International Business Machines Corporation

Globalfoundries U.S. 2 LLC

Douglas J Griffith

Anil Kalavakolanu

Angela Astrid Jaehde

Sreenivas Makineedi

Robert Scott Manning

Andrew Dunshea

Astrid Jaehde

Srinivasa Rao Muppala

Anand Teerth Desai

Adekunle Bello

Matthew Ryan Ochs

Minh Q Pham

Antonio Garcia

Richard B Sutton

Mathew Accapadi

Manjunath Basappa Muttur

Gaurav Batra

Stephen A Schlachter

Somasundaram Krishnasamy

Srinivasa M Raghavan

Aruna Yedavilli

Vani D Ramagiri

Deepti Umarani

William F Quinn

Demetrice Browder

Evan Allen Zoss

Yanhua Yang

Isac Rodrigues Da Silva

Frank Bernhard Schmuck

James Anthony Pafumi

Eric N Lais

Soumitra Sarkar

Yi Zhou

Peter Joseph Heyrman

Brian W Hart

Lohitashwa Thyagaraj

Theodore Brian Vojnovich

Roger Lee Haskin

Shah Mohammad Rezaul Islam

William J Green

Felipe Knop

Myung Mun Bae

Robert J Curran

Thomas K Clark

Sudhir Gurunandan Rao

Venkataraghavan Lakshminarayanachar

Evelyn Tingmay Yeung

Shashidhar Bomma

Jean-Philippe Sugarbroad

Amar Devegowda

Callum Foshee

Rama Mothey Tenjarla

Srinivasa Muppala Rao

Kristian Doggett

Ahmed Hikal

Ashley Lim

Akeem Lawal

Paul Vaters

Anil Kumar K Damodaran

Amarendar N Sulu

Shanna Beck

Vidya Makineedi

Maha Emad

Emmanuelle Samir Hanna Matta

Abraham Alvarez

Raul Salajan

Cindy Barrett

Srinivasa Raghavan Masthi Parthasarathi

A computer system, computer readable storage medium, and computer-implemented method for detecting if one or more processing devices have separately sourced power feeds. The method includes determining transmission of a first signal in a first electric path. The method also includes monitoring for a second signal in a second electric path that is different from the first electric path. The method further includes determining, subject to the monitoring, electrical isolation between the first electric path and the second electric path. The claimed computer-implemented method dynamically, and automatically, determines that power sources are separate, isolated, and redundant.

Detecting redundant power feeds

Methods, systems and computer program products for recognition of partially digested medications are provided. Aspects include receiving an image depicting regurgitated stomach contents of an individual and obtaining medical data regarding the individual. Aspects also include analyzing the image, by a recognition model, to identify one or more pills depicted in the image and a percentage of the one or more pills that has not been digested. Aspects further include performing an action based on the medical data, the identification of the one or more pill and the percentage of the one or more pills that has not been digested.

Recognition of partially digested medications

A method for managing Live Partition Mobility (LPM) on a computer system that includes receiving, by a processor, a LPM request, verifying that the LPM request includes a parameter that does not exceed a threshold value, and transmitting an approval query to an outside authority. The method also includes collecting a response to the approval query, scheduling, respondent to a positive approval query response, a LPM event, and executing the LPM event.

LPM management using contingent and conditional inputs

For a first virtual machine (VM) executing on a physical machine and virtualizing a set of redundant physical adapters installed in the physical machine, a second VM is instantiated on the physical machine. A first physical adapter is reassigned from the first VM to the second VM, the first physical adapter comprising one of the set of redundant physical adapters, the reassigning performed without rebooting a first operating system executing in the first VM. A second rule configuration of the second VM is updated to match a first rule configuration of the first VM, forming an updated second VM. A hypervisor managing the physical machine is caused to redirect traffic for a first virtual adapter associated with the reassigned first physical adapter to the updated second VM.

Live updating a virtual machine virtualizing physical resources

A method for optimization of low-level memory operations in a distributed memory storage configuration that includes receiving, at a first processor, a request to migrate data from the first processor to a second processor, where the first processor and the second processor comprise a processor and memory, and identifying a command instruction associated with the requested data. The method also includes comparing a first performance metric associated with the first processor to a second performance metric associated with the second processor, where the first performance metric and the second performance metric are associated with executing the command instruction, and where, based on the comparing, a decision to move the command instruction to the second processor is formed, and migrating, responsive to the decision, the data and the command instruction to the second processor.

Optimization of low-level memory operations in a NUMA environment

Embodiments are disclosed for managing heap metadata corruption. The techniques include detecting a metadata corruption error in a first heap disposed in a first region of memory. The techniques also include generating a second heap in a free memory region that is disposed beyond a break value address of a memory allocation system. The techniques further include updating a first entry for the first heap in a heap directory. Additionally, the techniques include generating a second entry for the second heap in the heap directory. The techniques also include processing a call to the memory allocation system for the first heap based on the first entry and the second entry.

Managing heap metadata corruption

Threads of a multithreaded application may be scheduled to different cores and executed in various orders and at various frequencies. Controlling how the threads are scheduled and clock rates of processor cores enables testing multiple possible execution scenarios, which may force previously unknown timing window problems to occur. These timing window problems may then be detected.

Method and technique to find timing window problems

A method for determining affinity domain information based on virtual memory address in a computing system where access to memory is non-uniform includes receiving a request to identify an affinity domain associated with a specified virtual memory address. The affinity domain includes a cluster of processors and memory local to the cluster of processors. A physical memory page corresponding to the specified virtual memory address is determined using a page table mapping a plurality of virtual memory addresses to a plurality of physical addresses. An affinity domain associated with the determined physical memory page is identified. Affinity domain information is provided for the identified affinity domain.

Determining affinity domain information based on virtual memory address

Embodiments include method, systems and computer program products for performing Spectre mitigation on a workload. The method includes starting, by at least one processor of a plurality of processors, a process. The at least one processor determines that the process is a kernel process. The at least one processor determines that an interrupt has occurred in response to the determination that the process is a kernel process. The at least one processor processes the interrupt in response to determining that an interrupt has occurred. The at least one processor suppresses a malware mitigation to be applied to the kernel process in response to interrupt being processed.

Interrupt context switching using dedicated processors

A method begins by sending, by a user computing device of a storage network, a read request regarding data to a host computing device of the storage network in accordance with a transport layer protocol, where the read request includes data retrieval information associated the data. The method continues with determining, by the host computing device, a storage entity of the storage network that is storing the data based on the data retrieval information. The method continues with sending, by the host computing device, socket information and data retrieval information to the storage entity. The method continues with sending, by the storage entity, the data directly to the user computing device in accordance with the socket information and using the session identifier.

Direct file send from storage to end client by transferring socket information to the storage

Examples of techniques for deferred disclaim of memory pages are described herein. An aspect includes, based on freeing of a last allocation on a first memory page, placing, by a processor, the first memory page on a deferred disclaim list. Another aspect includes, based on freeing of the last allocation on the first memory page, setting, by the processor, a first hidden flag in a first page table entry corresponding to the first memory page.

Deferred disclaim of memory pages

Data in a database cache in memory of an operating database server is copied to memory of a standby database server, without requiring synchronization between the operating server and the standby server. If the operating server fails, the database is recovered to a consistent state in the standby server using a sequential database log and the copied data in the cache of the standby server. Preferably, recovery is performed by reading the log to determine a set of database actions to recover, verifying blocks of data in the standby server's cache, using verified blocks to recover at least some actions, and reading blocks from storage only when a corresponding verified block is not available in the cache.

Managing a redundant computerized database using a replicated database cache

A method, system, and computer program product for a diagnostic heartbeat throttling are provided in the illustrative embodiments. A component, executing using a processor and a memory in a data processing system, sends diagnostic heartbeat packets over a communication link at a first rate, wherein a diagnostic heartbeat packet is a packet comprises a header, a set of heartbeat parameters, and a set of diagnostic attributes. The component detects a change in data traffic over the communication link. The component changes a rate of sending diagnostic heartbeat packets from the first rate to a second rate responsive to the change in the data traffic over the communication link.

Diagnostic heartbeat throttling

Technical solutions are described for generating a secured system snapshot of a system. An example computer-implemented method includes receiving an instruction to generate a system snapshot. The system snapshot captures data from a computer executable object loaded in a memory. The method also includes accessing metadata that is associated with the computer executable object from a mapping list. The method also includes capturing the secured system snapshot by. Capturing the secured system snapshot includes determining sensitivity of the computer executable object by comparing the metadata with a predetermined criteria, and excluding a capture of sensitive data from the computer executable object into the system snapshot in response to the metadata of the computer executable object matching the predetermined criteria. The method also includes storing the secured system snapshot.

Dynamically excluding sensitive information from system snapshot

A computer system is monitored for conditions bearing on the effective age of various hardware components of the system. Upon detecting an age adjustment condition, the affected hardware components are identified. An age adjustment is determined for each of the affected hardware components. The adjusted age is stored for reference when taking actions based on the adjusted age, such a component replacement and/or workload placement.

Predicting hardware failures in a server

Growing community of inventors

Spicewood, TX, United States of America

Douglas J Griffith