Abstract: A method and an apparatus for determining a to-be-migrated task based on cache awareness in a computing system having multiple processor cores is disclosed. In the method, the computing system determines a source processor core and a destination processor core according to a load of each processor core. Through respectively monitoring the number of cache misses of each task and the number of executed instructions of each task in the source processor core and the destination processor core, the computing system obtain an average cache miss per kilo instructions of the source processor core and an average cache miss per kilo instructions of the destination processor core. Then, the computing system determines, according to the obtained average cache miss per kilo instructions of the source processor core and the destination processor core, a task to be migrated from the source processor core to the destination processor core.

Abstract: Embodiments relate to a heterogeneous core microarchitecture. An aspect includes binding, by an operating system that is executing on a processor comprising a core comprising a heterogeneous microarchitecture comprising two or more flows, a job that is being executed by the operating system to a flow of the two or more flows. Another aspect includes issuing an instruction corresponding to the job with a tag indicating the binding of the job to which the instruction corresponds. Yet another aspect includes executing the instruction by the flow in the core that is indicated by the tag.

Abstract: Providing unblocked read operations concurrent with write operations with respect to shared data resources in parallel processing systems. In an embodiment, for each data resource, a pair of fields and an index field is maintained. The index field indicates which of the two fields (e.g., first field) stores a current value for the data resource. However, when a new value is to be stored for the data resource, the value is first stored in the second field using a execution entity, while ensuring exclusive access for the execution entity to the second field. The index field is then updated to indicate that the second field stores the current value, such that the new value in the second field is thereafter available as the current value for read operations. All read operations by any corresponding concurrent execution entities, during the write operation, are continued unblocked.

Abstract: Provided is to a program conversion device which can use processor resources of a system to the utmost and enhance performance ability. The program conversion device includes: specific process determining unit which determines a range of a partial program to perform a specific process in a target program which includes a first execution scheme specifying program which can be executed in parallel with a first ratio of being a usage ratio of a first usage quantity with respect to a first resource of a first processor and a second usage quantity with respect to a second resource of a second processor; and process converting unit which converts the partial program into a second execution scheme specifying program which can be executed in parallel with a second ratio of being the usage ratio different from the first ratio.

Abstract: A technique includes writing a first count value associated with a first timestamp counter to a first memory local to the first timestamp counter. The technique includes writing a second count value associated with a second timestamp counter to a second memory local to the second timestamp counter. The timestamp counters are synchronized based at least in part on the first and second count values.

Abstract: A method, system, and computer program product for performing software upgrades. The method serves to preserve an inter-process connection between two endpoints during patching operations. The method commences by suspending at least some communication activity over the inter-process connection while preserving one or more functioning states of the inter-process connection. A patching facility produces a patched endpoint (e.g., a software component) by performing a patch operation to one of the endpoints of the inter-process connection while the at least some communication activity remains suspended. After patching, a process reconfigures at least some of the one or more preserved functioning states of the inter-process connection to connect to the patched endpoint. When the preserved functioning states of the inter-process connection have been restored, then communication activity resumes over the connection, using the patched endpoint.

Abstract: A method for interposing on operating system calls in a host is provided. The method includes patching an operating system kernel function, the patching comprising adding a first pointer that invokes an agent function, the patching performed by an agent. The method includes executing the agent function, responsive to a system call stub calling the operating system kernel function, which invokes the agent function via the first pointer, wherein at least one action of the method is performed by a processor of a host having an operating system.

Abstract: A system and method for messaging application content that includes providing an application content messaging application programming interface (API); receiving a content delivery request from an account, through the application content messaging API; retrieving device information of a destination endpoint specified in the content delivery request; based on the device information, selecting an application content format from a set of formats and obtaining application content in the application content format; and transmitting the application content.

Abstract: The disclosure generally describes computer-implemented methods, software, and systems, including a method for generating and storing adapter characterization information. Adapter-related information associated with an adapter is received. Communication patterns associated with the adapter are determined. Quality-of-service patterns are applied to the communication patterns. An adapter flow is configured for the adapter. A visualization of the adapter flow for the adapter is provided. Characterization information determined for the adapter is stored.

Abstract: Trusted Client-Centric Application Architecture (TC2A2) provides the ability to securely exchange data between applications. TC2A2 may be used to perform functions requiring data exchange between applications that typically may not be able to communicate with each other. TC2A2 uses a universal data set to exchange data. Application data from a source application is converted to a universal data set, and then converted to application data for one or more target applications. Application data is then propagated to respective native applications. TC2A2 provides the ability to update, modify, and manipulate data for a plurality of applications using a single user interface.

Abstract: A technique manages operation of a host computer having access to a storage volume on a storage system via two or more distinct paths. The technique involves operating a multipathing driver within the host computer, the multipathing driver controlling path access from the host computer to the storage volume. The technique further involves operating a host bus adaptor (HBA) driver within the host computer to interface the host computer to a fabric connecting the host computer to the storage system. The technique further involves conveying fabric topology state change event information from the HBA driver to the multipathing driver to enable the multipathing driver to take action in response to fabric topology state change events. In some arrangements, an event monitoring handler receives fabric event information from registered state change notifications (RSCNs) containing fabric event information from the HBA driver, and forwards that information on to the multipathing driver.

Abstract: An event processing method in a stream processing system includes matching a basic event with basic events stored in engine memories corresponding to each matching mode in a rule engine, to determine an engine memory including the basic event, and when it is determined that the engine memory including the basic event is an engine memory corresponding to a full-loop mode, inputting the basic event into the full-loop mode of the rule engine, adding a full-loop identifier to the basic event. This method implements classification processing on complex events by using different matching modes of the rule engine, improving performance of processing a complex event in an Event Stream Processing (ESP) service processing process.

Abstract: Predictive monitoring of objects in a distributed network system providing cloud services is disclosed. In one embodiment, the methods and systems observing one or more update messages sent and received among components of the distributed network system, the update messages comprising information associated with a state of an object on the distributed network system, determine the state of the object in response to the one or more update messages, and reference a predictive object state model to predict occurrence of an artifact in response to the state of the object. Advantageously, the present embodiments provide advanced warning of potential failures in a distributed network systems, which may enable a system administrator or dynamic process to resolve the failure before it ever occurs. Additional benefits and advantages of the present embodiments will become evident in the following description.

Abstract: A service manages a plurality of virtual machine instances for low latency execution of user codes. The service can provide the capability to execute user code in response to events triggered on an auxiliary service to provide implicit and automatic rate matching and scaling between events being triggered on the auxiliary service and the corresponding execution of user code on various virtual machine instances. An auxiliary service may be configured as an event triggering service to detect events and generate event messages for execution of the user codes. The service can request, receive, or poll for event messages directly from the auxiliary service or via an intermediary message service. Event messages can be rapidly converted to requests to execute user code on the service. The time from processing the event message to initiating a request to begin code execution is less than a predetermined duration, for example, 100 ms.

Abstract: A method for correcting a memory error of an application program are provided, which includes: when an error occurs in a memory occupied by an application program, suspending a process of the application program; waking up an error correction program that corresponds to the application program, where the error correction program is created when the application program is started; performing, by the error correction program, correction processing on the memory in which the error occurs; if the correction processing performed on the memory in which the error occurs fails, closing, by the error correction program, the application program after saving key data of the application program; and if the correction processing performed on the memory in which the error occurs succeeds, restoring, by the error correction program, the process of the application program that is suspended. Thus reliability and security can be improved when the application program is applied.

Abstract: A method begins by creating a vault as a virtual memory block within memory of a dispersed storage network (DSN). A segment of data is encoded into a set of encoded data slices and stored in the vault. The method continues by dividing the virtual memory block into a set of vault regions. The method continues by determining, for each vault region of the set of vault regions, vault parameters to produce a set of vault parameters. Vault parameters include a decode threshold number of encoded data slices and a total number of encoded data slices for encoding the segment of data. The method continues by facilitating data access to the vault in accordance with the set of vault parameters.

Abstract: In an example, network node failures may be predicted by extracting performance metrics for the network nodes from a plurality of data sources. A fail condition may be defined for the network nodes and input variables related to the fail condition for the network nodes may then be derived from the extracted performance metrics. A plurality of models may then be trained to predict the fail condition for the network nodes using a training set from the extracted performance metrics with at least one of the identified input variables. Each of the plurality of trained models may be validated using a validation set from the extracted performance metrics and may be rated according to predefined criteria. As a result, a highest rated model of the validated models may be selected to predict the fail condition for the network nodes.

Abstract: Changes in the distribution of memory cells across memory states allow calculation of Bit Error Rate (BER). Comparison of test data stored in memory and a known good copy of the test data provides test data BER from which user data BER may be obtained. Data may be handled differently according to its BER.

Abstract: A system may obtain a current bit error count that identifies a quantity of bit errors in a bit stream during a time interval. The system may determine that the current bit error count identifies one or more bit errors. The system may determine whether an estimated bit error rate (BER) for the bit stream is likely to satisfy a threshold. The system may select an approach for determining the estimated BER for the bit stream. The estimated BER may be determined based on combining the current bit error count with a quantity of bits received in the time interval when the estimated BER is likely to exceed the threshold, and the estimated BER may be determined based on the current bit error count and one or more past bit error counts when the estimated BER is unlikely to exceed the threshold. The system may determine the estimated BER.

Abstract: A system for applying security label on a kernel core crash file is disclosed. A method of the disclosure includes accessing, by a processing device, a crash recovery configuration file, parsing the crash recovery configuration file to determine a storage location of a core file, the core file comprising an image of a kernel of an operating system (OS), the image being captured when the OS fails, locating the core file at the determined storage location, and upon determining that a security label is not associated with the core file, sending a command to apply the security label to the core file.

Abstract: A method for supporting failure mode and effects analysis includes storing a meta-model in a computer-readable storage medium. The meta-model includes generic parts of technical systems, generic failure modes, and associations between the generic parts and the generic failure modes. The associations indicate, for each generic part, one or more generic failure modes associated with the generic part. Each generic failure mode identifies a type of failure for a respective generic part. A processor instantiates the generic parts and the generic failure modes to generate part instances and failure mode instances specifying a technical system. The part instances and the failure mode instances are stored, such as in the computer-readable storage medium.

Abstract: Systems, methods, architectures and/or apparatus providing a visualization tool wherein an initial or simplified correlation tree includes a path between two hierarchically related objects; namely, a root cause object and an object representing an entity associated with an event of interest caused by the root cause entity, wherein the correlation tree may be incrementally increased in size and complexity in response to user input, such as via a graphical user interface, such that the user attention is focused on the specific entities and their relationships to thereby enable a user to quickly understand the various failure relationships.

Abstract: A method is provided for providing mobile device support services. The method may include monitoring a mobile device status. The method may additionally include performing device diagnostics based at least in part on captured deice status data to identify potential faults that may affect mobile device functionality. A corresponding system, apparatus, and computer program product are also provided.

Abstract: A method for processing a plurality of received copies of the same original data, the method comprising performing maximum ratio combining on equivalent data portions of the received copies to derive at least one further equivalent data portion. The received and the constructed copies are then divided into sub-portions and combinations of divided sub-portions are assembled to provide reconstructed data portions. An error rate assessment is performed on the reconstructed data portions; and on this basis one is selected as an output.

Abstract: A storage cluster is provided. The storage cluster includes a plurality of storage nodes, each of the plurality of storage nodes having nonvolatile solid-state memory and a plurality of operations queues coupled to the solid-state memory. The plurality of storage nodes is configured to distribute the user data and metadata throughout the plurality of storage nodes such that the plurality of storage nodes can access the user data with a failure of two of the plurality of storage nodes. Each of the plurality of storage nodes is configured to determine whether a read of 1 or more bits in the solid-state memory via a first path is within a latency budget. The plurality of storage nodes is configured to perform a read of user data or metadata via a second path, responsive to a determination that the read of the bit via the first path is not within the latency budget.

Abstract: In an SSD controller reading from flash memory, subsequent to failure of an initial soft-decision decoding attempt based on a nominal LLR, soft-decision re-decoding attempts are made using compensated LLR soft-decision information sets, pre-calculated at respective read-equilibrium points corresponding to mean shifts and variance change in the actual charge-state distributions of the flash memory channel. According to embodiment, soft-decision re-decoding attempts are performed without a retry read, or overlapped with one or more retry reads. By overlapping re-decoding with one or more retry reads, the probability of successful decoding increases, the need for further retry reads diminishes, and throughput is improved. The LLR compensation becomes very effective over a large number of retry reads, improving decoding reliability and achieving close to optimal bit error rates, even in the presence of large channel variation.

Abstract: A method of reading from a memory module which includes a plurality of memories is provided. The method includes reading data corresponding to a plurality of burst length units from the plurality of memories; correcting an error of the read data using a storage error correction code; and outputting the error corrected data by a unit of data corresponding to one burst length unit.

Abstract: In one embodiment, a node of a cluster having a plurality of nodes, executes a storage input/output (I/O) stack having a redundant array of independent disks (RAID) layer. The RAID layer organizes solid state drives (SSDs) within one or more storage arrays as a plurality of RAID groups associated with one or more extent stores. The RAID groups are formed from slices of storage spaces of the SSDs instead of entire storage spaces of the SSDs. This provides for RAID groups to co-exist on a same set of the SSDs.

Abstract: A flash memory codeword architecture is provided. A non-integer count of logical pages is packed into a codeword payload data container. A codeword payload header is generated. The codeword payload header includes an offset to a first logical page that is packed, at least in part, into the codeword payload data container. The codeword payload data container and the codeword payload header are concatenated to generate a codeword payload. Error-correcting code data is generated based, at least in part, on the codeword payload using a systematic error-correcting code. The codeword payload and error-correcting code data is concatenated to generate a codeword. A physical page is programmed with the codeword.

Abstract: A communication device includes: a first communication section, a second communication section, a storage section, a determination section, and a control section. The first communication section communicates with a storage device based on predefined interface communication standards to perform data transfer. The second communication section communicates with an external device in a method other than the interface communication standards to perform data transmission. The storage section stores the selected error code that is previously defined to cause a bit error by noise. The determination section determines whether or not an error code indicated by the error information agrees with the selected error code. The control section, upon determination by the determination section that the error codes agrees with each other, gives the first communication section and the second communication section instructions for cancelling the data transfer and performing data re-transfer.

Abstract: Process control system and methods are disclosed. An example method includes operating a first cluster including first virtual machines and first servers and operating a second cluster including second virtual machines and second servers. The example method also includes storing first data from the first virtual machines at a first data store of the first cluster and storing a replica of the first data at a second data store of the second cluster. The example method also includes storing second data from the second virtual machines at the second data store and storing a replica of the second data at the first data store and identifying a failure of the first cluster. The method also includes, in response to the failure, restarting the first virtual machines using the second servers and the replica of the first data at the second data store.

Abstract: Provided in one embodiment of the present invention is a computer system including a database server and a terminal device for communicating with the database server; the said database server retaining a database; and the terminal device including: an interface for receiving data, which is stored in the database retained in the database server, via a communication network; a buffer for storing the data received by the interface in order to display the data in a window which is to be displayed on a display device; and a controller for starting saving the data, which is stored into the buffer, in a file at a time interval, with the window being displayed on the display device being as a trigger.

Abstract: Techniques for providing data management using a backup data bank system are disclosed. In one particular exemplary embodiment, the techniques may be realized as a method for providing data management using a backup data bank system comprising: storing, on the backup data bank system, a data directory associated with a user, receiving, from a computing resource system, a new entry for the data directory, wherein the new entry is associated with first data belonging to the user that is stored on the computing resource system, and applying, using the backup data bank system, a protection scheme to second data associated with the data directory.

Abstract: Maintaining a set of extents corresponding to a portion of an initial logical volume that is to be copied includes initializing a table having entries corresponding to different portions of the initial logical volume, where each of the entries is initialized with a first value, following initializing the table, providing a second value different from the first value to an entry in the table corresponding to a portion of the initial logical volume to which a write operation is performed and establishing the set of extents, where the first value is provided to entries in the table that correspond to portions of the initial logical device indicated by the extents. Data of the initial logical volume corresponding to the set of extents may be copied to at least one other logical volume.

Abstract: Example apparatus and methods reserve space in a journal using an observation based approach instead of a fixed sized approach or a worst case scenario approach. One example method receives a request to allocate space in a journal to support a file system transaction. The example method reserves an amount of space in the journal based on a pre-existing reservation size estimate. Unlike conventional systems, the estimate is not based on a worst-case scenario. The example method observes the actual amount of storage used in the journal by the file system transaction and then selectively automatically adjusts the pre-existing reservation size estimate. The estimate may slowly shrink if no overflows are encountered but may quickly grow if an overflow is detected.

Abstract: A computer implemented method includes creating a child disk for a machine. A configuration of a backed up disk drive is derived from a storage container that includes a block level backup copy of the disk drive. The child disk is populated with selected data from blocks of data corresponding to selected files desired to be used on the machine. Drivers may be injected and registries modified to start with booting of the virtual.

Abstract: A method, article of manufacture, and apparatus for protecting data. In some embodiments, this includes identifying a parent virtual container, identifying a linked child virtual container, creating a fast copy of the parent virtual container and the linked child virtual container, and consolidating the copy of the parent virtual container and the copy of the linked child virtual container based on the format of the parent virtual container.

Abstract: Systems and methods are disclosed for rapidly restoring client data set for a computer by storing the client data and one or more pat sets required to revert to one or more version of the client data on a remote server; storing a local copy of the replicated client data on a local data storage device coupled to the computer; receiving a request to revert to a predetermined version of the client data; using the local copy as a seed, receiving a patch set corresponding to a predetermined version; and updating the local copy using the patch set to generated the predetermined version.

Abstract: A system and methods are disclosed for performing virtual machine (VM) backups. In accordance with one embodiment, a hypervisor executed by a processing device suspends execution of a VM and initiates a backup procedure to save a current state of the VM. The hypervisor reads a value of a flag that is written to by the VM and is stored in a portion of memory accessible by the VM and the hypervisor. In response to determining that the value read by the hypervisor equals a first value, the hypervisor resumes execution of the VM prior to receiving a status message regarding the backup procedure. In response to determining that the value read by the hypervisor equals a second value, the hypervisor waits to resume execution of the VM until the hypervisor has received a status message indicating that the backup procedure was successful.

Abstract: According to certain aspects, an information management cell with failover management capability can include secondary storage computing devices configured to conduct primary data from a primary storage device(s) to a secondary storage device(s) during secondary copy operations, at the direction of a remote storage manager, wherein a first secondary storage computing device implements a failover storage manager configured to, in the event of a loss of connectivity between the cell and the remote storage manager: access a stored storage policy; initiate a first secondary copy operation according to the storage policy in which the first secondary storage computing device is involved in the creation of a first secondary copy on the secondary storage device(s); and initiate a second secondary copy operation according to the storage policy in which a second secondary storage computing device is involved in the creation of a second secondary copy on the secondary storage device(s).

Abstract: According to certain aspects, an information management cell can include at least one secondary storage computing device configured to conduct primary data generated by at least one client computing device to a secondary storage device(s) as part of secondary copy operations, wherein the secondary storage computing device normally operates to conduct primary data to the secondary storage device(s) for storage as a secondary copy in a first secondary copy file format, at the direction of a main storage manager; and can include a failover storage manager configured to activate in response to loss of connectivity between the cell and the main storage manager, and instruct a secondary copy application to perform a secondary copy operation in which the primary data generated by the at least one client computing device is stored as a secondary copy in a second secondary copy file format different than the first secondary copy file format.

Abstract: According to certain aspects, an information management cell can include a failover storage manager configured to: instruct a secondary copy application to perform a secondary copy operation in which primary data generated by at least one client computing device is stored as a secondary copy in a second secondary copy file format different than a first secondary copy file format; and subsequent to reestablishment of connectivity to a main storage manager, restore the secondary copy stored in the second secondary copy file format to obtain restored data that is no longer in the second secondary copy file format; and can include at least one secondary storage computing device configured to, subsequent to the restore of the secondary copy, and at the direction of the main storage manager, conduct the restored data to a secondary storage device(s) to create a secondary copy in the first secondary copy file format.

Abstract: According to certain aspects, an information management cell with failover management capability can include secondary storage computing devices configured to conduct primary data from a primary storage device(s) to a secondary storage device(s) during secondary copy operations, at the direction of a remote storage manager, wherein a first secondary storage computing device implements a failover storage manager configured to, in the event of a loss of connectivity between the cell and the remote storage manager: access a stored storage policy; initiate first and secondary copy operations according to the storage policy in which the first and second secondary storage computing devices are each involved in the creation of a first and second secondary copies; and subsequent to reestablishment of connectivity between the cell and the remote storage manager, transmit synchronization information associated with the secondary copy operations to the remote storage manager.

Abstract: Methods and apparatus that restore a resource from a first source and a second source to a device are described. Availability of the resource from a second source may be dynamically determined after a portion of the resource has been restored to the device from the first source. If the second source is determined to be more efficiently connected with the device than the first source, a remaining portion of the resource may be restored from the second source to the device after the portion of the resource has been restored to the device.

Abstract: In one embodiment of the present description, a copy relationship is established between a storage location at a first site and a storage location at a second site in a data storage system, wherein a dynamically assignable bitmap preset to one of a plurality of different predetermined bit patterns is selected as a function of both the availability of the selected bitmap and the type of predetermined bit pattern identified for the selected bitmap. The selected bitmap may be assigned as an out-of-sync bitmap wherein updates to the storage location at one site, which are to be copied to the storage location at the other site, are indicated in the selected bitmap, and data writes being written to the storage location at the one site, are copied to the storage location at the other site, using the selected bitmap as an out-of-sync bitmap. Other aspects are described.

Abstract: Various systems and methods for determining whether a distributed storage cluster is operating with a last failure domain are disclosed. The last failure domain is the only node with access to a latest copy of configuration data and an up-to-date copy of application data. In response to a determination that the distributed storage cluster is operating with the last failure domain, the method causes the last failure domain to copy one or more changed blocks of the up-to-date copy of the application data from one or more mirrored volumes to a recovery server for storage.

Abstract: A method, an apparatus, and a system for handling a virtual machine internal fault. The method includes: monitoring, by a virtual machine internal fault detecting apparatus, a state of a virtual machine operating system; when detecting that the virtual machine operating system encounters an exception, obtaining, by an exception catching module in the virtual machine internal fault detecting apparatus, exception information corresponding to the exception according to a context of the virtual machine operating system; and reporting, by the exception catching module, the exception information to a virtual machine monitoring apparatus, so that the virtual machine monitoring apparatus determines, according to the exception information, a policy for resolving the exception corresponding to the exception information, and resolves the exception corresponding to the exception information by using the policy. The present invention is applicable to a virtualized environment having a virtual machine.

Abstract: An approach for efficient failover detection includes detecting an attempt by a first server to transition from a standby mode to an active mode, diagnosing a loss of connectivity to the first server in a control plane as a cause of the attempt, and transitioning to a standby mode based on the diagnosed cause of the attempt.

Abstract: The present disclosure includes methods, devices, and systems for error detection/correction based memory management. One embodiment includes performing a read operation with respect to a particular group of memory cells of a memory device and, if the read operation results in an uncorrectable error, determining whether to retire the particular group of memory cells in response to a status of an indicator corresponding to the particular group of memory cells, wherein the status of the indicator indicates whether the particular group of memory cells has a previous uncorrectable error associated therewith.

Abstract: A storage system includes a first control apparatus; at least one second control apparatus managed by the first control apparatus; and a storage unit accessed by the second control apparatus. The second control apparatus determines based on detection of an error of an input/output process for storage in the storage unit whether the storage is in a blocking state, executes a resumption process of the input/output process when the storage is in the blocking state, judges whether an error occurrence frequency of the input/output process is at least a predetermined value, when the storage is not in the blocking state, and transmits to the first control apparatus, a blocking process request for the storage, when the error occurrence frequency is at least the predetermined value. The first control apparatus executes a blocking process and an error process of the storage, based on reception of the blocking process request.