By [Tom Dykstra](https://github.com/tdykstra), [Steve Smith](https://ardalis.com/), [Stephen Halter](https://twitter.com/halter73), and [Chris Ross](https://github.com/Tratcher)
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](xref:fundamentals/request-features) composed into an <xref:Microsoft.AspNetCore.Http.HttpContext>.
* [Kestrel server](xref:fundamentals/servers/kestrel) is the default, cross-platform HTTP server implementation.
* IIS HTTP Server is an [in-process server](#in-process-hosting-model) for IIS.
* [HTTP.sys server](xref:fundamentals/servers/httpsys) is a Windows-only HTTP server based on the [HTTP.sys kernel driver and HTTP Server API](/windows/desktop/Http/http-api-start-page).
When using [IIS](/iis/get-started/introduction-to-iis/introduction-to-iis-architecture) or [IIS Express](/iis/extensions/introduction-to-iis-express/iis-express-overview), the app either runs:
* In the same process as the IIS worker process (the [in-process hosting model](#in-process-hosting-model)) with the [IIS HTTP Server](#iis-http-server). *In-process* is the recommended configuration.
* In a process separate from the IIS worker process (the [out-of-process hosting model](#out-of-process-hosting-model)) with the [Kestrel server](#kestrel).
The [ASP.NET Core Module](xref:host-and-deploy/aspnet-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>.
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)](/iis/manage/provisioning-and-managing-iis/features-of-the-windows-process-activation-service-was).
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](/dotnet/core/tools/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)](/iis/manage/provisioning-and-managing-iis/features-of-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 <xref:Microsoft.AspNetCore.Hosting.WebHostBuilderIISExtensions.UseIISIntegration*> extension 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:
* [HTTP.sys server](xref:fundamentals/servers/httpsys) is a Windows-only HTTP server based on the [HTTP.sys kernel driver and HTTP Server API](/windows/desktop/Http/http-api-start-page).
When using [IIS](/iis/get-started/introduction-to-iis/introduction-to-iis-architecture) or [IIS Express](/iis/extensions/introduction-to-iis-express/iis-express-overview), the app runs in a process separate from the IIS worker process (*out-of-process*) with the [Kestrel server](#kestrel).
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)](/iis/manage/provisioning-and-managing-iis/features-of-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](xref:host-and-deploy/iis/index#enable-the-iisintegration-components) 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:
* With a *reverse proxy server*, such as [Internet Information Services (IIS)](https://www.iis.net/), [Nginx](http://nginx.org), or [Apache](https://httpd.apache.org/). A reverse proxy server receives HTTP requests from the Internet and forwards them to Kestrel.
![Kestrel communicates indirectly with the Internet through a reverse proxy server, such as IIS, Nginx, or Apache](kestrel/_static/kestrel-to-internet.png)
Either hosting configuration—with or without a reverse proxy server—is supported for ASP.NET Core 2.1 or later apps.
If the app is exposed to the Internet, Kestrel must use a *reverse proxy server*, such as [Internet Information Services (IIS)](https://www.iis.net/), [Nginx](http://nginx.org), or [Apache](https://httpd.apache.org/). A reverse proxy server receives HTTP requests from the Internet and forwards them to Kestrel.
![Kestrel communicates indirectly with the Internet through a reverse proxy server, such as IIS, Nginx, or Apache](kestrel/_static/kestrel-to-internet.png)
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.
IIS HTTP Server is an [in-process server](#in-process-hosting-model) for IIS and required for in-process deployments. The [ASP.NET Core Module](xref:host-and-deploy/aspnet-core-module) handles native IIS requests between IIS and IIS HTTP Server. For more information, see <xref:host-and-deploy/aspnet-core-module>.
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>.
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.
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](xref:fundamentals/owin) demonstrates how to write a [Nowin](https://github.com/Bobris/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.
* [Visual Studio](https://visualstudio.microsoft.com) – Launch profiles can be used to start the app and server with either [IIS Express](/iis/extensions/introduction-to-iis-express/iis-express-overview)/[ASP.NET Core Module](xref:host-and-deploy/aspnet-core-module) or the console.
* [Visual Studio Code](https://code.visualstudio.com/) – The app and server are started by [Omnisharp](https://github.com/OmniSharp/omnisharp-vscode), which activates the CoreCLR debugger.
* [Visual Studio for Mac](https://visualstudio.microsoft.com/vs/mac/) – The app and server are started by the [Mono Soft-Mode Debugger](https://www.mono-project.com/docs/advanced/runtime/docs/soft-debugger/).
When launching the app from a command prompt in the project's folder, [dotnet run](/dotnet/core/tools/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](/dotnet/core/tools/dotnet-run) and [.NET Core distribution packaging](/dotnet/core/build/distribution-packaging).
†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.
* Target framework: Not applicable to IIS out-of-process deployments.
::: moniker-end
An HTTP/2 connection must use [Application-Layer Protocol Negotiation (ALPN)](https://tools.ietf.org/html/rfc7301#section-3) and TLS 1.2 or later. For more information, see the topics that pertain to your server deployment scenarios.