International Business Machines Corporation

Jesse Paul Arroyo

Timothy J Schimke

Charles Scott Graham

Prathima Kommineni

Christopher John Engel

Kaveh Naderi

Ellen Marie Bauman

Gregory Michael Nordstrom

Timothy Roy Block

Srinivas Kotta

Thomas R Sand

Harald Pross

Anjan Kumar Guttahalli Krishna

Sakethan R Kotta

Rama K Hazari

Kumaraswamy Sripathy

James E Smith

Daniel J Larson

Josep Cors

John Ronald Oberly, Iii

Shyama Venugopal

Leonardo Letourneaut

Eric N Lais

William Gavin Holland

Thomas M Brey

Theodore Brian Vojnovich

Joefon Jann

Curtis Shannon Eide

Scott Neil Dunham

Joseph Edward Bolan

Gregory William Dake

Paul Gregory Crumley

William Alan Thompson

Vinod Bussa

Manu Anand

Ching-Farn Eric Wu

James Aloysius Donnelly

Juan J Alvarez

Kyle Alan Lucke

Jonathan Louis Kaus

Randall Scott Nelson

David Lee Dosch

Mark Harrison Goff

Michael Anthony Migliacio

Amareswari Veguru

Timothy M Schimke

Christoper J Engel

Anjam Kumar Guttahalli Krishna

Theodore Brian c/o Ibm United Kingdom Limited Vojnovich

Scott Randall Nelson

Apparatuses, methods, program products, and systems are presented for interrupt migration in connection with migration of a logical partition.

Interrupt migration

A system and method dynamically assign interrupts to a virtual machine from an input/output (I/O) adapter based on I/O metrics of the I/O adapter. An interrupt manager monitors I/O adapter traffic flow metrics such as latency of data transfers, usage levels, and transfers per unit of time. The interrupt manager determines when a traffic flow metric for a virtual machine meets a predetermined performance threshold and updates virtual interrupt assignments in a logical interrupt table to improve performance of the system.

Dynamic assignment of interrupts based on input/output metrics

A system and method dynamically assign interrupts to a virtual machine from an input/output (I/O) adapter based on I/O metrics of the I/O adapter. An interrupt manager monitors I/O adapter traffic flow metrics such as latency of data transfers, usage levels, and transfers per unit of time. The interrupt manager determines when a traffic flow metric for a virtual machine meets a predetermined performance threshold and updates virtual interrupt assignments in a logical interrupt table to improve performance of the system. The interrupt manager uses hint data provided by the device driver to make the interrupt assignments.

Apparatuses, methods, program products, and systems are presented for interrupt virtualization. An apparatus includes an adapter module that detects a switch from a first physical input/output ('I/O') adapter associated with a logical partition to a second physical I/O adapter associated with the logical partition. The apparatus includes an interrupt module that updates one or more I/O interrupt management structures for the logical partition so that the logical partition receives I/O interrupt information from the second physical I/O adapter and not the first physical I/O adapter without the logical partition being aware of the switch to the second I/O adapter. The apparatus includes an abstraction module that updates physical device information at a hypervisor for the logical partition to reflect the switch to the second physical I/O device.

Interrupt virtualization

A PCI host bridge (PHB) includes a warm reset mode and a full reset mode. When a fatal error occurs, the type of fatal error is determined, a reset mode corresponding to that type of fatal error is determined, and a reset corresponding to the reset mode is performed. A full reset clears the error registers, status registers and configuration registers, which then requires the configuration registers to be reconfigured before the PHB can be reinitialized. A warm reset clears the error registers and status registers, but does not clear the configuration registers. A warm reset thus does not require the time to write to the configuration registers, and the PHB can be reinitialized using the existing configuration data in the configuration registers while link training is done in parallel. When initialization of the PHB after a warm reset is not successful, a full reset is performed.

Multiple reset modes for a PCI host bridge

Managing a pool of virtual functions including generating a virtual function pool comprising a plurality of virtual functions for at least one single root input/output virtualization (SR-IOV) adapter; creating a control path from a client virtual network interface controller (VNIC) driver in a first client partition to a target network using an active virtual function; receiving a failure alert indicating that the control path from the client VNIC driver in the first client partition to the target network using the active virtual function has failed; selecting, from the virtual function pool, a backup virtual function for the first client partition based on the failure alert; and recreating the control path from the client VNIC driver in the first client partition to the target network using the backup virtual function.

Managing a pool of virtual functions

A method, system and computer program product are provided for detecting state and sparing of optical Peripheral Component Interconnect Express (PCI-Express or PCIE) cable channels attached to an IO drawer. System firmware is provided for implementing health check functions and state detection and sparing functions. One or more optical cables are connected between a host bridge and an PCIE enclosure, each optical cable includes one or more spare optical channels. An identified failed optical channel is rerouted to the spare optical channel.

Detecting and sparing of optical PCIE cable channel attached IO drawer

Managing flexible adapter configurations in a computer system including assigning an initial amount of resources to a set of empty expansion bus slots of the computer system; detecting an adapter has been attached to one of the set of empty expansion bus slots; receiving, by a hypervisor, a request for additional resources for use by the detected adapter, wherein the additional resources are in addition to the initial amount of resources assigned to the expansion bus slot occupied by the detected adapter; determining, by the hypervisor, an availability of the additional resources for the detected adapter; in response to determining that the additional resources are available for the detected adapter, assigning, by the hypervisor at runtime, the requested additional resources to the detected adapter.

Managing by a hypervisor flexible adapter configurations and resources in a computer system

Live partition mobility in a computing environment that includes a source system and a target system may be carried out by: pausing a logical partition on the source system, wherein the logical partition is mapped to an I/O adapter of the source system; copying, to the target system, configuration information describing the mapping of the logical partition to the I/O adapter; copying, to the target system, the logical partition of the source system; placing an I/O adapter of the target system into an error state; mapping, in dependence upon the configuration information, the logical partition of the target system to the I/O adapter of the target system; placing the I/O adapter of the target system into an error recovery state; and resuming the logical partition on the target system.

Live partition mobility with I/O migration

The present disclosure relates to sharing an I/O device across multiple virtual machines. According to one embodiment, a computing system configures shared ownership of the I/O device between a first partition and one or more of the plurality of virtual machines. The computing system transfers partial ownership of the I/O device from the first partition to the one or more virtual machines and generates device configuration information for the I/O device. The virtual machines can use the generated device configuration information to access and configure the I/O device. Once the I/O device is configured for shared ownership, the computing system boots the one or more virtual machines.

Sharing ownership of an input/output device using a device driver partition

Failover of a virtual function exposed by an SR-IOV adapter of a computing system, including: instantiating, by a hypervisor, a standby virtual function in the computing system; detecting a loss of communication between a logical partition and an active virtual function mapped to the logical partition; placing the active virtual function and the standby virtual function in an error state; remapping the logical partition to the standby virtual function; and placing the standby virtual function in an error recovery state.

Failover of a virtual function exposed by an SR-IOV adapter

A method, system and computer program product are provided for implementing cable failover in multiple cable Peripheral Component Interconnect Express (PCIE) IO interconnections to an external IO enclosure. System firmware is provided for implementing health check functions for the PCIE IO interconnections to identify a faulted low byte cable. A cable failover mechanism recovers a PCI link to the external IO enclosure. A multiplexer logic is provided between the PCIE host bridge (PHB) and the cable connected to the IO enclosure to perform a full lane reversal of the PCIE lanes.

Implementing cable failover in multiple cable PCI Express IO interconnections

Growing community of inventors

Rochester, MN, United States of America

Jesse Paul Arroyo