1

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

我尝试上传的数据（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"

该模式包含 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，速度仅为大约 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" }
   ]
}
  }
}

然后我将顶点分成文件并仅针对顶点运行 ETL 作业，这次速度接近 12500 行/秒。这相当快，这对我有用。（当我删除索引时，速度几乎翻了一番）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，当我尝试单独插入边缘时，速度变得非常慢，为 2200 行/秒。事实证明，这甚至比一次运行整个操作还要低。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什么，请告诉我，还请提出更好的性能改进方法

4

0 回答 0