International Business Machines Corporation

Google Inc.

Andrew Dunshea

Jos Manuel Accapadi

Dirk Michel

Mysore Sathyanarayana Srinivas

Douglas J Griffith

Mathew Accapadi

Diane Garza Flemming

Agustin Mena, Iii

Anil Kalavakolanu

Mysore Sathyanaranyana Srinivas

Mark Elliott Hack

Anand Teerth Desai

Antonio Garcia

James William Van Fleet

Catherine Moriarty Nunez

Venkat Venkatsubra

Satya Prakash Sharma

Adekunle Bello

Li Li

David Alan Hepkin

Nikhil Hegde

Aruna Yedavilli

Kavitha Vittal Murthy Baratakke

Grover Herbert Neuman

Greg Robert Mewhinney

Vandana Mallempati

Shashidhar Bomma

Matthew Accapadi

Linda Zimmer

Paul Henry Hernandez

Lynne Marie Weber

Brian W Hart

Sujatha Kashyap

Herman Dietrich Dierks

Zachary Merlynn Loafman

Jean-Philippe Sugarbroad

Andrew James Declercq

Stephen Alfred Haley

Suzanne Shi

Matthew John Harding

Maha Emad

Gary L Nevling

Abraham Alvarez

William Lee Britton

Miho Ogishima

Jos Manuel Aecapadi

Described herein is a system and method for associating process priority with I/O queuing. The system can receive a first I/O request from a first process; store the first I/O request in an I/O queue; receive a second I/O request from a second process; store the second I/O request in the I/O queue; and sort the I/O queue based, at least in part, on a first priority of the first process and a second priority of the second process.

Associating process priority with I/O queuing

A method for enhanced restart of a core dumping application is provided. The method includes stopping a plurality of threads in an address space, except for the thread performing the core dump. Computational segments are remapped to client segments. Each open file descriptor in the address space is closed. The application is terminated and the client segments are flushed to external storage.

Enhanced restart of a core dumping application

Input/output (I/O) requests generated by processes are typically stored in I/O queues. Because the queued I/O requests may not be associated with the processes that generated them, changing a process' priority may not affect the priority of the I/O requests generated by the process. Therefore, after the process' priority has been increased, it may be forced to wait for an I/O handler to service its I/O request, which may be stuck behind an I/O request generated by a lower priority process. Functionality can be implemented to associate the processes' priorities with the I/O requests generated by the processes. Also, reordering the queued I/O requests to reflect changes in the processes' priorities can ensure that the I/O requests from high priority processes are serviced before the I/O requests from low priority processes. This can ensure efficient processing and lower wait times for high priority processes.

A method, system and computer-usable medium are disclosed for persisting Lightweight Memory Trace (LMT) data across reboots of a system. One or more LMT traces are stored in a predetermined pinned memory area with a server's operating system (OS) through a system reboot. A pointer to each LMT is likewise stored in nonvolatile storage (NVS) at a known memory location. The pointers in NVS point to a page which describes where the LMT trace and other kernel structures are in real memory. During initialization, the OS guards these preserved pages to prevent them from being used. By keeping the current and prior address within NVS, the current LMT and prior traces can be retrieved and processed to determine the cause of the system reboot.

Persistent data across reboots

Sharing kernel services among kernels, including receiving, by a partition manager from an application in a logical partition, a first system call for a kernel service from a first kernel, the first system call having form and content compatible with the first kernel, generating, in dependence upon the first system call, a second system call for the kernel service from a second kernel, the second system call having form and content compatible with the second kernel, and sending the second system call through the partition manager to the second kernel for execution.

Sharing kernel services among kernels

Sharing a kernel of an operating system among logical partitions, including installing in a partition manager a kernel of a type used by a plurality of logical partitions; installing in the partition manager generic data structures specifying computer resources assigned to each of the plurality of logical partitions; and providing, by the kernel to the logical partitions, kernel services in dependence upon the generic data structures.

Sharing a kernel of an operating system among logical partitions

A computer implemented method, data processing system, and computer program product for configuring a partition with needed system resources to enable an application to run and process in a secure environment. Upon receiving a command to create a short lived secure partition for a secure application, a short lived secure partition is created in the data processing system. This short lived secure partition is inaccessible by superusers or other applications. System resources comprising physical resources and virtual allocations of the physical resources are allocated to the short lived secure partition. Hardware and software components needed to run the secure application are loaded into the short lived secure partition.

Secure application partitioning enablement

A service module that provides for discovery of one or more network interfaces connecting a prospective remote procedure call (RPC) client, facilitates the provision of RPC programs in a network including multi-horned systems. When a request for a network address to an RPC application providing an RPC program is received from the RPC client, the RPC bind daemon discovers from the module, using the client response address, over which interface(s) the client is accessible. The daemon then selects an address of a network path to the RPC application that the prospective client can access and returns the corresponding network address. The service module monitors the network stack for RPC get address requests and builds tables of client address entries with corresponding network interface identifiers. The entries are retired according to an aging policy.

Remote procedure call (RPC) bind service with physical interface query and selection

The exemplary embodiments provide a computer-implemented method, apparatus, and computer-usable program code for managing memory. A notice of a shortage of real memory is received. For each active thread, the thread classification of the active thread is compared to a global hierarchy of thread classifications to determine a thread to affect. The global hierarchy of thread classifications defines the relative importance of each thread classification. An action to take for the determined thread is determined. The determined action is performed for the determined thread.

Thread classification suspension

Functionality can be implemented in a virtual memory manager (VMM) to allow small pages (e.g., 4 KB) to be coalesced into large pages (e.g., 64 KB), so that a single free list can be maintained for the large pages ('maintained pages'). When a process requests a small page, the VMM can associate a maintained page with a memory segment accessible by the process. Then, the maintained page can be divided to form a set of small pages ('fragments'). The fragments can become available pages in a broken page list. The VMM can satisfy the request by allocating one of the fragments in the broken page list. If the process requests additional small pages, the additional requests can be satisfied from the broken page list. When the process terminates, the fragments in the broken page list become a maintained page and can be returned to the free list.

Automatic page promotion and demotion in multiple page size environments

A computer program product for scheduling threads in a multiprocessor computer comprises computer program instructions configured to select a thread in a ready queue to be dispatched to a processor and determine whether an interrupt mask flag is set in a thread control block associated with the thread. If the interrupt mask flag is set in the thread control block associated with the thread, the computer program instructions are configured to select a processor, set a current processor priority register of the selected processor to least favored, and dispatch the thread from the ready queue to the selected processor.

Computer program product for scheduling ready threads in a multiprocessor computer based on an interrupt mask flag value associated with a thread and a current processor priority register value

A multiprocessor data processing system (MDPS) with a weakly-ordered architecture providing processing logic for substantially eliminating issuing sync instructions after every store instruction of a well-behaved application. Instructions of a well-behaved application are translated and executed by a weakly-ordered processor. The processing logic includes a lock address tracking utility (LATU), which provides an algorithm and a table of lock addresses, within which each lock address is stored when the lock is acquired by the weakly-ordered processor. When a store instruction is encountered in the instruction stream, the LATU compares the target address of the store instruction against the table of lock addresses. If the target address matches one of the lock addresses, indicating that the store instruction is the corresponding unlock instruction (or lock release instruction), a sync instruction is issued ahead of the store operation. The sync causes all values updated by the intermediate store operations to be flushed out to the point of coherency and be visible to all processors.

Efficient memory update process for well behaved applications executing on a weakly-ordered processor

Growing community of inventors

Austin, TX, United States of America

Andrew Dunshea