elasticsearch查询之大数据集分页性能分析

一、测试环境

python 3.7
elasticsearch 6.8
elasticsearch-dsl 7

安装elasticsearch-dsl

pip install elasticsearch-dsl

测试elasticsearch连通性

from elasticsearch import Elasticsearchfrom elasticsearch_dsl import Searchclient = Elasticsearch(hosts=['http://127.0.0.1:9200'])s = Search(using=client, index="my_store_index") .query("match_phrase_prefix", name="us")s = s.source(['id'])s = s.params(http_auth=["test", "test"])response = s.execute()for hit in response:    print(hit.meta.score, hit.name)11.642133 945d0426-033e-4a8a-86db-b776c6c9a08211.642133 3c1aead4-aa6f-4256-a126-f29f84c9ac8911.642133 77782add-ab58-4eb6-85af-bcbe79be962311.642133 75a02b9a-be31-4a78-a3d9-9af72f98cbf911.642133 d5aacf16-61fc-4f0c-b05d-3d57c8ab623611.642133 30912e1d-4662-4f24-bd5b-5a997e44c29011.642133 95c28501-66a6-4786-917b-0f1e3870764811.642133 605f4e11-08c8-4d60-b803-7925cf325cea11.642133 5dd93a29-e75c-44e3-9f26-bd90e588bc1d11.642133 84e97af5-4e99-466f-bd82-10cd2b79aa18

二、from + size一次性返回大量数据性能测试

通过以下code，直接使用from + size返回100000记录，耗时17279ms；

from elasticsearch import Elasticsearchfrom elasticsearch_dsl import Search, Qdef from_size_query(client):    s = Search(using=client, index="my_store_index")    s = s.params(http_auth=["test", "test"], request_timeout=50);    q = Q('bool',        must_not=[Q('match_phrase_prefix', name='us')]    )    s = s.query(q)        s = s.source(['id'])    s = s[0:100000]    response = s.execute()        print(f'hit total {response.hits.total}')    print(f'request time {response.took}ms')client = Elasticsearch(hosts=['http://127.0.0.1:9200'])from_size_query(client)hit total 485070request time 17279ms

三、使用search after分页返回大量数据性能测试

通过以下code，使用search_after分多次共返回100000记录；从执行结果可以看到当每页获取记录达到5000时，执行的时间基本变化不大；考虑到size增大对cpu和内存的影响，在测试数据情况下，size设置为3000或者4000比较合适；

def search_after_query(client, result):    s = Search(using=client, index="my_store_index")    s = s.params(http_auth=["test", "test"], request_timeout=50);    q = Q('bool',          must_not=[Q('match_phrase_prefix', name='us')]          )    s = s.query(q)    if result['after_value']:        s = s.extra(search_after= [result['after_value']])    s = s.source(['id'])    s = s[:result['size']]    s = s.sort('id')    response = s.execute()    fetch = len(response.hits)    result['total'] += response.took    result['times'] -= 1    while fetch == result['size'] and  result['times'] > 0:        sort_val = response.hits.hits[-1].sort[-1]        s = s.extra(search_after=[sort_val])        response = s.execute()        fetch = len(response.hits)        result['total'] += response.took        result['times'] -= 1client = Elasticsearch(hosts=['http://127.0.0.1:9200'])times = 100result = {"total": 0, "times":times, "size": 1000, "after_value":None}search_after_query(client, result)print(f'size {result["size"]}  request  {times} times total {result["total"]}ms ')times = 50result = {"total": 0, "times":times, "size": 2000, "after_value":None}search_after_query(client, result)print(f'size {result["size"]}  request  {times} times total {result["total"]}ms ')times = 25result = {"total": 0, "times":times, "size": 4000, "after_value":None}search_after_query(client, result)print(f'size {result["size"]}  request  {times} times total {result["total"]}ms ')times = 20result = {"total": 0, "times":times, "size": 5000, "after_value":None}search_after_query(client, result)print(f'size {result["size"]}  request  {times} times total {result["total"]}ms ')times = 10result = {"total": 0, "times":times, "size": 10000, "after_value":None}search_after_query(client, result)print(f'size {result["size"]}  request  {times} times total {result["total"]}ms ')times = 5result = {"total": 0, "times":times, "size": 20000, "after_value":None}search_after_query(client, result)print(f'size {result["size"]}  request  {times} times total {result["total"]}ms ')times = 2result = {"total": 0, "times":times, "size": 50000, "after_value":None}search_after_query(client, result)print(f'size {result["size"]}  request  {times} times total {result["total"]}ms ')size 1000  request  100 times total 14111ms size 2000  request  50 times total 11987ms size 4000  request  25 times total 11167ms size 5000  request  20 times total 10589ms size 10000  request  10 times total 9930ms size 20000  request  5 times total 9978ms  size 50000  request  2 times total 9946ms 

四、使用scroll分页返回大量数据性能测试

通过以下code，使用search_after分多次共取回100000记录；从执行结果通过不同的size获取数据，执行的时间变化不大，所以elasticsearch官方也不建议使用scroll；

def search_scroll_query(client, result):    s = Search(using=client, index="my_store_index")    s = s.params( request_timeout=50, scroll='1m');    q = Q('bool',          must_not=[Q('match_phrase_prefix', name='us')]          )    s = s.query(q)    s = s.source(['id'])    s = s[:result['size']]    response = s.execute()    fetch = len(response.hits)    result['total'] += response.took    result['times'] -= 1    scroll_id = response._scroll_id    while fetch == result['size']  and  result['times'] > 0:        response = client.scroll(scroll_id=scroll_id, scroll='1m', request_timeout=50)        scroll_id = response['_scroll_id']        fetch = len(response['hits']['hits'])        result['total'] += response['took']        result['times'] -= 1client = Elasticsearch(hosts=['http://127.0.0.1:9200'], http_auth=["test", "test"])times = 100result = {"total": 0, "times":times, "size": 1000}search_scroll_query(client, result)print(f'size {result["size"]}  request  {times} times total {result["total"]}ms ')times = 50result = {"total": 0, "times":times, "size": 2000}search_scroll_query(client, result)print(f'size {result["size"]}  request  {times} times total {result["total"]}ms ')times = 25result = {"total": 0, "times":times, "size": 4000}search_scroll_query(client, result)print(f'size {result["size"]}  request  {times} times total {result["total"]}ms ')times = 20result = {"total": 0, "times":times, "size": 5000}search_scroll_query(client, result)print(f'size {result["size"]}  request  {times} times total {result["total"]}ms ')times = 10result = {"total": 0, "times":times, "size": 10000}search_scroll_query(client, result)print(f'size {result["size"]}  request  {times} times total {result["total"]}ms ')times = 5result = {"total": 0, "times":times, "size": 20000}search_scroll_query(client, result)print(f'size {result["size"]}  request  {times} times total {result["total"]}ms ')times = 2result = {"total": 0, "times":times, "size": 50000}search_scroll_query(client, result)print(f'size {result["size"]}  request  {times} times total {result["total"]}ms ')size 1000  request  100 times total 16573ms size 2000  request  50 times total 17678ms size 4000  request  25 times total 16719ms size 5000  request  20 times total 16031ms size 10000  request  10 times total 16008ms size 20000  request  5 times total 16074ms size 50000  request  2 times total 14390ms 

五、测试总结

通过对以上三种分页方式的性能测试，可以看到对于获取10W条记录级别的数据集，search_after的性能最好，在不考虑其他性能优化的基础上建议，可以考虑此种分页方式；