Abstract: A plurality of requests are received for computing processing. At least some of the plurality of requests are replicated. The requests are replicated based on a fractional replication factor. Each received request and each replicated request are transmitted to a computer resource for processing. At least some embodiments provide the capability for meeting tail latency targets with improved performance and reduced cost.

Abstract: A plurality of requests are received for computing processing. At least some of the plurality of requests are replicated. The requests are replicated based on a fractional replication factor. Each received request and each replicated request are transmitted to a computer resource for processing. At least some embodiments provide the capability for meeting tail latency targets with improved performance and reduced cost.

Abstract: A plurality of requests are received for computing processing. At least some of the plurality of requests are replicated. The requests are replicated based on a fractional replication factor. Each received request and each replicated request are transmitted to a computer resource for processing. At least some embodiments provide the capability for meeting tail latency targets with improved performance and reduced cost.

Abstract: A computer-implemented method for preventing the occurrence of performance tickets in a computing system comprising a plurality of virtual machines hosted by a host computing system. The method comprising the steps of: monitoring a resource usage parameter associated with the workload of a virtual machine in order to obtain historic resource usage information; determining information regarding certain dependencies within the historic resource usage information; selecting partial information from the historic resource usage information based on said determined information regarding certain dependencies; estimating the future workload of the virtual machines based on said selected partial information; and resizing the computational resources of one or more virtual machines based on the estimated future workload such that a usage threshold of a computational resource is below a given threshold in order to avoid the generation of a performance ticket.

Abstract: A computing system comprises one or more multicore processor(s) comprising a set of multiple processing units each operable at a variable frequency, and a main memory operable at a variable frequency. A feedback controller is configured to control the frequency of each processing unit of the set and the frequency of the main memory dependent on a measure representative of a current performance of an application running on one or more of the multiple processing units of the set.

Abstract: The present invention is notably directed to systems and methods for detecting resource contention on a computerized system collocation of computer processes. Most basically, such methods comprise: monitoring data produced by each computer process of a set of computer processes co-located on the computerized system; detecting in the monitored data a change in a behavior of data produced by a given computer process of the set of computer processes; and throttling other computer processes of the set than said given computer process to detect potential resource contention at said given computer process. Such systems and methods advantageously apply to co-located virtual machines.

Abstract: A plurality of requests are received for computing processing. At least some of the plurality of requests are replicated. The requests are replicated based on a fractional replication factor. Each received request and each replicated request are transmitted to a computer resource for processing. At least some embodiments provide the capability for meeting tail latency targets with improved performance and reduced cost.

Abstract: A device is described. The device includes a daughterboard having a first distinct side and a second distinct side. A first connector on the first distinct side is attached to a first baseboard. A second connector on the second distinct side is attached to a second baseboard. A method for attaching a daughterboard to a second device is described. Connectors are included on opposing distinct sides of the daughterboard. The second device includes baseboards mechanically secured in parallel by lead screw actuators. As part of the method, the lead screw actuators are actuated so as to move the baseboards away from each other. A first connector is attached to one of the baseboards. The lead screw actuators are again actuated so as to move the baseboards toward each other until a second connector is brought into attachment with the other of the baseboards.

Abstract: A computer-implemented method for preventing the occurrence of performance tickets in a computing system comprising a plurality of virtual machines hosted by a host computing system. The method comprising the steps of: monitoring a resource usage parameter associated with the workload of a virtual machine in order to obtain historic resource usage information; determining information regarding certain dependencies within the historic resource usage information; selecting partial information from the historic resource usage information based on said determined information regarding certain dependencies; estimating the future workload of the virtual machines based on said selected partial information; and resizing the computational resources of one or more virtual machines based on the estimated future workload such that a usage threshold of a computational resource is below a given threshold in order to avoid the generation of a performance ticket.

Abstract: The present invention is notably directed to systems and methods for detecting resource contention on a computerized system collocation of computer processes. Most basically, such methods comprise: monitoring data produced by each computer process of a set of computer processes co-located on the computerized system; detecting in the monitored data a change in a behavior of data produced by a given computer process of the set of computer processes; and throttling other computer processes of the set than said given computer process to detect potential resource contention at said given computer process. Such systems and methods advantageously apply to co-located virtual machines.

Abstract: The sizing of virtual machines is optimized based on projected performance metrics. All virtual machine configuration resources are normalized by a processing device. The normalized resources for the virtual machine configurations are then stored in a catalogue. An application is then profiled to obtain resource demand estimates for each virtual machine configuration and a base performance is calculated for the application. The base performance is used to predict performance estimates on all virtual machine configurations in the catalogue. Accordingly, a virtual machine configuration having a lowest response time is selected.

Abstract: A computing system comprises one or more multicore processor(s) comprising a set of multiple processing units each operable at a variable frequency, and a main memory operable at a variable frequency. A feedback controller is configured to control the frequency of each processing unit of the set and the frequency of the main memory dependent on a measure representative of a current performance of an application running on one or more of the multiple processing units of the set.

Abstract: A device is described. The device includes a daughterboard having a first distinct side and a second distinct side. A first connector on the first distinct side is attached to a first baseboard. A second connector on the second distinct side is attached to a second baseboard. A method for attaching a daughterboard to a second device is described. Connectors are included on opposing distinct sides of the daughterboard. The second device includes baseboards mechanically secured in parallel by lead screw actuators. As part of the method, the lead screw actuators are actuated so as to move the baseboards away from each other. A first connector is attached to one of the baseboards. The lead screw actuators are again actuated so as to move the baseboards toward each other until a second connector is brought into attachment with the other of the baseboards.

Abstract: The sizing of virtual machines is optimized based on projected performance metrics. All virtual machine configuration resources are normalized by a processing device. The normalized resources for the virtual machine configurations are then stored in a catalog. An application is then profiled to obtain resource demand estimates for each virtual machine configuration and a base performance is calculated for the application. The base performance is used to predict performance estimates on all virtual machine configurations in the catalog. Accordingly, a virtual machine configuration having a lowest response time is selected.

Abstract: The interface for inter-thread communication between a plurality of threads including a number of producer threads for producing data objects and a number of consumer threads for consuming the produced data objects includes a specifier and a provider. The specifier is configured to specify a certain relationship between a certain producer thread of the number of producer threads which is adapted to produce a certain data object and a consumer thread of the number of consumer threads which is adapted to consume the produced certain data object. Further, the provider is configured to provide direct cache line injection of a cache line of the produced certain data object to a cache allocated to the certain consumer thread related to the certain producer thread by the specified certain relationship.

Abstract: In some embodiments of this disclosure, a computer-implemented method includes accessing a set of two or more activity logs associated with two or more virtual machines, each activity log being associated with a corresponding virtual machine. A computational capacity is calculated, by a computer processor, for each of the virtual machines based at least in part on the activity logs. A rank is calculated for each of the virtual machines, where a first rank calculated for a first virtual machine is based, at least in part, on a monetary cost of the first virtual machine and the calculated computational capacity of the first virtual machine.

Abstract: A system for hierarchical occupancy based congestion management includes a buffer embodied in a computer readable storage medium including a plurality of buffer units for storing packets of a data flow received from sources. The system includes a buffer manager that stores information about the packets stored in the buffer, including a selection criterion associated with each of the plurality of sources and a congestion estimator that monitors a congestion level in the buffer. The system also includes a occupancy sampler that randomly selects at least two occupied buffer units from the plurality of buffer units and identifies the source of the packet stored in each of the occupied buffer units and a congestion notification message generator that generates a congestion notification message; wherein if the congestion level in the buffer exceeds a threshold value the congestion notification message is sent to the identified source with a higher selection criteria.

Abstract: A method for hierarchical occupancy based congestion management includes receiving, by a computing device, a plurality of data flows, each of the plurality of data flows is received from a source and includes a plurality of data packets and storing the plurality of data packets in a buffer including multiple storage units. The method includes determining if the buffer is congested, responsive to determining the buffer is congested randomly selecting at least two occupied units of the buffer and identifying a source of each of the data packets stored in the occupied units of the buffer and generating a congestion notification message. The method also includes comparing a selection criterion associated with each identified source to determine which identified source has a higher selection criterion and sending the congestion notification message to the identified source with the higher selection criterion.

Abstract: In an exemplary embodiment, a computer-implemented method includes receiving a plurality of load data related to a plurality of physical machines in a computing environment. The plurality of load data is converted to a plurality of data points, each data point representing a corresponding physical machine from among the physical machines. A graph is generated, by a computer processor, of the plurality of data points representing the plurality of physical machines. A misbehavior alert is output for each of the physical machines that falls outside a predetermined safe range in the graph.

Abstract: In some embodiments of this disclosure, a computer-implemented method includes accessing a set of two or more activity logs associated with two or more virtual machines, each activity log being associated with a corresponding virtual machine. A computational capacity is calculated, by a computer processor, for each of the virtual machines based at least in part on the activity logs. A rank is calculated for each of the virtual machines, where a first rank calculated for a first virtual machine is based, at least in part, on a monetary cost of the first virtual machine and the calculated computational capacity of the first virtual machine.