Abstract:
PROBLEM TO BE SOLVED: To provide a system and method for hot plug/remove of PCIe fabric, etc. SOLUTION: The addition of a new component in the fabric is detected and an event is sent to a multiple root fabric configuration manager. The multiple root fabric configuration manager gathers information about the new component and updates its I/O component tree structure in its configuration data structure to include the new component. The new component may then be utilized via the updated configuration data structure. When a component is to be removed, the multiple root fabric configuration manager receives an event indicating the component to be removed, determines which branches of the tree structure are affected by the removal, and updates its configuration data structure accordingly to remove the component and its associated components from the virtual plane of the removed component. COPYRIGHT: (C)2008,JPO&INPIT
Abstract:
PROBLEM TO BE SOLVED: To provide a method, apparatus, and computer program for defining to an I/O fabric whether or not any host node and I/O fabric device can be affected by a specific error and transmitting an error message to only a host node affected by the error. SOLUTION: In a data processing environment including a plurality of host computer system sharing a plurality of devices by making use of the fabric, the error is detected at one device. A route designation table memorized in the fabric device in its fabric is used to discriminate the host computer system affected by the error among the host computer systems. The error message discriminating the error is routed to the discriminated host computer system among the host computer systems. COPYRIGHT: (C)2007,JPO&INPIT
Abstract:
A number of improvements in network adapters that offload protocol processing from the host processor are provided. Specifically, a mechanism for improving connection establishment in a system utilizing an offload network adapter (730) is provided. The connection establishment mechanism provides the ability to offload connection establishment (1030) and maintenance of connection state information to the offload network adapter (730). As a result of this offloading of connection establishment (1030) and state information maintenance, the number of communications needed between the host system (710) and the offload network adapter (730) may be reduced. In addition, offloading of these functions to the offload network adapter (730) permits bulk notification of established connections and state information to the host system (710) rather than piecemeal notifications as is present in known computing systems.
Abstract:
PROBLEM TO BE SOLVED: To provide a system and method for communication between host systems using socket connection and shared memories. SOLUTION: In the socket-based communication, a work queue in host systems can be used to listen for an incoming socket initialization request. As shown in Fig. 10, a first host system 1010 wishing to establish socket communication connection with a second host system 1020 can generate a socket initialization request work queue element in its work queue and can inform the second host system 1020 that the socket initialization request work queue element is available for processing. Then, the second host system can accept or deny the request. When the second host system accepts the request, the second host system returns a second half of a socket parameter for use by the first host system in performing socket based communications between the first and second host systems. COPYRIGHT: (C)2008,JPO&INPIT
Abstract:
PROBLEM TO BE SOLVED: To provide a system and a method for migration of single route stateless virtual function. SOLUTION: A Single-Root PCI Configuration Manager (SR-PCIM) provides a system image (SI) with possible virtual function (VF) migration scenarios supported by the endpoint (EP). The SR-PCIM may be instructed that a stateless migration of a VF and its associated application(s) from one SI to another is required. Outstanding requests to the VF are completed and any applications associated with the VF are removed from the SI and the VF is detached from its associated physical function (PF). The SWI may then attach the VF to a target PF which may be in the same or a different EP. The SWI makes the VF available to the SI with which the VF is now associated and the SI configures the VF thereby making it available for use by associated applications. COPYRIGHT: (C)2008,JPO&INPIT
Abstract:
PROBLEM TO BE SOLVED: To provide a system and method for initializing shaped memories for sharing endpoints across a plurality of root complexes. SOLUTION: A multi-root PCIe manager (MR-PCIM) initializes the shared memory between root complexes and endpoints by discovering the PCIe switch fabric by traversing all the links accessible through the interconnected switches of the PCIe switch fabric. As the links are traversed, the MR-PCIM compares information obtained for each of the root complexes and endpoints to determine which endpoints and root complexes reside on the same blade. A virtual PCIe tree data structure is then generated that ties the endpoints available on the PCIe switch fabric to each root complex. COPYRIGHT: (C)2008,JPO&INPIT
Abstract:
PROBLEM TO BE SOLVED: To provide a system and method for communication between host systems using a transaction protocol and shared memory. SOLUTION: The shared memory is initialized based on a finding process in communication fabric so that at least one end point has an address range in the shared memory of at least two host systems. For communication between the end point and a root complex of the same or different host systems using the shared memory of the host systems, transaction oriented protocol can be established. The transaction oriented protocol specifies a series of transactions to be executed by various elements such as the root complex or the end point in order to push or pull data. Various combinations of push transactions and pull transactions can be used. COPYRIGHT: (C)2008,JPO&INPIT
Abstract:
PROBLEM TO BE SOLVED: To share PCI adapters between multiple blades. SOLUTION: The present invention relates to a method for routing PCI transaction packets through switches between hosts and adapters in a distributed computing system that includes multiple route nodes, one or more PCI switches and PCI adapters, wherein each route node includes multiple hosts and one of the route nodes includes a PCI configuration manager (PCM). A table is created within specified one of switches and when a particular host is connected to the specified switch, a destination identifier including a set of bits designated by operating the PCM is entered to the table. The destination identifier is appended as an address to PCI packet directed through the specified switch from the particular host to one of the adapters. The destination identifier is used to determine that a PCI packet, routed through the specified switch from one of the adapters, is intended for the particular host. COPYRIGHT: (C)2007,JPO&INPIT
Abstract:
A number of improvements in network adapters that offload protocol processing from the host processor are provided. Specifically, mechanisms for handling memory management and optimization within a system utilizing an offload network adapter are provided. The memory management mechanism permits both buffered sending and receiving of data as well as zero-copy sending and receiving of data. In addition, the memory management mechanism permits grouping of DMA buffers that can be shared among specified connections based on any number of attributes. The memory management mechanism further permits partial send and receive buffer operation, delaying of DMA requests so that they may be communicated to the host system in bulk, and expedited transfer of data to the host system.
Abstract:
A number of improvements in network adapters that offload protocol processing from the host processor are provided. Specifically, a mechanism for improving connection establishment in a system utilizing an offload network adapter (730) is provided. The connection establishment mechanism provides the ability to offload connection establishment (1030) and maintenance of connection state information to the offload network adapter (730). As a result of this offloading of connection establishment (1030) and state information maintenance, the number of communications needed between the host system (710) and the offload network adapter (730) may be reduced. In addition, offloading of these functions to the offload network adapter (730) permits bulk notification of established connections and state information to the host system (710) rather than piecemeal notifications as is present in known computing systems.