Question

我目前使用ETL工具将一堆CSV数据插入到OrientDB中。系统我用于试用的配置是EC2 M3大（7.5 GiB内存，2个vCPU，32 GB基于SSD的本地实例存储，64位平台）。

我试图上传的数据（屏蔽）格式如下：

"101.186.130.130","527225725","233 djfnsdkj","0.119836317542" 
"125.143.534.148","112212983","1227 sdfsdfds","0.0465215171983" 
"103.149.957.752","112364761","1121 sdfsdfds","0.0938863016658" 
"103.190.245.128","785804692","6138 sdfsdfsd","0.117767539364"

架构包含2个节点类和一个边缘类。当我尝试使用plocal选项中的ETL工具加载数据时速度只有大约2300行/秒。 ETL配置如下所述：

{
   "source": { "file": { "path": "/home/ubuntu/labvolume1/orientdb/bin/0001_part_00" } },
"extractor": { "csv": {"columnsOnFirstLine": false, "columns":["ip:string", "dpcb:string", "address:string", "prob:string"] } },
  "transformers": [ { "merge": { "joinFieldName":"ip", "lookup":"IpAddress.ip" } },
{ "field":
  { "fieldName": "addr_key",
     "expression": "dpcb.append('_').append(address)"
}
},{ "vertex": { "class": "IpAddress" } },
{ "edge": { "class": "Located",
            "joinFieldName": "addr_key",
            "lookup": "PhyLocation.loc",
            "direction": "out",
            "targetVertexFields": { "geo_address": "${input.address}", "dpcb_number": "${input.dpcb}"},
            "edgeFields": { "confidence": "${input.prob}" },
            "unresolvedLinkAction": "CREATE"
        }
    }
],
"loader": {
"orientdb": {
   "dbURL": "plocal:/home/ubuntu/labvolume1/orientdb/databases/Bulk_Transfer_Test1",
   "dbType": "graph",
   "dbUser": "admin",
   "dbPassword": "admin",
   "serverUser": "admin",
   "wal": false,
   "serverPassword":"admin",
   "classes": [
     {"name": "IpAddress", "extends": "V"},
     {"name": "PhyLocation", "extends": "V"},
     {"name": "Located", "extends": "E"}
   ], "indexes": [
     {"class":"IpAddress", "fields":["ip:string"], "type":"UNIQUE" },
     {"class":"PhyLocation", "fields":["loc:string"], "type":"UNIQUE" }
   ]
}
  }
}

然后我将顶点分离成文件并仅为顶点运行ETL作业，这次速度接近12500行/秒。这个速度相当快，这对我来说很有用。（当我删除索引时，速度几乎翻倍）我使用的配置是：

{
  "source": { "file": { "path": "/home/ubuntu/labvolume1/orientdb/bin/only_ip_05.csv" } },
  "extractor": { "csv": {"columnsOnFirstLine": false, "columns":["ip:string"] } },
  "transformers": [
{ "vertex": { "class": "IpAddress" } }],
  "loader": {
"orientdb": {
   "dbURL": "plocal:/home/ubuntu/labvolume1/orientdb/databases/Bulk_Transfer_Test7",
   "dbType": "graph",
   "dbUser": "admin",
   "dbPassword": "admin",
   "serverUser": "admin",
   "wal": false,
   "serverPassword":"admin",
   "classes": [
     {"name": "IpAddress", "extends": "V"}
   ],
   "indexes": [
     {"class":"IpAddress", "fields":["ip:string"], "type":"UNIQUE" }
   ]
}
}
}

然而，当我试图单独插入边缘时，速度在2200行/秒时变得非常慢。事实证明，这比在一次运行中运行整个操作更低。配置文件附在下面：

{
  "source": { "file": { "path": "/home/ubuntu/labvolume1/orientdb/bin/edge5.csv" } },
  "extractor": { "csv": {"columnsOnFirstLine": false, "columns":["ip:string", "loc:string", "prob:string"] } },
  "transformers": [
{ "merge": { "joinFieldName":"ip", "lookup":"IpAddress.ip" } },
{ "vertex": { "class" : "IpAddress", "skipDuplicates" : true }},
{ "edge": { "class": "Located",
            "joinFieldName": "loc",
            "lookup": "PhyLocation.loc",
            "direction": "out",
            "edgeFields": { "confidence": "${input.prob}" },
            "unresolvedLinkAction": "NOTHING"
        }
    }
 ],
  "loader": {
"orientdb": {
   "dbURL": "plocal:/home/ubuntu/labvolume1/orientdb/databases/Bulk_Transfer_Test7",
   "dbType": "graph",
   "dbUser": "admin",
   "dbPassword": "admin",
   "serverUser": "admin",
   "wal": false,
   "tx":false,
   "batchCommit":10000,
   "serverPassword":"admin",
   "classes": [
     {"name": "IpAddress", "extends": "V"},
     {"name": "PhyLocation", "extends": "V"},
     {"name": "Located", "extends": "E"}
   ]
}
  }
}

如果我在这里做错了，请你告诉我。还请建议更好的改善方法

性能调整，用于在OrientDB中加载数GB的数据

0 个答案: