Add Sharding Estimate basic algorithm

Author: euiyounghwang

controller/cluster_estimate_controller.py

@@ -2,7 +2,11 @@
 from fastapi import APIRouter
 from repository.schemas import Search
 from injector import (logger, doc)
-# from injector import (logger, doc, SearchOmniHandlerInject, QueryBuilderInject)
+from injector import (logger, 
+                      doc, 
+                      SearchOmniHandlerInject, 
+                      QueryBuilderInject, 
+                      ClusterShardingInject)
 import json
 import datetime
 
@@ -26,7 +30,7 @@ async def Cluster_sharding_estimate(request: Search):
 
         EndTime = datetime.datetime.now()
 
-        # return await SearchOmniHandlerInject.search(QueryBuilderInject, oas_query=request_json)
+        return await ClusterShardingInject.sharding_predict(oas_query=request_json)
         return {'results' : 
             {
                 "the number of primary shards" : 1,

injector.py

@@ -2,6 +2,7 @@
 from config.log_config import create_log
 from config import config
 from service.handler.es_search_handler import (SearchOmniHandler)
+from service.handler.cluster_sharding import (ClusterShardingHandler)
 from service.handler.es_query_builder import (QueryBuilder)
 from elasticsearch import Elasticsearch
 from dotenv import load_dotenv
@@ -45,5 +46,6 @@ def get_headers():
 
 SearchOmniHandlerInject = SearchOmniHandler(es_client, logger, doc['app'])
 QueryBuilderInject = QueryBuilder(es_client, logger, doc['app'])
+ClusterShardingInject = ClusterShardingHandler(es_client, logger)
 
 

service/handler/cluster_sharding.py

@@ -0,0 +1,35 @@
+
+import json
+
+class ClusterShardingHandler(object):
+    ''' 
+    You will want to limit your maximum shard size to 30-80 GB if running a recent version of Elasticsearch. 
+    In fact, a single shard can hold as much as 100s of GB and still perform well. (If running below version 6.0 then estimate 30-50 GB.) 
+    
+    Using the 30-80 GB value, you can calculate how many shards you’ll need.
+    
+    For instance, let’s assume you rotate indices monthly and expect around 600 GB of data per month. 
+    In this example, you would allocate 8 to 20 shards.
+    '''
+    
+    def __init__(self, es_client, logger):
+        self.es_client = es_client
+        self.logger = logger
+        
+    async def sharding_predict(self, oas_query=None):
+        ''' Search with QuerBuilder '''
+        if not oas_query:
+            oas_query = {}
+            
+        sharding_results = {'results' : 
+            {
+                "the number of primary shards" : 1,
+                "the number of replica shards" : 1
+            }
+        }
+        
+        self.logger.info(json.dumps(sharding_results, indent=2))
+                
+        return sharding_results
+    
+