18 KiB
title | author | description | ms.author | ms.custom | ms.date | uid |
---|---|---|---|---|---|---|
Web server implementations in ASP.NET Core | guardrex | Discover the web servers Kestrel and HTTP.sys for ASP.NET Core. Learn how to choose a server and when to use a reverse proxy server. | tdykstra | mvc | 02/14/2019 | fundamentals/servers/index |
Web server implementations in ASP.NET Core
By Tom Dykstra, Steve Smith, Stephen Halter, and Chris Ross
An ASP.NET Core app runs with an in-process HTTP server implementation. The server implementation listens for HTTP requests and surfaces them to the app as a set of request features composed into an xref:Microsoft.AspNetCore.Http.HttpContext.
::: moniker range=">= aspnetcore-2.2"
Windows
ASP.NET Core ships with the following:
- Kestrel server is the default, cross-platform HTTP server implementation.
- IIS HTTP Server is an in-process server for IIS.
- HTTP.sys server is a Windows-only HTTP server based on the HTTP.sys kernel driver and HTTP Server API.
When using IIS or IIS Express, the app either runs:
- In the same process as the IIS worker process (the in-process hosting model) with the IIS HTTP Server. In-process is the recommended configuration.
- In a process separate from the IIS worker process (the out-of-process hosting model) with the Kestrel server.
The ASP.NET Core Module is a native IIS module that handles native IIS requests between IIS and the in-process IIS HTTP Server or Kestrel. For more information, see xref:host-and-deploy/aspnet-core-module.
Hosting models
In-process hosting model
Using in-process hosting, an ASP.NET Core app runs in the same process as its IIS worker process. In-process hosting provides improved performance over out-of-process hosting because requests aren't proxied over the loopback adapter, a network interface that returns outgoing network traffic back to the same machine. IIS handles process management with the Windows Process Activation Service (WAS).
The ASP.NET Core Module:
- Performs app initialization.
- Loads the CoreCLR.
- Calls
Program.Main
.
- Handles the lifetime of the IIS native request.
The in-process hosting model isn't supported for ASP.NET Core apps that target the .NET Framework.
The following diagram illustrates the relationship between IIS, the ASP.NET Core Module, and an app hosted in-process:
A request arrives from the web to the kernel-mode HTTP.sys driver. The driver routes the native request to IIS on the website's configured port, usually 80 (HTTP) or 443 (HTTPS). The module receives the native request and passes it to IIS HTTP Server (IISHttpServer
). IIS HTTP Server is an in-process server implementation for IIS that converts the request from native to managed.
After the IIS HTTP Server processes the request, the request is pushed into the ASP.NET Core middleware pipeline. The middleware pipeline handles the request and passes it on as an HttpContext
instance to the app's logic. The app's response is passed back to IIS through IIS HTTP Server. IIS sends the response to the client that initiated the request.
In-process hosting is opt-in for existing apps, but dotnet new templates default to the in-process hosting model for all IIS and IIS Express scenarios.
Out-of-process hosting model
Because ASP.NET Core apps run in a process separate from the IIS worker process, the module handles process management. The module starts the process for the ASP.NET Core app when the first request arrives and restarts the app if it shuts down or crashes. This is essentially the same behavior as seen with apps that run in-process that are managed by the Windows Process Activation Service (WAS).
The following diagram illustrates the relationship between IIS, the ASP.NET Core Module, and an app hosted out-of-process:
Requests arrive from the web to the kernel-mode HTTP.sys driver. The driver routes the requests to IIS on the website's configured port, usually 80 (HTTP) or 443 (HTTPS). The module forwards the requests to Kestrel on a random port for the app, which isn't port 80 or 443.
The module specifies the port via an environment variable at startup, and the IIS Integration Middleware configures the server to listen on http://localhost:{PORT}
. Additional checks are performed, and requests that don't originate from the module are rejected. The module doesn't support HTTPS forwarding, so requests are forwarded over HTTP even if received by IIS over HTTPS.
After Kestrel picks up the request from the module, the request is pushed into the ASP.NET Core middleware pipeline. The middleware pipeline handles the request and passes it on as an HttpContext
instance to the app's logic. Middleware added by IIS Integration updates the scheme, remote IP, and pathbase to account for forwarding the request to Kestrel. The app's response is passed back to IIS, which pushes it back out to the HTTP client that initiated the request.
For IIS and ASP.NET Core Module configuration guidance, see the following topics:
macOS
ASP.NET Core ships with Kestrel server, which is the default, cross-platform HTTP server.
Linux
ASP.NET Core ships with Kestrel server, which is the default, cross-platform HTTP server.
::: moniker-end
::: moniker range="< aspnetcore-2.2"
Windows
ASP.NET Core ships with the following:
- Kestrel server is the default, cross-platform HTTP server.
- HTTP.sys server is a Windows-only HTTP server based on the HTTP.sys kernel driver and HTTP Server API.
When using IIS or IIS Express, the app runs in a process separate from the IIS worker process (out-of-process) with the Kestrel server.
Because ASP.NET Core apps run in a process separate from the IIS worker process, the module handles process management. The module starts the process for the ASP.NET Core app when the first request arrives and restarts the app if it shuts down or crashes. This is essentially the same behavior as seen with apps that run in-process that are managed by the Windows Process Activation Service (WAS).
The following diagram illustrates the relationship between IIS, the ASP.NET Core Module, and an app hosted out-of-process:
Requests arrive from the web to the kernel-mode HTTP.sys driver. The driver routes the requests to IIS on the website's configured port, usually 80 (HTTP) or 443 (HTTPS). The module forwards the requests to Kestrel on a random port for the app, which isn't port 80 or 443.
The module specifies the port via an environment variable at startup, and the IIS Integration Middleware configures the server to listen on http://localhost:{port}
. Additional checks are performed, and requests that don't originate from the module are rejected. The module doesn't support HTTPS forwarding, so requests are forwarded over HTTP even if received by IIS over HTTPS.
After Kestrel picks up the request from the module, the request is pushed into the ASP.NET Core middleware pipeline. The middleware pipeline handles the request and passes it on as an HttpContext
instance to the app's logic. Middleware added by IIS Integration updates the scheme, remote IP, and pathbase to account for forwarding the request to Kestrel. The app's response is passed back to IIS, which pushes it back out to the HTTP client that initiated the request.
For IIS and ASP.NET Core Module configuration guidance, see the following topics:
macOS
ASP.NET Core ships with Kestrel server, which is the default, cross-platform HTTP server.
Linux
ASP.NET Core ships with Kestrel server, which is the default, cross-platform HTTP server.
::: moniker-end
Kestrel
Kestrel is the default web server included in ASP.NET Core project templates.
::: moniker range=">= aspnetcore-2.0"
Kestrel can be used:
-
By itself as an edge server processing requests directly from a network, including the Internet.
-
With a reverse proxy server, such as Internet Information Services (IIS), Nginx, or Apache. A reverse proxy server receives HTTP requests from the Internet and forwards them to Kestrel.
Either hosting configuration—with or without a reverse proxy server—is supported for ASP.NET Core 2.1 or later apps.
::: moniker-end
::: moniker range="< aspnetcore-2.0"
If the app only accepts requests from an internal network, Kestrel can be used by itself.
If the app is exposed to the Internet, Kestrel must use a reverse proxy server, such as Internet Information Services (IIS), Nginx, or Apache. A reverse proxy server receives HTTP requests from the Internet and forwards them to Kestrel.
The most important reason for using a reverse proxy for public-facing edge server deployments that are exposed directly the Internet is security. The 1.x versions of Kestrel don't include important security features to defend against attacks from the Internet. This includes, but isn't limited to, appropriate timeouts, request size limits, and concurrent connection limits.
::: moniker-end
For Kestrel configuration guidance and information on when to use Kestrel in a reverse proxy configuration, see xref:fundamentals/servers/kestrel.
Nginx with Kestrel
For information on how to use Nginx on Linux as a reverse proxy server for Kestrel, see xref:host-and-deploy/linux-nginx.
Apache with Kestrel
For information on how to use Apache on Linux as a reverse proxy server for Kestrel, see xref:host-and-deploy/linux-apache.
::: moniker range=">= aspnetcore-2.2"
IIS HTTP Server
IIS HTTP Server is an in-process server for IIS and required for in-process deployments. The ASP.NET Core Module handles native IIS requests between IIS and IIS HTTP Server. For more information, see xref:host-and-deploy/aspnet-core-module.
::: moniker-end
HTTP.sys
If ASP.NET Core apps are run on Windows, HTTP.sys is an alternative to Kestrel. Kestrel is generally recommended for best performance. HTTP.sys can be used in scenarios where the app is exposed to the Internet and required capabilities are supported by HTTP.sys but not Kestrel. For more information, see xref:fundamentals/servers/httpsys.
HTTP.sys can also be used for apps that are only exposed to an internal network.
For HTTP.sys configuration guidance, see xref:fundamentals/servers/httpsys.
ASP.NET Core server infrastructure
The xref:Microsoft.AspNetCore.Builder.IApplicationBuilder available in the Startup.Configure
method exposes the xref:Microsoft.AspNetCore.Builder.IApplicationBuilder.ServerFeatures property of type xref:Microsoft.AspNetCore.Http.Features.IFeatureCollection. Kestrel and HTTP.sys only expose a single feature each, xref:Microsoft.AspNetCore.Hosting.Server.Features.IServerAddressesFeature, but different server implementations may expose additional functionality.
IServerAddressesFeature
can be used to find out which port the server implementation has bound at runtime.
Custom servers
If the built-in servers don't meet the app's requirements, a custom server implementation can be created. The Open Web Interface for .NET (OWIN) guide demonstrates how to write a Nowin-based xref:Microsoft.AspNetCore.Hosting.Server.IServer implementation. Only the feature interfaces that the app uses require implementation, though at a minimum xref:Microsoft.AspNetCore.Http.Features.IHttpRequestFeature and xref:Microsoft.AspNetCore.Http.Features.IHttpResponseFeature must be supported.
Server startup
The server is launched when the Integrated Development Environment (IDE) or editor starts the app:
- Visual Studio – Launch profiles can be used to start the app and server with either IIS Express/ASP.NET Core Module or the console.
- Visual Studio Code – The app and server are started by Omnisharp, which activates the CoreCLR debugger.
- Visual Studio for Mac – The app and server are started by the Mono Soft-Mode Debugger.
When launching the app from a command prompt in the project's folder, dotnet run launches the app and server (Kestrel and HTTP.sys only). The configuration is specified by the -c|--configuration
option, which is set to either Debug
(default) or Release
. If launch profiles are present in a launchSettings.json file, use the --launch-profile <NAME>
option to set the launch profile (for example, Development
or Production
). For more information, see dotnet run and .NET Core distribution packaging.
HTTP/2 support
HTTP/2 is supported with ASP.NET Core in the following deployment scenarios:
::: moniker range=">= aspnetcore-2.2"
- Kestrel
- Operating system
- Windows Server 2016/Windows 10 or later†
- Linux with OpenSSL 1.0.2 or later (for example, Ubuntu 16.04 or later)
- HTTP/2 will be supported on macOS in a future release.
- Target framework: .NET Core 2.2 or later
- Operating system
- HTTP.sys
- Windows Server 2016/Windows 10 or later
- Target framework: Not applicable to HTTP.sys deployments.
- IIS (in-process)
- Windows Server 2016/Windows 10 or later; IIS 10 or later
- Target framework: .NET Core 2.2 or later
- IIS (out-of-process)
- Windows Server 2016/Windows 10 or later; IIS 10 or later
- Public-facing edge server connections use HTTP/2, but the reverse proxy connection to Kestrel uses HTTP/1.1.
- Target framework: Not applicable to IIS out-of-process deployments.
†Kestrel has limited support for HTTP/2 on Windows Server 2012 R2 and Windows 8.1. Support is limited because the list of supported TLS cipher suites available on these operating systems is limited. A certificate generated using an Elliptic Curve Digital Signature Algorithm (ECDSA) may be required to secure TLS connections.
::: moniker-end
::: moniker range="< aspnetcore-2.2"
- HTTP.sys
- Windows Server 2016/Windows 10 or later
- Target framework: Not applicable to HTTP.sys deployments.
- IIS (out-of-process)
- Windows Server 2016/Windows 10 or later; IIS 10 or later
- Public-facing edge server connections use HTTP/2, but the reverse proxy connection to Kestrel uses HTTP/1.1.
- Target framework: Not applicable to IIS out-of-process deployments.
::: moniker-end
An HTTP/2 connection must use Application-Layer Protocol Negotiation (ALPN) and TLS 1.2 or later. For more information, see the topics that pertain to your server deployment scenarios.