摘要:
In this embodiment, techniques are provided that may permit operations performed by hardware and software to process one or more (e.g., network traffic-related) workloads to be coordinated, at least in part. Such coordination may permit this embodiment to operate in accordance with one or more advantageous usage models, and/or to achieve advantages such as, accelerated network traffic processing, while permitting and/or facilitating a multi-tenant (e.g., software-defined) network environment to be provided, for example, via enforcement of one or more associated policies. Many modifications are possible without departing from this embodiment.
摘要:
A device may abstract access to hardware resources in the device to a single operating system (OS) running in the device utilizing an abstraction layer and a software partition. The abstraction layer and the software partition may enable virtualizing the hardware resources during interfacing between the single OS and the hardware resources, such that the actual characteristics and/or number of the hardware resources may be abstracted. The abstraction layer may comprise a hypervisor, which may be optimized to support network abstraction based operations. The software partition may enable managing configuration and/or use of the hardware resources via the abstraction layer. The hardware resources may comprise networking resources. Accordingly, operations of a plurality of virtual drivers within the OS corresponding to each of one or more of the plurality of hardware resources may be supported. Data transfers between the OS and the hardware resources may be performed via the software partition.
摘要:
Aspects of the invention may comprise receiving an incoming TCP packet at a TEEC and processing at least a portion of the incoming packet once by the TEEC without having to do any reassembly and/or retransmission by the TEEC. At least a portion of the incoming TCP packet may be buffered in at least one internal elastic buffer of the TEEC. The internal elastic buffer may comprise a receive internal elastic buffer and/or a transmit internal elastic buffer. Accordingly, at least a portion of the incoming TCP packet may be buffered in the receive internal elastic buffer. At least a portion of the processed incoming packet may be placed in a portion of a host memory for processing by a host processor or CPU. Furthermore, at least a portion of the processed incoming TCP packet may be DMA transferred to a portion of the host memory.
摘要:
Methods and systems for direct device access are disclosed. Aspects of one method may include a plurality of GOSs directly accessing a first network interface device, where the first network interface device may provide access to a network. One or more of the GOSs may be migrated to directly access a second network interface device, based on state information for each of the GOSs, where the state information may be maintained by the host. The GOSs may communicate data to a device coupled to the network by direct accessing the first and/or second network interface device. Similarly, the first and/or second network interface device may communicate data received from a device coupled to the network to one or more of the plurality of GOSs via direct access of the first and/or second network interface device.
摘要:
Certain aspects of a method and system for managing network power policy and configuration of data center bridging may include a network domain that comprises a single logical point of management (LPM) that coordinates operation of one or more devices, such as network interface controllers (NICs), switches, and/or servers in the network domain: The single LPM may be operable to manage one or both of a network power policy and/or a data center bridging (DCB) configuration policy for the network domain.
摘要:
Systems and methods that identify the Upper Layer Protocol (ULP) message boundaries are provided. In one example, a method that identifies ULP message boundaries is provided. The method may include one or more of the following steps: attaching a framing header of a frame to a data payload to form a packet, the framing header being placed immediately after the byte stream transport protocol header, the framing header comprising a length field comprising a length of a framing protocol data unit (PDU); and inserting a marker in the packet, the marker pointing backwards to the framing header and being inserted at a preset interval.
摘要:
A system for reordering frames may include at least one processor that enable receiving of an out-of-order frame via a network subsystem. The at least one processor may enable placing data of the out-of-order frame in a host memory, and managing information relating to one or more holes resulting from the out-of-order frame in a receive window. The at least one processor may enable setting a programmable limit with respect to a number of holes allowed in the receive window. The out-of-order frame is received via a TCP offload engine (TOE) of the network subsystem or a TCP-enabled Ethernet controller (TEEC) of the network subsystem. The network subsystem may not store the out-of-order frame on an onboard memory, and may not store one or more missing frames relating to the out-of-order frame. The network subsystem may include a network interface card (NIC).
摘要:
A local manager in a local networking domain may configure, in conjunction with one or more switching devices, a plurality of network and/or switching devices to establish guaranteed end-to-end data flows in the local networking domain for servicing applications and/or processes running in the network devices. The network devices supporting or using guaranteed end-to-end data flows may determine data flow requirements for each serviced application, and may communicate the determined data flow requirements to switching devices supporting the local manager, for configuring the guaranteed end-to-end data flows. Data flow requirements may comprise bandwidth, quality of service (QoS), security, and/or service level agreement (SLA) related parameters. The network devices may allocate networking resources to guarantee the end-to-end data flow for each application running in each network device. Data flow routing tables maybe maintained and/or updated based on use of existing guaranteed end-to-end data flows.
摘要:
A method and system for handling or processing out-of-order TCP segments in a wireless system may comprise at least one of: placing a first TCP segment received by a wireless network processor in a host buffer and having a mapping between a TCP sequence number and a corresponding buffer address. It may be determined whether a second TCP segment received by the wireless network processor is one of an in-order TCP segment or an out-of-order TCP segment. If the second received TCP segment is an out-of-order TCP segment, then control information associated with at least the second TCP segment may be stored locally on the wireless network processor. The out-of-order TCP segment may be placed in a portion of the host buffer.
摘要:
A device may abstract access to hardware resources in the device to a single operating system (OS) running in the device utilizing an abstraction layer and a software partition. The abstraction layer and the software partition may enable virtualizing the hardware resources during interfacing between the single OS and the hardware resources, such that the actual characteristics and/or number of the hardware resources may be abstracted. The abstraction layer may comprise a hypervisor, which may be optimized to support network abstraction based operations. The software partition may enable managing configuration and/or use of the hardware resources via the abstraction layer. The hardware resources may comprise networking resources. Accordingly, operations of a plurality of virtual drivers within the OS corresponding to each of one or more of the plurality of hardware resources may be supported. Data transfers between the OS and the hardware resources may be performed via the software partition.