Question

I wrote a simple import/export application that transforms data from source->destination using EntityFramework and AutoMapper. It basically:

1. selects batchSize of records from the source table
2. ‘maps‘ data from source->destination entity
3. add new destination entities to destination table and saves context

I move around 500k records in under 5 minutes. After I refactored the code using generics the performance drops drastically to 250 records in 5 minutes.

Are my delegates that return DbSet<T> properties on the DbContext causing these problems? Or is something else going on?

Fast non-generic code:

public class Importer
{        
    public void ImportAddress()
    {
        const int batchSize = 50;
        int done = 0;
        var src = new SourceDbContext();

        var count = src.Addresses.Count();

        while (done < count)
        {
            using (var dest = new DestinationDbContext())
            {
                var list = src.Addresses.OrderBy(x => x.AddressId).Skip(done).Take(batchSize).ToList();
                list.ForEach(x => dest.Address.Add(Mapper.Map<Addresses, Address>(x)));

                done += batchSize;

                dest.SaveChanges();
            }
        }

        src.Dispose();
    }
}

(Very) slow generic code:

public class Importer<TSourceContext, TDestinationContext>
    where TSourceContext : DbContext
    where TDestinationContext : DbContext
{
    public void Import<TSourceEntity, TSourceOrder, TDestinationEntity>(Func<TSourceContext, DbSet<TSourceEntity>> getSourceSet, Func<TDestinationContext, DbSet<TDestinationEntity>> getDestinationSet, Func<TSourceEntity, TSourceOrder> getOrderBy) 
        where TSourceEntity : class
        where TDestinationEntity : class
    {
        const int batchSize = 50;
        int done = 0;
        var ctx = Activator.CreateInstance<TSourceContext>();
        //Does this getSourceSet delegate cause problems perhaps?

        //Added this
        var set = getSourceSet(ctx);

        var count = set.Count(); 

        while (done < count)
        {
            using (var dctx = Activator.CreateInstance<TDestinationContext>())
            {
                var list = set.OrderBy(getOrderBy).Skip(done).Take(batchSize).ToList(); 
                //Or is the db-side paging mechanism broken by the getSourceSet delegate?
                //Added this
                var destSet = getDestinationSet(dctx);
                list.ForEach(x => destSet.Add(Mapper.Map<TSourceEntity, TDestinationEntity>(x)));

                done += batchSize;
                dctx.SaveChanges();
            }
        }

        ctx.Dispose();
    }
}

Answer 1

Problem is invocation of the Func delegates you’re doing a lot. Cache the resulting values in variables and it’ll be fine.