International Business Machines Corporation

Amazon Technologies, Inc.

Manu Anand

Charles Scott Graham

Timothy J Schimke

Jesse Paul Arroyo

Prathima Kommineni

Lalit Jain

Visakh Sakthidharan Nair

Aman Singhal

Ajit Balachandran

Kumar Shubhankar

Systems and methods are disclosed herein for determining the validity of certificates possessed by a plurality of computer system instances operating under a service of a computing resource service provider. A certificate authority may hold an election to determine an intermediary computer system instance among the plurality of computer system instances to communicate between the certificate authority and the plurality of computer system instances. The intermediary instance may receive a set of certificate fingerprints from the plurality of computer system instances. The intermediary instance may compare the set of certificate fingerprints to a valid certificate fingerprint generated using a valid certificate to determine the validity of certificates possessed by the plurality of computer system instances. The intermediary instance may generate a report based on the determination of the validity of the certificates. The certificate authority may modify the instances operating under the service based on the report.

Network traffic distribution using certificate scanning in agent-based architecture

A tiering service that supports cold tier indexing includes a warm tier and a cold tier and a resource manager that automatically relocates data items between the warm tier and the cold tier or removes data items from the cold tier in accordance with a tiering policy. The tiering service also includes a client interface configured to receive a request specifying index criteria for a cold tier index to be created. The tiering service generates a cold tier index based on data items stored in cold tier flat files satisfying the index criteria included in the request to create a cold tier index. Also, the tiering service automatically updates the cold tier index after it is stored in the cold tier as data items are relocated between the warm tier and the cold tier or removed from the cold tier in accordance with the tiering policy. In some embodiments, the tiering service also provides a common interface for accessing the cold tier index and a warm tier index.

Data tiering service with cold tier indexing

A client-configurable tiering service implements an interface allowing a client to specify a tiering policy selected from a plurality of supported tiering policies for data of the client stored in a warm tier, wherein the tiering policies specify conditions for relocating portions of the data to a cold tier. The interface also allows a client to specify a tombstone forwarding policy selected from a plurality of supported tombstone forwarding policies, wherein the tombstone forwarding policies specify how data relocated from the warm tier to the cold tier is subsequently retrieved in response to an access request directed to the warm tier. The client-configurable tiering service relocates and retrieves data between a warm tier and a cold tier in accordance with the client's selected policies. In some embodiments, a client may specify further aspects of how data is stored and relocated between different tiers of a data store.

Client-configurable data tiering service

A tiering service that supports multiple cold tier quality of service (QoS) policies includes a configuration manager that receives a specification for one or more QoS parameters for a cold tier and reserves resources of a provider network to implement the cold tier in accordance with the specified QoS parameters. The QoS parameters may specify one of a plurality of supported cold tier access level policies for the cold tier. Also other QoS parameters may be specified. The cold tier access level policies may specify combinations of local and/or remote resources to be used for the cold tier. In some embodiments, a client may specify or modify cold tier QoS policies in order to perform different tasks. Also a client may modify the specified QoS policies for the cold tier after completion of the tasks or to perform other tasks.

Data-tiering service with multiple cold tier quality of service levels

Firmware management of SR-IOV adapters in a computing system includes: receiving, by a hypervisor, a request to update a hypervisor-hosted firmware image including replacing a firmware image previously stored in a reserved memory space of the hypervisor with a replacement firmware image, where the hypervisor-hosted firmware image includes an SR-IOV adapter firmware image configured for installation on SR-IOV adapters of a particular type; determining whether all SR-IOV adapters of the particular type in the computing system have been updated to the previously stored firmware image; and updating the hypervisor-hosted firmware image only if all SR-IOV adapters of the particular type in the computing system have been updated to the previously stored firmware image, including replacing, in the reserved memory space, the previously stored firmware image with the replacement firmware image.

Firmware management of SR-IOV adapters

A computing environment includes a computing system, where the computing system includes a plurality of logical partitions, a hypervisor supporting the plurality of logical partitions, a plurality of SR-IOV adapters, where at least one of the logical partitions is mapped to a virtual function on a first SR-IOV adapter of the plurality of adapters, and where migrating an SR-IOV adapter configuration in the computing environment includes: cloning, on a second SR-IOV adapter, a configuration of the first SR-IOV adapter; placing the second SR-IOV adapter and the virtual function in an error state; remapping the virtual function from the first SR-IOV adapter to the second SR-IOV adapter; and placing the second SR-IOV adapter and the virtual function in an error recovery state.

Migrating single root I/O virtualization adapter configurations in a computing system

A method, system and computer program product are provided for implementing dynamic cost calculation for a Single Root Input/Output Virtualization (SRIOV) virtual function (VF) in cloud environments. A management function periodically queries the SRIOV adapter for activity statistics for each assigned virtual function. The management function builds a usage heuristic based on the resource usage statistics. The management function calculates dynamic cost for the SRIOV VF based on the resource usage statistics. Calculated dynamic costs for the SRIOV VF are provided to a virtual function user and users are enabled to scale their VF resources. The VF resources are selectively scaled-up and scaled-down responsive to user input based upon VF resource usage.

Implementing dynamic cost calculation for SRIOV virtual function (VF) in cloud environments

A method, system and computer program product are provided for implementing dynamic configuration of a Single Root Input/Output Virtualization (SRIOV) virtual function in a virtualized system. A management function, a hypervisor, a hypervisor based PF device driver and a partition based virtual function (VF) device driver are used to implement usage based VF resizing. The management function periodically queries the SRIOV adapter for activity statistics for every assigned virtual function. The management function builds a usage heuristic based on these statistics and calculates VF resource usage based on these statistics. The usage information determines whether VF resources need to be scaled-up or scaled-down. A corresponding resize event is generated and send by the management function to both the hypervisor based PF device driver and partition based VF device driver. Both the PF and VF device drivers scale to the corresponding VF resource of the resize event.

Growing community of inventors

Hyderabad Telangana, India

Manu Anand