Abstract: Techniques for selecting an anomaly based on a context are disclosed. A set of metrics corresponding to communications with nodes of a computer system are identified. A set of insights are generated based on the set of metrics. A context for determining a primary anomaly is determined. A subset of metrics associated with the context are identified. A subset of insights that are generated based on the subset of metrics are identified. An insight is selected from the subset of insights as the primary anomaly. A visualization associated with the primary anomaly is presented at a user interface. One or more secondary anomalies may be concurrently presented with the visualization. Additionally, the primary anomaly, the selected visualization, and/or the secondary anomaly is used to determine a new context for selecting another primary anomaly. Hence, a series of primary anomalies may be selected, each primary anomaly being related to each other.

Abstract: Embodiments of the present disclosure relate to a fault tolerant root cause analysis (RCA) system that is able to handle calculation failures during runtime. Calculations (e.g., evaluation of a diagnostic model for a specific component or device) that are performed during the RCA are integrated using different resources of the system under analysis. In order to make a final diagnosis, the resources exchange messages containing calculation inputs and outputs. Calculation problems due to calculation failures in a particular resource can be resolved efficiently which reduces resource utilization and minimizes failure propagation to other parts of the system. Accordingly, the system is able to recover and output a diagnosis even if some of the resources fail or generate problems.

Abstract: A method and apparatus for providing environmental management in a monitored facility. In one embodiment, the method comprises obtaining at least one mathematical expression representing the behavior of at least one piece of equipment in a monitored equipment housing facility; and generating, for the at least one piece of equipment and using the at least one mathematical expression, a predicted impact of an operational state of the at least one piece of equipment.

Abstract: A data collection apparatus includes a data collection section configured to receive sequential time-series output data pieces for each of data sources, a data shaping section configured to perform data shaping processing on the sequential time-series output data pieces based on a predetermined data shaping rule set for each of the data sources such that the resulting data pieces are reduced in number or in data amount as compared with the output data pieces output from the data source, a data transmission section configured to transmit the output data pieces to the monitor control apparatus, and a data shaping rule control section configured to receive the data shaping rule set for each of the data sources from the monitor control apparatus and to set the received data shaping rule in the data shaping section.

Abstract: Embodiments are directed to monitoring network traffic in a network. A network monitoring engine may be employed to monitor the network to provide metric profiles based on a plurality of characteristics associated with one or more network flows. The network monitoring engine may provide profile objects based on the metric profiles. The network monitoring engine may provide the profile objects to a classifier engine. The classifier engine provide trained activity models selected from a plurality of trained activity models that may be based on a ranked ordering of characteristics of the trained activity models and the profile objects. The classifier engine may provide classification results for the profile objects based on the trained activity models. And, the network monitoring engine may execute policies based on the classification results associated with the profile objects.

Abstract: A device may receive error data indicating that an error occurred, the error being associated with a data processing job scheduled to be performed by a data processing platform. The device may identify input data for the data processing job associated with the error and determine that the error is based on the data processing platform not receiving the input data. In addition, the device may determine a location of the input data and determine a measure of priority associated with the data processing job. Based on the location of the input data and the measure of priority, the device may perform an action to correct the error.

Abstract: In accordance with embodiments of the present disclosure, an information handling system may include a processor and an air mover control system for controlling at least one air mover configured to drive airflow to one or more components of the information handling system. The air mover control system may be configured to read from an information handling resource of the information handling system, wherein the information handling resource comprises an active cooling system, a fault condition cooling requirement defining a minimum airflow required by the information handling resource from the at least one air mover in presence of a fault condition of the active cooling system. The air mover control system may also be configured to read from the information handling resource a variable indicating whether the fault condition of the active cooling system exists.

Abstract: A fault processing method, a related apparatus, and a computer. When it is determined that a computer crashes, a baseboard management controller in the computer can send a read request message to a processor in the computer, where the read request message is used for requesting reading of first error data recorded by the processor, receive a read response message returned by the processor, and obtain, according to the read response message, the first error data recorded by the processor. By means of the embodiments of the present invention, an operating system does not need to be used, acquisition of error data in a computer after the computer crashes is implemented using a baseboard management controller, and a problem in the prior art that error data in a computer cannot be acquired after a severe uncorrectable error occurring in the computer causes a system crash is resolved.

Abstract: Described are techniques for processing event occurrence. A first notification may be received regarding a first occurrence of a first event. Responsive to receiving the first notification, first processing may be performed that includes mapping the first event to a first profile, and performing second processing using the first profile to collect first data regarding the first occurrence of the first event.

Abstract: The present disclosure provides a method and apparatus for a redundant array of independent disks, RAID. The method includes: dividing the RAID into a plurality of sub-RAIDs; generating sub-RAID metadata corresponding to each of the sub-RAIDs; and in response to a disk in the RAID being replaced, rebuilding data in a corresponding sub-RAID based on the sub-RAID metadata. The present disclosure further provides a computer readable storage medium and a storage system.

Abstract: System management services can discover the addition of new physical devices, take automated actions to provision software (operating system and other related cloud services software components) on them, and scale out management infrastructure based on the new capacity of the total resources (including the newly added resources). A configuration file can contain the rules for automatic expansion and contraction of the system.

Abstract: A computing platform may receive a primary model corresponding to one or more features of an application. The computing platform may populate, using a processing engine and based on the primary model, a secondary model indicating an object definition corresponding to the one or more features. The computing platform may generate, using a pre-deployment engine and based on the primary model, a script corresponding to the one or more features. The computing platform may generate one or more commands directing a production server to execute, in a production environment, the script corresponding to the one or more features. The computing platform may transmit, to the production server and via the communication interface, the one or more commands directing the production server to execute the script. The computing platform may receive, based on the one or more commands, an error corresponding to the one or more features.

Abstract: A zero downtime upgrade procedure is initiated that upgrades a first version of software executing on a source system comprising at least one source server to a second version of software executing on a target system comprising at least one target server. The source system initially starts operating in a read-write mode. Thereafter, concurrent with the operation of the source system, operation of the target system is initiated in a read-only mode. Operations of the source system are then ceased by ramping down activities of the source system. Upon cessation of operation of the source system, operation of the target system is initiated in a read-write mode.

Abstract: A method of upgrading a version of a program of the present disclosure executes version upgrade of the program of a plurality of component mounting facilities sequentially from a first component mounting facility of the plurality of component mounting facilities to the plurality of component mounting facilities on a downstream side in a component mounting line in which the plurality of component mounting facilities are connected to each other. The first component mounting facility completes mounting of a board under production at the time of receiving an instruction for executing version upgrade and executes the version upgrade after carrying-out of the board to an adjacent component mounting facility is completed among the plurality of component mounting facilities on the downstream side.

Abstract: Techniques for running diagnostic rules across multiple nodes are disclosed. A root cause of an error occurring on a particular node is determined. A root cause of an error on the particular node is identified based on a metric corresponding to another node and/or based on a previously-reported error on another node. Additionally or alternatively, an error is predicted to occur on a particular node. The error is predicted based on a trend associated with a metric corresponding to another node.

Abstract: There is provided a distributed object storage system that includes several performance optimizations with respect to efficiently storing data objects when coping with a desired concurrent failure tolerance of concurrent failures of storage elements which is greater than two and with respect to optimizing encoding/decoding overhead and the number of input and output operations at the level of the storage elements.

Abstract: For each event detected during execution of a monitored application comprising a plurality of application components, a determination is made of which of the plurality of application components corresponds to the detected event. Also, a dependency subgroup that includes the application component that corresponds to the detected event is identified, wherein a dependency subgroup indicates dependencies among a subgroup of the plurality of application components. A location within the dependency subgroup of the application component corresponding to the detected event is determined. An order of correction for the application components determined to correspond to detected events are determined based, at least in part, on the determined location. Correction of the application components determined to correspond to detected events are initiated according to the determined order of correction.

Abstract: Provided are a computer program product, system, and method for processing a health condition message on a health condition to determine whether to perform a swap operation. A health condition message is received from a first server indicating an estimated Input/Output (I/O) delay to access a first storage resulting from a health condition experienced at the first server. A determination is made as to whether the estimated I/O delay exceeds a threshold response time for the first storage. A swap operation is performed to redirect I/O requests to data from the first server to the second server to access the data at the second storage in response to determining that the estimated I/O delay exceeds the threshold response time.

Abstract: In an electronic component mounting system, when a change in a recipe (setting data) for a control computer are input in any one of a plurality of circuit board working machines, such as component mounting machines, the control computer reports changed content to a host computer. The host computer, which receives the report, updates the data, which is stored in the DB server, based on the changed content of the recipe. The control computer, which receives input of the change in the recipe, executes a process in which only the partial data, which is updated by the host computer, is acquired among the data items, which are stored in the DB server.

Abstract: A flash memory device includes an array of non-volatile memory (NVM) cells, at least one detection NVM cell, and a sensing circuit. The array of NVM cells are configured to store data. The sensing circuit is coupled to the at least one detection NVM cell and is configured to measure a charge on the at least one detection NVM cell. The sensing circuit is also configured to compare the measured charge with a threshold charge level and to trigger a refresh of the array of NVM cells in response to the measured charge being less than the threshold charge level.

Abstract: In an approach for identifying an incident requiring action, a processor receives a plurality of notifications from a plurality of sensors, wherein each notification is related to a problem identified by a sensor of the plurality of sensors. A processor determines an event type corresponding to each of the plurality of notifications based on a type of sensor from which a respective notification originates. A processor creates a group of notifications based on a location from which each respective notification originated and a time period during which each respective notification originated. A processor calculates a weight for each notification of the group based on the corresponding event type, wherein the weight indicates a likelihood to cause other notifications. A processor issues an incident report that includes a maintenance ticket, wherein the maintenance ticket identifies a notification within the group of a higher weight than other notifications of the group.

Abstract: Methods and systems for inferring call stacks in a program, such as a video game or simulation program, are described herein. The call stack data can be inferred using a database of previously captured call stacks along with a minimal set of identifiers that fingerprint each call stack. If just the minimal fingerprint can be captured during a subsequent profile, then the corresponding call stack can be inferred.

Abstract: An electronic device including a memory storing an application program that provides a guide about a user action, collects information on a performance of the user action, or collects information on a user state. A processor connected to the memory is configured to execute the application program, to detect a cause by which the application program is stopped, and to automatically reexecute the application program or to provide a user interface for receiving a user input for the reexecution of the application program on the basis of at least a portion of the detected cause.

Abstract: Systems and methods are disclosed for a server learning new words generated by user client devices in a crowdsourced manner while maintaining local differential privacy of client devices. A client device can determine that a word typed on the client device is a new word that is not contained in a dictionary or asset catalog on the client device. New words can be grouped in classifications such as entertainment, health, finance, etc. A differential privacy system on the client device can comprise a privacy budget for each classification of new words. If there is privacy budget available for the classification, then one or more new terms in a classification can be sent to new term learning server, and the privacy budget for the classification reduced. The privacy budget can be periodically replenished.

Abstract: A module health system includes a module health circuit comprising a hardware register that is set to a first value in response to the system starting, an application register that is set to the first value in response to the system starting and a watchdog timer register that is set to the first value in response to the system starting. The system further includes a power on self-test that determines whether the system has passed a plurality of tests and that selectively sets the hardware register to a second value based on the determination, an external software application that determines whether a safety critical system is healthy and selectively sets the application register based on the determination, a watchdog timer application that selectively sets the watchdog timer register, a central processing unit that determines whether to de-assert a module health signal.

Abstract: Systems and methods for generating a graphical display region including a synchronized display of alert data and impact data indicative of conditions of a computing infrastructure are herein disclosed as comprising, in an implementation, identifying alerts, each alert having a timestamp indicative of a first time at which it was identified, performing an impact calculation to generate the impact data based on alerts valid as of a second time proximate to an impact calculation start time, and generating a graphical display region including impact data valid as of a display time and alert data indicative of the alerts valid as of the second time.

Abstract: Embodiments are directed to monitoring network traffic in a network. A network monitoring engine may be employed to monitor the network to provide metric profiles based on a plurality of characteristics associated with one or more network flows. The network monitoring engine may provide profile objects based on the metric profiles. The network monitoring engine may provide the profile objects to a classifier engine. The classifier engine provide trained activity models selected from a plurality of trained activity models that may be based on a ranked ordering of characteristics of the trained activity models and the profile objects. The classifier engine may provide classification results for the profile objects based on the trained activity models. And, the network monitoring engine may execute policies based on the classification results associated with the profile objects.

Abstract: Embodiments of the innovation relate to a host device having a memory and a processor, the host device configured to determine an anomaly associated with an attribute of a computer environment resource of the computer infrastructure. The host device is configured to correlate an object associated with the attribute of the detected anomaly with a related object of the computer infrastructure. The host device is configured to determine a root cause probability for each object of the correlated objects, the root cause probability identifying a probability of the correlated object functioning as a cause of the detected anomaly. The host device is configured to output an identification of a root object associated with the anomaly based upon the identified root cause probability.

Abstract: Automatically associating information technology resource patterns with specific information technology products by receiving a set of data about information technology assets, matching a subset of that data to a pattern in a set of patterns, determining that the subset of the data represents a product associated with that pattern, reporting this determination; receiving feedback on the accuracy of the determination, and updating pattern set information in response to that feedback.

Abstract: In accordance with an embodiment, described herein is a system and method for dynamic debugging in an application server environment. An exemplary method can provide, at one or more computers, including an application server environment executing thereon, a plurality of deployable resources which can be used within the application server environment, one or more running managed servers, the one or more managed servers being within a domain, and a debug framework, the debug framework comprising a debug patch directory, the debug patch directory containing one or more debug patches. The method can activate a selected debug patch within the domain, the selected debug patch comprising at least one class, the selected debug patch designed to gather information about the problem within the domain. The managed servers, upon activation of the selected debug patch, can remain running. The method can also deactivate the selected debug patch without requiring a restart.

Abstract: A method, executed by a computer, for allocating resources includes assigning resiliency attributes to a server having a workload, linking each server to a partner resource, duplicating the workload of each server in an offsite location accessible to the partner resource, detecting a disaster event, and transferring the workload of the server automatically to the partner resource. In some embodiments, the partner resource is a plurality of pool servers. The partner resource may be calculated by performing a capacity analysis. The partner resource may not a specifically assigned resource until a disaster occurs. In some embodiments, the workload is duplicated such that the recovery point objective of the workload is minimized. A computer program product and computer system corresponding to the methods are also disclosed herein.

Abstract: Systems and methods which implement one or more data organization techniques that facilitate efficient access to source data stored by a storage system are disclosed. Data organization techniques implemented according to embodiments are adapted to optimize (e.g., maximize) input/output efficiency and/or (e.g., minimize) storage overhead, while maintaining mean time to data loss, repair efficiency, and/or traffic efficiency. Data organization techniques as may be implemented by embodiments include blob based organization techniques, grouped symbols organization techniques, data ordering organization techniques, and combinations thereof.

Abstract: A communication apparatus for preventing the broadcasting of unauthorized messages on a broadcast bus network, the communication apparatus comprising: a first memory adapted to store first information; a second memory adapted to store second information; a monitoring unit adapted to: monitor the bus for processing messages being broadcasted on the bus, and output a third information and fourth information a comparing unit adapted to compare the first information with the third information and the second information with the fourth information; and, a message destroyer adapted to: when: the first information matches with the third information, and the second information does not match with the fourth information, causing the body of the current message to be altered while the current message is being broadcasted on the bus.

Abstract: For failure interval determination, a determination module determines a failure interval for transactions in a transaction queue based on a number of processed transactions. A transaction timeout module fails a first transaction in response to the first transaction not processing within the failure interval.

Abstract: An electronic device having a scratchpad memory and a management method are provided. A recording circuit records multiple counter values which correspond to entries in a Translation Lookaside Buffer (TLB). A virtual address is matched with a first entry. If a cache miss occurs, the recording circuit updates a first counter value corresponding to the first entry, and determines if the first counter value meets a threshold criterion. If the first counter value meets the threshold criterion, the recording circuit transmits an interrupts signal to a processing unit, and the processing unit moves data into the scratchpad memory. If the first counter value does not meet the threshold criterion, the data is moved into a cache.

Abstract: Website management services are disclosed. The services include presenting, by a website management host computer, a web page to a client device. The web page includes options that are configurable by a user of the client device for selecting a provider entity from a list of provider entities. The provider entities provide subscription-based technical services to subscribers. The subscription-based technical services include a links checker configured to verify operability of web page links for a website owned by the user of the client device and a monitor service configured to monitor performance characteristics of the website. The services include receiving, from the client device, a subscription-based technical service and a corresponding provider entity. The provider entities are third-party entities with respect to the website management host computer.

Abstract: Methods, systems, and computer storage media for implementing neural networks in fixed point arithmetic computing systems. In one aspect, a method includes the actions of receiving a request to process a neural network using a processing system that performs neural network computations using fixed point arithmetic; for each node of each layer of the neural network, determining a respective scaling value for the node from the respective set of floating point weight values for the node; and converting each floating point weight value of the node into a corresponding fixed point weight value using the respective scaling value for the node to generate a set of fixed point weight values for the node; and providing the sets of fixed point floating point weight values for the nodes to the processing system for use in processing inputs using the neural network.

Abstract: Methods and systems are disclosed related to dynamic load balancing in circuit simulation. In one embodiment, a computer implemented method of performing dynamic load balancing in simulating a circuit includes identifying a plurality of simulation tasks to be performed, determining estimated processing durations corresponding to performance of the plurality of simulation tasks, distributing the plurality of simulation tasks to a plurality of processors according to the estimated processing duration of each simulation task, and performing the plurality of simulation tasks at the plurality of processors in parallel.

Abstract: In a system in which a server and a client to which a device is connected communicate, the server can execute processes based on the result of checking device operation. The POS terminal of a network system has a device control function for controlling the device, and a diagnostic function for checking operation of the device. To check the operation of the device connected to the client, a maintenance server sends a control command instructing starting the diagnostic function to the POS terminal. The POS terminal stops the device control function if the device control function is executing, starts the diagnostic function, checks operation of the device with the diagnostic function, and returns the result of the checked operation to the maintenance server.

Abstract: A modularized architecture using vertical partitioning of a database is configured to store object metadata and processing results of one or more objects analyzed by a state machine, such as an analysis engine of a malware detection system. The database may include data structures, such as one or more master blocks, state sub-blocks, and state co-tables, as well as state transition queues. The modularized architecture may organize the database as one or more stages of the state machine, such that each stage corresponds to a module of the state machine, wherein the module generates results that are stored in its associated state co-table, which then provides information for a next stage. Each next stage may have a dependency on the one or more prior stages that provide input for execution of the next stage module.

Abstract: It is a challenge task to conduct Entropy computation on the attributes of packet header in high-speed networks. Motivated by Ashwin Lall et al., we present a stream-based scheme to estimate to the entropy norm based on Count Sketch algorithm. The system is implemented on a NetFPGA-10G platform. It is capable of processing IP packets and computing the entropy in 30 Gbps line rate.

Abstract: A computer implemented method, computer program product and system for data quality monitoring includes measuring a data quality of loaded data relative to a predefined data quality metric. The measuring the data quality includes identifying delta changes in at least one of the loaded data and the data quality rules relative to a previous measurement of the data quality of the loaded data. Logical calculus defined in the data quality rules is applied to the identified delta changes.

Abstract: Apparatus and methods for learning and implementing rules for remediating system errors are provided. The method may include identifying a configuration item that is not in compliance with a configuration baseline. The method may also include tracking a workflow executed by a remote user in an attempt to remediate the configuration error. The method may additionally include monitoring the status of the configuration item. In the event the workflow brings the configuration item in compliance with the configuration baseline, the method may further include storing the workflow in a database.

Abstract: Detection of defects in an online system includes, for example, receiving, by one or more processor, a plurality of search conditions regarding a search screen of the online system, generating, by the one or more processor, a plurality of test models having factors based on the plurality of search conditions and levels having one or more of the search conditions, generating, by the one or more processor, a plurality of test cases based on the generated plurality of test models having the factors based on the plurality of search conditions and the levels having one or more of the search conditions, and executing, by the one or more processor, the plurality of test cases on the online system to detect defects in the online system.

Abstract: To detect an abnormality in an interrupt control system without completely depending on dualization of a circuit, without the need to create a test pattern for a built-in self-test by spending time, and without considerably increasing an amount of power consumption. A test interrupt request is generated periodically using a timer or the like in an interrupt signal system from an interrupt controller to a central processing unit, the state of an interrupt request flag within the interrupt controller is checked in an interrupt processing routine, and in the case where it is detected that the same interrupt request flag is kept in a set state twice or more in succession, it is supposed that there is a high possibility that a failure has occurred in the interrupt signal system and it is considered that there is an abnormality.

Abstract: A system for identifying abnormal resource usage in a data center is provided. In some embodiments, the system employs a prediction model for each of a plurality of resources and an abnormal resource usage criterion. For each of a plurality of resources of the data center, the system retrieves current resource usage data for a current time and past resource usage data for that resource. The system then extracts features from the past resource usage data for that resource, predicts using the prediction model for that resource usage data for the current time based on the extracted features, and determines an error between the predicted resource usage data and the current resource usage data. After determining the error data for the resources, the system determines whether errors satisfy the abnormal resource usage criterion. If so, the system indicates that an abnormal resource usage has occurred.

Abstract: Implementations disclosed herein provide for a method comprising receiving a read request to read data from a target die of a storage device, and rebuilding the data stored on the target die using data stored on other dies of the storage device, if a current operation to the target die of the storage device prevents the servicing of the read request until completion of the current operation.

Abstract: A device may include countermeasure circuitry that provides a countermeasure check that protects device logic. The device may also include enforcement circuitry that non-deterministically enforces the countermeasure check on the device logic so that the device logic is not always protected by a countermeasure action within the countermeasure check. The device may non-deterministically enforce the countermeasure check according to an enforcement rate, and the device may adjust the enforcement rate depending on a priority of the device logic or device logic portion protected by a particular countermeasure check.

Abstract: A sequence of contiguous pages in an erase block in a non-volatile memory device is programmed and erased. Next, all of the pages in the erase block are programmed with data. Then, the data is read back and verified to determine whether there is an error in the data. When there is an error in the data, then the last page in the sequence is identified as being unstable. If there is no error in the data, then the last page in that sequence is identified as being stable. Thus, the recorded information identifies a point of instability in the erase block. Instabilities can be stabilized by performing additional writes to fill the partially filled word line.

Abstract: A technique of optimizing analytic flows includes sampling source data using a sampling method, executing a flow over the sampled data, obtaining runtime statistics from the executed flow, and combining runtime statistics with historical statistics.