如何使用C#更快地从Oracle向Elasticsearch表中插入400万条记录？

Question

我有以下用C#编写的代码,但据此,将数据从Oracle数据库迁移到Elasticsearch需要4-5天.我是以100个批次插入记录.还有其他方式可以更快地移动400万条记录(如果可能的话,可能在不到一天的时间内)吗？

   public static void Selection()
        {
            for(int i = 1; i < 4000000; i += 1000)
            {
                for(int j = i; j < (i+1000); j += 100)
                {
                    OracleCommand cmd = new OracleCommand(BuildQuery(j), 
                                                     oracle_connection);
                    OracleDataReader reader = cmd.ExecuteReader();
                    List<Record> list=CreateRecordList(reader);
                    insert(list);
                }
            }
        }

   private static List<Record> CreateRecordList(OracleDataReader reader)
        {
            List<Record> l = new List<Record>();
            string[] str = new string[7];
            try
            {
                while (reader.Read())
                {
                    for (int i = 0; i < 7; i++)
                    {
                        str[i] = reader[i].ToString();
                    }

                    Record r = new Record(str[0], str[1], str[2], str[3],                              
                                str[4], str[5], str[6]);
                    l.Add(r);
                }
            }
            catch (Exception er)
            {
                string msg = er.Message;
            }
            return l;
        }

   private static string BuildQuery(int from)
        {
            int to = from + change - 1;
            StringBuilder builder = new StringBuilder();
            builder.AppendLine(@"select * from");
            builder.AppendLine("(");
            builder.AppendLine("select FIELD_1, FIELD_2, 
            FIELD_3, FIELD_4, FIELD_5, FIELD_6, 
            FIELD_7, ");
            builder.Append(" row_number() over(order by FIELD_1) 
             rn");
            builder.AppendLine("   from tablename");
            builder.AppendLine(")");
            builder.AppendLine(string.Format("where rn between {0} and {1}", 
            from, to));
            builder.AppendLine("order by rn");
            return builder.ToString();
        }

   public static void insert(List<Record> l)
        {
            try
            {
                foreach(Record r in l)
                    client.Index<Record>(r, "index", "type");
            }
            catch (Exception er)
            {
                string msg = er.Message;
            }
        }

Answer 1

该ROW_NUMBER()函数会对性能产生负面影响，并且您会运行它数千次。您已经在使用OracleDataReader- 它不会一次将所有 400 万行拉到您的机器上，它基本上一次将它们流式传输一个或几个。

这必须在几分钟或几小时内完成，而不是几天——我们有几个流程可以以类似的方式在 Sybase 和 SQL 服务器之间移动数百万条记录，并且需要不到五分钟的时间。

也许可以尝试一下：

OracleCommand cmd = new OracleCommand("SELECT ... FROM TableName", oracle_connection);
int batchSize = 500;    
using (OracleDataReader reader = cmd.ExecuteReader())
{
    List<Record> l = new List<Record>(batchSize);
    string[] str = new string[7];
    int currentRow = 0;

    while (reader.Read())
    {
        for (int i = 0; i < 7; i++)
        {
            str[i] = reader[i].ToString();
        }

        l.Add(new Record(str[0], str[1], str[2], str[3], str[4], str[5], str[6]));

        // Commit every time batchSize records have been read
        if (++currentRow == batchSize)
        {
            Commit(l);
            l.Clear();
            currentRow = 0;
        }
    }

    // commit remaining records
    Commit(l);
}

看起来可能是Commit这样的：

public void Commit(IEnumerable<Record> records)
{
    // TODO: Use ES's BULK features, I don't know the exact syntax

    client.IndexMany<Record>(records, "index", "type");
    // client.Bulk(b => b.IndexMany(records))... something like this
}