Abstract: In a read processing storage system, using a pool of CPU cores, the CPU cores are assigned to process either write operations, read operations, and read and write operations, that are scheduled for processing. A minimal number of the CPU cores are allocated for processing the write operations, thereby increasing write latency.

Abstract: A virtual computer system service receives a request to migrate a virtual machine instance from a first physical host to another physical host. The virtual computer system service identifies a configuration of the first physical host and obtains a data structure that specifies compatibility values for pairings of physical host configurations. The virtual computer system uses the configuration of the first physical host and the data structure to select a compatible physical host configuration. Using this compatible physical host configuration, the virtual computer system service selects a set of physical hosts that have this compatible physical host configuration. The set of physical hosts is used to select a second physical host onto which the virtual machine instance is migrated.

Abstract: Described herein are methods and system for sharing a wireless interface (102) among various multiple host processors in a multi-processor computing system (100) to provide simultaneous access of a wireless network to the host processors.

Abstract: There is provided a method, a system and a computer program product for improving performance and fairness in sharing a cluster of dynamically available computing resources among multiple jobs. The system collects at least one parameter associated with availability of a plurality of computing resources. The system calculates, based on the collected parameter, an effective processing time each computing resource can provide to each job. The system allocates, based on the calculated effective processing time, the computing resources to the multiple jobs, whereby the multiple jobs are completed at a same time or an approximate time.

Abstract: A control method is disclosed. The control method is suitable for an electronic device including first processing cores. The control method includes operations as follows. A device status of the electronic device is monitored. A threshold loading level of the first processing cores is dynamically set according to the device status. A loading management of multi-processor is performed according to a current loading level of the processing cores and the threshold loading level.

Abstract: An adaptive virtual desktop architecture is provided. Application install or assignment is evaluated, such as by using heuristics to identify applications that may present compatibility problems. Upon determining that a newly installed application may have compatibility problems when associated with a non-persistent virtual desktop, a promotion to a persistent virtual desktop occurs.

Abstract: An apparatus and method for load balancing in a ray tracing architecture. For example, one embodiment of a graphics processing apparatus comprises: an intersection unit engine to test a plurality of rays against a plurality of primitives to identify a closest primitive that each ray intersects; an intersection unit queue to store work to be performed by the intersection unit engine; and an intersection unit offload engine to monitor the intersection unit queue to determine a pressure level on the intersection unit engine, the intersection unit offload engine to responsively offload some of the work in the intersection unit queue to intersection program code executed on one or more execution units of the graphics processor.

Abstract: A method for scheduling work for processing by a GPU is disclosed. The method includes accessing a work completion data structure and accessing a work tracking data structure. Dependency logic analysis is then performed using work completion data and work tracking data. Work items that have dependencies are then launched into the GPU by using a software work item launch interface.

Abstract: Memory is reserved in a virtualized computing environment for graphics processing of each child partition in the computing environment. A video memory controller can identify video settings for child partitions. The video memory controller can determine an amount of memory for graphics processing for a child partition based on the video settings for that child partition. The video memory can also request an amount of memory to be reserved for that child partition based on the calculated amount of memory. Reserving memory for graphics processing of child partitions in this way allows for a sufficient amount of memory to be reserved for a child partition without wasting memory resources by reserving significantly more memory than is needed for the child partition.

Abstract: A method in a server end station is described. The method includes performing an iteration of a rebalancing computation by selecting a set of one or more service sets for rebalancing, wherein the selecting the set of one or more service sets is based on service set constraints and host constraints; generating candidate solutions, wherein each candidate solution includes a randomized one-to-one mapping of each of the service sets to one of the hosts; performing one or more crossover operations on the candidate solutions; performing one or more mutation operations on the additional candidate solutions; selecting as a solution one of the candidate solutions that has a best fitness score, wherein a fitness score for a candidate solution is calculated based on the distribution of resources resulting from and number of migrations needed for the candidate solution; and repeating the iteration of the rebalancing computation an additional number of times.

Abstract: A system and method for monitoring a plurality of servers by a monitoring server in a computer network. A list of servers and a plurality of services to monitor in the computer network is generated at the monitoring server. A status query is transmitted sequentially by the monitoring server to each of the plurality of servers, the status query including the plurality of services to monitor at each server. A status message report is received from each of the plurality of servers in response to each status query. An event is reported in an event log for each server that has an abnormal service status. The transmission of the status query to each server is performed by the monitoring server at a specified service time interval.

Abstract: A health check method for a distributed load balancer in which a router receives packets from at least one client and routes packet flows to multiple load balancer (LB) nodes, which in turn distribute the packet flows among multiple server nodes. Each LB node may be responsible for health checking one or more other LB nodes. In addition, each LB node may health check one or more of the server nodes. Heartbeat information for the nodes may be disseminated among the LB nodes according to a gossip protocol. The LB nodes may send LB node membership information to the server nodes. Failure of a node may be detected by the LB nodes according to the heartbeat information, and appropriate actions taken.

Abstract: A method for dynamically assigning resources of a distributed server infrastructure, the method comprising the steps of comparing an observed relative load of an assigned portion of said distributed server infrastructure with a desired relative load; if said observed relative load exceeds said desired relative load assigning additional resources, and redistributing tasks from said assigned portion to said additional resources; and if said desired relative load exceeds said desired relative load: selecting removable resources, redistributing tasks from said removable resources to other resources in said assigned portion, and removing said removable resources from said assigned portion; wherein said redistributing of tasks is performed in such a way that state information related to said tasks is preserved.

Abstract: A resource management system and method for performing resource management operations in a distributed computer system uses a dispersion rule to try to uniformly disperse clients in a cluster of host computers in the distributed computer system. The dispersion rule is used to compute a dispersion score for at least one candidate distribution of the clients in the cluster of host computers, which is used to select a particular candidate distribution of the clients in the cluster of host computers to disperse the clients.

Abstract: One embodiment provides a system for scheduling I/O resources of a virtual machine. During operation, in response to receiving a plurality of I/O requests, the system identifies a plurality of target virtual disks to which the I/O requests are to be sent, wherein a virtual disk corresponds to a previously created I/O queue. The system assigns a respective I/O request to the corresponding I/O queue for an identified target virtual disk. The system schedules I/O resources to be used by the respective I/O request based on a scheduling parameter that corresponds to the identified target virtual disk.

Abstract: A multi-core processor system and a method for assigning tasks are provided. The multi-core processor system includes a plurality of processor cores, configured to perform a plurality of tasks, and each of the tasks is in a respective one of a plurality of scheduling classes. The multi-core processor system further includes a task scheduler, configured to obtain first task assignment information about tasks in a first scheduling class assigned to the processor cores, obtain second task assignment information about tasks in one or more other scheduling classes assigned to the processor cores, and refer to the first task assignment information and the second task assignment information to assign a runnable task in the first scheduling class to one of the processor cores.

Abstract: A cache affinity and processor utilization technique efficiently load balances work in a storage input/output (I/O) stack among a plurality of processors and associated processor cores of a node. The storage I/O stack employs one or more non-blocking messaging kernel (MK) threads that execute non-blocking message handlers (i.e., non-blocking services). The technique load balances work between the processor cores sharing a last level cache (LLC) (i.e., intra-LLC processor load balancing), and load balances work between the processors having separate LLCs (i.e., inter-LLC processor load balancing). The technique may allocate a predetermined number of logical processors for use by an MK scheduler to schedule the non-blocking services within the storage I/O stack, as well as allocate a remaining number of logical processors for use by blocking services, e.g., scheduled by an operating system kernel scheduler.

Abstract: Techniques are described for formally expressing whether sequences of operations performed on block storage devices are sequential or random. In embodiments, determinations of whether these sequences of operations are sequential or random may be used to predict latencies involved with running particular workloads, and to predict representative workloads for particular latencies.

Abstract: Redirecting message flows to bypass load balancers. A destination intermediary receives a source-side message that includes a virtual address of a load balancer as a destination, and that is augmented to include a network address of a destination machine as a destination. The destination intermediary determines that a source intermediary should address subsequent network messages that originate from a source machine and that are associated with the same multi-message flow to the destination machine while bypassing the load balancer. The destination intermediary modifies the source-side message so the destination for the source-side message addresses the destination machine, and passes the modified source-side message to the destination machine.

Abstract: A method of reducing execution jitter includes a processor having several cores and control logic that receives core configuration parameters. Control logic determines if a first set of cores are selected to be disabled. If none of the cores is selected to be disabled, the control logic determines if a second set of cores is selected to be jitter controlled. If the second set of cores is selected to be jitter controlled, the second set of cores is set to a first operating state. If the first set of cores is selected to be disabled, the control logic determines a second operating state for a third set of enabled cores. The control logic determines if the third set of enabled cores is jitter controlled, and if the third set of enabled cores is jitter controlled, the control logic sets the third set of enabled cores to the second operating state.

Abstract: In one embodiment, a method for load balancing in a software-define networking (SDN) system includes, upon receiving a packet, determining whether a matching entry for the packet in a server distribution table contains both a current and new server selection. If the matching entry contains both, it is determined whether there is a matching entry for the packet in a transient flow table, where the transient flow table maintains server selections when at least one of the plurality of servers is reconfigured. Upon determining that there is no matching entry for the packet in the transient flow table, the method determines whether the packet is a first packet of a traffic flow. If the packet is the first packet of a traffic flow, the packet is forwarded according to the new server selection of the matching entry in the server distribution table, and the transient flow table is updated.

Abstract: An apparatus and associated methodology contemplating a data storage system having a group of processor-controlled intelligent storage elements (ISEs). Each ISE in the group individually includes storage resources and a network interface. The storage resources of all the ISEs in the group collectively define a field of storage (FoS). A portion of the FoS is addressable by a remote device or by another ISE via the respective ISE's network interface. An ISE FoS structure (ISEFoS) is individually stored in nonvolatile memory within each of the ISEs in the group. Each ISEFoS contains parametric data pertaining to every ISE in the group. Orchestration logic executed by one of the ISEs of the group (a recipient ISE), in response to the recipient ISE receiving a storage management operation request via the network interface, queries the recipient ISE's ISEFoS in order to optimally determine which ISE in the group to use in executing the storage management operation request.

Abstract: Method to perform an operation, by, responsive to a request specifying to transition a state of a virtual machine in a cloud computing environment from a first state to a second state, allocating one or more system resources to the virtual machine during the transition from the first state to the second state, and, upon completion of the transition, releasing a portion of the allocated one or more system resources to a pool of available resources, so that the virtual machine is left with a remaining portion of the allocated one or more resources sufficient for operation during the second state.

Abstract: A conformance checker is received on a system that contains hostable content, and is executed. One or more results provided by the conformance checker are evaluated; and the hostable content is migrated to a destination host in accordance with the evaluating step.

Abstract: Methods, systems, and computer program products are provided for optimizing virtual graphics processing unit utilization. Embodiments include assigning a computing intensity level to each virtual machine of a plurality of virtual machines; assigning a priority level to each virtual machine of the plurality of virtual machines; determining for each server of a plurality of servers whether the server includes a virtual graphics processing unit (VGPU) that is available to perform compute intensive tasks for the plurality of virtual machines; and assigning one or more VGPUs to a virtual machine of the plurality of virtual machines in dependence upon the computing intensity level and the priority level of the virtual machine and the number of VGPUs available to perform the compute intensive tasks.

Abstract: One aspect is a method that includes analyzing, by a processor of an analysis system, an instruction set architecture of a targeted complex-instruction set computer (CISC) processor to generate an instruction set profile for each CISC architectural instruction variant of the instruction set architecture. A combination of instruction sequences for the targeted CISC processor is determined from the instruction set profile that corresponds to a desired stressmark type. The desired stressmark type defines a metric representative of functionality of interest of the targeted CISC processor. Performance of the targeted CISC processor is monitored with respect to the desired stressmark type while executing each of the instruction sequences. One of the instruction sequences is identified as most closely aligning with the desired stressmark type based on performance results of execution of the instruction sequences with respect to the desired stressmark type.

Abstract: A system to improve cluster machine processing that may include a plurality of interconnected computers that process data as one if necessary, and at least one other plurality of interconnected computers that process data as one if necessary. The system may also include a central manager to control what data processing is performed on a shared processing job performed by the plurality of interconnected computers and the at least one other plurality of interconnected computers. Each of the plurality of interconnected computers runs parallel jobs scheduled by a local backfill scheduler. In order to schedule a cluster spanning parallel job, the local schedulers cooperate on placement and timing of the cluster spanning job, using existing backfill rules in order not to disturb the local job streams.

Abstract: A device or system includes a plurality of storage resources each associated with a respective performance class, each being associated with selected performance characteristics such as IOPS, bandwidth, etc. The device or system includes a compute instance having access to allocated storage resources, the allocated storage devices including one or more storage resources. The device or system also includes an optimization component adapted to obtain information relating to utilization by the compute instance component of the allocated storage resources, determine that a change to the allocated storage resources is necessary, based on the information, cause data to be migrated from a first storage resource associated with a first performance class to a second storage resource associated with a second storage class, and cause a removal from the allocated storage resources of the first storage resource and an addition to the allocated storage resources of the second storage resource.

Abstract: A first cell transmits a virtual cell identifier and state information associated with the virtual cell identifier over an interface to a second cell. The first cell and one or more third cells use the virtual cell identifier for transmissions to first user equipment. The state information indicates one of a plurality of states that indicate whether the virtual cell identifier is associated with at least one non-virtual reference signal for the first cell, the second cell, or one or more third cells. The second cell receives the virtual cell identifier and the state information and transmits the virtual cell identifier and state information over an air interface to second user equipment served by the second cell. The second user equipment performs interference cancellation or suppression of transmissions to the first user equipment based on the virtual cell identifier and the state information.

Abstract: Systems include a network element with a plurality of server blades, including a control server and one or more application servers. The control server communicates with each application server to acquire state information about each application server. A switch is in communication with each server blade. The switch is configured to communicate with the control server in order to obtain therefrom the state information acquired by the control server about each application server.

Abstract: Each of a plurality of database objects can be assigned to a specific message-passing worker of a plurality of message-passing workers, each executing on a first logical core that shares with at least a second logical core one or more resources of a physical processor core of a plurality of physical processor cores. The second logical core can execute a job worker of a plurality of job workers that implement procedural code. Exclusive write access can be provided to a database object of the plurality of database objects via a message-passing worker of the plurality of message-passing workers while read-only access is provided to any database object of the plurality of database objects via any of the plurality of job workers. Operations can be executed by the message-passing worker in an order in which request messages are received in a message queue of the message-passing worker.

Abstract: Briefly, methods and apparatus to rebalance workloads among processing cores utilizing a hybrid work donation and work stealing technique are disclosed that improve workload imbalances within processing devices such as, for example, GPUs. In one example, the methods and apparatus allow for workload distribution between a first processing core and a second processing core by providing queue elements from one or more workgroup queues associated with workgroups executing on the first processing core to a first donation queue that may also be associated with the workgroups executing on the first processing core. The method and apparatus also determine if a queue level of the first donation queue is beyond a threshold, and if so, steal one or more queue elements from a second donation queue associated with workgroups executing on the second processing core.

Abstract: Systems and methods are provided for generating multiple system state projections using a grid computing environment. A central coordinator software component executes on a root data processor and provides commands and data to a plurality of node coordinator software components. A node coordinator software component manages threads which execute on its associated node data processor and which perform a set of matrix operations. Stochastic simulations use results of the matrix operations to generate multiple state projections. Additional processing can be performed by the grid computing environment based upon the generated state projections, such as to develop possible change information for users.

Abstract: This disclosure relates generally to identity management, and more particularly to systems and methods for managing performance of identity management services. In one embodiment, a processor-implemented identity management performance control method is disclosed. The method may include receiving, via one or more hardware processors, an identity management architecture specification. The method may also include identifying, via the one or more hardware processors, a plurality of identity management attributes for the identity management architecture specification. The method may include selecting, via the one or more hardware processors, measurement criteria based on a target environment for implementing the identity management architecture. The method may include calculating, via the one or more hardware processors, an attribute measurement quotient for the plurality of identified identity management attributes using the selected measurement criteria.

Abstract: A system and method of decreasing server loads and, more particularly, to decrease server load by automatically determining subgroups based on object interactions and computational expenditures. The system includes a plurality of servers; a subgroup optimization module configured to segment a plurality of objects into optimal subgroups; and a server transfer module configured to apportion one or more of the optimal subgroups between the plurality of servers based on a load of each of the plurality of servers. The method includes determining a relationship amongst a plurality of objects; segmenting the objects into optimized subgroups based on the relationships; and apportioning the optimized subgroups amongst a plurality of servers based on server load.

Abstract: In particular embodiments, a method includes receiving a request for a signature verification. In response to the request, signature data is encrypted. A first data size associated with the signature data is determined. A second data size associated with data of a data packet is determined. The method includes comparing the sum of the first data size and the second data size to a pre-determined data size. When the sum is less than or equal to the pre-determined data size, the encrypted signature data is included in the data packet; and the data packet is transmitted over a network.

Abstract: Methods are provided. A method for swapping-out an offload process from a coprocessor includes issuing a snapify_pause request from a host processor to the coprocessor to initiate a pausing of the offload process executing by the coprocessor and another process executing by the host processor using a plurality of locks. The offload process is previously offloaded from the host processor to the coprocessor. The method further includes issuing a snapify_capture request from the host processor to the coprocessor to initiate a local snapshot capture and saving of the local snapshot capture by the coprocessor. The method also includes issuing a snapify_wait request from the host processor to the coprocessor to wait for the local snapshot capture and the saving of the local snapshot capture to complete by the coprocessor.

Abstract: An apparatus includes a memory, a first processor, and a second processor, wherein the first processor is configured to retain first order data that indicate a first order of the plurality of devices, generate second order data that indicate a second order which is a portion of a first order, and decrease power consumption of the first processor after generate the second order data, the memory is configured to retain the second order data, the second processor is configured to detect a plurality of devices, determine whether or not a detection order of the plurality of devices corresponds with the second order, and output a correspondence signal in a case where the detection order corresponds with the second order, and the first processor is configured to increase the power consumption of the first processor based on the correspondence signal.

Abstract: A hardware controller includes a first hardware interface, a second hardware interface, first hardware logic, and second hardware logic. The first hardware interface is to couple the hardware controller to hardware entities of a hardware device in which the hardware controller is to be included. The second hardware interface is to couple the hardware controller to a memory to receive instructions. The first hardware logic is to choose a selected hardware entity from the hardware entities. The second hardware logic is to execute the instructions in relation to the selected hardware entity.

Abstract: Specialized processing devices comprise both processing circuitry that is pre-configured to perform a discrete set of computing operations more quickly than generalized central processing units and network transport circuitry that communicationally couples each individual specialized processing device to a network as its own unique network client. Requests for hardware acceleration from workflows being executed by generalized central processing units of server computing devices are directed to hardware accelerators in accordance with a table associating available hardware accelerators with the computing operations they are optimized to perform. Load balancing, as well as dynamic modifications in available hardware accelerators, is accomplished through updates to such a table.

Abstract: Measures, including methods, apparatus and computer program products, are provided for amending content transmitted by a server to a client. The methods are performed by a system remote from the client and the server and arranged to receive requests from the client to the server and to receive responses from the server to the client. A method comprises configuring a domain name service to route requests for pages hosted at the server to the system; receiving a request from the client to the server for a page, the request being received at the system on the basis of the configuring; transmitting the request to the server in response to receipt of the request from the client; receiving a page from the server, the page corresponding to the transmitted request; inserting content into the page to form an amended page; and transmitting the amended page to the client.

Abstract: Techniques are provided to generate and store a network graph database comprising information that indicates a service node topology, and virtual or physical network services available at each node in a network. A service request is received for services to be performed on packets traversing the network between at least first and second endpoints. A subset of the network graph database is determined that can provide the services requested in the service request. A service chain and service chain identifier is generated for the service based on the network graph database subset. A flow path is established through the service chain by flow programming network paths between the first and second endpoints using the service chain identifier.

Abstract: A work distribution unit distributes work batches to general processing clusters (GPCs) based on the number of streaming multiprocessors included in each GPC. Advantageously, each GPC receives an amount of work that is proportional to the amount of processing power afforded by the GPC. Embodiments include a method for distributing batches of processing tasks to two or more general processing clusters (GPCs), including the steps of updating a counter value for each of the two or more GPCs based on the number of enabled parallel processing units within each of the two or more GPCs, and distributing a batch of processing tasks to a first GPC of the two or more GPCs based on a counter value associated with the first GPC and based on a load signal received from the first GPC.

Abstract: A method includes a set of execution units of a dispersed storage network (DSN) receiving sets of sub-task requests from a computing device and storing the sets of sub-task requests, where each execution unit stores a request of each of the sets of sub-task requests to produce a corresponding plurality of sub-task requests. The method continues with each execution unit generating sub-task estimation data and adjusting timing, sequencing, or processing of the corresponding plurality of sub-task requests based on the estimation data to produce a plurality of partial results, where, due to one or more difference factors from a list of difference factors, the execution units process pluralities of sub-task requests at difference paces, where the list of difference factors includes differences in amounts of data to be processed per sub-task request, processing capabilities, memory storage capabilities, and networking capabilities.

Abstract: A method for managing a plurality of workloads executing on both a primary system and on a secondary system, and synchronizing both a plurality of software data and a plurality of hardware data stored on the primary system with the secondary system is provided. The method may include receiving a region switch request and stopping the execution of the plurality of workloads on the primary system; suspending the replication of the plurality of software and hardware data stored on the primary system with the plurality of software and hardware data stored on the secondary system; and switching the replication of the plurality of software data and the plurality of hardware data that occurs from the primary system to the secondary system to occur from the secondary system to the primary system. The method may further include activating the execution of and synchronizing the plurality of workloads on the secondary system.

Abstract: A system and method of dynamically provisioning virtualized computational resources in a networked computer architecture includes at least one client device operable to run one or more client applications, at least one server device and a resource controller. Each server device comprises one or more physical processors with local memory. Each server device provides a virtual resource layer through which one or more virtual processing resources can be defined and through which the physical processors of the server device can be assigned to the virtual processing resources. In use, one or more virtual processing resources is assigned to a client application for processing of data processing workloads. The resource controller then monitors the utilization of each virtual processing resource and/or any physical processor assigned to the virtual processing resource. The resource controller can dynamically adjust which, and how many, physical processors are assigned to the virtual processing resource.

Abstract: A dynamic resource repositioning load balancing and location management system repositions an incoming resource in a grid network of nodes. The system includes a first mapping device to map topology of said gird network of nodes, along with its resources; a determination device to determine at least an incoming resource's initial placement in terms of relative position of said node that the resource currently occupies and in terms of relative number of edges on which said resource currently resides; and resource repositioning device to reposition said at least a resource, in said grid network of nodes, in response to an incoming resource, said repositioning based on said determined position of said incoming resource; characterized, in that, said repositioning mechanism being guided by at least a step or a combination of steps or repetition of steps selected from a group of steps.

Abstract: A method includes receiving, at a load balancer for a plurality of computing components, a workload request. The method also includes accessing a database including a respective non-linear scalability model for each of the plurality of computing components. The method further includes determining a particular computing component from the plurality of computing components based on each respective non-linear scalability model; and scheduling the workload request for execution by the particular computing component.

Abstract: The disclosed computer-implemented method for dynamic load balancing on disks may include (1) calculating the spare throughput for each disk, (2) identifying a lightly loaded disk and a heavily loaded disk, (3) identifying a set of workloads to be transferred from the heavily loaded disk to the lightly loaded disk by: (a) beginning with the set empty, (b) identifying candidate workloads on the heavily loaded disk, (c) adding a new workload from the candidate workloads to the set when the new workload would not reduce the spare throughput on the lightly loaded disk below a threshold if both the set and the workload were transferred to the lightly loaded disk, and (d) considering each workload for transfer in order from most throughput consumed to least throughput consumed, and (4) transferring the set of workloads. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: A computer system may receive an instruction to perform an action on an object. A schedule manager may identify a set of processes associated with the action that need to be performed by the computer system. A subset of primary process and a subset of secondary processes may be identified from the set of processes associated with the action. The schedule manager may schedule an asynchronous process to perform the subset of secondary processes on the object. The computer system may perform the subset of primary processes on the object. The subset of secondary process may be performed by the asynchronous process based upon the scheduling.