我正在尝试重现您所见到的问题,因为您无法分享数据,所以我尝试生成了一些测试数据。但是,在我的机器上(.NET 4.6.2 F#4.1),我没有看到需要几分钟,而只需几秒钟。
也许您可以尝试查看我的示例应用程序在您的设置中的表现,然后我们可以从那里开始?
open System
open System.Diagnostics
open System.IO
let clock =
let sw = Stopwatch ()
sw.Start ()
fun () ->
sw.ElapsedMilliseconds
let time a =
let before = clock ()
let v = a ()
let after = clock ()
after - before, v
let generateDataSet () =
let random = Random 19740531
let firstDate = DateTime(1970, 1, 1)
let randomInt () = random.Next () |> int64 |> (+) 10000000000L |> string
let randomDate () = (firstDate + (random.Next () |> float |> TimeSpan.FromSeconds)).ToString("s")
let randomString () =
let inline valid ch =
match ch with
| '"'
| '\\' -> ' '
| _ -> ch
let c = random.Next () % 16
let g i =
if i = 0 || i = c + 1 then '"'
else 32 + random.Next() % (127 - 32) |> char |> valid
Array.init (c + 2) g |> String
let columns =
[|
"Id" , randomInt
"ForeignId" , randomInt
"BirthDate" , randomDate
"OtherDate" , randomDate
"FirstName" , randomString
"LastName" , randomString
|]
use sw = new StreamWriter ("perf.csv")
let headers = columns |> Array.map fst |> String.concat ";"
sw.WriteLine headers
for i = 0 to 700000 do
let values = columns |> Array.map (fun (_, f) -> f ()) |> String.concat ";"
sw.WriteLine values
open FSharp.Data
[<Literal>]
let sample = """Id;ForeignId;BirthDate;OtherDate;FirstName;LastName
11795679844;10287417237;2028-09-14T20:33:17;1993-07-21T17:03:25;",xS@ %aY)N*})Z";"ZP~;"
11127366946;11466785219;2028-02-22T08:39:57;2026-01-24T05:07:53;"H-/QA(";"g8}J?k~"
"""
type PerfFile = CsvProvider<sample, ";">
let readDataWithTp () =
use streamReader = new StreamReader ("perf.csv")
let csvFile = PerfFile.Load streamReader
let length = csvFile.Rows |> Seq.length
printfn "%A" length
[<EntryPoint>]
let main argv =
Environment.CurrentDirectory <- AppDomain.CurrentDomain.BaseDirectory
printfn "Generating dataset..."
let ms, _ = time generateDataSet
printfn " took %d ms" ms
printfn "Reading dataset..."
let ms, _ = time readDataWithTp
printfn " took %d ms" ms
0
性能指标(在我的桌面上使用.NET462):
Generating dataset...
took 2162 ms
Reading dataset...
took 6156 ms
性能数据(在我的Macbook Pro上运行Mono 4.6.2):
Generating dataset...
took 4432 ms
Reading dataset...
took 8304 ms
更新
事实证明,显式指定CsvProvider
的Culture
会严重降低性能。这可以是任何文化,不仅限于sv-SE
,但原因是什么呢?
如果检查提供程序为快速和慢速情况生成的代码,则会注意到差异:
快速情况
internal sealed class csvFile@78
{
internal System.Tuple<long, long, System.DateTime, System.DateTime, string, string> Invoke(object arg1, string[] arg2)
{
Microsoft.FSharp.Core.FSharpOption<string> fSharpOption = TextConversions.AsString(arg2[0]);
long arg_C9_0 = TextRuntime.GetNonOptionalValue<long>("Id", TextRuntime.ConvertInteger64("", fSharpOption), fSharpOption);
fSharpOption = TextConversions.AsString(arg2[1]);
long arg_C9_1 = TextRuntime.GetNonOptionalValue<long>("ForeignId", TextRuntime.ConvertInteger64("", fSharpOption), fSharpOption);
fSharpOption = TextConversions.AsString(arg2[2]);
System.DateTime arg_C9_2 = TextRuntime.GetNonOptionalValue<System.DateTime>("BirthDate", TextRuntime.ConvertDateTime("", fSharpOption), fSharpOption);
fSharpOption = TextConversions.AsString(arg2[3]);
System.DateTime arg_C9_3 = TextRuntime.GetNonOptionalValue<System.DateTime>("OtherDate", TextRuntime.ConvertDateTime("", fSharpOption), fSharpOption);
fSharpOption = TextConversions.AsString(arg2[4]);
string arg_C9_4 = TextRuntime.GetNonOptionalValue<string>("FirstName", TextRuntime.ConvertString(fSharpOption), fSharpOption);
fSharpOption = TextConversions.AsString(arg2[5]);
return new System.Tuple<long, long, System.DateTime, System.DateTime, string, string>(arg_C9_0, arg_C9_1, arg_C9_2, arg_C9_3, arg_C9_4, TextRuntime.GetNonOptionalValue<string>("LastName", TextRuntime.ConvertString(fSharpOption), fSharpOption));
}
}
缓慢
internal sealed class csvFile@78
{
internal System.Tuple<long, long, System.DateTime, System.DateTime, string, string> Invoke(object arg1, string[] arg2)
{
Microsoft.FSharp.Core.FSharpOption<string> fSharpOption = TextConversions.AsString(arg2[0]);
long arg_C9_0 = TextRuntime.GetNonOptionalValue<long>("Id", TextRuntime.ConvertInteger64("sv-SE", fSharpOption), fSharpOption);
fSharpOption = TextConversions.AsString(arg2[1]);
long arg_C9_1 = TextRuntime.GetNonOptionalValue<long>("ForeignId", TextRuntime.ConvertInteger64("sv-SE", fSharpOption), fSharpOption);
fSharpOption = TextConversions.AsString(arg2[2]);
System.DateTime arg_C9_2 = TextRuntime.GetNonOptionalValue<System.DateTime>("BirthDate", TextRuntime.ConvertDateTime("sv-SE", fSharpOption), fSharpOption);
fSharpOption = TextConversions.AsString(arg2[3]);
System.DateTime arg_C9_3 = TextRuntime.GetNonOptionalValue<System.DateTime>("OtherDate", TextRuntime.ConvertDateTime("sv-SE", fSharpOption), fSharpOption);
fSharpOption = TextConversions.AsString(arg2[4]);
string arg_C9_4 = TextRuntime.GetNonOptionalValue<string>("FirstName", TextRuntime.ConvertString(fSharpOption), fSharpOption);
fSharpOption = TextConversions.AsString(arg2[5]);
return new System.Tuple<long, long, System.DateTime, System.DateTime, string, string>(arg_C9_0, arg_C9_1, arg_C9_2, arg_C9_3, arg_C9_4, TextRuntime.GetNonOptionalValue<string>("LastName", TextRuntime.ConvertString(fSharpOption), fSharpOption));
}
}
更具体来说,这就是区别:
// Fast
TextRuntime.ConvertDateTime("", fSharpOption), fSharpOption)
// Slow
TextRuntime.ConvertDateTime("sv-SE", fSharpOption), fSharpOption)
当我们指定一个文化时,它被传递给ConvertDateTime
,并被转发到GetCulture
。
static member GetCulture(cultureStr) =
if String.IsNullOrWhiteSpace cultureStr
then CultureInfo.InvariantCulture
else CultureInfo cultureStr
这意味着,在默认情况下,我们使用
CultureInfo.InvariantCulture
,但对于每个字段和行的任何其他情况,我们都会创建一个
CultureInfo
对象。可以进行缓存,但目前未实现。创建过程本身似乎不需要太多时间,但每次使用新的
CultureInfo
对象解析时会出现问题。
在
FSharp.Data
中,解析
DateTime
的本质是这样的。
let dateTimeStyles = DateTimeStyles.AllowWhiteSpaces ||| DateTimeStyles.RoundtripKind
match DateTime.TryParse(text, cultureInfo, dateTimeStyles) with
因此,让我们进行性能测试,其中一个使用缓存的 CultureInfo
对象,另一个则每次创建一个新的。
open System
open System.Diagnostics
open System.Globalization
let clock =
let sw = Stopwatch ()
sw.Start ()
fun () ->
sw.ElapsedMilliseconds
let time a =
let before = clock ()
let v = a ()
let after = clock ()
after - before, v
let perfTest c cf () =
let dateTimeStyles = DateTimeStyles.AllowWhiteSpaces ||| DateTimeStyles.RoundtripKind
let text = DateTime.Now.ToString ("", cf ())
for i = 1 to c do
let culture = cf ()
DateTime.TryParse(text, culture, dateTimeStyles) |> ignore
[<EntryPoint>]
let main argv =
Environment.CurrentDirectory <- AppDomain.CurrentDomain.BaseDirectory
let ct = "sv-SE"
let cct = CultureInfo ct
let count = 10000
printfn "Using cached CultureInfo object..."
let ms, _ = time (perfTest count (fun () -> cct))
printfn " took %d ms" ms
printfn "Using fresh CultureInfo object..."
let ms, _ = time (perfTest count (fun () -> CultureInfo ct))
printfn " took %d ms" ms
0
.NET 4.6.2 F#4.1 的性能数据:
Using cached CultureInfo object...
took 16 ms
Using fresh CultureInfo object...
took 5328 ms
因此,似乎在FSharp.Data
中缓存CultureInfo
对象应当显著提高指定区域性时CsvProvider
的性能。
CacheRows=false
来避免急切地加载所有数据吗?参见这里:http://stackoverflow.com/questions/40852191/csvprovider-throws-outofmemoryexception - TheInnerLight