The Experts below are selected from a list of 123 Experts worldwide ranked by ideXlab platform
R. S. Burugula - One of the best experts on this subject based on the ideXlab platform.
-
Dynamic reconfiguration: Basic building blocks for autonomic computing on IBM pSeries servers
Ibm Systems Journal, 2020Co-Authors: J. Jann, L. M. Browning, R. S. BurugulaAbstract:A Logical Partition in an IBM pSeriesTM symmetric multiprocessor (SMP) system is a subset of the hardware of the SMP that can host an operating system (OS) instance. Dynamic reconfiguration (DR) on these Logically Partitioned servers enables the movement of hardware resources (such as processors, memory, and I/O slots) from one Logical Partition to another without requiring reboots. This capability also enables an autonomic agent to monitor usage of the Partitions and automatically move hardware resources to a needy OS instance nondisruptively. Today, as SMPs and nonuniform memory access (NUMA) systems become larger and larger, the ability to run several instances of an operating system(s) on a given hardware system, so that each OS instance plus its subsystems scale or perform well, has the advantage of an optimal aggregate performance, which can translate into cost savings for customers. Though static Partitioning provides a solution to this overall performance optimization problem, DR enables an improved solution by providing the capability to dynamically move hardware resources to a needy OS instance in a timely fashion to match workload demands. Hence, DR capabilities serve as key building blocks for workload managers to provide self-optimizing and self-configuring features. Besides dynamic resource balancing, DR also enables Dynamic Capacity Upgrade on Demand, and self-healing features such as Dynamic CPU Sparing, a winning solution for users in this age of rapid growth in Web servers on the Internet.
-
Dynamic reconfiguration: Basic building blocks for autonomic computing on IBM pSeries servers
IBM Systems Journal, 2003Co-Authors: J. Jann, L. M. Browning, R. S. BurugulaAbstract:A Logical Partition (LPAR) in an IBM pSeries™ Symmetric Multiprocessor (SMP) system is a subset of the hardware of the SMP that can host an OS instance. Dynamic Reconfiguration (DR) on these Logically Partitioned servers enables the movement of hardware resources (such as processors, memory, and I/O slots) from one Logical Partition to another without requiring reboots. This capability also enables an autonomic agent to monitor usage of the Partitions and automatically move hardware resources to a needy OS instance non-disruptively. Nowadays, as SMPs and NUMA systems get larger and larger, the ability to run several instances of an Operating System[s] on a given hardware system, so that each OS instance plus its subsystems scale or perform well, provides the advantage of optimal aggregate performance, which can translate to cost savings for the customers. Though static Partitioning provides a solution to this overall performance optimization problem, DR enables an improved solution by providing the capability to dynamically move hardware resources to a needy OS instance in a timely fashion to match the workload demands. Hence DR capabilities serve as key building blocks for workload managers to provide self-opimizing and self-configuring features. Besides dynamic resource balancing, DR also enables dynamic capacity upgrade on demand, and self-healing features such as dynamic CPU sparing, a winning solution for users in this age of rapid growth in Web servers on the Internet.
J. P. Kubala - One of the best experts on this subject based on the ideXlab platform.
-
IBM z13 firmware innovations for simultaneous multithreading and I/O virtualization
IBM Journal of Research and Development, 2015Co-Authors: C. Axnix, J. P. Kubala, G. Bayer, H. Böhm, J. Von Buttlar, M. S. Farrell, Cranton L. Heller, S. E. Lederer, R. Mansell, Nuñez A. MenciasAbstract:The IBM z13™ delivers significant new capabilities in terms of overall system capacity provided by simultaneous multithreading (SMT), and new I/O virtualization functionality for PCI Express™ (PCIe™) adapters. In this paper, we describe how the host firmware stack was enhanced to enable these new functions. For SMT, new support was added in the firmware running on the Central Processor Complex (CPC) to represent and manage the operation of more processor cores compared with the previous z Systems™ generation, with multiple threads each. The Processor Resource/Systems Manager™ (PR/SM™) hypervisor design was modified to allow exploitation of SMT under the control of the operating system running in a Logical Partition. The z13 supports Single Root I/O Virtualization (SR-IOV) for PCIe adapters to allow sharing of adapters among operating system images running in separate Logical Partitions. The virtualization intermediary firmware runs in a new firmware execution environment, the Firmware Platform Container (FPC). The IBM internal Central Electronics Complex (CEC) SIMulation (CECSIM) environment was extended to reflect the new system structure, scale, and functions, to allow early verification of the z13 firmware designs, and to ensure excellent firmware quality for an efficient hardware bring-up and system test.
-
Logical Partition mode physical resource management on the IBM eServer z990
IBM Journal of Research and Development, 2004Co-Authors: I. G. Siegel, B. A. Glendening, J. P. KubalaAbstract:The IBM eServer™ z990 provides tremendously increased processor, I/O, and memory capacity exceeding the capability of even the premier IBM operating systems. The modular or book-form system topology of the z990 enables a highly flexible and more cost-effective concurrent upgrade infrastructure, as well as improved hardware failure survivability and serviceability. The multibook form of the z990 has two significant memory access performance issues which are addressed here: First, there is increased cache coherency overhead when the same memory is accessed by central processing units (CPUs) from multiple books; second, access from CPUs to memory on books other than the book on which a CPU is resident is not as efficient as access from the same book. Awareness of this multifold increase in capacity and complexity is effectively managed by the IBM zSeries® Logical Partition (LPAR) hypervisor, obviating the need for operating system involvement. This paper describes changes made to the zSeries LPAR hypervisor to manage CPU and memory resources on the z990 machine topology.
Wei Du - One of the best experts on this subject based on the ideXlab platform.
-
The algorithm of the join data stream with diskresident relation
2013 Ninth International Conference on Natural Computation (ICNC), 2013Co-Authors: Wei DuAbstract:Current data integration approaches are moving towards real-time updates. One important element in real-time data integration is the join of a continuous incoming data stream with a disk-resident relation. Because data stream is infinite, it is impossible to adopt blocking join algorithms such as sort-merge and hash join. The novel algorithm MESHJOIN has been proposed for joining a continuous stream with a disk-resident relation. The crux of MESHJOIN algorithm is that the whole memory block of disk-based relation is replaced at each iteration. We propose that the memory block is divided into a number of Logical Partitions, and then only one Logical Partition of memory block is replaced at each iteration. The experimental results show that the service rate of the join is increased because I/O cost for one loop iteration is decreased.
-
ICNC - The algorithm of the join data stream with diskresident relation
2013 Ninth International Conference on Natural Computation (ICNC), 2013Co-Authors: Wei DuAbstract:Current data integration approaches are moving towards real-time updates. One important element in real-time data integration is the join of a continuous incoming data stream with a disk-resident relation. Because data stream is infinite, it is impossible to adopt blocking join algorithms such as sort-merge and hash join. The novel algorithm MESHJOIN has been proposed for joining a continuous stream with a disk-resident relation. The crux of MESHJOIN algorithm is that the whole memory block of disk-based relation is replaced at each iteration. We propose that the memory block is divided into a number of Logical Partitions, and then only one Logical Partition of memory block is replaced at each iteration. The experimental results show that the service rate of the join is increased because I/O cost for one loop iteration is decreased.
J. Jann - One of the best experts on this subject based on the ideXlab platform.
-
Dynamic reconfiguration: Basic building blocks for autonomic computing on IBM pSeries servers
Ibm Systems Journal, 2020Co-Authors: J. Jann, L. M. Browning, R. S. BurugulaAbstract:A Logical Partition in an IBM pSeriesTM symmetric multiprocessor (SMP) system is a subset of the hardware of the SMP that can host an operating system (OS) instance. Dynamic reconfiguration (DR) on these Logically Partitioned servers enables the movement of hardware resources (such as processors, memory, and I/O slots) from one Logical Partition to another without requiring reboots. This capability also enables an autonomic agent to monitor usage of the Partitions and automatically move hardware resources to a needy OS instance nondisruptively. Today, as SMPs and nonuniform memory access (NUMA) systems become larger and larger, the ability to run several instances of an operating system(s) on a given hardware system, so that each OS instance plus its subsystems scale or perform well, has the advantage of an optimal aggregate performance, which can translate into cost savings for customers. Though static Partitioning provides a solution to this overall performance optimization problem, DR enables an improved solution by providing the capability to dynamically move hardware resources to a needy OS instance in a timely fashion to match workload demands. Hence, DR capabilities serve as key building blocks for workload managers to provide self-optimizing and self-configuring features. Besides dynamic resource balancing, DR also enables Dynamic Capacity Upgrade on Demand, and self-healing features such as Dynamic CPU Sparing, a winning solution for users in this age of rapid growth in Web servers on the Internet.
-
Dynamic reconfiguration: Basic building blocks for autonomic computing on IBM pSeries servers
IBM Systems Journal, 2003Co-Authors: J. Jann, L. M. Browning, R. S. BurugulaAbstract:A Logical Partition (LPAR) in an IBM pSeries™ Symmetric Multiprocessor (SMP) system is a subset of the hardware of the SMP that can host an OS instance. Dynamic Reconfiguration (DR) on these Logically Partitioned servers enables the movement of hardware resources (such as processors, memory, and I/O slots) from one Logical Partition to another without requiring reboots. This capability also enables an autonomic agent to monitor usage of the Partitions and automatically move hardware resources to a needy OS instance non-disruptively. Nowadays, as SMPs and NUMA systems get larger and larger, the ability to run several instances of an Operating System[s] on a given hardware system, so that each OS instance plus its subsystems scale or perform well, provides the advantage of optimal aggregate performance, which can translate to cost savings for the customers. Though static Partitioning provides a solution to this overall performance optimization problem, DR enables an improved solution by providing the capability to dynamically move hardware resources to a needy OS instance in a timely fashion to match the workload demands. Hence DR capabilities serve as key building blocks for workload managers to provide self-opimizing and self-configuring features. Besides dynamic resource balancing, DR also enables dynamic capacity upgrade on demand, and self-healing features such as dynamic CPU sparing, a winning solution for users in this age of rapid growth in Web servers on the Internet.
ピーターソン ベス - One of the best experts on this subject based on the ideXlab platform.
-
avoidance of the failure of the initial program load in a Logical Partition of the data storage system
2008Co-Authors: クラーク ブライアン, コロナド ファン, ピーターソン ベスAbstract:An initial program load (IPL) of a Logical Partition (LPAR) is managed by establishing a Logical path to the LPAR from a storage controller. When a notice is received by the storage controller from the LPAR that the IPL has commenced, the LPAR address is stored in a data structure. After the storage controller initiates a pack change state interrupt, the stored address is compared with the addresses in a list of all LPARS to which the interrupt is directed. If the list of addresses includes the stored address, the stored address is removed from the list. Thus, the pack change state interrupt is transmitted only to the addresses in the list, leaving the LPAR to complete the IPL without interruption. After the storage controller receives a notice from the LPAR that the IPL has completed, the address of the LPAR is removed from the data structure.
