International Business Machines Corporation

Colin Robert DeVilbiss

Charles Scott Graham

Timothy J Schimke

James Brian Cunningham

Steven Edward Royer

David Charles Boutcher

Adrian Cuenin Gerhard

David R Engebretsen

A first operation in a computing environment with a set of nodes is monitored. A subset of nodes that are utilized by the first operation is identified. The subset of nodes is a subset of the set of nodes. For each node in the subset of nodes, an operation counter for the respective node is incremented and an operation time for the first operation is added to a total operation timer for the respective node. For each node in the subset of nodes, the respective total operation timer is divided by the respective operation counter. A node in the subset of nodes that appears to be slow is identified based on the dividing. The data for multiple operations could be aggregated in the operation counters and total operation timers for each node within the set of nodes, enabling nodes that appear to be slow to be identified on aggregate data.

Identifying slow nodes in a computing environment

Automated dynamic load balancing across VNIC fast switchover devices including monitoring, by a resource monitor, resource utilization metrics of at least one resource used to send data along a first communications path through a hypervisor; in response to detecting, by the resource monitor based on the resource utilization metrics, that the at least one resource crosses a resource utilization threshold, sending a notification to a rebalancer, wherein the notification comprises a subset of the resource utilization metrics; generating, by the rebalancer based on the subset of the resource utilization metrics, a resource optimized mapping for the at least one resource used to send data along the first communications path; and issuing, by the rebalancer, the resource optimized mapping to the hypervisor, wherein the hypervisor reconfigures, based on the resource optimized mapping, the at least one resource used to send data along the first communications path.

Automated dynamic load balancing across virtual network interface controller fast switchover devices using a rebalancer

The present invention provides computer implemented method, system, and computer program product of switching servers without interrupting a client command-response queue. In an embodiment, the present invention includes selecting standby computer server systems, connecting a CRQ of a client computer system to a previous active computer server system and to the selected standby computer server systems, transmitting setup commands to the selected standby computer server systems, communicating data with the previous active computer server system via at least one sub-CRQ, communicating management commands with the previous active computer server system and the selected standby computer server systems via the CRQ, receiving a notification that a switchover has occurred, redirecting the CRQ to one of the selected standby computer server systems, in response to the redirecting, communicating data with a new active computer server system via at least one sub-CRQ, and sending new setup commands to the new computer server system.

Switching servers without interrupting a client command-response queue

Automated dynamic load balancing across virtual network interface controller fast switchover devices

Techniques are disclosed for providing Ethernet link aggregation for logically independent entities that share a plurality of physical ports. A client operating system (OS) executing in a host computing system receives a selection of two or more logical Ethernet ports. Each logical Ethernet port is assigned to one of a plurality of physical Ethernet ports of a network adapter. The client OS generates a first link aggregate from the logical Ethernet ports. System firmware assigns an identifier to the first link aggregate that associates an aggregate configuration with the first link aggregate. The firmware registers the aggregate configuration with a network device that maintains configurations of at least a second link aggregate.

Ethernet link aggregation with shared physical ports

Techniques are disclosed for providing Ethernet link aggregation over physical ports shared by logically independent entities. An aggregation manager receives a frame at a first logical port that receives frames targeted to at least a second logical port. A client operating system receives the frame at the second logical port. The aggregation manager determines whether the second logical port received the frame. Upon determining that the second logical port did not receive the frame, the aggregation manager forwards the frame to the client OS via a sideband interface associated with the client OS.

An apparatus and method provide a protocol for communicating between an operating system that owns a shared resource and other operating systems that use the shared resource so that the operating systems that use the shared resource will not crash if the operating system that owns the shared resource is restarted. Messages are defined that allow handshaking between operating systems so that operating systems that share a resource will realize the resource will be unavailable for some period of time, and that allow resuming the sharing of the resource once the operating system that owns the shared resource is restarted.

Restarting a shared virtual resource

A memory tag mechanism creates a logical memory tag of a first length that corresponds to an I/O address of a second length. The memory tag is 'logical' because it does not represent physical memory. When an I/O adapter device driver that expects an address of the first length is invoked, the memory tag is passed. When the I/O adapter device driver makes a call to the partition manager to convert the address of the first length (i.e., memory tag) to an I/O address of the second length, the partition manager detects that the passed address is a memory tag instead of a real address, and returns the corresponding I/O address. In this manner existing device drivers that expect addresses of the first length may be used for redirected DMA, which allows performing DMA operations directly from a shared I/O adapter in a hosting partition to memory in a hosted partition.

Growing community of inventors

Rochester, MN, United States of America

Colin Robert DeVilbiss