Abstract: A method, system and computer program product for remote direct memory access (RDMA) optimized producer-consumer message processing in a messaging hub is provided. The method includes initializing a shared memory region in memory of a host server hosting operation of a messaging hub. The initialization provides for a control portion and one or more data portions, the control portion storing an index to an available one of the data portions. The method also includes transmitting to a message producer an address of the shared memory region and receiving a message in one of the data portions of the shared memory region from the message producer by way of an RDMA write operation on a network interface of the host server. Finally, the method includes retrieving the message from the one of the data portions and processing the message in the messaging hub in response to the receipt of the message.

Abstract: A method to share remote DMA (RDMA) pointers to a key-value store among a plurality of clients. The method allocates a shared memory and accesses the key-value store with a key from a client and receives an information from the key-value store. The method further generates a RDMA pointer from the information, maps the key to a location in the shared memory, and generates a RDMA pointer record at the location. The method further stores the RDMA pointer and the key in the RDMA pointer record and shares the RDMA pointer record among the plurality of clients.

Abstract: Methods and arrangements for task scheduling. A job is accepted, the job comprising a plurality of phases, each of the phases comprising at least one task. For each of a plurality of slots, a fetching cost associated with receipt of one or more of the tasks is determined. The slots are grouped into a plurality of sets. A pair of thresholds is determined for each of the sets, the thresholds being associated with the determined fetching costs and comprising upper and lower numerical bounds for guiding receipt of one or more of the tasks. Other variants and embodiments are broadly contemplated herein.

Abstract: A method for selecting a consensus protocol comprises separating a consensus protocol into one or more communication steps, wherein the consensus protocol is useable to substantially maintain data consistency between nodes in a distributed computing system, and wherein a communication step comprises a message transfer, attributable to the consensus protocol, in the distributed computing system, and computing an estimated protocol-level delay based on one or more attributes associated with the separated communication steps of the consensus protocol.

Abstract: A method for selecting a consensus protocol comprises separating a consensus protocol into one or more communication steps, wherein the consensus protocol is useable to substantially maintain data consistency between nodes in a distributed computing system, and wherein a communication step comprises a message transfer, attributable to the consensus protocol, in the distributed computing system, and computing an estimated protocol-level delay based on one or more attributes associated with the separated communication steps of the consensus protocol.

Abstract: Predicting acceleration in a hybrid system may comprise determining a number of cross system calls in a first host-accelerator computer architecture running a workload. Host machine overhead and accelerator overhead in the first host-accelerator computer architecture associated with each of the cross system calls may be determined. Communication delay associated with each of the cross system calls in the first host-accelerator computer architecture running a workload may be determined. An application response time may be predicted for a candidate application to be run in a second host-accelerator computer architecture, based at least on the determined host machine overhead, the accelerator overhead, and the communication delay associated with each of the cross system calls in the first host-accelerator computer architecture running a workload.

Abstract: Embodiments relate to methods, systems and computer program products for cache management in a Remote Direct Memory Access (RDMA) data store. Aspects include receiving a request from a remote computer to access a data item stored in the RDMA data store and creating a lease including a local expiration time for the data item. Aspects further include creating a remote pointer to the data item, wherein the remote pointer includes a remote expiration time and transmitting the remote pointer to the remote computer, wherein the lease is an agreement that that the remote computer can perform RDMA reads on the data item until the remote expiration time.

Abstract: Embodiments relate to methods, systems and computer program products for cache management in a Remote Direct Memory Access (RDMA) data store. Aspects include receiving a request from a remote computer to access a data item stored in the RDMA data store and creating a lease including a local expiration time for the data item. Aspects further include creating a remote pointer to the data item, wherein the remote pointer includes a remote expiration time and transmitting the remote pointer to the remote computer, wherein the lease is an agreement that that the remote computer can perform RDMA reads on the data item until the remote expiration time.

Abstract: A tool for autoscaling applications in a shared cloud resource environment. The tool registers, by one or more computer processors, one or more trigger conditions. The tool initiates, by one or more computer processors, a scaling event based, at least in part, on at least one of the one or more trigger conditions. The tool determines, by one or more computer processors, a scaling decision for the scaling event based, at least in part, on one or more scaling rules related to the one or more trigger conditions.

Abstract: Systems and methods for resource aware scheduling of processes in a distributed computing environment are described herein. One aspect provides for accessing at least one job and at least one resource on a distributed parallel computing system; generating a current reward value based on the at least one job and a current value associated with the at least one resource; generating a prospective reward value based on the at least one job and a prospective value associated with the at least one resource at a predetermined time; and scheduling the at least one job based on a comparison of the current reward value and the prospective reward value. Other embodiments and aspects are also described herein.

Abstract: Predicting acceleration in a hybrid system may comprise determining a number of cross system calls in a first host-accelerator computer architecture running a workload. Host machine overhead and accelerator overhead in the first host-accelerator computer architecture associated with each of the cross system calls may be determined. Communication delay associated with each of the cross system calls in the first host-accelerator computer architecture running a workload may be determined. An application response time may be predicted for a candidate application to be run in a second host-accelerator computer architecture, based at least on the determined host machine overhead, the accelerator overhead, and the communication delay associated with each of the cross system calls in the first host-accelerator computer architecture running a workload.

Abstract: Predicting acceleration in a hybrid system may comprise determining a number of cross system calls in a first host-accelerator computer architecture running a workload. Host machine overhead and accelerator overhead in the first host-accelerator computer architecture associated with each of the cross system calls may be determined. Communication delay associated with each of the cross system calls in the first host-accelerator computer architecture running a workload may be determined. An application response time may be predicted for a candidate application to be run in a second host-accelerator computer architecture, based at least on the determined host machine overhead, the accelerator overhead, and the communication delay associated with each of the cross system calls in the first host-accelerator computer architecture running a workload.

Abstract: Methods and arrangements for managing data segments. At least one job is received, each job comprising a dependee set of tasks and a depender set of at least one task, and the at least one of the dependee set of tasks is executed. There is extracted, from the at least one of the dependee set of tasks, at least one service common to at least another of the dependee set of tasks. Other variants and embodiments are broadly contemplated herein.

Abstract: Methods and arrangements for yielding resources in data processing. At least one job is received, each job comprising a dependee set of tasks and a depender set of at least one task, and the at least one of the dependee set of tasks is executed. At least one resource of the at least one of the dependee set of tasks is yielded upon detection of resource underutilization in at least one other location. Other variants and embodiments are broadly contemplated herein. Other variants and embodiments are broadly contemplated herein.

Abstract: Methods and arrangements for assembling tasks in a progressive queue. At least one job is received, each job comprising a dependee set of tasks and a depender set of at least one task. The dependee tasks are assembled in a progressive queue for execution, and the dependee tasks are executed. Other variants and embodiments are broadly contemplated herein.

Abstract: Predicting acceleration in a hybrid system may comprise determining a number of cross system calls in a first host-accelerator computer architecture running a workload. Host machine overhead and accelerator overhead in the first host-accelerator computer architecture associated with each of the cross system calls may be determined. Communication delay associated with each of the cross system calls in the first host-accelerator computer architecture running a workload may be determined. An application response time may be predicted for a candidate application to be run in a second host-accelerator computer architecture, based at least on the determined host machine overhead, the accelerator overhead, and the communication delay associated with each of the cross system calls in the first host-accelerator computer architecture running a workload.

Abstract: Methods, systems and computer program products for data fetching in a networked computing environment. In one embodiment, the method comprises receiving a request from an analytical node for a set of data for a defined job, and identifying in networked storage a subset of the data for the job. The subset of data is loaded to the analytical node based on the sequence in which the data are projected to be accessed in the job. In an embodiment, the request includes a specification for the job, and the specification is analyzed to identify the subset of data. In one embodiment, the subset of data is identified by identifying another job having a relationship to the defined job, and identifying the data used for that other job. In an embodiment, the networked computing environment is a cloud computing environment, and the defined job is an analytics job.

Abstract: A method, system and computer program product for remote direct memory access (RDMA) optimized producer-consumer message processing in a messaging hub is provided. The method includes initializing a shared memory region in memory of a host server hosting operation of a messaging hub. The initialization provides for a control portion and one or more data portions, the control portion storing an index to an available one of the data portions. The method also includes transmitting to a message producer an address of the shared memory region and receiving a message in one of the data portions of the shared memory region from the message producer by way of an RDMA write operation on a network interface of the host server. Finally, the method includes retrieving the message from the one of the data portions and processing the message in the messaging hub in response to the receipt of the message.

Abstract: A method, system and computer program product for remote direct memory access (RDMA) optimized producer-consumer message processing in a messaging hub is provided. The method includes initializing a shared memory region in memory of a host server hosting operation of a messaging hub. The initialization provides for a control portion and one or more data portions, the control portion storing an index to an available one of the data portions. The method also includes transmitting to a message producer an address of the shared memory region and receiving a message in one of the data portions of the shared memory region from the message producer by way of an RDMA write operation on a network interface of the host server. Finally, the method includes retrieving the message from the one of the data portions and processing the message in the messaging hub in response to the receipt of the message.

Abstract: Identifying resource bottleneck in multi-stage workflow processing may include identifying dependencies between logical stages and physical resources in a computing system to determine which logical stage involves what set of resources; for each of the identified dependencies, determining a functional relationship between a usage level of a physical resource and concurrency level of a logical stage; estimating consumption of the physical resources by each of the logical stages based on the functional relationship determined for each of the logical stages; and performing a predictive modeling based on the estimated consumption to determine a concurrency level at which said each of the logical stages will become bottleneck.