摘要:
The present invention allows data to be accessible by kernel mode filters and other processing components while simultaneously allowing connection-oriented device drivers to be written in a simplified fashion in an integrating component environment. Furthermore, this is done without requiring proprietary mechanisms in the device driver itself in order to place the data stream into the kernel mode filter environment. This is done by providing a special raw data client transport that is written to the transport interface of an integrating component. Driver development is simplified by programming to the driver interface of the integrating component in a standardized fashion.
摘要:
An integrating component exposes a connection interface for creating and maintaining connections. A proxy client component is disclosed that interacts with a known application-level interface and converts known application-level interface commands into appropriate commands for the connection interface of the integrating component. The proxy client component interacts with the integrating component to represent underlying connection-oriented devices and attendant device characteristics to the known application-level interface. This allows an application programmer to take advantage of a connection-oriented I/O subsystem and underlying connection-oriented devices without requiring the programmer to learn another interface. Benefits include the ability to dynamically redirect a data stream received over a created connection from one data transport to another under application control. This is useful in multimedia applications where different types of data may come over the same connection.
摘要:
In an I/O subsystem comprising device drivers for controlling connection-oriented hardware adapters, connection-oriented data transports, and an integrating component allowing data transport drivers and hardware device drivers to be “bound” together to form data communication channels. The integrating component exposes a connection interface for creating and maintaining connections. Furthermore, a proxy client component is disclosed that interacts with a known application-level interface, such as TAPI, and converts such known application-level interface commands into appropriate commands for the connection interface of the integrating component. Additionally, the proxy client component will interact with the integrating component in order to represent the underlying connection-oriented devices and attendant device characteristics to the known application-level interface. All this allows the application programmer to take advantage of a connection-oriented I/O subsystem and underlying connection-oriented devices without requiring the programmer to learn yet another interface. Added benefits include the ability to dynamically redirect a data stream received over a created connection from one data transport to another under application control. This is useful in multimedia applications where different types of data may come over the same connection.
摘要:
Offloading specific processing tasks that would otherwise be performed in a computer system's processor and memory, to a peripheral device. The computing task is then performed by the peripheral, thereby saving computer system resources for other computing tasks. In one preferred embodiment, the disclosed method is utilized in a layered network model, wherein computing tasks that are typically performed in network applications are instead offloaded to the network interface card (NIC) peripheral.
摘要:
The present invention is directed to a method and computer program product for offloading specific processing tasks that would otherwise be performed in a computer system's processor and memory, to a peripheral device, or devices, that are connected to the computer. The computing task is then performed by the peripheral, thereby saving computer system resources for other computing tasks and increasing the overall computing efficiency of the computer system. In one preferred embodiment, the disclosed method is utilized in a layered network model, wherein computing tasks that are typically performed in network applications are instead offloaded to the network interface card (NIC) peripheral. An application executing on the computer system first queries the processing, or task offload capabilities of the NIC, and then selectively enables those capabilities that may be subsequently needed by the application. The specific processing capabilities of a NIC are made available by creating a task offload buffer data structure, which contains data indicative of the processing capabilities of the corresponding NIC. Once an application has discerned the capabilities of a particular NIC, it will selectively utilize any of the enabled task offload capabilities of the NIC by appending packet extension data to the network data packet that is forwarded to the NIC. The device driver of the NIC will review the data contained in the packet extension, and then cause the NIC to perform the specified operating task(s). This offloading of computing tasks on a per-packet basis allows an application to selectively offload tasks on a dynamic, as-needed basis. As such, applications executing on the computer system processor are able to offload tasks in instances where it is busy processing other computing tasks and processor overhead is high. Multiple tasks can also be offloaded in batches to a particular peripheral.
摘要:
Offloading specific processing tasks that would otherwise be performed in a computer system's processor and memory, to a peripheral device. The computing task is then performed by the peripheral, thereby saving computer system resources for other computing tasks. In one preferred embodiment, the disclosed method is utilized in a layered network model, wherein computing tasks that are typically performed in network applications are instead offloaded to the network interface card (NIC) peripheral.
摘要:
A system and method for transferring a plurality of data packets between a link layer and a transport layer is presented. The system and method provide a standardized development interface for development of link layer and transport layer drivers across multiple platforms. The abstract interface provides a standardized functional module through which multiple packet transfer commands are received and passed. The abstract interface discerns the level of sophistication of interfacing drivers and when drivers lack the capability for transferring multiple packets in a single command, the abstract interface emulates multiple transfer capabilities for such drivers.
摘要:
In an I/O subsystem comprising device drivers for controlling connection-oriented hardware adapters, connection-oriented data transports, and an integrating component allowing data transport drivers and hardware device drivers to be “bound” together to form data communication channels. The integrating component exposes a connection interface for creating and maintaining connections. Furthermore, a proxy client component is disclosed that interacts with a known application-level interface, such as TAPI, and converts such known application-level interface commands into appropriate commands for the connection interface of the integrating component. Additionally, the proxy client component will interact with the integrating component in order to represent the underlying connection-oriented devices and attendant device characteristics to the known application-level interface. All this allows the application programmer to take advantage of a connection-oriented I/O subsystem and underlying connection-oriented devices without requiring the programmer to learn yet another interface. Added benefits include the ability to dynamically redirect a data stream received over a created connection from one data transport to another under application control. This is useful in multimedia applications where different types of data may come over the same connection.
摘要:
Methods are provided that allow high-level protocol drivers to cancel transmission requests that have been sent to low-level protocol drivers. Transmission requests are assigned cancel identifiers. Because one original request may be divided into several packets for transmission, the same cancel identifier is given to every packet that derives from the original request. High-level protocol drivers can request cancellation of all pending requests whose cancel identifiers match the one indicated. Cancel identifiers generated by different high-level protocol drivers are mutually distinct so one protocol driver cannot inadvertently cancel requests made by another. The protocol driver may divide its requests into logical flows and assign the same cancel identifier to all requests within one flow. Then, the protocol driver may cancel all pending requests within one flow while allowing requests in other flows to proceed to transmission. An application can use these methods to cancel requests sent to high-level protocol drivers.
摘要:
Methods, systems, and computer program products for abstracting device driver development by layering certain functionality. A driver layer encapsulates device commands and data within a format that is independent of the type of connection between the device and a host computer. Once encapsulated, the device commands and data pass through an intermediate layer responsible for transferring the encapsulated device commands and data to a connection-specific layer. The connection-specific layer then places the encapsulated device commands and data on the particular connection that couples the device and host computer. A single driver layer, potentially provided by an operating system, can thus operate a plurality of devices. Accordingly, hardware developers can be freed from the burden of writing the numerous host-based device drivers that are otherwise required to support an increasing number of connections between devices and host computers, specifically exemplified by improved bus and networking technologies.