Abstract: An information handling system receives a notification regarding a state of the information handling system, and determines an alert management policy associated with the notification regarding the state of the information handling system. The system also applies an alert management action to enforce the alert management policy.

Abstract: There is provided a processor configured to transfer data to a plurality of processor circuits. The apparatus includes broadcast circuitry that broadcasts first machine learning data to at least a subset of the plurality of processor circuits.

Abstract: In variants, the system can include a set of blockchain modules and a set of interaction mechanism handlers configured to convert a unified set of system commands into blockchain-specific commands for each of a set of blockchains and/or blockchain nodes.

Abstract: Apparatuses, systems, and techniques to execute CUDA programs. In at least one embodiment, an application programming interface is performed to indicate two or more blocks of threads to be scheduled in parallel.

Abstract: Apparatuses, systems, and techniques to execute CUDA programs. In at least one embodiment, an application programming interface is performed to determine which of two or more blocks of threads are to be scheduled in parallel.

Abstract: Apparatuses, systems, and techniques to execute CUDA programs. In at least one embodiment, an application programming interface is performed to indicate a scheduling policy of one or more blocks of one or more threads.

Abstract: Apparatuses, systems, and techniques to execute CUDA programs. In at least one embodiment, an application programming interface is performed to indicate one or more attributes of one or more groups of blocks of one or more threads.

Abstract: Apparatuses, systems, and techniques to execute CUDA programs. In at least one embodiment, an application programming interface is performed to indicate one or more limitations of one or more attributes of one or more groups of blocks of one or more threads.

Abstract: Apparatuses, systems, and techniques to execute CUDA programs. In at least one embodiment, an application programming interface is performed to indicate whether one or more threads within a group of blocks of threads have performed a barrier instruction and to cause performance of one or more threads within the group of blocks of threads to stop at least until all threads within the group of blocks have performed the barrier instruction.

Abstract: Apparatuses, systems, and techniques to execute CUDA programs. In at least one embodiment, an application programming interface is performed to cause memory to be shared between two or more groups of blocks of threads.

Abstract: An acquiring unit configured to connect via a network to a device management system that manages functions of devices, and acquire device management information based on which a device usable by a user and a function usable by the user among functions of the device are managed from the device management system; a generating unit configured to generate a WebAPI based on the device management information acquired, and generate a virtual device configured to respond to an access to the WebAPI in cooperation with the device; an informing unit configured to inform a terminal used by the user of information including how to access the WebAPI; and an accessing unit configured to access the device via the virtual device are provided.

Abstract: An electrostatic interference processing method, apparatus, and device, and a readable storage medium are provided. The method includes: receiving input data in real time, and determining whether an electrostatic interference signal is present in the input data; in response to determining that the electrostatic interference signal is present in the input data, interrupting reception of the input data; determining whether an interference frequency of the electrostatic interference signal is lower than a preset value; and in response to determining that the interference frequency of the electrostatic interference signal is lower than the preset value, continuing to receive the input data.

Abstract: A data storage device includes a controller. The controller is coupled to a host device. The controller is configured to determine a quality of a peripheral component interconnect express (PCIe) link, wherein the quality of the PCIe link is either greater than or less than a threshold quality, and transmit an error notification to the host device via a sideband when the quality of the PCIe link is less than the threshold quality. The sideband is a different communication channel than the PCIe link. The error notification includes additional information regarding events occurring in the data storage device resulting in the quality of the PCIe link.

Abstract: System and computer-implemented method for managing multi-availability zone (AZ) clusters of host computers in a cloud computing environment automatically detects a degraded state of a first AZ in the cloud computing environment based on host failure events for host computers in a first cluster section of a multi-AZ cluster of host computers located in the first AZ and a recovered state of the first AZ based a successful scale-in operation of another multi-AZ cluster located partially in the first AZ. In response to the detection of the degraded state of the first AZ, a second cluster section of the multi-AZ cluster of host computers located in a second AZ is scaled out. In response to the detection of the recovered state of the first AZ, the second cluster section of the multi-AZ cluster of host computers located in the second AZ is scaled in.

Abstract: The present subject matter discloses techniques to automatically cluster events generated by a plurality of distinct ecosystems deployed in a connected environment in relation to a product. In operation, the clustered events may be correlated, and one or more of the correlated events that trigger a response may be identified as an actionable item. Based on a correlation between the actionable items, a hierarchical product parameter responsible for the actionable item may be identified. The hierarchical product parameter is an operational factor in a hierarchy of operational factors associated with the product, where the hierarchy of operational factors span over the plurality of distinct ecosystems operating in relation to the product. Subsequently, one or more entities across the distinct ecosystems may be notified of the actionable item, to initiate a required action. Further, techniques to detect operational factors associated with the product deployed in the distinct ecosystems are disclosed.

Abstract: The disclosure relates to systems and methods of detecting anomalies using a plurality of machine learning models. Each of the machine learning models may be trained to detect a respective behavior of historical data values for a given metric. Thus, a system may perform anomaly detection based on different behaviors of the same metric of data, reducing instances of false positive anomaly detection while also reducing instances of false negative reporting. The plurality of machine learning models may be trained to detect anomalies across multiple different types of metrics as well, providing robust multi-metric anomaly detection across a range of behaviors of historical data values. The system may implement a pluggable architecture for the plurality of machine learning models in which models may be added or removed from pluggable architecture. In this way, the system may detect anomalies using a configurable set of machine learning models.

Abstract: A computing system automatically manages error reports. Each error report specifies an error that occurred within a subsystem of the computing system. A received error report is added into a root cause grouping. Each root cause grouping contains error reports having error types traceable to a same root cause. A deployment time at which the subsystem corresponding to the error report was deployed within the computing system is determined. A severity score for the root cause grouping is generated as a function of the deployment time. The severity score inversely correlates to a time period length between the deployment time and the occurrence time of the error. The root cause grouping is assigned to a ranked error container of a plurality of ranked error containers based on the generated severity score. Each ranked error container contains root cause groupings having severity scores within a specified score range.

Abstract: Systems and methods for automated remediation of issues arising in a data management storage system are provided. Deployed assets of a storage solution vendor may deliver telemetry data to the vendor on a regular basis. The received telemetry data may be processed by an AIOps platform to perform predictive analytics and arrive at “community wisdom” from the vendor's installed user base. In one embodiment, an insight-based approach is used to facilitate risk detection and remediation including proactively addressing issues before they turn into more serious problems. For example, based on continuous learning based on the community wisdom and making one or both of a rule set and a remediation set derived therefrom available for use by cognitive computing co-located with a customer's storage system, a risk to which the storage system is exposed may be determined and a corresponding remediation may be deployed to address or mitigate the risk.

Abstract: In one general embodiment, a method for selecting parameters of an error recovery procedure includes detecting an error during performance of a data operation on a data storage medium by an apparatus. In response to detecting the error, parameters of an error recovery procedure are selected based at least in part on: (a) first information about previous interactions between the apparatus and multiple data storage media, and (b) second information about previous interactions between the data storage medium and other apparatuses.

Abstract: Systems, computer program products, and methods are described herein for dynamic error resolution in an extended reality environment. The present invention identifies user errors in real time based on user selections in an extended reality (XR) environment. In this regard, the present invention focuses on electronic applications (and the electronic work products/electronic data hosted thereon) within an XR environment and uses machine learning processes to identify real time user errors. The invention may then use a second set of machine learning processes to create, in real-time, digital support content which is visible via an XR platform (accessible using a virtual/augmented/mixed reality device). As such, the system may provide specific improvements over prior systems by automatically providing users with custom error resolution support in real time.

Abstract: Described herein are systems, methods, and software to manage configuration attempts for a service following a failure associated with the service according to an implementation. In one example, a management service monitors hosts in a computing environment and identifies a failure associated with a service on a first host. In response to identifying the failure, the management service identifies one or more criteria to initiate an attempt to configure the service based on the type of failure and initiates the attempt to configure the service when the one or more criteria are satisfied. Additional attempts can be initiated by the management service if the initial configuration attempt fails after a timeout interval.

Abstract: The present disclosure relates to a method, and apparatus for detecting an application freezing problem, and a device and a storage medium. The method comprises: detecting time consumed for a Runloop in a first thread of an application executing a task; when it is detected that the consumed time reaches a preset threshold value, at least acquiring a call stack of the first thread and the current first execution state of the Runloop, and writing the call stack into a preset file; detecting an execution state of the Runloop after the time consumed for the task reaches the preset threshold value; and if the Runloop does not enter a second execution state after the first execution state before the application is closed, sending the preset file to a remote server. By means of the solution provided in the embodiments of the present disclosure, an application freezing problem can be identified and detected.

Abstract: Aspects of the present disclosure involve systems and methods for improving the performance of a telecommunications network by monitoring the performance of one or more storage drives. Operational data is received from a plurality of storage drives of a storage server of a telecommunications network. A plurality of operational coefficients for each of the plurality of storage drives is derived based on the operational data, and a cluster plot is created from the plurality of operational coefficients for each of the plurality of storage drives. A distance is calculated between a subset of operational coefficients of the plurality of operational coefficients of the cluster plot, and a remedial action is initiated on a storage drive of the plurality of storage drives when a calculated distance of an operational coefficient associated with the storage drive exceeds a distance value from a cluster of the cluster plot.

Abstract: A request to validate a project object model (POM) is received from a client device. The POM references one or more modules, each of which is associated with one or more artifacts. The artifacts associated with a module are downloaded to a staging repository along with checksums of the artifacts. The downloaded checksum is compared to a checksum calculated on the staging repository. Upon determining that the downloaded checksum matches the calculated checksum for all artifacts of all modules, the POM is moved to the staging repository.

Abstract: An error correction code circuit includes a first error correction code circuit configured to generate correction data and a first correction check bit according to received source data and a source check bit corresponding to the received source data, a second error correction code circuit connected to the first error correction code circuit, and configured to, according to the correction data and at least one of the first correction check bit or the source check bit, determine whether the correction data is wrong and generate a second correction check bit, and a comparison circuit connected between the first error correction code circuit and the second error correction code circuit, and configured to compare the first correction check bit with the second correction check bit and determine whether the first correction check bit is wrong.

Abstract: A request to access data programmed to a memory sub-system is received. A determination is made of whether memory cells of the memory sub-system that store the programmed data satisfy one or more cell degradation criteria. In response to a determination that the memory cells satisfy the one or more cell degradation criteria, an error correction operation to access the data is performed in accordance with the request.

Abstract: An exemplary method for reading data stored in a flash memory includes: selecting an initial gate voltage combination from a plurality of predetermined gate voltage combination options; controlling a plurality of memory units in the flash memory according to the initial gate voltage combination, and reading a plurality of bit sequences; performing a codeword error correction upon the plurality of bit sequences, and determining if the codeword error correction successful; if the codeword error correction is not successful, determining an electric charge distribution parameter; determining a target gate voltage combination corresponding to the electric charge distribution parameter by using a look-up table; and controlling the plurality of memory units to read a plurality of updated bit sequences according to the target gate voltage combination.

Abstract: A memory component internally generates and stores the check bits of error detect and correct code (EDC). In a first mode, during a read transaction, the check bits are sent to the memory controller along with the data on the data mask (DM) signal lines. In a second mode, an unmasked write transaction is defined where the check bits are sent to the memory component on the data mask signal lines. In a third mode, a masked write transaction is defined where at least a portion of the check bits are sent from the memory controller on the data signal lines coincident with an asserted data mask signal line. By sending the check bits along with the data, the EDC code can be used to detect and correct errors that occur between the memory component and the memory controller.

Abstract: The present disclosure relates to utilizing a storage system that improves memory storage and access by utilizing a distributed erasure coding RAID. For example, the storage system stores a mapping table within volatile memory of one or more SSDs on a set of RAID SSDs. In particular, a mapping table stored in one SSD in the SSD set includes mapping information corresponding to data stored in another SSD in the SSD set. In this manner, the storage system can significantly reduce the number of operations needed to write new data to the set of SSDs from previous methods that required multiple reads and multiple writes.

Abstract: Methods, systems, and devices for hardware reset management for universal flash storage (UFS) are described. A UFS device may initiate a boot-up procedure that includes multiple phases. The UFS device may perform a first reset operation to reset one or more circuits based on receiving a first reset command during a first phase. The UFS device perform a second phase and may initiate a portion of a second reset operation to reset the one or more circuits during the second phase based on a likelihood that a second reset command is to be received. The UFS device may receive the second reset command during the second phase after initiating the portion of the second reset operation. The UFS device may initiate a second portion of the second reset operation based on receiving the second reset command and initiating the portion of the second reset operation.

Abstract: A data center for data backup and replication, including a pool of multiple storage units for storing a journal of I/O write commands issued at respective times, wherein the journal spans a history window of a pre-specified time length, and a journal manager for dynamically allocating more storage units for storing the journal as the journal size increases, and for dynamically releasing storage units as the journal size decreases.

Abstract: Embodiments of a targeted deduplication process that splits protected data into variable size segments, generates a fingerprint for each segment, and then combines fingerprints into groups to form group fingerprints. An embodiment auto-generates and persists the group fingerprints for the backups which are already on the storage server, thus enabling the backup client to fetch these fingerprints using an identifier and enforce synthesis for the new backup or replication copy against any previously written backup. For this embodiment, group fingerprints are generated on the storage server itself, rather than being generated on and pushed from the backup client for mere storage on the storage server, so that, as files are ingested, the storage server also auto-generates group fingerprints on its own.

Abstract: A backup system stores recipes during backup file creation when virtual synthetic backups are used, where a recipe comprises a specific sequence of steps used to generate the backup file. Replication logic of the backup system replays the recipe to generate the same backup file on the backup target so that an old backup combined with new backup data comprises the recipe. Embodiments of a server-side group fingerprint system include a process to auto-generate recipes for server resident files by formulating a file as a series of L1 fingerprints which are in turn a set of L0s and GFPs where some of the L1s are shared with other files. The recipe can be used to convert the representation of the file from a native fingerprint based representation into a virtual synthetic format.

Abstract: Embodiments automate the timely remediation of issues by matching failed operations to a script that is configured to fix the problem or problems without causing additional side effects, thus minimizing unavailability of services/data and loss of data. A method detects a backup operation alert message sent from a data manager or storage system that encodes one or more attributes affected by the backup operation. A script library is scanned to identify scripts that match the alert message. A component generates a score for each script, where the score factors the relevance of the script to the backup operation, and executes the script with the highest score, as the script most likely to remediate the issue causing the alert message.

Abstract: Embodiments automate the timely remediation of issues by matching failed operations to a script or set of scripts that is configured to fix the problem. A method detects a backup operation alert message sent from a data manager or storage system that encodes one or more attributes affected by the backup operation, wherein the attributes are weighted to reflect a percentage importance of the a corresponding script to fix the problem. A script library is scanned to identify scripts that match the alert message. A component generates a score for each script, where the score factors the relevance of the script to the backup operation based on the weighted attributes. Scores for each single script each possible combination of multiple scripts are computed and compared, and the script or script combination with the highest score is executed by the self-healing process.

Abstract: Making inline deduplicated backups of protected data using group fingerprints resident in a storage server by generating group fingerprints on a storage server for a backup client that is not capable of using group fingerprints, from individual fingerprints generated for each segment of protected data divided into variable size segments and then grouped together. Each fingerprint comprises a signature for a respective data segment. The method further maintains the group fingerprints for files resident on the storage server, compares, in the storage server, respective group fingerprints for these files with a new backup file to be backed up from the backup client to determine duplicated data between these files, and converts the new backup file to a virtual synthetic backup during a backup time of the new file.

Abstract: A computer system includes memory hardware configured to store software application files and computer-executable instructions executed by processor hardware. The instructions include determining memory space required for reinstallation of an archived target software application into a directory and preserving the memory space by creating a storage space preservation file in the directory based on the determined memory space. The storage space preservation file is unusable as the archived target software application. The instructions include detecting an execution call to a first replacement executable file and, in response to detecting the execution call, restoring files of the archived target software application to the directory and forwarding the execution call to a first executable file of the archived target software application in the directory.

Abstract: A storage manager for an information management system determines whether one or more predetermined conditions have been met for transferring metadata of previously performed backup jobs stored in a first management database. A backup job may correspond to a backup operation of a primary storage device of a first client computing device. In response to a determination that one or more of the predetermined conditions have been met, the storage manager may transfer metadata for a second plurality of backup jobs to a second management database of a recovery manager. The recovery manager may receive a request to restore data to the primary storage device of the first client computing device based on the metadata of the second plurality of backup jobs. A media agent managed by the recovery manager may then restore the requested data to the primary storage device of the first client computing device.

Abstract: The present inventors devised a holistic approach for protecting serverless applications in single-cloud, multi-zone, multi-cloud, and/or non-cloud data center computing environments. An illustrative data storage management system discovers application assets, relationships, and interoperability dependencies and creates an “application entity” that references the various assets. Protection preferences apply to the application entity as a whole. An orchestration function in the system coordinates storage management operations (e.g., backup, replication, live synchronization, etc.) in a suitable order of operations gleaned from asset dependencies, if any. A set of copies of the application's discovered assets are generated in coordinated fashion and represent a point-in-time copy of the application. The point-in-time copy can be restored and/or migrated to other computing services by the data storage management system.

Abstract: Embodiments automate the timely remediation of issues by matching failed operations to a script that is configured to fix the problem or problems without causing additional side effects, thus minimizing unavailability of services and loss of data. A method detects a backup operation alert message sent from a data manager or storage system that encodes one or more attributes affected by the backup operation, wherein the attributes are weighted to reflect a percentage importance of the a corresponding script to fix the problem. A script library is scanned to identify scripts that match the alert message. A component generates a score for each script, where the score factors the relevance of the script to the backup operation based on the weighted attributes, and executes the script with the highest score, as the script most likely to fix the issue causing the alert message.

Abstract: A recovery orchestration pipeline has stages configured to control efficient failover and recovery of applications in a multi-site disaster recovery (DR) environment. The applications run on user virtual machines (UVMs) at a primary site of the DR environment and connect to block storage devices (BSDs) that export virtual disks over a storage protocol to consume data including a recovery plan for disaster recovery. The recovery plan includes a recovery configuration whose generation is triggered by a user via a graphical user interface (GUI) and specifies resource requirements needed to recover the applications at a secondary site in the event of a disaster. The orchestration pipeline is initiated via single click of the GUI and completion of the stages of the pipeline is displayed as progress via the GUI to allow recovery of the applications without user intervention.

Abstract: A management server stops a sub-server in advance and prepares a sub-storage that operates in response to a request from the sub-server at the time of transition at which a business process of using data stored in a regular storage is performed in the sub-server. The management server recovers data using recovery data stored in an object storage and stores the data in the sub-storage and starts the sub-server.

Abstract: An inference service management method, apparatus, and system for an inference platform, and a medium, the method comprising: detecting whether there is inference service corresponding to the inference service record in a server according to an inference service record in a database (S110); and if not, then restoring the corresponding inference service according to the inference service record (S120). According to the method, an inference service in a server is detected according to an inference service record in a database to determine whether there is inference service corresponding to the inference service record in the server, if not, it means that the inference service record is inconsistent with a real inference service, and then corresponding inference service may be restored according to the inference service record.

Abstract: A method of database recovery includes starting a first database server, starting a second database server, starting a third database server, and starting an application server after starting the first database server, the second database server, and the third. The first, second, and third database servers are configured to store data according to first, second, and third database management systems, respectively, and the application server is configured to run application modules of a set of application modules. The method of database recovery further includes starting a search module, starting a product catalog management module, starting a web connectivity module after starting the search module, starting a graphical user interface module after starting the web connectivity module, and starting at least one business operations module.

Abstract: An intermittent network connection between a source system and a destination system is established by establishing a first connection from a management resource to a first port of the destination system, causing a second port of the destination system to be enabled including by providing an instruction via the first connection to the first port of the destination system, establishing a second connection from the management resource to a first port of a source system, causing a second port of the source system to be enabled including by providing an instruction via the second connection to the first port of the source system, registering the destination system with the source system, and causing a third connection to be established between the second port of the source system and the second port of the destination system for transferring data from the source system to the destination system.

Abstract: Embodiments of the present disclosure are directed to dynamic shadow operations configured to dynamically shadow data-plane resources in a network device. In some embodiments, the dynamic resource shadow operations are used to locally maintain a shadow copy of data plane resources to avoid having to read them through a bus interconnect. In other embodiments, the dynamic shadow framework is used to provide memory protection for hardware resources against SEU failures. The dynamic shadow framework may operate in conjunction with adaptive memory scrubbing operations. In other embodiments, the dynamic shadow infrastructure is used to facilitate fast boot-up and fast upgrade operations.

Abstract: Contents of a full snapshot for storage in one or more cloud storage volumes are received. The contents of the full snapshot is stored in the one or more cloud storage volumes. A snapshot of a virtual machine data volume and a snapshot of a virtual machine boot volume are generated based on the contents of the full snapshot stored in the one or more cloud storage volumes. An image of the virtual machine boot volume is generated based on the snapshot of the virtual machine boot volume. The snapshot of the virtual machine data volume, the snapshot of the virtual machine boot volume, and the image of the virtual machine boot volume are stored in a cloud object storage.

Abstract: A graphics processing system includes a plurality of processing units, wherein the graphics processing system is configured to process a task first and second times at the plurality of processing units. Data identifying which processing unit of the plurality of processing units the task has been allocated to is consulted on allocating the task to a processing unit for processing for a second time, and, in response, the task is allocated for processing for the second time to any processing unit of the plurality of processing units other than the processing unit to which the task was allocated for processing for a first time.

Abstract: Multi-site distributed storage systems and computer-implemented methods are described for improving a resumption time of input/output (I/O) operations during an automatic unplanned failover (AUFO). A computer-implemented method includes determining, with a second storage cluster, whether heartbeat information from one or more storage objects of a CG of a first set of CGs is received during a time period, determining an out of sync state for a data replication relationship between the CG of the first set of CGs and a mirrored CG of a second set of CGs when the heartbeat information is not received during the time period and sending a single bulk role change call with a cluster identifier from the second cluster to an external mediator to provide a role change from follower to leader in the second set of CGs.

Abstract: Multi-site distributed storage systems and computer-implemented methods are described for improving a resumption time of input/output (I/O) operations during an automatic unplanned failover (AUFO). A computer-implemented method includes monitoring, with a second cluster, heartbeat information received at ultra-short time intervals from a first connection of one or more storage objects of the first cluster, determining, with the second cluster, whether the heartbeat information from the first connection is received during an ultra-short time interval, and intelligently routing heartbeat information from the one or more storage objects of the first cluster from the first connection to a second connection when the heartbeat information from the first connection is not received during the ultra-short time interval.