Abstract: Disclosed is a novel system and method for managing requests for an additional virtual machine. The method begins with operating at least one virtual machine accessing at least one computer resource associated with at least one physical machine within a computing cluster. One or more non-deterministic virtual machine requests for the computer resource are received. An over-utilization of the computer resource as a probability distribution function is modeled. In one example, the probability distribution function is a Beta distribution function to represent a one of a plurality of probability distribution functions. Next, an additional virtual machine on the physical machine associated with the computer resource is added in response to a probability of a utilization of the computer resource being greater than a probalistic bound on the over-utilization of the computer resource. Otherwise, the additional virtual machine is not added.

Abstract: Described herein are methods, systems, apparatuses and products for cost-aware replication of intermediate data in dataflows. An aspect provides receiving at least one measurement indicative of a reliability cost associated with executing a dataflow; computing a degree of replication of at least one intermediate data set in the dataflow based on the reliability cost; and communicating at least one replication factor to at least one component of a system responsible for replication of the at least one intermediate data set in the dataflow; wherein the at least one intermediate data set is replicated according to the replication factor. Other embodiments are disclosed.

Abstract: A system, method and computer program product for detecting data omissions between intermittently-connected devices. An example system includes physical computing resources available for utilization. A placement server communicates with a client. The client seeks to use a portion of the computer resources to execute the software product instances. The placement server receives resource utilization parameters from the client and assigns the portion of the computer resources to the software product instances based on the resource utilization parameters and the physical computing resources available for utilization. The resource utilization parameters include specification of a hierarchal arrangement of the software product instances.

Abstract: A system, method and computer program product for detecting data omissions between intermittently-connected devices. An example system includes physical computing resources available for utilization. A placement server communicates with a client. The client seeks to use a portion of the computer resources to execute the software product instances. The placement server receives resource utilization parameters from the client and assigns the portion of the computer resources to the software product instances based on the resource utilization parameters and the physical computing resources available for utilization. The resource utilization parameters include specification of a hierarchal arrangement of the software product instances.

Abstract: An exemplary method of allocating a workload among a set of computing devices includes obtaining at least one efficiency model for each device. The method also includes, for each of a set of allocations of the workload among the devices, determining, for each device, the power consumption for the device to perform the workload allocated to the device by the allocation, the power consumption being determined based on the at least one efficiency model for each device; and determining a total power consumption of the devices. The method also includes selecting an allocation of the workload among the devices based at least in part on the total power consumption of the devices for each allocation. The method also includes implementing the selected allocation of the workload among the devices.

Abstract: A method and structure for processing an application program on a computer. In a memory of the computer executing the application, an in-memory cache structure is provided for normally temporarily storing data produced in the processing. An in-memory storage outside the in-memory cache structure is provided in the memory, for by-passing the in-memory cache structure for temporarily storing data under a predetermined condition. A sensor detects an amount of usage of the in-memory cache structure used to store data during the processing. When it is detected that the amount of usage exceeds the predetermined threshold, the processing is controlled so that the data produced in the processing is stored in the in-memory storage rather than in the in-memory cache structure.

Abstract: A method, system and computer program product for storing data in memory. An example system includes at least one multistage application configured to generate intermediate data in a generating stage of the application and consume the intermediate data in a subsequent consuming stage of the application. A runtime profiler is configured to monitor the application's execution and dynamically allocate memory to the application from an in-memory data grid.

Abstract: Systems and methods for admission control to a physical host system are provided herein. One aspect provides for receiving at least one resource request at an admission control component of a distributed computing system, the at least one resource request comprised of at least one system type; processing the at least one resource request utilizing at least one physical host accessible to the distributed computing system; specifying a number of resource request slots to be reserved for at least one system type based on at least one future reservation threshold accessible to the admission control component; and blocking resource requests from entering the system through the admission control component based on a number of available resource request slots and the at least one future reservation threshold. Other embodiments and aspects are also described herein.

Abstract: An optimization problem models the dynamic placement of applications on servers under two types of simultaneous resource requirements, those that are dependent on the loads placed on the applications and those that are independent. The demand (load) for applications changes over time and the goal is to satisfy all the demand while changing the solution (assignment of applications to servers) as little as possible.

Abstract: A technique is provided for creating virtual units in a computing environment. A virtual system definition is received by a processor that is utilized to create the virtual units for a virtual system. Relationship constraints between the virtual units in the virtual system are received by the processor. The relationship constraints between the virtual units include a communication link requirement between the virtual units and/or a location requirement between the virtual units. The virtual units in the virtual system are deployed by the processor according to the relationship constraints between virtual units.

Abstract: A system for learning admission policy for optimizing quality of service of computer resources networks is provided herein. The system includes a statistical data extractor configured to extract historical data of deployment requests issued to an admission unit of a computer resources network. The system further includes a Markov decision process simulator configured to generate a simulation model based on the extracted historical data and resources specifications of the computer resources network, in terms of a Markov decision process. The system further includes a value function generator configured to determine a value function for deployment requests admissions. The system further includes a machine learning unit configured to train a classifier based on the simulation model and the value function, to yield an admission policy usable for processing incoming deployment requests.

Abstract: A method for determining an application instance placement in a set of machines under one or more resource constraints includes the following steps. An estimate is computed of a value of the first metric that can be achieved by a current application instance placement and a current application load distribution. A new application instance placement and a new application load distribution are determined, wherein the new application instance placement and the new load distribution optimize the first metric.

Abstract: A method and structure for processing an application program on a computer. In a memory of the computer executing the application, an in-memory cache structure is provided for normally temporarily storing data produced in the processing. An in-memory storage outside the in-memory cache structure is provided in the memory, for by-passing the in-memory cache structure for temporarily storing data under a predetermined condition. A sensor detects an amount of usage of the in-memory cache structure used to store data during the processing. When it is detected that the amount of usage exceeds the predetermined threshold, the processing is controlled so that the data produced in the processing is stored in the in-memory storage rather than in the in-memory cache structure.

Abstract: Described herein are methods, systems, apparatuses and products for cost-aware replication of intermediate data in dataflows. An aspect provides receiving at least one measurement indicative of a reliability cost associated with executing a dataflow; computing a degree of replication of at least one intermediate data set in the dataflow based on the reliability cost; and communicating at least one replication factor to at least one component of a system responsible for replication of the at least one intermediate data set in the dataflow; wherein the at least one intermediate data set is replicated according to the replication factor. Other embodiments are disclosed.

Abstract: Systems and methods are provided for dynamically controlling application placement and server resource allocation in a distributed system wherein a performance manager and power manager collaborate during run-time execution of data processing tasks to coordinate management and control of workload placement and server usage and dynamically determine a tradeoff between performance level and power usage that meets power and performance objectives.

Abstract: Systems and methods for managing a system of heterogeneous workloads are provided. Work that enters the system is separated into a plurality of heterogeneous workloads. A plurality of high-level quality of service goals is gathered. At least one of the plurality of high-level quality of service goals corresponds to each of the plurality of heterogeneous workloads. A plurality of control functions are determined that are provided by virtualizations on one or more containers in which one or more of the plurality of heterogeneous workloads run. An expected utility of a plurality of settings of at least one of the plurality of control functions is determined in response to the plurality of high-level quality of service goals. At least one of the plurality of control functions is exercised in response to the expected utility to effect changes in the behavior of the system.

Abstract: An optimization problem models the dynamic placement of applications on servers under two types of simultaneous resource requirements, those that are dependent on the loads placed on the applications and those that are independent. The demand (load) for applications changes over time and the goal is to satisfy all the demand while changing the solution (assignment of applications to servers) as little as possible.

Abstract: Coordinating tasks of performance management and application placement management in a dynamic fashion by: estimating capacity needs for various service classes of service requests; computing desired capacities of at least one application for said service requests; deciding whether the desired capacities are satisfied by a current application placement; making no change to current application placement if the desired capacities are satisfied; determining a new application placement based on the desired capacities and a projected load if the desired capacities are not satisfied; computing corresponding capacity constraints for all pairs of service classes and servers; and computing an optimal allocation of capacities among the service classes so as to optimize a quality of service.

Abstract: An optimization problem models the dynamic placement of applications on servers under two types of simultaneous resource requirements, those that are dependent on the loads placed on the applications and those that are independent. The demand (load) for applications changes over time and the goal is to satisfy all the demand while changing the solution (assignment of applications to servers) as little as possible.

Abstract: Techniques for placement of a virtual machine in a computing system. A first request is sent from a pool management subsystem to a placement subsystem. The first request includes specification of available storage capacities of storage systems in a computer network. The placement subsystem automatically determines a target storage system based, at least in part, on the available storage capacities. An identification of the target storage system is received at the pool management subsystem. At least one disk image of the virtual machine is written to the target storage system. Then, a second request is sent to the placement subsystem. The placement subsystem automatically determines a target computer. The latter determination is based, at least in part, on connectivity between the target computer and the target storage system. The virtual machine is installed at the target computer. The techniques facilitate live migration of virtual machines placed thereby.