Abstract: A method for creating snapshots and backups in a virtual computing environment is provided. The method includes writing application output of an application spanning one or more virtual machines as an application consistency group to a writeback cache, wherein the one or more virtual machines are implemented using one or more compute nodes and wherein the writeback cache is implemented in direct attached storage in the one or more compute nodes. The method includes pausing I/O (input/output) operations of the application and marking the pausing, in the writeback cache. The method includes resuming the I/O operations of the application, after the marking and dumping data, according to the marking, from the writeback cache to a data node, as a snapshot.

Abstract: Embodiments of the present invention also provide a system for increasing inter-application efficiency by conducting recovery of end-to-end transactions. Embodiments of the invention allow a transaction manager to track the status of a transaction being processed by a plurality of nodes in an array in order to perform error recovery of failed transactions within a node. The recovery process may involve restarting the transaction at the global step and the local step at which the transaction failed. By avoiding restarting the end-to-end transaction from the first step, the system may save precious computing resources of the computer systems within the nodes processing the end-to-end transaction, including, but not limited to, processing power, memory space, storage space, cache space, electric power, networking bandwidth, and I/O calls.

Abstract: In an approach for resolving terminated transactions in a transactional memory environment, a processor initiates a hardware transaction in a computing environment, wherein the hardware transaction accesses a memory location, and wherein the hardware transaction includes a transaction begin indicator and a transaction end indicator. A processor detects a conflicting access of the memory location while executing the hardware transaction. A processor aborts the hardware transaction based on the conflicting access of the memory location. Hardware determines that the conflicting access of the memory location is a transient condition. A processor reinitiates the hardware transaction.

Abstract: Exemplary embodiments of the invention provide a technique to validate physical cabling and logical path before provisioning volume. In accordance with an aspect, a computer comprises a memory storing software and a processor executing the software. The software is operable to: identify first server port and second server port forming redundant ports of a server and first storage port and second storage port forming redundant ports of a storage system; and check whether a redundant relationship is formed by at least one of (i) a physical connection between the first server port and the first storage port and a physical connection between the second server port and the second storage port, or (ii) a logical connection between the first server port and the first storage port and a logical connection between the second server port and the second storage port.

Abstract: The disclosed computer-implemented method for modifying track logs during restore processes may include (1) identifying a backup application that maintains a track log used to identify changed blocks during backup operations, (2) detecting a restore process launched by the backup application to restore at least one block backed up in a backup image, (3) retrieving, from the backup image, block information about the block being restored by the restore process, and then (4) recording the block information to the track log during the restore process such that the backup application does not identify the block as changed during a subsequent backup operation due at least in part to the block already being backed up in the backup image. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: An information processing system includes a storage unit storing application identification information of an application for executing a first process in association with information relating to the first process; a receiving unit that receives a request including the application identification information and information relating to electronic data from a device; a process execution unit that executes the first process on electronic data based on the information relating to the first process stored in association with the application identification information included in the request and the information relating to the electronic data included in the request; and a process generation unit that generates information relating to a second process for rolling back a processing result of the first process executed by the process execution unit. The process execution unit executes the second process based on the generated information relating to the second process when an error occurs in the first process.

Abstract: A method and apparatus is disclosed herein for maintaining data consistency in persistent memory in an in-place-update file system of a deduplication computing system. The method may include receiving a data write request to write a block of data from a volatile memory to a non-volatile memory in an in-place-update file system of deduplication computing system. Furthermore, the method may include determining whether the data write request is to perform an in-place update of an existing block in the non-volatile memory, and converting a type of write operation associated with the request from a requested write operation type to a new data allocation write operation when the data write request modifies the existing block. Furthermore, the method may include processing the new data allocation write operation to write the block of data from the volatile memory to the non-volatile memory using an ordered sequence of file system data journaling and writes to the non-volatile memory.

Abstract: A system for applying a recovery mechanism to a network of medical diagnostics instruments is provided herein. The system includes the following: a plurality of medical diagnostics instruments, each associated with a network connected component; a plurality of communication modules, each associated with a corresponding one of the plurality of network connected components, wherein each one of the plurality of communication modules is arranged to report on malfunctioning components that are network connected with the corresponding component, and a recovery module, configured to: (i) obtain reports from the communication modules; (ii) re-establish the malfunctioning components; and (iii) notify all communication modules of the re-establishment of the malfunctioning components, wherein the communication modules are further configured to re-establish connection between the corresponding components and the re-established components.

Abstract: Embodiments of the present disclosure generally relate to an improved method and system for error correction in non-volatile memory cells. The method includes writing data to a first location in non-volatile memory from a block of user data stored in DRAM and verifying the written data matches the block of user data. If the written data fails verification, the method further includes writing an error location pointer indicative of one or more error locations in the first location to a second location in non-volatile memory. Writing the one or more error locations to the error location pointer includes verifying the written error location pointer matches an address of the one or more error locations in the first location to ensure integrity of the error location pointer. Use of the error location pointer results in non-volatile memory with increased data rate, decreased read latency and a low probability of data loss.

Abstract: During a distributed transaction, a computing device that hosts a participant of the distributed transaction intercepts an operation to change a resource from an initial state to a resultant state. The computing device determines an inverse operation that will change the resource from the resultant state back to the initial state. The computing device records the inverse operation and performs the operation.

Abstract: An information processing apparatus that can execute a start-up process properly, even when electric power is cut off without performing a normal power turn-OFF process. A first storage unit stores a program. A second storage unit continues holding information even when a power supply stops. A third storage unit stores information showing a power-OFF-timing state of the information processing apparatus. A control unit determines whether the information showing the power-OFF-timing state obtained from the third storage unit needs read-out of a program at a power ON timing of the information processing apparatus, performs a start-up process after reading and developing the program from the first storage unit to the second storage unit when the read-out of the program is needed, and performs the start-up process without reading and developing the program from the first storage unit to the second storage unit when the read-out of the program is not needed.

Abstract: A sorted key-value store is implemented using a write-back cache maintained in memory, a B-tree data structured maintained in disk, and a logical and physical log for providing transactions. The logical log and write-back cache are used to answer client requests, while dirty blocks in the write-back cache are periodically flushed to disk using the physical log.

Abstract: In an approach for resolving terminated transactions in a transactional memory environment, a processor initiates a hardware transaction in a computing environment, wherein the hardware transaction accesses a memory location, and wherein the hardware transaction includes a transaction begin indicator and a transaction end indicator. A processor detects a conflicting access of the memory location while executing the hardware transaction. A processor aborts the hardware transaction based on the conflicting access of the memory location. Hardware determines that the conflicting access of the memory location is a transient condition. A processor reinitiates the hardware transaction.

Abstract: In an approach for resolving terminated transactions in a transactional memory environment, a processor initiates a hardware transaction in a computing environment, wherein the hardware transaction accesses a memory location, and wherein the hardware transaction includes a transaction begin indicator and a transaction end indicator. A processor detects a conflicting access of the memory location while executing the hardware transaction. A processor aborts the hardware transaction based on the conflicting access of the memory location. Hardware determines that the conflicting access of the memory location is a transient condition. A processor reinitiates the hardware transaction.

Abstract: A method for managing access of virtual machines executed by a host computer system to storage area networks, the storage area networks connecting the host computer system with storage systems via switches, where the host computer system includes one or more host ports to connect with a switch each, and where one or more port names are assigned to each virtual machine. The method includes, for each storage area network connected with the host computer system, sending the port names of a virtual machine and a target port name as part of a validate access command to the respective switch; and when receiving the validate access command by the switch, the switch returning success information to the sending host computer system in case all received virtual machine port names have access to a target port assigned to the received target port name, otherwise returning a fail information.

Abstract: A method for managing access of virtual machines executed by a host computer system to storage area networks, the storage area networks connecting the host computer system with storage systems via switches, where the host computer system includes one or more host ports to connect with a switch each, and where one or more port names are assigned to each virtual machine. The method includes, for each storage area network connected with the host computer system, sending the port names of a virtual machine and a target port name as part of a validate access command to the respective switch; and when receiving the validate access command by the switch, the switch returning success information to the sending host computer system in case all received virtual machine port names have access to a target port assigned to the received target port name, otherwise returning a fail information.

Abstract: Mechanisms are provided, in a cloud computing data processing system comprising a plurality of components, hosted on one or more hardware computing devices of the cloud computing data processing system, for transactional resource and topology management. A cloud service system is instantiated that comprises component instances having allocated resources. The cloud service system comprises orchestration engine logic which generates a transactional data structure that stores objects corresponding to transactions executed in association with resources and component instance state changes. The orchestration engine logic receives transactions associated with resources or component instances of the cloud service system and records the transactions as objects in the transactional data structure in response to receiving the transactions.

Abstract: Mechanisms are provided, in a cloud computing data processing system comprising a plurality of components, hosted on one or more hardware computing devices of the cloud computing data processing system, for transactional resource and topology management. A cloud service system is instantiated that comprises component instances having allocated resources. The cloud service system comprises orchestration engine logic which generates a transactional data structure that stores objects corresponding to transactions executed in association with resources and component instance state changes. The orchestration engine logic receives transactions associated with resources or component instances of the cloud service system and records the transactions as objects in the transactional data structure in response to receiving the transactions.

Abstract: A microcontroller unit having a functional state, a reset state, and one or more assertable fault sources is described. Each fault source has its own fault source assertion count and its own fault source assertion limit; the MCU is arranged to perform the following sequence of operations in a cyclic manner: if one or more of the fault sources are asserted, pass from the functional state to the reset state and increase the respective fault source assertion counts by one increment; if one or more of the fault source assertion counts exceeds the respective fault source assertion limit, disable the respective fault source; and pass from the reset state to the functional state. A method of operating an MCU is also disclosed.

Abstract: A data processing apparatus includes a storage unit configured to store plural data processing programs and a corresponding error processing program for when an error occurs with a first data processing program; and a processor configured to record to memory before executing the first data processing program, information of the error processing program that corresponds to the first data processing program; update and record in the memory after the first data processing program ends, information of a second data processing program scheduled to be executed next; and switch to any one among the first data processing program that corresponds to information recorded in the memory and the error processing program, when program processing is started next.

Abstract: A method and system for incremental backup is disclosed. The method includes writing a first update to a secondary node and writing a second update to the secondary node. The secondary node comprises a replication storage group (RSG). Further, the order in which the updates are written at the secondary node is consistent with the order in which the updates were written at a primary node.

Abstract: Executing a confined recovery in a distributed system having a plurality of worker systems including a failed worker system at a current superstep. The confined recovery includes determining states of the partitions of the worker systems during the supersteps preceding the current superstep, and determining a recovery initiation superstep preceding the current superstep in which all messages for recovery initiation superstep are available. The recovery initiation superstep is determined responsive to determining the states of the partitions. Additionally, a recovery set of partitions is determined for which messages in supersteps after the recovery initiation superstep are not available. The worker systems having the partitions in the recovery set are instructed to execute the defined function for the partitions in the recovery set starting at the recovery initiation superstep to recover the lost exchanged messages.

Abstract: Real system devices (RSD's) emulate virtual system devices (VSD's); system elements can use RSD's and manipulate VSD's, while users can only use VSD's. Identifying when RSD's have erroneous data. Providing a mapping of RSD's to VSD's, to recover a maximum set of VSD's. Providing a mapping of VSD's to RSD's, to recover a specified most valuable VSD. Reconstructing VSD's from RSD's having erroneous data, and coordinating with a user's assistance to couple RSD's in an order allowing data recovery. Metadata is maintained coupling data identifiable on VSD's with corresponding data on RSD's; it is possible to trace connections between RSD's and VSD's even without complete data.

Abstract: A method and system for facilitating an undo operation. In one embodiment, the method includes generating a plurality of control files, where each of the control files is associated with a batch of data that is received from a sending partition during a redistribution process, and where each control file includes a list of pages and corresponding ranges of rows of data that have been appended to the pages. The method also includes writing the control files to a persistent memory for each control file where all of the associated rows of the respective consistency point have been appended to pages and written to a persistent memory. The method also includes, in response to an interruption in the redistribution process, identifying pages and rows to be deleted during an undo operation based on the plurality of control files.

Abstract: Handling garbage collection and exceptions in hardware assisted transactions. Embodiments are practiced in a computing environment including a hardware assisted transaction system. A method includes beginning a hardware assisted transaction, raising an exception while in the hardware assisted transaction, including creating an exception object, determining that the transaction should be rolled back, and as a result of determining that the transaction should be rolled back, marshaling the exception object out of the hardware assisted transaction.

Abstract: In one embodiment, a method detects a failure of a container in a controller node where the container includes a service being performed and isolated from other services being performed in other containers on the controller node. The controller node terminates the container including the service and determines a known state for the service. The known state is known to be operational without including a cause of the failure and the service operated from the known state saving changes to the known state during operation separately from the known state. The controller node restarts the service in a new container that replaces the terminated container where the restarted service starts from the known state without using the changes.

Abstract: Disclosed herein are system, method, and computer program product embodiments for utilizing an intrusive data hash table to support processing transactions. An embodiment operates by receiving a transaction comprising a plurality of operations. Responsive to the receiving, the transaction is verified by verifying the validity of the plurality of operations. Responsive to verifying the transaction, the transaction is applied to the intrusive hash table.

Abstract: Methods, apparatuses, and computer program products for event and alert analysis are provided. Embodiments include a local event analyzer embedded in an alert analyzer receiving events from an event queue. Embodiments also include the local event analyzer creating, based on the received events and local event analysis rules specific to the alert analyzer, a temporary alert for the alert analyzer. Embodiments also include the alert analyzer analyzing the temporary alert based on alert analysis rules.

Abstract: Embodiments described herein provide an object store that efficiently manages and services objects for use by clients of a distributed data processing system. Illustratively, the object store may be embodied as a quasi-shared storage system that interacts with nodes of the distributed data processing system to service the objects as blocks of data stored on a plurality of storage devices, such as disks, of the storage system. To that end, an architecture of the object store may include an on-disk layout, e.g., of the storage system, and an incore layout, e.g., of the nodes, that cooperate to illustratively convert the blocks to objects for access by the clients.

Abstract: In one embodiment, a method for dynamically allocating a memory includes dividing a memory into a first portion and a second portion in response to detecting an error condition when reading data from a data storage medium. The first portion is allocated for processing normal read and/or write requests. The second portion is allocated for processing error recovery procedure (ERP) requests. In another embodiment, a computer program product for dynamically allocating a memory includes a computer readable storage medium having program code embodied therewith. The program code is readable/executable by a processor to divide, by the processor, a memory into a first portion and a second portion in response to detecting an error condition when reading data from a data storage medium. The first portion is allocated for processing normal read and/or write requests. The second portion is allocated for processing ERP requests.

Abstract: Techniques are described for providing a messaging service that employs a distributed key-value store for message persistence. On receiving a message to be enqueued for subsequent delivery, a message identifier is generated and employed as a key to store the message in the key-value store. The message identifier may be generated based on an available location in a message tracking data structure. In some cases, the message tracking data structure may be an append tree data structure that is substantially self-balancing as an increasing number of messages are tracked using the append tree data structure. The message tracking data structure may be further employed to determine a message identifier for a message to be vended from the key-value store.

Abstract: Crash recovery of a computing system in the context in which the computing system includes a volatile memory which has contents lost due to the crash, an intermediate non-volatile memory that (together with the volatile memory) contributes to the active memory of the computing system, and non-volatile storage. The recovery occurs by identifying pages that were in the volatile memory at the time of the crash. For each of these pages, the recovery determines whether to recover the page into the volatile memory from either the intermediate non-volatile memory or the storage, and then performs the recovery. In embodiments in which access speeds for the intermediate non-volatile memory may be much faster than for the storage, and in which much of the pages to be recovered are recovered from the intermediate non-volatile memory, the recovery time may be reduced.

Abstract: A method and a system for verifying quality of server thereof are provided. The method and the system are used for verifying a plurality of servers constructed in a server cluster. The method includes: installing a cloud computing platform in the servers, creating an input file folder on a cloud computing platform file system included in the cloud computing platform and storing calculation data into the input file folder. The method further includes: creating a plurality of mapreduce tasks corresponding to a calculation job by the servers and distributively executing the mapreduce tasks by using a mapreduce frame included in the cloud computing platform to obtain a plurality of calculation results, and storing and analyzing the calculation results to verify a quality of each of the servers. Accordingly, the method is capable of conformably verifying quality of servers in the server cluster.

Abstract: An information processing apparatus includes a processor, a first memory, and a second memory, wherein the second memory includes a first data storage region having a first data capacity and a second data storage region having a second data capacity smaller than the first data capacity, and the processor is configured to, in a case of executing first processing, select the first data storage region as a storage region for data to be written into the second memory by the first processing, and select the second data storage region as a storage region for data to be written into the second memory by second processing, and in a case of not executing the first processing, select the first data storage region as a storage region for data to be written from the first memory to the second memory by the second processing.

Abstract: A technique for failure monitoring and recovery of a first application executing on a first virtual machine includes storing machine state information during execution of the first virtual machine at predetermined checkpoints. An error message that includes an application error state at a failure point of the first application is received, by a hypervisor, from the first application. The first virtual machine is stopped in response to the error message. The hypervisor creates a second virtual machine and a second application from the stored machine state information that are copies of the first virtual machine and the first application. The second virtual machine and the second application are configured to execute from a checkpoint preceding the failure point. In response to receipt of a failure interrupt by the second application, one or more recovery processes are initiated in an attempt to avert the failure point.

Abstract: Various embodiments relating to saving and recovering a hardware architecture state are provided. In one embodiment, during a first mode of operation, entries in a first portion of a random-access memory (RAM) are manipulated. A current version of less than all of the entries of the first portion is saved to a checkpointed version in response to a checkpoint event that triggers operation in a second mode of operation. During the second mode of operation, entries in a second portion of the RAM are manipulated. The checkpointed version of less than all of the entries of the first portion is recovered as the current version in response to a restore event that triggers resumption of operation in the first mode.

Abstract: The memory system includes at least one volatile memory configured to store data. The memory system also includes a non-volatile memory controller configured to provide a control signal to allow the data to be stored in a non-volatile memory during a power interruption mode. In addition, the memory system includes a termination resistor (TER) configured to control a data path in response to a power interruption signal.

Abstract: A method, computer program product, and computing system for defining a transactional log file for a data storage system including defining a transactional log file for a data storage system including a data array. A plurality of IO requests for the data storage system are processed. The transactional log file is updated to include information concerning the plurality of IO requests, wherein the information includes an LGT indicator for each of the plurality of IO requests. The occurrence of a malfunction within the data storage system is sensed.

Abstract: A symbolic encoding of predicated execution for static verification, based on a plurality of data parallel program instructions, is obtained. A result of static verification of one or more attributes associated with the plurality of data parallel program instructions is obtained, based on the symbolic encoding.

Abstract: A method of achieving fault tolerance in a distributed stream processing system organized as a directed acyclic graph includes the initial step of managing a stream process within the distributed stream processing system including one or more operators. The one or more operators of the stream process are communicatively associated with one or more downstream operators. The method includes the steps of maintaining one or more data copies of a processing state of the one or more operators until the one or more data copies can be safely discarded, notifying the one or more operators when it is safe to discard at least one of the at least one of the one or more data copies of the processing state; and using an identifier to denote the data copy of the processing state to be safely discarded.

Abstract: Replicated instances in a database environment provide for automatic failover and recovery. A monitoring component can periodically communicate with a primary and a secondary replica for an instance, with each capable of residing in a separate data zone or geographic location to provide a level of reliability and availability. A database running on the primary instance can have information synchronously replicated to the secondary replica at a block level, such that the primary and secondary replicas are in sync. In the event that the monitoring component is not able to communicate with one of the replicas, the monitoring component can attempt to determine whether those replicas can communicate with each other, as well as whether the replicas have the same data generation version. Depending on the state information, the monitoring component can automatically perform a recovery operation, such as to failover to the secondary replica or perform secondary replica recovery.

Abstract: The method relates to a method for the radiation hardening of an electronic circuit by partitioning, said circuit including an odd number K of parallel branches connected to a same primary input I and each including a same series of N modules and N?1 nodes linking two consecutive modules, the K branches together forming a series of N?1 gates respectively consisting of parallel K nodes, and a primary arbiter forming a majority vote from the output signal of the K branches, the method being characterized in that it includes the following steps which are repeated for each one of the gates: determining a reliability of a subcircuit upstream from the gate consisting of the portions of the K branches located between the primary input and the gate, and the insertion of at least one arbiter at the gate forming a majority vote from the output signals of said portions of branches constituting the scanned subcircuit and outputting at least one majority signal to the respective inputs of an additional subcircuit formed b

Abstract: Techniques are disclosed for qualified checkpointing of a data flow model having data flow operators and links connecting the data flow operators. A link of the data flow model is selected based on a set of checkpoint criteria. A checkpoint is generated for the selected link. The checkpoint is selected from different checkpoint types. The generated checkpoint is assigned to the selected link. The data flow model, having at least one link with no assigned checkpoint, is executed.

Abstract: Techniques are disclosed for qualified checkpointing of a data flow model having data flow operators and links connecting the data flow operators. A link of the data flow model is selected based on a set of checkpoint criteria. A checkpoint is generated for the selected link. The checkpoint is selected from different checkpoint types. The generated checkpoint is assigned to the selected link. The data flow model, having at least one link with no assigned checkpoint, is executed.

Abstract: A method for providing a dedicated software framework for exception and event management in an embedded software system is disclosed. In one embodiment, each of exceptions/events originated from users are uniquely identified and severity of the exceptions/events is categorized. The users are software subsystems, software layers and software modules in the embedded software system. Further, information regarding the exceptions/events is reported through various layers, subsystems and modules for use by an application. Furthermore, information associated with one or more of the reported exceptions/events is logged using a logging framework. In addition, the exceptions/events are handled to keep applications running without causing an unexpected behavior in the embedded software system.

Abstract: A system and method for distributed fault detection. In an exemplary method, unplanned application exits and crashes may be detected at a node local level. Further, application hangs may be detected using at least one of a script and a binary at the node local level. Also, node crashes and operating system crashes may be detected using node to node heart-beating.

Abstract: Apparatuses and methods for providing flow control over a network are disclosed. One such method comprises receiving a first remote procedure call at a first computer from a second computer remote from the first computer, the first computer including a first memory and a first processor configured to execute instructions stored in the first memory, generating a second remote procedure call from the first processor to the second computer, the second remote procedure call responsive to the first remote procedure call, monitoring the first processor for receipt of a release signal from the second computer, the release signal indicating when the second computer is able to receive data responsive to the first remote procedure call, and transmitting the data from the first memory of the first computer to the second computer responsive to receipt of the release signal at the first processor.

Abstract: A system and method of data management with modular erase in a data storage system with a memory array having an erase block and a target block with the target block in a logical unit separate from the erase block including: performing an erase operation on the erase block, the erase operation having an operation matrix configured for partial erasing of the erase block; updating a command status for the erase block; enabling an intervening command on the target block based on the command status indicating an incomplete erase status with the intervening command updating the command status; performing an erase optimization based on the command status; performing an additional erase operation based on the erase optimization; and updating the command status to an erase complete status based on the additional erase operation.

Abstract: A lock manager running on a machine may write a first entry for a first process to a queue associated with a resource. If the first entry is not at a front of the queue, the lock manager identifies a second entry that is at the front of the queue, and determines whether a second process associated with the second entry is operational. If the second process is not operational, the lock manager removes the second entry from the queue. Additionally, if the queue becomes unavailable, the lock manager may initiate failover to a backup copy of the queue.

Abstract: According to some aspects, a method of operating an automatic test system comprising a plurality of paths and programmed with a test pattern is provided. One such method comprises executing vectors in the test pattern with circuitry comprising a plurality of paths, the executing comprising upon processing, in a first of the plurality of paths, the operation portion of a vector specifying an operation capable of generating a branch in the flow of execution of the vectors in the test pattern to a non-sequential location in the test pattern, initiating processing of the test pattern in a second of the plurality of paths from the non-sequential location. Some aspects include a system for executing instructions comprising a plurality of paths comprising control circuitry to initiate processing of operation portions from sequential locations of a memory within an available path of the plurality of paths.