Abstract: Systems and methods are described for managing computing resources. In one embodiment, data representative of an abstracted firmware framework is maintained. The data may comprise computing firmware settings and determined based on standardized associations between vendor-specific firmware settings and abstracted firmware settings that are independent of the vendor-specific firmware settings. In response to receiving a request for a computing firmware setting, the requested computing firmware setting is translated to one or more vendor-specific firmware settings based on the data. A computing resource capable of implementing the one or more vendor-specific firmware settings is identified.

Abstract: Efficient and highly-scalable network solutions are provided that each utilize deployment units based on Clos networks, but in an environment such as a data center of Internet Protocol-based network. Each of the deployment units can include multiple stages of devices, where connections between devices are only made between stages and the deployment units are highly connected. In some embodiments, the level of connectivity between two stages can be reduced, providing available connections to add edge switches and additional host connections while keeping the same number of between-tier connections. In some embodiments, where deployment units (or other network groups) can be used at different levels to connect other deployment units, the edges of the deployment units can be fused to reduce the number of devices per host connection.

Abstract: Techniques for using hardware-based mechanisms for updating computing resources are described herein. At a time after receiving a code update request, one or more hardware-supported system management capabilities of processors within a computing system are invoked at least to interrupt execution of currently running instructions. While the system management capabilities are active and instruction execution is suspended, programmatic routines are updated. After the updates are complete, instruction execution is resumed.

Abstract: Systems and methods for handling resources in a computer system differently in certain situations, such as catastrophic events, based upon an assigned layer of the resource to the system. The layer can be based, for example, on criticality of the resource to the system. Services or computing device resources can be physically segregated in accordance with layers, and can be managed in accordance with the segregation. As an example, critical layers can be fenced off or otherwise made not available except to users with secure clearance or authorization. In addition, a light or other indicator can be provided for indicating that a datacenter component is in a particular layer. The indicators can be at a device level, rack level, and/or room or area level.

Abstract: Approaches for automatically backing up data from volatile memory to persistent storage in the event of a power outage, blackout or other such failure are described. The approaches can be implemented on a computing device that includes a motherboard, central processing unit (CPU) a main power source, volatile memory (e.g., random access memory (RAM)), an alternate power source and circuitry (e.g., a specialized application-specific integrated circuit (ASIC)) for performing the backup of volatile memory to a persistent storage device. In the event of a power failure of the main power source, the alternate power source is configured to supply power to the specialized ASIC for backing up the data in the volatile memory. For example, when power failure is detected, the ASIC can read the data from the DIMM socket using power supplied from the alternate power source and write that data to a persistent storage device.

Abstract: Host machines and other devices performing synchronized operations can be dispersed across multiple racks in a data center to provide additional buffer capacity and to reduce the likelihood of congestion. The level of dispersion can depend on factors such as the level of oversubscription, as it can be undesirable in a highly connected network to push excessive host traffic into the aggregation fabric. As oversubscription levels increase, the amount of dispersion can be reduced and two or more host machines can be clustered on a given rack, or otherwise connected through the same edge switch. By clustering a portion of the machines, some of the host traffic can be redirected by the respective edge switch without entering the aggregation fabric. When provisioning hosts for a customer, application, or synchronized operation, for example, the levels of clustering and dispersion can be balanced to minimize the likelihood for congestion throughout the network.

Abstract: The deployment and scaling of a network of electronic devices can be improved by utilizing one or more network transpose boxes. Each transpose box can include a number of connectors and a meshing useful for implementing a specific network topology. Different tiers of a network can be connected to one or more of the network transpose boxes, and operated as a logical switch. A control server can be used to manage the control plane operations of the logical switch.

Abstract: Workloads can be intelligently placed across a group of resources in order to attempt to balance or otherwise manage the level of wear among various components of those resources. Devices such as solid state drives or other NAND-type devices can have a limited number of operations that can be performed before those devices become unreliable, such that it can be desirable to monitor the wear level of each of these devices. As it can be easier to manage resources with similar wear levels for large groups of resources, it can be desirable to attempt to level the relative amount of wear among at least groups of these resources. Attempts can be made to level across a fleet or resources, within pools of resources, and/or within the resources themselves, such as where a server includes multiple devices with potentially different wear levels, such as multiple NAND-type devices.

Abstract: Systems and methods for handling battery backup resources in a computer system differently in certain situations, such as catastrophic events, based upon an assigned layer of the datacenter components to which the battery backup resource provides backup power. The layer can be based, for example, on criticality of the resource to the system. Less critical layers can shed load or gracefully shut down to respond to the event, and the battery resources can be reallocated or reconfigured to provide battery power to the more critical layers.

Abstract: Systems and methods are described for testing computing resources. In one embodiment, a request is received for testing a computing configuration. A set of computing settings that can be implemented on one or more computing devices is searched. An initial test population for testing the computing configuration is determined. The initial test population is iteratively updated based on test results and a fitness function.

Abstract: Systems and methods are described for testing computing resources. In one embodiment, a search space of computing settings is analyzed in accordance with weighted data that maps computing performance parameters with the computing settings. A subset of the computing settings is selected to generate a test population to optimize at least one computing performance parameter. One or more computing devices in a computing environment are configured in accordance with the test population, and the test conditions are iteratively updated based on test results in accordance with the test population and a fitness function.

Abstract: Operating profiles for consumers of computing resources may be automatically determined based on an analysis of actual resource usage measurements and other operating metrics. Measurements may be taken while a consumer, such as a virtual machine instance, uses computing resources, such as those provided by a host. A profile may be dynamically determined based on those measurements. Profiles may be generalized such that groups of consumers with similar usage profiles are associated with a single profile. Assignment decisions may be made based on the profiles, and computing resources may be reallocated or oversubscribed if the profiles indicate that the consumers are unlikely to fully utilize the resources reserved for them. Oversubscribed resources may be monitored, and consumers may be transferred to different resource providers if contention for resources is too high.

Abstract: A service provider can maintain one or more host computing devices that can be accessed as host computing device resources by customers. A hosting platform includes components arranged in a manner to limit modifications to software or firmware on hardware components. In some aspects, the hosting platform may include a master latch that indicates whether the components may be configured, and the master latch may be set once and only reset upon completion of a power cycle. In another aspect, the hosting platform can implement management functions for establishing control plane functions between the host computing device and the service provider that is independent of the customer. Additionally, the management functions can also be utilized to present different hardware or software attributes of the host computing device.

Abstract: Customers in a multi-tenant environment can obtain energy consumption information for a set of resources or other computing components used by those customers, including time-accurate accounting for various components of those resources utilized on behalf of the customer. A customer can also have the ability to specify how the resources are to be operated when used for the customer, in order to manage the amount of energy consumption. The accounting can be performed even when the resources are shared among multiple users or entities. Various hardware components or agents can be used to provide detailed energy consumption information for those components that is associated with a particular customer. The information can be used not only for accounting and monitoring purposes, but also to make dynamic adjustments based on various changes in usage, energy consumption, or other such factors.

Abstract: Efficient and highly-scalable network solutions are provided that each utilize deployment units based on Clos networks, but in an environment such as a data center of Internet Protocol-based network. Each of the deployment units can include multiple stages of devices, where connections between devices are only made between stages and the deployment units are highly connected. In some embodiments, the level of connectivity between two stages can be reduced, providing available connections to add edge switches and additional host connections while keeping the same number of between-tier connections. In some embodiments, where deployment units (or other network groups) can be used at different levels to connect other deployment units, the edges of the deployment units can be fused to reduce the number of devices per host connection.

Abstract: A system and method for preventing dependency problems, such as deadlocks, within network-based computing service workflows, such as workflows that occur within computing assets that provide network-based computing services. The system and method creates a remedial workflow or action for the computing services to address deadlocks or other blocking conditions within the services which may occur should the underlying computing assets need to be restarted, rebooted or sequentially execute and reach a problematic operational state. The system and method will determine the reliance of each computing service upon the functionality of one or more other network-based computing services and structure the remedial workflow accordingly. Other aspects of the disclosure are described in the detailed description, figures, and claims.

Abstract: Systems and methods are described for testing computing resources. In one embodiment, a request for verification of a computing setting related to a computing environment is received. Computing environment parameters and performance metrics are analyzed to determine an initial test population for testing the computing setting. A computing device in the computing environment is configured in accordance with the initial test population. Testing in accordance with the initial test population is performed and the initial test population is iteratively updated based on results of the testing.

Abstract: Generally described, systems and methods are provided for monitoring and detecting causes of failures of network paths. The system collects performance information from a plurality of nodes and links in a network, aggregates the collected performance information across paths in the network, processes the aggregated performance information for detecting failures on the paths, analyzes each of the detected failures to determine at least one root cause, and initiates a remedial workflow for the at least one root cause determined. In some aspects, processing the aggregated information may include performing a statistical regression analysis or otherwise solving a set of equations for the performance indications on each of a plurality of paths. In another aspect, the system may also include an interface which makes available for display one or more of the network topology, the collected and aggregated performance information, and indications of the detected failures in the topology.

Abstract: Approaches are described for updating code and/or instructions in one or more computing devices. In particular, various embodiments provide approaches for updating the microcode of one or more processors of a computing device without requiring a restart of the computing device and without disrupting the various components (e.g., applications, virtual machines, etc.) executing on the computing device. The microcode updates can be performed on host computing devices deployed in a resource center of a service provider (e.g., cloud computing service provider), where each host computing device may be executing a hypervisor hosting multiple guest virtual machines (or other guest applications) for the customers of the service provider.

Abstract: Systems and methods are described for managing computing resources. In one embodiment, mappings between a plurality of parameters of an abstracted firmware framework to corresponding firmware settings of computing components are maintained. The mappings are determined based on predetermined associations between vendor-specific firmware settings and abstracted firmware settings that implement a standardized interface that is independent of the vendor-specific firmware settings. In response to receiving one of the plurality of parameters, the received parameter is translated to corresponding vendor-specific firmware settings based on the mappings.