可能是一个新手问题，但我希望根据总数据库大小将我们的服务器库存分成几个大小相等的组，并且难以弄清楚如何对它们进行分组。我认为NTILE可能会起作用，但我无法将我的头围绕均匀地分开。我下面的例子就是随机排序服务器。我希望结果是3组相当均匀的大小（显然不准确）。
使用SQL Server 2012.感谢任何帮助。感谢。
declare @Servers table (ServerName sysname, TotalSizeGB decimal (12,2))
insert into @Servers values
('Server1',123.45),
('Server2',234.56),
('Server3',345.67),
('Server4',456.78),
('Server5',567.89),
('Server6',678.90),
('Server7',789.01),
('Server8',890.12),
('Server9',901.23),
('Server10',1023.35)
select GroupNumber, sum(TotalSizeGB) as TotalSizeGB
from (
select ServerName, sum(TotalSizeGB) as TotalSizeGB, ntile(3) over (order by newid()) as GroupNumber
from (
select ServerName, TotalSizeGB from @Servers
) x
group by ServerName
) y
group by GroupNumber
这里的预期产量将是三组，每组约2000GB。我希望它不会准确，但至少接近。如果按服务器分组，可能如下所示：
ServerName TotalSizeGB GroupNumber
Server10 1023.35 1
Server1 123.45 1
Server5 567.89 1
Server3 345.67 1
Server4 456.78 2
Server7 789.01 2
Server6 678.90 2
Server2 234.56 3
Server9 901.23 3
Server8 890.12 3
如果我每组拿一笔钱，它会是这样的：
GroupNumber TotalSizeGB
1 2060.36
2 1924.69
3 2025.91
答案 0 :(得分：1)
SELECT *
FROM(
SELECT y.TotalSizeGB,
CASE
WHEN y.AnotherGrp%2=0 AND y.PseudoGrpNumber=0 THEN 2
WHEN y.AnotherGrp%2=0 AND y.PseudoGrpNumber=1 THEN 1
WHEN y.AnotherGrp%2=0 AND y.PseudoGrpNumber=2 THEN 0
ELSE y.PseudoGrpNumber
END GrpNumber
FROM(
SELECT
x.ServerName,
x.TotalSizeGB,
(2+ROW_NUMBER() OVER(ORDER BY x.TotalSizeGB DESC))%3 PseudoGrpNumber,
(2+ROW_NUMBER() OVER(ORDER BY x.TotalSizeGB DESC))/3 AnotherGrp,
ROW_NUMBER() OVER(ORDER BY x.TotalSizeGB DESC) RowNum
FROM @Servers x
)y
)z
PIVOT( SUM(z.TotalSizeGB) FOR z.GrpNumber IN([0],[1],[2]) ) pvt;
结果：
0 1 2
------- ------- -------
2048.02 1925.80 2037.14
一些解释：
我们的想法是对TotalSizeGB列下降的数据进行排序。然后，每{3}个顺序将每3个连续行组合在一起（列AnotherGrp），然后按DESC顺序（列ASC和PseudoGroNumber）组合在一起。如果它执行GrpNumber衍生表，那么结果将是：
SELECT * FROM () y答案 1 :(得分：1)
这个任务实际上是科学的（Packing problem，或者某种类型），可能更适合math.stackexchange：）
我的解决方案有两个步骤（因为许多优化问题都是） - 找到一些初始解决方案并尝试对其进行优化。
初始解决方案：
ServerName GroupNo TotalSizeGB
---------- ----------- -----------
Server1 3 123.45
Server2 3 234.56
Server3 2 345.67
Server4 1 456.78
Server5 2 567.89
Server6 1 678.90
Server7 3 789.01
Server8 3 890.12
Server9 1 901.23
Server10 2 1023.35
GroupNo GroupSizeGb
----------- -----------
1 2036.91
2 1936.91
3 2037.14
<强>优化
ServerName GroupNo TotalSizeGB
---------- ----------- -----------
Server1 3 123.45
Server2 3 234.56
Server3 2 345.67
Server4 1 456.78
Server5 3 567.89
Server6 1 678.90
Server7 2 789.01
Server8 2 890.12
Server9 1 901.23
Server10 3 1023.35
GroupNo GroupSizeGb
----------- -----------
1 2036.91
2 2024.80
3 1949.25
不幸的是，我无法在SQLFiddle上进行设置，因为使用了显式事务。
set nocount on
-- Parameters
declare
@nGroups int, -- Number of groups to split servers to
@tolerance float, -- let say 0.0 ... 0.1 (0.1 mean that (+/-)10% deviation allowed from target group size)
@nTries int, -- refinement tries 100, 1000, 10000 or as much as you can wait if you are not satisfied with initial solution
@mFactor float, -- refinement param 0.0 ... 1.0
@tolerance2 float -- let say 0.1 ... 0.3
set @nGroups = 3
set @tolerance = 0
set @nTries = 1000
set @mFactor = 0.3
set @tolerance2 = 0.3
-- Initial Data
create table #Servers (ID int identity, ServerName sysname, TotalSizeGB decimal (12,2), primary key clustered(ID))
insert into #Servers (ServerName, TotalSizeGB) values
('Server1',123.45),
('Server2',234.56),
('Server3',345.67),
('Server4',456.78),
('Server5',567.89),
('Server6',678.90),
('Server7',789.01),
('Server8',890.12),
('Server9',901.23),
('Server10',1023.35)
create table #Groups (GroupNo int not NULL, primary key clustered (GroupNo))
insert into #Groups (GroupNo)
select N from (select row_number() over (order by @@spid) from sys.all_columns) S(N) where N <= @nGroups
create table #ServerGroups (ServerID int not NULL, GroupNo int not NULL, primary key clustered(ServerID))
create index #IX_GroupServers_GroupNo on #ServerGroups (GroupNo)
declare
@srvCnt int,
@grSize decimal (12,2),
@grNo int,
@grSz decimal (12,2),
@srvID int
select @srvCnt = count(1), @grSize = sum(TotalSizeGB) / @nGroups from #Servers
select @grSize as [Target approx. group size]
-- Find initial solution
while (select count(1) from #ServerGroups) < @srvCnt
begin
select top 1 @grNo = g.GroupNo
from #Groups g
left join #ServerGroups sg on sg.GroupNo = g.GroupNo
left join #Servers s on s.ID = sg.ServerID
group by g.GroupNo
order by sum(s.TotalSizeGB)
select @grSz = IsNull(sum(s.TotalSizeGB), 0)
from #Groups g
left join #ServerGroups sg on sg.GroupNo = g.GroupNo
left join #Servers s on s.ID = sg.ServerID
where g.GroupNo = @grNo
select top 1 @srvID = ID
from #Servers s
where not exists (select 1 from #ServerGroups where ServerID = s.ID)
order by abs(@grSize - @grSz - s.TotalSizeGB)
insert into #ServerGroups (ServerID, GroupNo) values (@srvID, @grNo)
end
select g.GroupNo, SUM(s.TotalSizeGB) GroupSizeGb
from #Groups g
join #ServerGroups sg on sg.GroupNo = g.GroupNo
join #Servers s on s.ID = sg.ServerID
group by g.GroupNo
-- Refinement
declare @fTarg float
select @fTarg = sum(abs(case when abs(re) > @tolerance then re else 0 end))
from (
select g.GroupNo, SUM(s.TotalSizeGB) GroupSizeGb
from #Groups g
join #ServerGroups sg on sg.GroupNo = g.GroupNo
join #Servers s on s.ID = sg.ServerID
group by g.GroupNo
) t
cross apply (select (GroupSizeGb - @grSize)/@grSize re) p
print @fTarg
if @fTarg > 0
begin
create table #MServerGroups (ServerID int not NULL, GroupNo int not NULL, primary key clustered (ServerID))
insert into #MServerGroups
select ServerID, GroupNo from #ServerGroups
while @nTries > 0
begin
set @nTries = @nTries - 1
begin transaction
;with MS as (
select top (100*@mFactor) percent ServerID, GroupNo
from #MServerGroups
order by checksum(newid())
)
update msg
set
msg.GroupNo = case when msg.ServerID = tt.ServerID1 then tt.NewNo1 else tt.NewNo2 end
from
#MServerGroups msg
join (
select ServerID1, NewNo1, ServerID2, NewNo2
from (
select MS.ServerID as ServerID1, SS.GroupNo as NewNo1, SS.ServerID as ServerID2, MS.GroupNo as NewNo2, row_number() over (partition by SS.ServerID order by @@spid) as rn
from MS
join #Servers s on s.ID = MS.ServerID
cross apply (
select top 1 *
from
#Servers s2
join #MServerGroups ms2 on ms2.ServerID = s2.ID
where
s2.ID != MS.ServerID and ms2.GroupNo != MS.GroupNo and abs(s2.TotalSizeGB - s.TotalSizeGB)/s.TotalSizeGB < @tolerance2
order by checksum(newid())
) SS
) t
where rn = 1
)tt on msg.ServerID in (tt.ServerID1, tt.ServerID2)
if @@rowcount = 0
begin
rollback transaction
continue;
end
declare @fT float
select @fT = sum(abs(case when abs(re) > @tolerance then re else 0 end))
from (
select g.GroupNo, SUM(s.TotalSizeGB) GroupSizeGb
from #Groups g
join #MServerGroups sg on sg.GroupNo = g.GroupNo
join #Servers s on s.ID = sg.ServerID
group by g.GroupNo
) t
cross apply (select (GroupSizeGb - @grSize)/@grSize re) p
if @fT < @fTarg
begin
set @fTarg = @ft
print @fTarg -- the less this number, the better solution is
commit transaction
end
else
rollback transaction
end
update s
set s.GroupNo = m.GroupNo
from #MServerGroups m
join #ServerGroups s on s.ServerID = m.ServerID
select g.GroupNo, SUM(s.TotalSizeGB) GroupSizeGb
from #Groups g
join #ServerGroups sg on sg.GroupNo = g.GroupNo
join #Servers s on s.ID = sg.ServerID
group by g.GroupNo
drop table #MServerGroups
end
else
print 'No refinement needed'
drop table #Groups
drop table #ServerGroups
drop table #Servers
我建议从@nTries = 0和合理的@tolerance开始（例如0.1,0.05）。
答案 2 :(得分：0)
检查一下，希望这会有所帮助。我不确定你的'均匀大小的团体是什么意思。 但我在这里做的是首先为一个组分配一个偶数大小，然后如果有任何剩余，然后将它分配给一个具有超过一般组大小的项目的组。 我会建议您决定组号（可能使用sp）并为每个服务器分配大小，而不是ntile。但是对于所描述的问题，下面可能没问题。 并注意我没有测试所有场景。
declare @TotalSizeGB decimal;
select @TotalSizeGB = sum(TotalSizeGB) from @Servers;
declare @Count int;
select @Count = count(TotalSizeGB) from @Servers;
declare @GroupSize int;
select @GroupSize = 3;
declare @NoofGroups int;
select @NoofGroups = 3;
declare @UnitSizeGB decimal
Set @UnitSizeGB =(@TotalSizeGB/@Count)*@NoofGroups;
Declare @Remainder decimal;
Set @Remainder = @TotalSizeGB-(@UnitSizeGB*@NoofGroups)
Select GroupNumber,
CASE
WHEN gcount = @GroupSize THEN @UnitSizeGB
WHEN gcount > @GroupSize THEN @UnitSizeGB+@Remainder
END
From (
Select
GroupNumber,count(ServerName) as gcount, @UnitSizeGB as UnitSizeGB from(
Select ServerName,ntile(@GroupSize) over (order by newid()) as GroupNumber
from (
select ServerName, TotalSizeGB from @Servers ) x
group by ServerName ) as d
group by GroupNumber ) as ff
这将提供输出
GroupNumber Size
1 2405
2 1803
3 1803
答案 3 :(得分：0)
这是一个解决方案，可以生成与@ i-one代码相同的结果，但可能更容易理解（至少对我而言）。我使用＆＃39; chunk＆＃39;而不是＆＃39; group＆＃39;避免关键字冲突。
前提如下。要创建n个大小均匀的块：
我已将代码上传到SQLFiddle，但它似乎并不喜欢表变量。 Here's the link anyways
-- Source data:
DECLARE @Servers TABLE (ServerName SYSNAME, TotalSizeGB DECIMAL (12,2))
INSERT INTO @Servers VALUES
('Server1',123.45),
('Server2',234.56),
('Server3',345.67),
('Server4',456.78),
('Server5',567.89),
('Server6',678.90),
('Server7',789.01),
('Server8',890.12),
('Server9',901.23),
('Server10',1023.35)
-- Solution start
DECLARE @ServersChunked TABLE (
ServerName SYSNAME,
TotalSizeGB DECIMAL (12,2),
RowNum INT,
ChunkNo INT
);
DECLARE
@ChunkCount INT = 3,
@MinRowNum INT,
@SmallestChunk INT;
-- Copy table into variable (skip this if the original table can be amended to include the RowNum and ChunkNo fields)
INSERT INTO @ServersChunked
SELECT
*,
RowNum = ROW_NUMBER() OVER (ORDER BY TotalSizeGB DESC),
ChunkNo = NULL
FROM @Servers
-- Assign the initial chunks to largest tables
UPDATE @ServersChunked
SET ChunkNo = RowNum
WHERE RowNum <= @ChunkCount
-- Assign chunks to remaining tables
WHILE EXISTS (SELECT 1 FROM @ServersChunked WHERE ChunkNo IS NULL) BEGIN
-- Find the next table (by descending row count)
SELECT @MinRowNum = MIN(RowNum) FROM @ServersChunked WHERE ChunkNo IS NULL
-- Find the smallest chunk
SELECT TOP 1 @SmallestChunk = ChunkNo
FROM @ServersChunked
WHERE ChunkNo IS NOT NULL
GROUP BY ChunkNo
ORDER BY Sum(TotalSizeGB) ASC
-- Assign the table to the chunk
UPDATE @ServersChunked
SET ChunkNo = @SmallestChunk
WHERE RowNum = @MinRowNum
END
结果如下：
ChunkNo SumTotalSizeGB
1 1936.91
2 2036.91
3 2037.14