         }
      }
   }
}

查询:

{
  "size" : 0,
  "aggs" : {
    "one-word-phrases" : {
      "terms" : {
        "field" : "body",
        "size"  : 200
      }
    },
    "two-word-phrases" : {
      "terms" : {
        "field" : "body.two-word-phrases",
        "size"  : 200
      }
    },
    "three-word-phrases" : {
      "terms" : {
        "field" : "body.three-word-phrases",
        "size"  : 200
      }
    },
    "four-word-phrases" : {
      "terms" : {
        "field" : "body.four-word-phrases",
        "size"  : 200
      }
    },
    "five-word-phrases" : {
      "terms" : {
        "field" : "body.five-word-phrases",
        "size"  : 200
      }
    },
    "six-word-phrases" : {
      "terms" : {
        "field" : "body.six-word-phrases",
        "size"  : 200
      }
    },
    "seven-word-phrases" : {
      "terms" : {
        "field" : "body.seven-word-phrases",
        "size"  : 200
      }
    },
    "eight-word-phrases" : {
      "terms" : {
        "field" : "body.eight-word-phrases",
        "size"  : 200
      }
    }
  }
}

Answer 1

您是否真的需要将整个收藏存储在内存中？您的分析可以重写为具有少量资源需求的批处理管道:

解析每个爬网的站点，并将带状疱疹输出到一系列平面文件中:n-grams in python, four, five, six grams?

对瓦状输出文件

进行排序

解析瓦片输出文件并输出瓦片计数文件

解析所有带状疱疹计数文件，并输出主聚合带状疱疹计数文件

按降序排序

(这类事情通常是在UNIX管道中完成并并行化的。)

或者，您可以使用更多的内存来运行它。