Abstract: A system and method for triggering a recovery action during a component disruption in a production environment includes receiving data inputs from a plurality of components comprising the production environment, detecting an abnormality associated with a component of the plurality of components by analyzing the data inputs, and in response to the detecting the abnormality, triggering an analysis of the abnormality, analyzing the abnormality using a plurality of artificial intelligence engines to determine a plurality of outcomes from each artificial engine, consolidating the plurality of outcomes into a single outcome, the single outcome being input into an annotator engine to determine the recovery action to take during the component disruption in the production environment, and implementing the recovery action specific to the component with the detected abnormality.

Abstract: Techniques detect incomplete write of data. The techniques involve obtaining metadata associated with a sector in a parity disk of a Redundancy Array of Independent Disks (RAID), wherein the metadata includes a sequence stamp and a partial write flag, the sequence stamp changing with a write operation on a stripe to which the sector belongs, and the partial write flag indicating whether the stripe is partially written. The techniques further involve determining whether incomplete write of data is present in the RAID based on the metadata, and the techniques further involve in response to determining the incomplete write of the data being present in the RAID, rebuilding at least one disk in the RAID. By adding a sequence stamp and a partial write flag in the metadata of the sector of the RAID, incomplete write of data can be detected more accurately, thereby improving the reliability of RAID.

Abstract: A system includes a host processor, a volatile memory device coupled to the host processor, and at least a first persistent memory device coupled to the host processor. The host processor is configured to execute one or more applications. The volatile memory device and the first persistent memory device are in respective distinct fault domains of the system, and at least one of a plurality of data objects generated by a given one of the applications is accessible from multiple distinct storage locations in respective ones of the distinct fault domains. For example, the host processor and the volatile memory device may be in a first one of the distinct fault domains and the first persistent memory device may be in a second one of the distinct fault domains. The data object remains accessible in one of the fault domains responsive to a failure in another of the fault domains.

Abstract: A method may include receiving a request for an output decision corresponding to a set of input parameters, the request including a test indication. The method also includes determining that the output decision is dependent on an output of a first module that is configured by default to communicate with a second module, the output of the first module being dependent on the output of the second module. Further, the method includes based on the test indication, causing the first module to transmit an information request to a simulation module, the simulation module identifying a predetermined output value corresponding to the first module in response to the information request. The method also includes generating the output decision according to a decisioning rule that is triggered based on the predetermined output value and transmitting the output decision to a testing module.

Abstract: A control device including a failure diagnosis unit configured to identify a phenomenon that is a cause of the detected error, wherein the failure diagnosis unit is configured to: calculate a diagnosable time available to be spent on the identification of the phenomenon that is the cause of the error; and identify, for each detected error, a phenomenon that is the cause of the error based on a posterior probability, which is calculated for each phenomenon that is likely to be the cause of the error as a probability of occurrence of the phenomenon, on a diagnosis time, which is obtained for each phenomenon as a period of time required to identify the phenomenon as the cause of the error, and on the diagnosable time.

Abstract: Disclosed herein are methods and systems enabling automatic powering on and off of a computer of a user when the user is within a predetermined range from the computer. When there is a startup error detected during the remote powering on process of the computer, an alert is generated and automatically transmitted to an analyst computer to resolve the startup error. The disclosed systems and methods save a lot of time for the user each day as the user does not have to wait for execution of computer startup processes and the computer is ready to use when the user arrives at a location of their computer.

Abstract: In an aspect of the disclosure, a method, a computer-readable medium, and a computer system are provided. The computer system includes an initialization component of a host. The initialization component obtains health data indicating that at least one hardware component of the host is in one of one or more predetermined health conditions when executed in a system management mode of the host. The initialization component then sends, to a service processor of the host, a message in accordance with a management protocol. The message includes the health data.

Abstract: A method of protecting against two or more board failures at the same time by providing an elastic consistency platform (ECP) of high availability (HA) in multiple board environments is described. The ECP is provided between transmission control protocol (TCP) and an application using TCP on each board, including providing input and output buffers to store data between a producer and a consumer. The ECP is used to generate a warning when an amount of data unsynchronized in an output buffer of the ECP on any board reaches a programmable limit.

Abstract: A system includes a plurality of solid-state storage devices and a storage controller coupled to the plurality of solid-state storage devices. The storage controller includes a processing device, the processing device to receive a write request from a host computing device. The write request includes data to be stored at one or more of the plurality of solid-state storage devices. The processing device is to send an acknowledgement to the host computing device in response to receipt of the write request, store the data at the one or more of the plurality of solid-state storage devices, determine whether the data stored at the one or more of the plurality of solid-state storage devices is readable, and in response to determining that the data is readable, notify, by the processing device, the host computing device that the stored data is readable from the one or more of the plurality of solid-state storage devices.

Abstract: A method to resolve or prevent a computer system failure is provided. The method may include capturing a plurality of snapshots associated with a computer system installation environment during a plurality of key times. The method may also include measuring each snapshot within the captured plurality of snapshots according to a measure of system health. The method may further include using each measured snapshot to develop a plurality of learned patterns of good and bad software installations. The method may additionally include providing a probability associated with a proposed installation operation based on the developed plurality of learned patterns of good and bad software installations. The method may also include providing at least one installation recommendation in response to a recovery from a system failure, whereby the provided at least one installation recommendation is based on the developed plurality of learned patterns of good and bad software installations.

Abstract: One embodiment provides a method comprising receiving metadata comprising univariate time series data for each variable of a multivariate time series. The method comprises, for each variable of the multivariate time series, applying a hybrid and hierarchical model selection process to select an anomaly detection model suitable for the variable based on corresponding univariate time series data for the variable and covariations and interactions between the variable and at least one other variable of the multivariate time series, and detecting an anomaly on the variable utilizing the anomaly detection model selected for the variable. Based on each anomaly detection model selected for each variable of the multivariate time series, the method further comprises performing ensemble learning to determine whether the multivariate time series is anomalous at a particular time point.

Abstract: A controller at a source site generates a set of tasks associated with a replication job. Each task includes one or more of copying an object from the source to destination site, or deleting an object from the destination site. The tasks are placed onto a message queue at the source site. Source worker nodes at the source site retrieve the tasks from the source site message queue for processing in conjunction with destination worker nodes at the destination site. A destination worker node, upon receiving a task from a source worker nodes, places the task onto a message queue at the destination site for retrieval by a backend worker node that handles writing to an object store at the destination site.

Abstract: Automatically managing an entire life-cycle of a practice failover. The system uses a virtualization management system that hosts one or more business applications which has capability and authority to manage both the application hosting infrastructure as well as the storage infrastructure that is used by the applications in a disaster recovery configuration. The set of applications is replicated along with an application platform together with the applications.

Abstract: A compliance user or auditor is enabled to inject failures into a sandbox environment, which may be similar to a production service. The sandbox environment may be monitored by the same automation that watches compliance controls in the production service. As the user injects compliance failures into the sandbox, they may detect the appropriate alerts fire in the monitoring system, thereby gaining trust that the monitoring works as it should. A rich report resulting from the test activities may allow the user or auditor to see how a failure of a compliance control leads to the expected monitoring alert.

Abstract: An information handling system includes a host processing system and a baseboard management controller (BMC). The host processing system includes a main processor that instantiates a management controller agent, and a general-purpose processing unit (GPU). The BMC is coupled to the host processing system and to the GPU. The BMC is configured to direct the management controller agent to retrieve first management information from the GPU, receive the first management information from the management controller agent, retrieve second management information from the GPU, and provide a health indication for the GPU based upon the first management information and the second management information.

Abstract: An apparatus of a System on Chip (SoC) to implement a one out of two diagnostics (1oo2D) safety system comprises a memory comprising firmware to provide monitoring of the SoC and a second SoC, and a communication interface to provide cross-monitoring between the SoC and the second SoC. The firmware and the communication interface enable the SoC and the second SoC to implement the 1oo2D safety system without significant hardware or software external to the SoC.

Abstract: A separate family space is provisioned as a separate fault domain for each production device in a storage system. The space provisioned for each family has contiguous logical block addresses that do not overlap with the address space of any other family. Snaps and clones in a first family space are used for fault recovery without interrupting IOs to a second family space. If the first family space points to the same virtual block as other families as a result of deduplication then the virtual block is un-deduped. For example, another instance of the virtual block may be created and pointers updated such that only the first family space points to one of the virtual block instances.

Abstract: A method for diagnosing a root cause of failure using automated test equipment is disclosed. The method comprises monitoring data traffic associated with testing a device under test (DUT) in the automated test equipment using a plurality capture modules, wherein the plurality of capture modules are programmed onto a programmable logic device, wherein the programmable logic device is controlled by a system controller and is operable to generate commands and data to test the DUT, wherein the plurality of capture modules are operable to selectively capture the data traffic to be monitored, and wherein the data traffic monitored comprises a flow of traffic between the DUT and the system controller. The method further comprises saving results associated with the monitoring in respective memories associated with each of the plurality of capture modules. Further, the method comprises transmitting the results upon request to an application program executing on the system controller.

Abstract: A computing device is provided including a motherboard including a control module, a first trusted platform module (TPM), and a second TPM. The control module directs security operations to the first TPM, wherein the control module is operable to detect whether or not the first TPM is damaged, and wherein the control module, in response to detecting that the first TPM is damaged, is operable to direct subsequent security operations to be performed by the second TPM. A computer program product is also provided including non-transitory computer readable storage media embodying program instructions executable by a processor to direct security operations to a first TPM coupled to a motherboard of the computing device, detect whether or not the first TPM is damaged, and, responsive to detecting that the first TPM is damaged, direct subsequent security operations to a second TPM coupled to the motherboard of the computing device.

Abstract: Systems and methods presented herein provide for failure detection and data recovery in a storage system. In one embodiment, a method operable in a storage system comprises locating failures in data blocks in storage area of a storage device, categorizing the failures into block groups, each block group comprising one or more data blocks having failures, and halting input/output (I/O) operations to data blocks in a first of the block groups due to the failures of the first block group. The method also includes detecting additional failures in one or more data blocks of other block groups remaining in the storage area, and determining when to fail the storage area of the storage device based on the detected failures.