Question

我在asp.net mvc核心1.1.0项目中使用EF Core并且查询相当复杂。

_context
.Profiles
.Include(p => p.Blog)
 .ThenInclude(b => b.Network)
.Include(p => p.Blog)
 .ThenInclude(i => i.AgeDistributions)
  .ThenInclude(i => i.AgeRange)
.Include(p => p.Blog)
 .ThenInclude(b => b.GenderDistributions)
.Include(p => p.Instagram)
 .ThenInclude(i => i.Network)
.Include(p => p.Instagram)
 .ThenInclude(i => i.AgeDistributions)
  .ThenInclude(i => i.AgeRange)
.Include(p => p.Instagram)
 .ThenInclude(b => b.GenderDistributions)
.Include(p => p.Youtube)
 .ThenInclude(y => y.Network)
.Include(p => p.Youtube)
 .ThenInclude(i => i.AgeDistributions)
  .ThenInclude(i => i.AgeRange)
.Include(p => p.Youtube)
 .ThenInclude(b => b.GenderDistributions)
.Include(p => p.Snapchat)
 .ThenInclude(s => s.Network)
.Include(p => p.Musically)
.Include(p => p.ProfileCategories)
 .ThenInclude(pc => pc.Category)
.Include(p => p.Tags)
 .ThenInclude(tag => tag.Tag)
.Where(p => !p.Deleted);

每个社交平台都可以有任何类型的统计信息。例如，AgeDistributions使用具有PlatformId的基类建模，每个派生{Platform}AgeDistribution指定导航属性，以便正确设置外键。

public class AgeInterval {
  public int Id { get; set; }
  // At most five length. -18, 18-24, ..., 65-
  public string Interval { get; set; }
}

public class PlatformAgeStatistics {
  public int PlatformId { get; set; }
  public int IntervalId { get; set; } 
  public AgeInterval Interval { get; set; } 
  public decimal Distribution { get; set; }
}

public class InstagramAgeStatistics : PlatformAgeStatistics  {
  [ForeignKey("PlatformId")]
  public Instagram Platform { get; set; } // 
}

以上查询有时很长时间（30秒后db执行超时）并检查sql让我觉得我有一个建模问题，EF无法正确确定或EF只是生成次优SQL。结果集使用skip and take进行分页，当前获取10条记录需要时间。

这是第一个执行的SQL

SELECT -- Emitted
FROM [Profiles] AS [p]
LEFT JOIN [BlogChannels] AS [b] ON [b].[ProfileId] = [p].[Id]
LEFT JOIN [InstagramChannels] AS [i] ON [i].[ProfileId] = [p].[Id]
LEFT JOIN [YoutubeChannels] AS [y] ON [y].[ProfileId] = [p].[Id]
LEFT JOIN [BlogChannels] AS [b2] ON [b2].[ProfileId] = [p].[Id]
LEFT JOIN [InstagramChannels] AS [i2] ON [i2].[ProfileId] = [p].[Id]
LEFT JOIN [YoutubeChannels] AS [y2] ON [y2].[ProfileId] = [p].[Id]
LEFT JOIN [BlogChannels] AS [b4] ON [b4].[ProfileId] = [p].[Id]
LEFT JOIN [Networks] AS [n] ON [b4].[NetworkId] = [n].[Id]
LEFT JOIN [InstagramChannels] AS [i4] ON [i4].[ProfileId] = [p].[Id]
LEFT JOIN [Networks] AS [n0] ON [i4].[NetworkId] = [n0].[Id]
LEFT JOIN [YoutubeChannels] AS [y4] ON [y4].[ProfileId] = [p].[Id]
LEFT JOIN [Networks] AS [n1] ON [y4].[NetworkId] = [n1].[Id]
LEFT JOIN [SnapchatChannels] AS [s] ON [s].[ProfileId] = [p].[Id]
LEFT JOIN [Networks] AS [n2] ON [s].[NetworkId] = [n2].[Id]
LEFT JOIN [MusicallyChannels] AS [m] ON [m].[ProfileId] = [p].[Id]
WHERE [p].[Deleted] = 0
ORDER BY [p].[FullName], [p].[Id], [b].[Id], [i].[Id], [y].[Id], [b2].[Id], [i2].[Id], [y2].[Id]
OFFSET @__p_0 ROWS FETCH NEXT @__p_1 ROWS ONLY

然后跟随更多看起来不正确的查询

SELECT [y3].[Gender], [y3].[ChannelId], [y3].[Distribution]
FROM [YoutubeGenderDistribution] AS [y3]
INNER JOIN (
    SELECT DISTINCT [t7].*
    FROM (
        SELECT [p].[FullName], [p].[Id], [b].[Id] AS [Id0], [i].[Id] AS [Id1], [y].[Id] AS [Id2], [b2].[Id] AS [Id3], [i2].[Id] AS [Id4], [y2].[Id] AS [Id5]
        FROM [Profiles] AS [p]
        LEFT JOIN [BlogChannels] AS [b] ON [b].[ProfileId] = [p].[Id]
        LEFT JOIN [InstagramChannels] AS [i] ON [i].[ProfileId] = [p].[Id]
        LEFT JOIN [YoutubeChannels] AS [y] ON [y].[ProfileId] = [p].[Id]
        LEFT JOIN [BlogChannels] AS [b2] ON [b2].[ProfileId] = [p].[Id]
        LEFT JOIN [InstagramChannels] AS [i2] ON [i2].[ProfileId] = [p].[Id]
        LEFT JOIN [YoutubeChannels] AS [y2] ON [y2].[ProfileId] = [p].[Id]
        WHERE [p].[Deleted] = 0
        ORDER BY [p].[FullName], [p].[Id], [b].[Id], [i].[Id], [y].[Id], [b2].[Id], [i2].[Id], [y2].[Id]
        OFFSET @__p_0 ROWS FETCH NEXT @__p_1 ROWS ONLY
    ) AS [t7]
) AS [y20] ON [y3].[ChannelId] = [y20].[Id5]
ORDER BY [y20].[FullName], [y20].[Id], [y20].[Id0], [y20].[Id1], [y20].[Id2], [y20].[Id3], [y20].[Id4], [y20].[Id5]

另一个“看起来”更正确

SELECT [b0].[AgeRangeId], [b0].[ChannelId], [b0].[Distribution], [a].[Id], [a].[Range]
FROM [BlogAgeDistribution] AS [b0]
INNER JOIN (
    SELECT DISTINCT [t2].*
    FROM (
        SELECT [p].[FullName], [p].[Id], [b].[Id] AS [Id0]
        FROM [Profiles] AS [p]
        LEFT JOIN [BlogChannels] AS [b] ON [b].[ProfileId] = [p].[Id]
        WHERE [p].[Deleted] = 0
        ORDER BY [p].[FullName], [p].[Id], [b].[Id]
        OFFSET @__p_0 ROWS FETCH NEXT @__p_1 ROWS ONLY
    ) AS [t2]
) AS [b1] ON [b0].[ChannelId] = [b1].[Id0]
LEFT JOIN [AgeRanges] AS [a] ON [b0].[AgeRangeId] = [a].[Id]
ORDER BY [b1].[FullName], [b1].[Id], [b1].[Id0]

知道为什么EF在请求统计数据时加入所有其他平台Instagram。

谢谢！

编辑：

有趣的是，Age的第一个查询会生成一个包含所有三个

的连接

SELECT [y0].[AgeRangeId], [y0].[ChannelId], [y0].[Distribution], [a1].[Id], [a1].[Range]
FROM [YoutubeAgeDistribution] AS [y0]
INNER JOIN (
    SELECT DISTINCT [t4].*
    FROM (
        SELECT [p].[FullName], [p].[Id], [b].[Id] AS [Id0], [i].[Id] AS [Id1], [y].[Id] AS [Id2]
        FROM [Profiles] AS [p]
        LEFT JOIN [BlogChannels] AS [b] ON [b].[ProfileId] = [p].[Id]
        LEFT JOIN [InstagramChannels] AS [i] ON [i].[ProfileId] = [p].[Id]
        LEFT JOIN [YoutubeChannels] AS [y] ON [y].[ProfileId] = [p].[Id]
        WHERE [p].[Deleted] = 0
        ORDER BY [p].[FullName], [p].[Id], [b].[Id], [i].[Id], [y].[Id]
        OFFSET @__p_0 ROWS FETCH NEXT @__p_1 ROWS ONLY
    ) AS [t4]
) AS [y1] ON [y0].[ChannelId] = [y1].[Id2]
LEFT JOIN [AgeRanges] AS [a1] ON [y0].[AgeRangeId] = [a1].[Id]
ORDER BY [y1].[FullName], [y1].[Id], [y1].[Id0], [y1].[Id1], [y1].[Id2]

Answer 1

EF Core查询所有平台的原因尽管您希望它只查询特定平台是由于查询的编码方式。您已将所有这些组合在同一个IQueryable中。在执行IQueryable之前，利用在C＃中的多个步骤构建IQueryable。

var query = _context
.Profiles.Where(p => searching.Contains(p.Name) && !p.Deleted)

if(searching.Contains("Blog"))
{
  query.Include(p => p.Blog)
   .ThenInclude(b => b.Network)
  .Include(p => p.Blog)
   .ThenInclude(i => i.AgeDistributions)
    .ThenInclude(i => i.AgeRange)
  .Include(p => p.Blog)
   .ThenInclude(b => b.GenderDistributions)
}

if(searching.Contains("Instagram"))
{
 .Include(p => p.Instagram)
  .ThenInclude(i => i.Network)
 .Include(p => p.Instagram)
  .ThenInclude(i => i.AgeDistributions)
   .ThenInclude(i => i.AgeRange)
 .Include(p => p.Instagram)
  .ThenInclude(b => b.GenderDistributions)
}

...

var results = query.ToList();

要记住的最后一件事是尽早过滤。这就是为什么我在一开始就设置了“search.Contains（p.Name）”。查询需要执行的内存占用量越小。应该执行得越快。

我可以补充的最后一点是，EF Core仍然相当新，并不是所有内容都完全在数据库中执行。在某些情况下，它构建一组查询以独立执行，然后将它们组合到调用客户端上下文中的最终结果集中。

EF Core多个左连接

1 个答案: