I have function that saves all records from SQL table to excel worksheet using EPPlus. If I export small amount of data everything works fine, but with 200+ columns and 500 000+ rows I get OutOfMemory exception.
I'd like to modify my code in a way to be able to save 50 000 records per file.
Here is my code that works for small data:
private Task SaveAsync(string tableName)
{
return Task.Run(() =>
{
try
{
using (var conn = new SqlConnection(_connectionString))
{
using (var cmd = new SqlCommand(string.Format(DataQuery, tableName), conn))
{
cmd.CommandType = CommandType.Text;
cmd.CommandTimeout = 360;
conn.Open();
using (SqlDataReader sdr = cmd.ExecuteReader())
{
var fileName = string.Format(TargetFile, tableName);
if (File.Exists(fileName))
{
File.Delete(fileName);
}
sdr.Read();
var numberOfRecordsInTable = sdr.GetInt32(0);
sdr.NextResult();
using (ExcelPackage pck = new ExcelPackage(new FileInfo(fileName)))
{
ExcelWorksheet ws = pck.Workbook.Worksheets.Add("Results");
int count = sdr.FieldCount;
int col = 1, row = 1;
for (int i = 0; i < count; i++)
{
ws.SetValue(row, col++, sdr.GetName(i));
}
row++;
col = 1;
while (sdr.Read())
{
for (int i = 0; i < count; i++)
{
var val = sdr.GetValue(i);
ws.SetValue(row, col++, val);
}
row++;
col = 1;
}
//autosize
ws.Cells[ws.Dimension.Address].AutoFitColumns();
//autofiltr
ws.Cells[1, 1, 1, count].AutoFilter = true;
}
}
conn.Close();
}
}
}
catch (Exception e)
{
Debug.WriteLine("Error at: " + Thread.CurrentThread.ManagedThreadId);
Debug.WriteLine(e);
}
});
}
and my modified code that splits records 50 000 per file:
private Task SaveAsync2(string tableName)
{
return Task.Run(() =>
{
try
{
using (var conn = new SqlConnection(_connectionString))
{
using (var cmd = new SqlCommand(string.Format(DataQuery, tableName), conn))
{
cmd.CommandType = CommandType.Text;
cmd.CommandTimeout = 360;
conn.Open();
using (SqlDataReader sdr = cmd.ExecuteReader())
{
var fileName = string.Format(TargetFile, tableName,"");
if (File.Exists(fileName))
{
File.Delete(fileName);
}
sdr.Read();
var max = sdr.GetInt32(0);
int filesCount = 1;
if (max > 50000)
{
fileName = string.Format(TargetFile, tableName, filesCount);
}
sdr.NextResult();
ExcelPackage pck = new ExcelPackage(new FileInfo(fileName));
ExcelWorksheet ws = pck.Workbook.Worksheets.Add("RESULTS");
int count = sdr.FieldCount;
int col = 1, row = 1;
for (int i = 0; i < count; i++)
{
ws.SetValue(row, col++, sdr.GetName(i));
}
row++;
col = 1;
while (sdr.Read())
{
for (int i = 0; i < count; i++)
{
var val = sdr.GetValue(i);
ws.SetValue(row, col++, val);
}
row++;
col = 1;
if (row > 50000)
{
pck.Save();
filesCount++;
fileName = string.Format(TargetFile, tableName, filesCount);
pck = new ExcelPackage(new FileInfo(fileName));
ws = pck.Workbook.Worksheets.Add("RESULTS");
count = sdr.FieldCount;
col = 1;
row = 1;
for (int i = 0; i < count; i++)
{
ws.SetValue(row, col++, sdr.GetName(i));
}
row++;
col = 1;
}
}
//autosize
ws.Cells[ws.Dimension.Address].AutoFitColumns();
//autofiltr
ws.Cells[1, 1, 1, count].AutoFilter = true;
pck.Save();
}
}
conn.Close();
}
}
catch (Exception e)
{
Debug.WriteLine("Error at: " + Thread.CurrentThread.ManagedThreadId);
Debug.WriteLine(e);
}
});
}
basically this works fine, but in first version of my code I was using everything inside using statement, when in second version I'm calling same code twice.
rows x columns? I found information that EPPlus should handle more than million rows, but not so much columns as I have. I thinks that I can export million rows with single column, but for 200+ columns for me 50 000 rows is limit. I'm wondering if there is number (rows x columns) that will be limit to which my export will work fine. I want that export function to be universal, so when I pass datatable with 50 columns it will export for example 100 000 rows per file and for 2 columns it will export half million per file.Unfortunately, there is no easy way to merge that much data with Epplus in a single file. Basically, the entire file is loaded into memory when open - its either all or nothing. In theory, you could generate the XML files that XLSX contains (they are zip files renamed) and manually insert it since it would have a smaller memory footprint but that is no small feat.
For you current code, you could always just call .dispose() manually if you want to avoid the using statement. But I understand you wanting to avoid duplicate code. What about something like this (but watch for memory usage when copying all the object data):
const int max = 10;
var loop = 0;
using (var sdr = cmd.ExecuteReader())
{
var fieldcount = sdr.FieldCount;
var getfi = new Func<int, FileInfo>(i =>
{
var fi = new FileInfo(String.Format(@"c:\temp\Multi_Files{0}.xlsx", i));
if (fi.Exists) fi.Delete();
return fi;
});
var savefile = new Action<FileInfo, List<Object[]>>((info, rows) =>
{
using (var pck = new ExcelPackage(info))
{
var wb = pck.Workbook;
var ws = wb.Worksheets.Add("RESULTS");
for (var row = 0; row < rows.Count; row++)
for (var col = 0; col < fieldcount; col++)
ws.SetValue(row + 1, col + 1, rows[row][col]);
pck.Save();
}
});
var rowlist = new List<Object[]>();
while (sdr.Read())
{
var rowdata = new Object[sdr.FieldCount];
sdr.GetValues(rowdata);
rowlist.Add(rowdata);
if (rowlist.Count == max)
{
savefile(getfi(++loop), rowlist);
rowlist.Clear();
}
}
if (rowlist.Count > 0)
savefile(getfi(++loop), rowlist);
}