Abstract: A method in a data processing system for managing transmission of pause frames. In response to detecting an overflow condition during a receipt of data from a network, enabling flow control in response to detecting the overflow condition. The flow control is enabled as long as the overflow condition is present. A determination is made as to whether the operating system unavailable after a period of time passes. If the operating system believed to have crashed and flow control is enabled, the flow control is disabled.

Abstract: A method, system, and computer program product in a data processing system are disclosed for dynamically selecting software butters for aggregation in order to optimize system performance. Data to be transferred to a device is received. The data is stored in a chain of software buffers. Current characteristics of the system are determined. Software buffers to be combined are then dynamically selected. This selection is made according to the characteristics of the system in order to maximize performance of the system.

Abstract: A method, system, and computer program product in a data processing system are disclosed for dynamically selecting software butters for aggregation in order to optimize system performance. Data to be transferred to a device is received. The data is stored in a chain of software buffers. Current characteristics of the system are determined. Software buffers to be combined are then dynamically selected. This selection is made according to the characteristics of the system in order to maximize performance of the system.

Abstract: A method is disclosed for dynamically selecting software buffers for aggregation in order to optimize system performance. Data to be transferred to a device is received. The data is stored in a chain of software buffers. Current characteristics of the system are determined. Software buffers to be combined are then dynamically selected. This selection is made according to the characteristics of the system in order to maximize performance of the system.

Abstract: A method for Ethernet packet load balancing includes receiving a transmit package for transmission on an Ethernet network. An offload adapter identifies a least busy port from a plurality of ports indicated in a port list, based on a byte count associated with each of the plurality of ports. The offload adapter determines whether the identified least busy port is in a working status. In the event the identified least busy port is in a working status, the offload adapter assigns the transmit packet to the identified least busy port and increments the byte count associated with the identified least busy port. In the event the identified least busy port is not in a working status, the offload adapter updates the port list and, based on a determination that there are additional working ports, assigns the transmit packet to one of the additional working ports.

Abstract: Method, system and computer program product for transferring data in a data processing system network. A method for transferring data in a data processing system network according to the invention includes determining an adapter among a plurality of adapters that has the lowest transmit latency, and assigning data to be transferred to the adapter determined to have the lowest transmit latency. The data to be transferred is then transferred by the assigned adapter. The present invention utilizes network adapters to transfer data in a more efficient manner.

Abstract: Methods and arrangements to monitor communication components such as a network adapters for activity, and identify components that have lower than normal levels of activity are provided. An identified communication component can become suspect component and a candidate for further testing, including different forms of interrogation. Process for interrogating candidates can include generating and sending test packets having the media access control (MAC) address of the candidate to the candidate and if activity is not detected subsequent to the interrogation, the candidate can be flagged as a failed component. Correspondingly, the component can be deactivated and removed from service. In a further embodiment, a backup component can be activated and assume the role previously held by the failed component.

Abstract: A method, apparatus, and computer instructions for transferring data from a memory to a network adapter in a data processing system. The frame size for a transfer of the data from the memory to the network adapter is identified. If the frame size is divisible by a cache line size without a remainder, a valid data length is set equal to the length field. However, if the frame size divided by the cache line size results in a remainder, the length field is set to align the data with the cache line size. The data transfer is then initiated using these fields.

Abstract: Method, system and computer program product for transferring data in a data processing system network. A method for transferring data in a data processing system network according to the invention includes determining an adapter among a plurality of adapters that has the lowest transmit latency, and assigning data to be transferred to the adapter determined to have the lowest transmit latency. The data to be transferred is then transferred by the assigned adapter. The present invention utilizes network adapters to transfer data in a more efficient manner.

Abstract: A method, system, and computer program product in a data processing system are disclosed for dynamically selecting software butters for aggregation in order to optimize system performance. Data to be transferred to a device is received. The data is stored in a chain of software buffers. Current characteristics of the system are determined. Software buffers to be combined are then dynamically selected. This selection is made according to the characteristics of the system in order to maximize performance of the system.

Abstract: Method, system and computer program product for protecting the integrity of data transferred between an input/output bus of a data processing system and an external network. A method for protecting the integrity of data transferred between an input/output bus and a network includes generating a Cyclic Redundancy Check (CRC) value on an interface between the input/output bus and an adapter for data being transferred from the input/output bus to the network, and checking a CRC value on the interface between the input/output bus and the adapter for data being transferred from the network to the input/output bus. By adding a CRC generator and a CRC checker on the interface between the input/output bus and the adapter, end-to-end data integrity protection is provided for data transferred between the input/output bus and the network.

Abstract: A method, apparatus, and computer instructions for transferring data from a memory to a network adapter in a data processing system. The frame size for a transfer of the data from the memory to the network adapter is identified. If the frame size is divisible by a cache line size without a remainder, a valid data length is set equal to the length field. However, if the frame size divided by the cache line size results in a remainder, the length field is set to align the data with the cache line size. The data transfer is then initiated using these fields.

Abstract: A method, system, and computer program product are disclosed in a data processing system for avoiding data loss during network port recovery. A first network port is linked to a second network port via a network. The second network port transmits data to the first network port via the network. A determination is made that the first network port needs to be reinitialized. Prior to the first network port executing a re-initialization process, the first network port notifies the second network port to pause its data transmissions to the first network port.

Abstract: A method to dynamically adjust the number of active Ethernet adapters in a EtherChannel group, the method including: monitoring a total EtherChannel throughput; determining availability of unused Ethernet adapters if the throughput is above a first predetermined throughput; powering up and adding an unused Ethernet adapter to the EtherChannel group if the throughput is above the first predetermined throughput; powering down and removing an active Ethernet adapter from the EtherChannel group if the throughput is less than the second predetermined throughput; and continue monitoring the total EtherChannel throughput after sleeping for a selected period of time. Accordingly, when an adapter is removed from the EtherChannel group, power to the removed adapter is cut off to reduce power consumption and reduce generation of thermal heat, thus increasing a potential lifespan of the plurality of adapters.

Abstract: A method, apparatus, and computer instructions for transferring data from a memory to a network adapter. A request is received to transfer data to a network adapter. An offset is set for a starting address of the data to align the data with an end of a frame in the memory, wherein the frame is transferred from the memory to the network adapter.

Abstract: Method, system and computer program product for protecting the integrity of data transferred between an input/output bus of a data processing system and an external network. A method for protecting the integrity of data transferred between an input/output bus and a network includes generating a Cyclic Redundancy Check (CRC) value on an interface between the input/output bus and an adapter for data being transferred from the input/output bus to the network, and checking a CRC value on the interface between the input/output bus and the adapter for data being transferred from the network to the input/output bus. By adding a CRC generator and a CRC checker on the interface between the input/output bus and the adapter, end-to-end data integrity protection is provided for data transferred between the input/output bus and the network.

Abstract: A method in a data processing system for managing transmission of pause frames. In response to detecting an overflow condition during a receipt of data from a network, enabling flow control in response to detecting the overflow condition. The flow control is enabled as long as the overflow condition is present. A determination is made as to whether the operating system unavailable after a period of time passes. If the operating system believed to have crashed and flow control is enabled, the flow control is disabled.