Abstract: A computer architecture allows for simplified recovery after mis-speculation during speculative execution by controlling speculation to occur within idempotent regions that may be recovered by re-execution of the region without the need for restoring complex state information from checkpoints. A compiler for increasing the size of idempotent regions is also disclosed.

Abstract: An apparatus, system, and method are disclosed for assuring delivery of an Enterprise Information System (EIS) event to a client. An adapter apparatus polls at least one EIS for an event. The event is staged to a staging table, consisting of an XA-compliant database, in preparation for delivery to the client. The status of the event is marked and the event is delivered to the client. Events delivered to clients that are unresponsive or otherwise unavailable are held until the clients become responsive and then the events are delivered. Delivery of events is confirmed using a transaction service.

Abstract: An automated method is provided for constructing or updating a service model that defines the entities in an enterprise's computing environment. The method includes: defining a group of templates for updating the service model, where the group of templates identify different types of entities which comprise the service model and relationships between the types of entities including an entity that links software applications to respective computing infrastructure that supports the software applications; monitoring messages received from monitoring tools residing in the computing environment; and updating a service model in accordance with the group of templates using data encapsulated in the messages.

Abstract: One embodiment provides a system that facilitates the execution of a transaction for a program in a hardware-supported transactional memory system. During operation, the system records a failure state of the transaction during execution of the transaction using hardware transactional memory mechanisms. Next, the system detects a transaction failure associated with the transaction. Finally, the system provides an advice state associated with the recorded failure state to the program to facilitate a response to the transaction failure by the program.

Abstract: Storage servers use a fast, non-volatile or persistent memory to store data until it can be written to slower mass storage devices such as disk drives. If the server crashes before a write can complete, the data remains safely stored in non-volatile memory. If the data cannot be committed to disk when the server reboots (e.g. because the destination mass storage device is unavailable), it is stored in a file. When the disk reappears, the data in the file may be used to restore a file or filesystem on the disk to a consistent state.

Abstract: The present invention provides a data migration management apparatus that can easily create a re-execution task for re-executing an error-terminated data migration task, and also can increase the possibility of the re-execution task being successful. In a case where a data migration from a migration-source volume to a migration-destination volume fails, the management apparatus uses the information of the failed task to create a re-execution task. The management apparatus changes the configuration of a volume pair as necessary. The management apparatus manages the failed task in association with the re-execution task.

Abstract: Embodiments include a computing system, a device, and a method. A computing system includes a processor subsystem having an adjustable operating parameter. The computing system also includes an information store operable to save a sequence of instructions. The computing system further includes a controller module. The controller module includes a monitor circuit for detecting an incidence of an operating-parameter-caused error corresponding to an execution of an instruction of the sequence of instructions by the processor subsystem. The controller further includes a control circuit for adjusting the adjustable operating parameter based upon an error-tolerant performance criterion.

Abstract: A method and system for accelerating recovery in an MPI environment are provided in the illustrative embodiments. A first portion of a distributed application executes using a first processor and a second portion using a second processor in a distributed computing environment. After a failure of operation of the first portion, the first portion is restored to a checkpoint. A first part of the first portion is distributed to a third processor and a second part to a fourth processor. A computation of the first portion is performed using the first and the second parts in parallel. A first message is computed in the first portion and sent to the second portion, the message having been initially computed after a time of the checkpoint. A second message is replayed from the second portion without computing the second message in the second portion.

Abstract: Methods and apparatus to debug a network application are described. A described example network includes a live control network to collect control messages to create a history of network states, the history of network states reflecting an order in which control messages are processed, the live control network to roll back from a current state to a past state upon detection of an improper sequence of messages and to process the messages in a corrected sequence, the corrected sequence to be stored in the history. The described example network further includes a virtualized network corresponding to the live control network, the virtualized network responsive to a command from an operator to step through the history to facilitate debugging.

Abstract: One embodiment provides a system that facilitates the execution of a transaction for a program in a hardware-supported transactional memory system. During operation, the system records a misspeculation indicator of the transaction during execution of the transaction using hardware transactional memory mechanisms. Next, the system detects a transaction failure associated with the transaction. Finally, the system provides the recorded misspeculation indicator to the program to facilitate a response to the transaction failure by the program.

Abstract: A pattern-dependent error correction method and system for a code group alignment finite state machine (FSM) are disclosed. A state corrector generates a start-of-stream delimiter (SSD) detected signal to the FSM when the FSM is in an idle state and at least one condition due to a lost SSD signal is met; and the state corrector generates an idle detected signal to the FSM when at least one condition due to a lost idle signal is met. A pattern corrector generates a corrected code pattern {J,K} to FSM when the FSM is in an idle state and at least one condition due to a false idle state is met; and the pattern corrector generates a corrected code pattern {T,R} to the FSM when the FSM is in a data state, a start of stream state or a data error state, and at least one condition due to a false packet end is met.

Abstract: Disaster recovery is performed based on journaling events prioritization in information in an information technology environment. One implementation involves prioritizing log file events for scheduling of jobs on a computing system, by logging events concerning each job execution plan, in a log file, and for disaster recovery, prioritizing logged events based on corresponding job urgency and relevance level and performing recovery by reapplying the events of log files in the priority order such that more urgent and relevant jobs are recovered first.

Abstract: Among other aspects disclosed are a method and system for processing a batch of input data in a fault tolerant manner. The method includes reading a batch of input data including a plurality of records from one or more data sources and passing the batch through a dataflow graph. The dataflow graph includes two or more nodes representing components connected by links representing flows of data between the components. At least one but fewer than all of the components includes a checkpoint process for an action performed for each of multiple units of work associated with one or more of the records. The checkpoint process includes opening a checkpoint buffer stored in non-volatile memory at the start of processing for the batch. For each unit of work from the batch, if a result from performing the action for the unit of work was previously saved in the checkpoint buffer, the saved result is used to complete processing of the unit of work without performing the action again.

Abstract: A background scheduler is provided that utilizes low-level communications (e.g., communications with a generic or controller-specific solid state, non-volatile memory driver) to control locking, reading, rewriting and unlocking of pages of data in the non-volatile memory. Such low-level communications cause data to be rewritten to the non-volatile memory independent of the file system in an effort to avoid data loss prior to an estimated data retention period.

Abstract: Embodiments include methods, apparatus, and systems for controlling of sparing in a storage system. In one embodiment, a method compares a first amount of time to complete sparing of data from a failed disk in a storage system with a second amount of time to complete a user request to the storage system in order to determine when to create a copy of the data from the failed disk.

Abstract: A computer-implemented method, apparatus and article of manufacture for performing an automatic error recovery in a database system. Automatic error recovery is performed for a query execution plan, following errors, problems or failures that occur during execution, by automatically or manually deactivating and/or activating components, features or code paths, and then re-submitting the query execution plan for execution in the computer system.

Abstract: Embodiments of the invention provide an interrupt handler configured to distinguish between critical and non-critical unrecoverable memory errors, yielding different actions for each. Doing so may allow a system to recover from certain memory errors without having to terminate a running process. In addition, when an operating system critical task experiences an unrecoverable error, such a task may be acting on behalf of a non-critical process (e.g., when swapping out a virtual memory page). When this occurs, an interrupt handler may respond to a memory error with the same response that would result had the process itself performed the memory operation. Further, firmware may be configured to perform diagnostics to identify potential memory errors and alert the operating system before a memory region state change occurs, such that the memory error would become critical.

Abstract: Methods, devices, and systems are provided for allowing a single machine, such as a server, to co-host multi-SIP Archive (SAR) applications offering SIP servlet based products. The concept of a Root Application Router is introduced that is adapted to coordinate other Sub-Application Routers rather than individual SARs. These other Sub-Application Routers are fully fledged Application Routers in their own right, but are unaware of the controlling Root Application Router.

Abstract: Fault tolerance is provided in a distributed system. The complexity of replicas and rollback requests are avoided; instead, a local failure in a component of a distributed system is tolerated. The local failure is tolerated by storing state related to a requested operation on the component, persisting that stored state in a data store, such as a relational database, asynchronously processing the operation request, and if a failure occurs, restarting the component using the stored state from the data store.

Abstract: Method, computer program product, and system for transferring data from positional data sources to partitioned databases are provided. A record is read from a positional data source. The record is to be written to one of a plurality of partitions of a database. A position of the record in the positional data source is obtained. A transaction is initiated to write the record to the one partition and to store the position of the record in the database. The transaction is committed after the record is successfully written to the one partition and the position of the record is successfully stored in the database.

Abstract: Storage servers use a fast, non-volatile or persistent memory to store data until it can be written to slower mass storage devices such as disk drives. If the server crashes before a write can complete, the data remains safely stored in non-volatile memory. If the data cannot be committed to disk when the server reboots (e.g. because the destination mass storage device is unavailable), it is stored in a file. When the disk reappears, the data in the file may be used to restore a file or filesystem on the disk to a consistent state.

Abstract: An apparatus and method are described for defining, maintaining and displaying a checkpoint result set to facilitate identification of desirable checkpoints during system recovery. The checkpoint result set may be mapped to a user-customizable namespace. The user customizes the namespace by selecting one or more characteristics of desirable file system checkpoints. Being able to customize the namespace in this manner enables the user to be provided a more streamlined checkpoint result set in the event of data corruption. As a result an appropriate checkpoint can be more quickly selected for use in recovery.

Abstract: In one embodiment, a processor comprises a first register file configured to store speculative register state, a second register file configured to store committed register state, a check circuit and a control unit. The first register file is protected by a first error protection scheme and the second register file is protected by a second error protection scheme. A check circuit is coupled to receive a value and corresponding one or more check bits read from the first register file to be committed to the second register file in response to the processor selecting a first instruction to be committed. The check circuit is configured to detect an error in the value responsive to the value and the check bits. Coupled to the check circuit, the control unit is configured to cause reexecution of the first instruction responsive to the error detected by the check circuit.

Abstract: A method and apparatus for detecting split brain in a distributed system is provided. After determining that a rogue instance is no longer an active member of the cluster, a recovery instance detects activity associated with a redo log that is updated by the rogue instance to store log records that describe changes made by the rogue instance to data associated with the cluster.

Abstract: A system and method communicates commands from a command originator to receiving devices, yet the receiving devices do not confirm receipt of the command. The most current command (e.g. the one with the highest sequence number) is rebroadcast by the command originator and the receiving devices, tending to be more frequent upon detection of an event indicating that the most current command was not received by at least one other device, and less frequently upon detection of an event indicating that the most current command was provided with sufficient duplication that if another device could receive it, the device likely did receive it, subject to a maximum and minimum rate.

Abstract: A method and apparatus for providing an undoable programming language. More specifically the present invention relates to providing a fully undoable programming language, where the language includes a fully undoable core language portion and a conventional language portion. In an embodiment of the present invention, a method of encoding a general-purpose undoable programming language to enable fully undoable instructions includes encoding a fully undoable core imperative language portion having a plurality of undoable core instructions, each of the plurality of undoable core instructions to perform at least one undoable operation upon execution, and the at least one undoable operation being fully undoable until final termination of a program written using any of the plurality of undoable core instructions.

Abstract: A method to enable an adaptive fault tolerance in a data system is provided. The method includes communicatively coupling a radiation hardened hardware element to at least one interrupt service routine application in a respective at least one processing element, triggering an interrupt service routine by an interrupt signal received from the radiation hardened hardware element at the interrupt service routine application after an execution of a code block by the at least one processing element, and inspecting the internal state of the at least one processing element to determine if an error occurred.

Abstract: A compressed replay buffer in a first electronic unit of an electronic system holds commands in a table. As commands are transmitted from the first electronic unit to a second electronic unit, the command, along with associated data, command type, and the like are stored in a row in the table. No rows in the table contain “dead cycles” to indicate that no command was sent on a particular cycle on a bus over which the commands were transmitted. The second electronic unit may request that the first electronic unit replay some number of commands. In response, the first electronic unit uses commands in the compressed replay buffer, along with required timings stored on the first electronic unit, to replay the number of commands requested.

Abstract: Provided are a method, system and program for batching transactions to apply to a database. A transaction manager receives a plurality of transactions to apply to a database and adds the transactions to a work queue. One of a plurality of agents processes a batch of transactions from the work queue. Each agent executes a batch of transactions from the work queue against the database independent of the operations of other of the agents executing batches of transactions. The agent applies the transactions in the batch against the database and commits the transactions in the batch to the database in response to completing all of the transactions.

Abstract: A method including receiving a request from another device to provide television content; sending a response that includes the television content; storing state information associated with the television content, wherein the state information includes an identifier of the other device and an identifier of the television content provided; detecting when an error occurs between the device and the other device; and resending a last television content that was successfully received by the other device before the error occurred.

Abstract: A method for accurately tracking fault status in a computer system. The method includes storing a prior state for a sensor associated with a component of the computer system and receiving a sensor reading. When the prior state indicates the sensor was unavailable or unreadable such as when the component was removed, the method includes resending or re-emitting a faulty event to the fault diagnosing module, e.g., after reinsertion of the component in the computer system while it is still faulty. The method may include, prior to the triggering of the resending of the faulty event, determining that the sensor is in a non-nominal state. The method may also include storing in the data storage a definition of a nominal state for the sensor such that the determining the sensor is in the non-nominal state includes comparing one or more sensor readings with the nominal state definition.

Abstract: A method, system, computer system, and computer-readable medium that enable quick recovery from failure of one or more nodes, applications, and/or communication links in a distributed computing environment, such as a cluster. Recovery is facilitated by regularly saving persistent images of the in-memory checkpoint data and/or of distributed shared memory segments. The persistent checkpoint images are written asynchronously so that applications can continue to write data even during creation and/or updating the persistent image and with minimal effect on application performance. Furthermore, multiple updater nodes can simultaneously update the persistent checkpoint image using normal synchronization operations. When one or more nodes fail, the persistent checkpoint image can be read and used to restart the application in the most recently-saved state prior to the failure.

Abstract: The invention is directed to a computer system comprising a server and a client and a method for operating a remote procedure call handler in the client and the server. The Method for operating a remote procedure call handler in the client according to the invention comprises the following steps: a) sending a collected call message comprising a number of call messages to the server, b) receiving an error message indicating a successful or erroneous transmission of the call messages comprised by the collected call message, wherein the error message indicates an erroneous transmission of at least one call message, wherein said at least one erroneous transmitted call message is retransmitted by the step of c) sending a further collected call message comprising said erroneous transmitted call message as well as a plurality of further call messages.

Abstract: A method of controlling a mobile terminal, method including performing, via a controller on the mobile terminal, data synchronizations with at least one external device, displaying, via a display on the mobile terminal, a list of data synchronization history corresponding to the performed data synchronizations, determining, via the controller, whether or not a particular data synchronization from the list includes an error, undoing, via the controller, the particular data synchronization to a state prior to the particular data synchronization, if it is determined that the particular data synchronization includes the error, and re-performing, via the controller, the particular data synchronization using data corresponding to the undone particular data synchronization.

Abstract: A processing system for assisting computer programs running in a distributed computer system is disclosed, the processing system including: a detector for detecting that a running program has encountered a problem caused by not having direct access to another piece of code; a requisitioner for obtaining the other piece of code from another part of the system; and a controller for controlling the computer to re-run the program from a point before the problem was encountered, in such a way that it has the necessary direct access to the other piece of code.

Abstract: In one embodiment, the present invention includes a method for selecting a first transaction execution mode to begin a first transaction in a unbounded transactional memory (UTM) system having a plurality of transaction execution modes. These transaction execution modes include hardware modes to execute within a cache memory of a processor, a hardware assisted mode to execute using transactional hardware of the processor and a software buffer, and a software transactional memory (STM) mode to execute without the transactional hardware. The first transaction execution mode can be selected to be a highest performant of the hardware modes if no pending transaction is executing in the STM mode, otherwise a lower performant mode can be selected. Other embodiments are described and claimed.

Abstract: A method for replicating a volume of data including selecting a target storage box to receive a physical copy of the actual volume of data stored on the source storage box for replication of the actual volume of data, selecting a point in time storage box to receive a physical copy of actual data stored on the target storage box, physically copying actual data stored on the target storage box to the point in time storage box, performing the replication of the actual volume of data by initiating the physical copying on the target storage box of the actual volume of data, and selectively undoing the physical copying on the target storage box of the actual volume of data by replacing the current actual data stored on the target storage box with the physical copy of actual target storage box data stored on the point in time storage box.

Abstract: This method is an error correction method such that, when an error is detected in a CPU with pipeline structure, a content of a register file is restored by a delayed register file which holds an execute completion state of an [Instruction N] correctly executed before this error, and a rollback control that re-executes an instruction from the [Instruction N+1] which is the next instruction of the [Instruction N] is performed. The method collects a parity check result of arbitrary Flip-Flops existing inside the CPU, and detects an error. As a result, the content of the register file is restored into the instruction execute completion state preceding to the instruction range likely to malfunction by the error, and the instruction can be roll backed from the beginning of the instruction range likely having malfunctioned by the error.

Abstract: A system and method can support a compensation work. The system includes one or more compensation functions that use a process state to realize the compensation work associated with a forward work, wherein the compensation work is executed at a different runtime from an execution time of the forward work, and wherein the process state contains data needed to execute the compensation work. The system also includes a process execution engine that can dynamically manage process state to make the state available to the compensation functions. The process state is retrieved based on a closure data structure that holds an expression and an environment of variable bindings, in which the expression is to be evaluated.

Abstract: Providing homogeneous recovery in a redundant memory system that includes a memory controller, a plurality of memory channels in communication with the memory controller, an error detection code mechanism configured for detecting a failing memory channel, and an error recovery mechanism. The error recovery mechanism is configured for receiving notification of the failing memory channel, for blocking off new operations from starting on the memory channels, for completing any pending operations on the memory channels, for performing a recovery operation on the memory channels and for starting the new operations on at least a first subset of the memory channels. The memory system is capable of operating with the first subset of the memory channels.

Abstract: Error handling in the intermediation of one-way transacted messages. Rather than receiving an inbound message under a transaction, the intermediary performs a non-destructive exclusive read of the message from the source outside of a transaction. Routing logic is applied against the content of the message to determine a collection of message consumers to which a copy of the inbound message is to be sent. Then, under a transaction, the copy of the message is attempted to be sent to each destination. If a send of the copy fails, the transaction is rolled back, but the failure is recorded such that the same transmission mechanism is not, or is less likely to be, tried again in subsequent attempts. The principles may apply to a single message to be sent under the transaction, or to multiple messages to be sent under a single transaction.

Abstract: A recording apparatus includes a server, a client, a virtual device, a judgment section, and a regeneration section. The server executes an access to a storage medium as a service. The client includes processes that require the service. The virtual device is used to perform communication between the server and the client using a socket. The judgment section judges, when a process of the client opens the virtual device, whether the virtual device is already opened. The regeneration section regenerates, when the virtual device is already opened, a file descriptor for the process that references the socket based on an existing kernel file table.

Abstract: The re-encryption of data can be performed with independent cryptographic agents that can automatically encrypt and decrypt data in accordance with cryptographic regions, such that data within a single cryptographic region is encrypted and decrypted with the same cryptographic key. An “in-place” re-encryption can be performed by reading data from a chunk in an existing cryptographic region, shrinking the existing cryptographic region past the chunk, expanding a replacement cryptographic region over the chunk, and then writing the data back to the same location, which is now part of the replacement cryptographic region. An “out-of-place” re-encryption can be performed by reading data from a chunk in an existing cryptographic region and then writing the data back to a location immediately adjacent that is part of a replacement cryptographic region. After the re-encrypted data is “shifted”, the cryptographic regions can be expanded and contracted appropriately, and another chunk can be selected.

Abstract: A file storage system that uses a server to communicate between a client and a storage system. The server receives a file storage request pertaining to a file, generates and stores a file record for the request and forwards the request to a file storage system. The server performs either an internal retry or forwards a no-file response from the storage system to the client computer in response to receiving a no-file file status from the storage system depending on an amount of elapsed time from the time the server initially receives the file storage request.

Abstract: The subject matter disclosed herein provides methods and apparatus, including computer program products for handing transactions. The method may include, for example, processing, at a state correlation engine, a plurality of transactions; saving the effects of at least one of the transactions to a persistence, when the at least one transaction includes a reliable interaction with an external application; saving other transactions to a buffer rather than to the persistence; and reading the at least one transaction from the persistence and continuously executing rules representing the other transactions in response to a failure causing a recovery. Related systems, apparatus, methods, and/or articles are also described.

Abstract: Methods and devices are provided where when an online parameter change is requested a data transfer unit is stopped, a parameter change is communicated and the data transfer unit is started with changed parameters to generate new data transfer units.

Abstract: Methods and systems are disclosed to generate a data map for a data storage device. A data map may be generated by scanning, during a power-on initialization process, data units of data stored on a data storage medium of a data storage device. The scanning may start from a selected data unit and proceed through the data units in an order opposite to a write order to identify a first data unit that is not fully erased. Also. an error recovery status of the first data unit may be determined based on an error correction code. A likely erased status of the first data unit may be assigned when the determined error recovery status is unrecoverable.

Abstract: On or more techniques and/or systems are provided for rapidly resuming processing of client requests after a system failure event. Accordingly, during a boot-up process, a storage system, upon detecting a system failure event of the storage system, conditions its system memory to reflect a state of the system memory at a time of the failure by processing client requests or commands stored in a non-volatile operations log. The storage system can resume processing client requests after processing the operations in the nonvolatile operations log and prior to flushing data to storage devices.

Abstract: A flash memory system includes a flash controller for controlling operation of at least two flash memory devices. A page buffer is allocated within each flash memory device, such that one page buffer functions as a designated target buffer and another page buffer functions as a mirror buffer. The flash controller transmits the page data to two flash memory devices simultaneously, such that no backup of the page data is required to be kept in the flash controller. Hence, there is no delay in writing the next page data from a host computer to the flash controller.

Abstract: Leaked memory in a computer system is detected and recovered by first detecting memory leakage within the computer system based on nonlinear and non-parametric time-series regression analysis of software telemetry data generated by one or more software process running on the computer system. If existence of memory leakage is detected, then memory that has leaked is specifically identified and recovered. This is done by halting one or more of the software processes, generating a core image file or files of the halted software process(es), and re-starting the halted process or processes without waiting for analysis of the core image file(s). Then, the core image file is evaluated to specifically identify leaked memory in the computer system based on the core image file. Finally, the identified leaked memory is recovered.