Abstract: Apparatuses, methods and storage medium associated with live migration of VMs from/to host computers with graphics virtualization are disclosed herein. In embodiments, an apparatus may include a VMM having a memory manager to manage accesses of system memory of the apparatus, including tracking of modified memory pages of the system memory. Additionally, the VMM may include a graphics command parser to analyze graphics commands issued to a GPU of the apparatus to detect writes to the system memory caused by the graphics commands, and augment the tracking of modified memory pages. Further, the VMM may include a live migration function to live migrate a VM to another apparatus, including provision of current memory content of the VM, utilizing modified memory pages tracked by the memory manager, as augmented by the graphics command parser. Other embodiments may be described and/or claimed.

Abstract: A virtual machine control device includes a processor configured to acquire usage information including an actual usage value of respective virtual machines operating on each of information processing apparatuses during each of past periods, and create, for each of the information processing apparatuses, prediction information including a prediction usage value of the respective virtual machines during each of periods. The processor is configured to determine, upon detecting a first virtual machine whose actual usage value is not included in the usage information, whether a first period exists, in which a sum of the actual usage value of the first virtual machine and prediction usage values of virtual machines operating on a first apparatus exceeds a criterion. The processor is configured to issue, upon determining that the first period exists, an instruction to move one of virtual machines operating on the first apparatus to a second apparatus before the first period.

Abstract: A method for network communications from a first device to a second device includes communicating data from the first device to the second device by spawning a first virtual machine for a first network connection that virtualizes network capabilities of the electronic device, and using the virtualized network capabilities of the first virtual machine, transmitting a plurality of packets for communication to a first network address and port combination associated with the second device. The method further includes repeatedly changing to a respective another network address and port combination by repeatedly spawning a respective another virtual machine for a respective another network connection that virtualizes network capabilities of the electronic device, and using the virtualized network capabilities of the spawned respective another virtual machine, transmitting a plurality of packets for communication to the respective another network address and port combination associated with the second device.

Abstract: Implementing static loaders and savers for the transfer of local and distributed data containers to and from storage systems can be difficult because there are so many different configurations of output formats, data containers and storage systems. Described herein is an extensible componentized data transfer framework for performant and scalable authoring of data loaders and data savers. Abstracted local and distributed workflows drive selection of plug-ins that can be composed by the framework into particular local or distributed scenario loaders and savers. Reusability and code sparsity are maximized.

Abstract: Various aspects may include methods, computing devices implementing such methods, and non-transitory processor-readable media storing processor-executable instructions implementing such methods for improving battery life with performance provisioning using machine learning based automated workload classification. Various aspects may include creating a machine learning model based at least in part on computing device metrics, training the machine learning model using performance provisioning rules for work groups; classifying a new work item for a software application into a work group using the trained machine learning model, and applying resource provisioning rules for the work group to the new work item.

Abstract: Technologies for assigning workloads based on resource utilization phases include an orchestrator server to assign a set of workloads to the managed nodes. The orchestrator server is also to receive telemetry data from the managed nodes and identify, as a function of the telemetry data, historical resource utilization phases of the workloads. Further, the orchestrator server is to determine, as a function of the historical resource utilization phases and as the workloads are performed, predicted resource utilization phases for the workloads, and apply, as a function of the predicted resources utilization phases, adjustments to the assignments of the workloads among the managed nodes as the workloads are performed.

Abstract: Technologies for dynamically managing the allocation of accelerator resources include an orchestrator server. The orchestrator server is to assign a workload to a managed node for execution, determine a predicted demand for one or more accelerator resources to accelerate the execution of one or more jobs within the workload, provision, prior to the predicted demand, one or more accelerator resources to accelerate the one or more jobs, and allocate the one or more provisioned accelerator resources to the managed node to accelerate the execution of the one or more jobs. Other embodiments are also described and claimed.

Abstract: A parallel processing system includes three or more node devices including a first node device. The first node device is configured to perform an allocation process of a computation resource targeting a processing, the first node device sends permission information to node devices of the three or more node devices, the permission information indicating permission to request the allocation process corresponding in number to a number of processings which the allocation process is able to execute in a unit time using a resource of the first node device in the unit time, the node devices being set to receive an execution request for the processing. The node devices spend the permission indicated by the permission information received from the first node device when receiving the execution request for the processing, and sends a request for execution of the allocation process that targets the processing to the first node device.

Abstract: A computing system is provided for providing task schedules, comprising an agent manager, a schedule information database configured to store resource and/or task information, at least one configurable agent, a scheduler, wherein the agent manager is configured to submit configuration instructions to the at least one configurable agent based on configuration information received by the agent manager, wherein the at least one configurable agent is configured to monitor resources used and/or tasks executed in the computing system depending on the configuration instructions and to store resource and/or task information derived from the monitored resources and/or tasks in the schedule information database, and wherein the scheduler is configured to generate and output a task schedule based on the resource and/or task information stored in the schedule information database.

Abstract: Examples may include a sled for a rack of a data center including physical compute resources. The sled comprises a processor component and a unitary memory module comprising a memory controller and a quantity of memory based on the processor component. The unitary memory module can comprise a quantity of memory based on a number of cores of processor component to which the unitary memory module is communicably coupled.

Abstract: A cross compiler generates a logical communication area number for first identifying information that is assigned to each of multiple processes contained in parallel processing. An area converter and an address acquisition unit keep correspondence information that makes it possible to, on the basis of the first identifying information and second identifying information representing the parallel processing, specify a memory area that is allocated according to each set of the second identifying information corresponding to the logical communication area number, receives a communication instruction containing the first identifying information, the second identifying information and the logical communication area number, and acquires a memory area corresponding to the acquired logical communication area number on the basis of the correspondence information. A communication controller performs communication by using the memory area that is acquired by the address acquisition unit.

Abstract: A system includes a server that comprises a virtualization layer in which a hardware resource is virtualized, and a virtualization control apparatus. The virtualization control apparatus requests first information regarding the hardware resource to the server, registers second information corresponding to the first information acquired from the server, and uses the second information to control a network function (Virtual Network Function: VNF) implemented and virtualized by software operating on a virtual machine implemented on the virtualization layer.

Abstract: Technologies for dynamically allocating tiers of disaggregated memory resources include a compute device. The compute device is to obtain target performance data, determine, as a function of target performance data, memory tier allocation data indicative of an allocation of disaggregated memory sleds to tiers of performance, in which one memory sled of one tier is to act as a cache for another memory sled of a subsequent tier, send the memory tier allocation data and the target performance data to the corresponding memory sleds through a network, receive performance notification data from one of the memory sleds in the tiers, and determine, in response to receipt of the performance notification data, an adjustment to the memory tier allocation data.

Abstract: According to an example of the present disclosure, an information technology (IT) environment, such as a data center, a cloud services platform or other type of computing environment, may include computer resources that are dynamically allocated to workloads. A model is generated to estimate performance and allocate computer resources to the workloads.

Abstract: A method, system and computer program product for load balancing of graph processing workloads. Synthetic proxy graphs are generated to characterize machines' graph processing speeds in a cluster. Each of the graph applications executing in the cluster is profiled using the synthetic graphs to form profiling sets. These formed profiling sets are run among the machines in the cluster to capture the machines' graph processing speeds. A metric for each of the graph applications is computed from a relative speedup among the machines in the cluster and/or the graph processing speeds. A graph file of a natural graph and a graph application are loaded. A metric out of the computed metrics is selected based on the graph application. The natural graph is then partitioned into multiple chunks which is distributed onto two or more machines in the cluster based on the selected metric and a user selected partitioning algorithm.

Abstract: Computational tasks are mapped with computational locations in a distributed system such as a cloud computing environment. Mapping does not rely on workload estimates. Instead, tasks whose prerequisite tasks or other preconditions are determined to be mutually exclusive are co-located, while other tasks are mapped to different locations than one another. Locations are servers, processor cores, virtual machines, applications, or computational processes, for example. Mutual exclusivity may be determined by detecting that preconditions require different values of a shared variable in order to be satisfied, for example, or determining that preconditions correspond to different branches of a conditional programming statement. A satisfiability engine may also provide a satisfiability determination. Co-located tasks may also be batched, for improved execution performance.

Abstract: An information processing apparatus is provided including a first operating system incapable of adding or deleting an application and a second operating system capable of adding and deleting an application; and determines whether a received command is a command directed to the first operating system or a command directed to the second operating system by referencing a table in which the command and an operating system for processing the command are associated with each other; retains the table; controls a memory so that the first operating system or the second operating system can start processing based on a result of the determining by the means for determining; and transfers the received command to the first operating system or the second operating system based on the result of the determining.

Abstract: Differing implementations associated with components of dissimilar execution environments are mediated to facilitate component integration. A host is provided to facilitate native interaction with foreign components by translating between native and foreign communications. Policies can be specified by either or both of a native and foreign component that control interaction.

Abstract: A system and method for providing delegated metric tools within a partially closed communication platform that includes receiving a tag identifier linked to at least a first identified platform interaction in the communication platform; associating the tag identifier with at least one logged event of an account associated with the first identified platform interaction; defining a tracking resource with at least one tag identifier; measuring platform interactions tracked by a tracking resource; and providing access to measured platform interactions through an application.

Abstract: Systems and methods of detecting a call sequence anomaly in a message-based operating system are provided. A message may be received that indicates a programmatic procedure of an operating system was invoked. The message may include a programmatic procedure identifier, a sender process identifier, and a receiver process identifier. An invocation hash may be generated based on the message. The invocation hash may be translated to a smaller invocation identifier. The invocation identifier may be included in a translated call sequence that comprises invocation identifiers for a series of invocations. Depending on whether the translated call sequence is included in previously generated predetermined call sequences, the translated call sequence may be determined as an anomaly or not an anomaly.

Abstract: Methods and systems for detecting anomalous behavior include performing a principal component analysis on a plurality of key performance indicators (KPIs) to determine a set of principal axes. The KPIs are clustered in a space defined by the set of principal axes. Local and structural anomalies are determined in the clustered KPIs. The structural and local anomalies are classified based on historical information. A management action is performed based on the classified structural and local anomalies.

Abstract: Tailoring diagnostic information specific to current activity of multiple threads within a computer system. A request to dump system state is received. A system dump is created, including main memory and system state information. The system dump is stored to a database. In response to a request to format the system dump, the system dump is loaded from the database, whereby a virtual memory image of system state at system dump time is created. The virtual memory image and system state information is scanned to identify tasks that were running, tasks that have failed due to an error, and tasks that were suspended at system dump time. State information and control blocks associated with the identified tasks are collected from the system dump and collated based on task number. The database is updated with a formatted system dump, including the state information and control blocks associated with the identified tasks.

Abstract: A method for storing data in a storage system having solid-state memory is provided. The method includes determining portions of the solid-state memory that have a faster access rate and portions of the solid-state memory that have a slower access rate, relative to each other or to a threshold. The method includes writing data bits of erasure coded data to the portions of the solid-state memory having the faster access rate, and writing one or more parity bits of the erasure coded data to the portions of the solid-state memory having the slower access rate. A storage system is also provided.

Abstract: Error correction in a memory subsystem includes a memory device generating internal check bits after performing internal error detection and correction, and providing the internal check bits to the memory controller. The memory device performs internal error detection to detect errors in read data in response to a read request from the memory controller. The memory device selectively performs internal error correction if an error is detected in the read data. The memory device generates check bits indicating an error vector for the read data after performing internal error detection and correction, and provides the check bits with the read data to the memory controller in response to the read request. The memory controller can apply the check bits for error correction external to the memory device.

Abstract: A decoder includes a channel mapper configured to generate a plurality of channel reception values based on hard decision information and soft decision information, a strong error detector configured to determine whether a strong error has occurred using a plurality of check node messages and the channel reception values and to correct the channel reception values according to a determination result to produce corrected channel reception values, a variable node unit configured to generate a plurality of variable node messages using the check node messages and the corrected channel reception values, and a check node unit configured to generate the check node messages using the variable node messages. The variable node unit includes a plurality of variable nodes and the check node unit includes a plurality of check nodes.

Abstract: In a flash memory, redundant columns are used alternatively as replacement columns for replacing bad columns or to provide additional redundancy for ECC encoding. Locations of bad columns are indicated to a soft-input ECC decoder so that data bits from bad columns are treated as having a lower reliability than data bits from other columns.

Abstract: A system and method for adaptive multiple read of NAND flash memory. A solid state drive may employ adaptive multiple-read to perform enhanced performance error correction using soft decisions without a performance penalty that otherwise might result from performing unnecessary reads. The soft decision error correcting algorithm may employ lookup tables containing log likelihood ratios. The method may include performing one or more read operations to obtain one or more raw data words for a code word, attempting to decode the code words using the one or more raw data words, and performing additional read operations when the decoding attempt fails. This process may be repeated until a decoding attempt succeeds.

Abstract: A method for a dispersed storage network (DSN) begins by determining an I/O (input/output) capacity of a storage level of DSN memory. The method continues by determining a required performance level to meet operational demands of services operating at the storage level. The method continues by setting a storage level throttle rate based on the I/O capacity and the required performance level and determining a remaining I/O performance of the DSN memory to be allocated to a higher storage level.

Abstract: A method begins by communicating memory management information between a dispersed storage (DS) management unit and a plurality of DS execution units. The method continues by generating, by the DS management unit, managing use information. The method continues by sending the managing use information to a DS optimization unit. The method continues by receiving from the DS optimization unit optimization information based on an analysis of the sent managing use information. The method continues by updating a DS management unit managing approach based on the received optimization information.

Abstract: A method begins by determining to rebuild a slice or slices to at least one of multiple distributed storage network (DSN) memory locations. The method continues by calculating a future risk estimation of each one of the multiple DSN memory locations, the future risk estimation including one or more risk factors. The method continues by determining a selection of which of the multiple DSN memory locations to rebuild and rebuilding the slice in the DSN memory of the selection.

Abstract: A method begins by determining to rebuild one or more encoded data slices to a dispersed storage network (DSN) memory unit. The method continues by determining a rebuild rate of the DSN memory unit. The method continues by determining, based on the rebuild rate, a rebuild rate status of the DSN memory unit. The method continues by when the rebuild rate status is a high rebuild rate status, reducing the rebuild rate to the DSN memory unit. The method continues by rebuilding, when the rebuild rate is not zero, the one or more encoded data slices in the DSN memory unit.

Abstract: A method begins by a dispersed storage (DS) processing module identifying an encoded slice requiring rebuilding. The method continues by the DS processing module determining whether the encoded data slice is part of a fan-out encoded data slice group and, when it is part of a fan-out encoded data slice group determining by the DS processing module whether a valid encoded data slice of the fan-out data slice group is available. When a copy of the encoded data slice of the fan-out encoded data slice group is not available, the method continues by the DS processing module rebuilding the encoded data slice. A storage unit then stores the rebuilt encoded data slice and creates copies of the rebuilt encoded data slice to produce a rebuilt fan-out encoded data slice group.

Abstract: A computing device of a dispersed storage network (DSN) includes a memory, interface and a processing module operable to identify an encoded data slice of the set of encoded data slices to produce an identified encoded data slice. The processing module generates a set of first write requests regarding the set of encoded data slices less the identified encoded data slice, and generates a set of second write requests regarding the identified encoded data slice. The set of second write requests include the identified encoded data slice and replications of the identified encoded data slice. The processing module sends the set of first write requests to storage units of the DSN, and sends the set of second write requests to a set of storage units of the DSN, where each storage unit of the set of storage units is sent a corresponding one of the set of second write requests.

Abstract: A system allows smart backup and restore of databases. The system identifies a database affected by a database operation recorded by a database event record, identifies a database operation time recorded by the database event record, and requests to restore the database to a version backed up prior to the database operation time.

Abstract: A method, a processing device, and a computer program product are provided. In various embodiments, a computing device reads predefined policy information defining one or more conditions for restarting a container. The computing device monitors the container to detect an occurrence of any one of the one or more conditions defined by the predefined policy information. The computing device automatically restarts the container after detecting the occurrence of any one of the one or more conditions defined by the predefined policy information. In some embodiments, the computing device waits a certain amount of time, as specified in the predefined policy information, before automatically restarting the container.

Abstract: In a method for data management, one or more processors identifying a source closure, a target file set, and a previously merged closure, wherein the source closure is a closure of files that includes changed files to merge into the target file set, and wherein the previously merged closure is a closure of files previously merged into the target file set. The method further includes one or more processors loading the identified source closure, the previously merged closure, and a closure of ancestor files shared by the identified source closure and the previously merged closure into a merge session. The method further includes one or more processors determining one or more file merge conflicts in the merge session based on differences between a comparison of the identified source closure to the closure of ancestor files and a comparison of the previously merged closure to the closure of ancestor files.

Abstract: An application may store data to a dataset comprising a plurality of volumes stored on a plurality of storage systems. The application may request a dataset image of the dataset, the dataset image comprising a volume image of each volume of the dataset. A dataset image manager operates with a plurality of volume image managers in parallel to produce the dataset image, each volume image manager executing on a storage system. The plurality of volume image managers respond by performing requested operations and sending responses to the dataset image manager in parallel. Each volume image manager on a storage system may manage and produce a volume image for each volume of the dataset stored to the storage system. If a volume image for any volume of the dataset fails, or a timeout period expires, a cleanup procedure is performed to delete any successful volume images.

Abstract: Systems and methods are disclosed for cross-system user-level management of data objects stored in one or more information management systems, and for user-level management of data storage quotas in information management systems, including data objects in secondary storage. An illustrative quota manager is associated with one or more information management systems. The quota manager comprises a quota value representing the maximum amount of data storage allowed for a given end-user's primary and secondary data in the one or more information management systems. The quota manager determines whether data associated with the end-user has exceeded the storage quota, and if so, prompts the end-user to select data for deletion, the deletion to be implemented globally, across the primary and secondary storage subsystems of the respective one or more information management systems. Meanwhile, so long as the quota is exceeded, the quota manager instructs storage managers to block backups of end-user's data.

Abstract: In one embodiment, a method for ransomware-aware file backup is implemented on a computing device and includes: backing up a target population of files from a target file location in a backup transaction, computing a backup delta score for the backup transaction, where the computing comprises comparing backup data from the backup transaction with backup data from a previous backup transaction, determining whether the computer backup delta score exceeds a pre-defined threshold, and upon the computed backup delta score exceeding the pre-defined threshold: determining that the backup transaction is indicative of a ransomware infection, and performing at least one counter-measure in response to the ransomware infection.

Abstract: A moving weighted average of application bandwidth is calculated based on updates to a first data storage by a first data site. A moving weighted average of transmission bandwidth is calculated based on replication of the updates to a second data storage via a second data site. A next coordinated consistency point is identified and the time remaining before the next consistency point is calculated. An amount of the updates that can be replicated before the next consistency point is determined based on the average transmission bandwidth. A prediction of an amount of additional updates that will be generated on the first data site before the next consistency point is made using heuristics based on the average application bandwidth. When update accumulation combined with the prediction exceeds the amount of updates that can be replicated before the next consistency point, pending updates are flushed to the second data storage.

Abstract: According to certain aspects, a method of creating customized bootable images for client computing devices in an information management system can include: creating a backup copy of each of a plurality of client computing devices, including a first client computing device; subsequent to receiving a request to restore the first client computing device to the state at a first time, creating a customized bootable image that is configured to directly restore the first client computing device to the state at the first time, wherein the customized bootable image includes system state specific to the first client computing device at the first time and one or more drivers associated with hardware existing at time of restore on a computing device to be rebooted; and rebooting the computing device to the state of the first client computing device at the first time from the customized bootable image.

Abstract: A computer-readable recording medium having stored therein a program for causing a first processor to execute a process, the first processor included in an information-processing system that includes a second processor to store data and receive a data transaction, and a third processor to operate as a stand-by apparatus while the second processor operates as an active apparatus, wherein the process includes generating a temporary-transaction identifier for identifying the transaction; adding the generated temporary-transaction identifier to a first request about the transaction, and transmitting the first request to the second and third processors; and upon receipt of a response to the first request from the second processor, extracting a transaction identifier for identifying the transaction and a data identifier for identifying the data from the response, adding the transaction and data identifiers to a second request about the transaction, and transmitting the second request to the second and third process

Abstract: Systems and methods are provided for flash memory devices to improve the write performance in case of write path errors and to hide the write path error correction latency. Some embodiments can provide instant parity correction to allow user data sharing the same strip with the data block having an error to be programmed into the flash memory before the failed data is corrected. Additionally, selected stalling can allow some independent data in different flash memory dies or planes to be programmed during the time of write path error correction.

Abstract: A fault monitoring device includes a notice reception part configured to receive a notice indicating occurrence of faults from a virtual network device, and a recovery process part configured to carry out a recovery process for one device having the highest priority of fault response among the virtual network device producing the notice, a physical device implementing the virtual network device, and another virtual network device involved in dependency with the virtual network device.

Abstract: An electronic device has a first terminal for receiving power from a connected external device, a second terminal for obtaining information of the external device, and a GND terminal connected to the second terminal. The electronic device causes a resistance between the second terminal and the GND terminal to change, and determines a type of the external device based on a voltage of the first terminal after the resistance is caused to change.

Abstract: A system for detecting false data injection attacks includes one or more sensors configured to each monitor a component and generate signals representing measurement data associated with the component. The system also includes a fault detection computer device configured to: receive the signals representing measurement data from the one or more sensors, receive a fault indication of a fault associated with the component, generate a profile for the component based on the measurement data, and determine an accuracy of the fault indication based upon the generated profile.

Abstract: Automated discovery of relationships between entities within an IT environment. A technique is performed by a relationship module that performs a discovery search for entity relationships to produce a set of relationship search results. The relationship module then generates a set of relationship definitions from the set of relationship search results which are stored to a relationship collection in a data store. A technique for automatically updating entity and relationship definitions and removing outdated entity and relationship definitions stored to a data store. An update module automatically updates entity and relationship definitions at predetermined time intervals. The update history in each definition is also modified to reflect the update process. A retire module automatically removes outdated definitions using the update history in each definition.

Abstract: A method, system, and computer program product are provided for determining whether a control unit for an attached device has lost knowledge of a supported host enabled facility associated with the attached device. I/O instructions are initiated that include a first instruction to determine whether the control unit currently has knowledge of the host enabled facility and a second instruction providing knowledge of the host enabled facility by the control unit. Based on responses from the control unit to the I/O instructions, it is determined whether the control unit has transitioned from not having knowledge of the host enabled facility to having such access. If it is determined that the control unit has made such transition as a result of the sequence of I/O instructions, parameters for use with the host enabled facility are initialized; otherwise, such initialization is prevented.

Abstract: A node in network is configured to buffer data received from other nodes across multiple channels. The node process a portion of the buffered data associated with a subset of those channels. When the node receives data on that subset of channels that includes a notification, the node then processes a larger portion of the buffered data associated with a larger number of channels. In doing so, the node may identify additional notifications include within data that was buffered but not previously processed. The node may also coordinate with other nodes in order to process buffered data upon identification of a notification.

Abstract: A test support device includes a processor configured to acquire event information on events which occur during an execution of a target program. The processor is configured to classify the events into event groups on basis of similarity of timings at which the respective events occur. The processor is configured to calculate, for each of the event groups, a summed value of evaluation values of the respective events classified into the relevant event group. The processor is configured to determine for each of the event groups, on basis of the summed value, whether a breakpoint of a target process executed by the target program is present at a timing corresponding to the relevant event group. The processor is configured to display timing information indicating a timing at which a breakpoint is determined to be present, in association with elapsed time after a start of executing the target program.