International Business Machines Corporation

Nicholas J Rogness

Steven Edward Royer

Kyle Alan Lucke

Andrew T Koch

Charles Scott Graham

Kristopher Craig Whitney

Colin R DeVilbiss

Bryan Mark Logan

Techniques are disclosed for performing input/output (I/O) requests to two or more physical adapters in parallel. An address for at least a first page associated with a virtual I/O request is mapped to an entry in a virtual translation control entry (TCE) table. A plurality of physical adapters required to service the virtual I/O request are identified. Upon determining, in each of the identified physical adapters, that an entry in the respective physical TCE table corresponding to the physical adapter is available, for each of the identified physical adapters, the entry in the virtual TCE table is mapped to an entry in the respective physical TCE table corresponding to the physical adapter, and a physical I/O request corresponding to each physical TCE table entry is issued to the respective physical adapter.

Parallel mapping of client partition memory to multiple physical adapters

Techniques are disclosed for performing input/output (I/O) requests to two or more physical adapters in parallel. One method for performing an input/output (I/O) request includes mapping an address for at least a first page associated with a virtual I/O request to an entry in a virtual TCE table and identifying a plurality of physical adapters required to service the virtual I/O request. For each of the identified physical adapters, the entry in the virtual TCE table is mapped to an entry in a physical TCE table corresponding to the physical adapter. This method may also include, in parallel, issuing physical I/O requests to the physical adapters.

A method, system, and computer program product for encapsulating a packet within a virtualized network. The method includes writing one or more first translation control entries (TCEs) from a TCE table of a client system to a TCE table of a host system, and writing one or more second TCEs to the TCE table of the host system. The first TCEs indicate a location within the client system of payload data for the packet, and the second TCEs indicate a location within the host system of at least one of header and footer information to be included with the payload data.

Packet encapsulation with redirected DMA for software defined networks

System and method for packet encapsulation wherein translation control entries (TCEs) may redirect DMA for software defined networks

Virtual Network Interface Connection (VNIC) is a client-server protocol that virtualizes access to a single physical Ethernet network adapter. 'Dedicated VNIC' describes a configuration where a VNIC server is connected to a single VNIC client via a command/response queue (CRQ), allowing minimal overhead when communicating between the client and the Ethernet network adapter. A VNIC server failover mechanism includes multiple VNIC servers on a prioritized list. The top VNIC server on the prioritized list is selected to serve a VNIC client when a CRQ is opened by the client. When the selected VNIC server stops working, the VNIC server failover mechanism selects the next VNIC client in the prioritized list as the active VNIC server, and establishes a connection to the VNIC client's CRQ. In this manner, recovery of a failure in a VNIC server is done in a way that does not require any changes to the VNIC client.

Server-side failover between dedicated VNIC servers

Hardware transmit and/or receive queues in a self-virtualizing IO resource are virtualized to effectively abstract away resource-specific details for the self-virtualizing IO resource. By doing so, a logical partition may be permitted to configure and access a desired number of virtual transmit and/or receive queues, and have an adjunct partition that interfaces the logical partition with the self-virtualizing IO resource handle the appropriate mappings between the hardware and virtual queues.

Virtualization of hardware queues in self-virtualizing input/output devices

A method, apparatus, and program product for managing partitionable resources in a logically partitioned computing system is disclosed. The method includes associating each of a plurality of partitionable resources in the logically partitioned computing system with a respective file entry in a virtual file system, associating each of a plurality of partitionable resources in the logically partitioned computing system with a respective file entry in a virtual file system, and allocating a first partitionable resource among the plurality of partitionable resources to a first logical partition among the plurality of logical partitions in response to a file system operation directed to the virtual file system to organize a respective file entry for the first partitionable resource within the respective directory for the first logical partition.

Growing community of inventors

Rochester, MN, United States of America

Nicholas J Rogness