Abstract: A method of rebuilding a replacement drive used in a RAID group of drives is disclosed. The rebuilding method includes tracking data modification operations continuously during use of the drives. The method also includes saving the tracked data modifications to a log in a persistent storage, where the tracked data modifications are associated with stripe data present on the drives. Then, rebuilding a failed one of the drives with a replacement drive. The rebuilding is facilitated by referencing the log from the persistent storage, and the log facilitating reading only portions of stripe data from surviving drives and omitting reading of portions from the drives where no data was written. Thus, the rebuilding only rebuilds the stripe data to the replacement drive. Also provided is a zoning method, which enables logical zone creation from storage area networks.

Abstract: A system and method in a data processing system for recovering data in a file system. A request to modify a data block in the file system is detected. In response to detecting the request to modify the data block, metadata describing the data block in the file system is written in a log. In response to detecting an error during the writing of the metadata, an error counter is incremented. Finally, in response to a request to recover the data in the file system, the metadata is read only if the error counter is less than or equal to a predetermined value.

Abstract: A method is provided for the recovery of an instance of a job manager running on one of a plurality of nodes used to execute the processing elements associated with jobs that are executed within a cooperative data stream processing system. The states of the processing elements are checkpointed to a persistence mechanism in communication with the job manager. From the checkpointed processing element states, the state of each distributed job is determined and checkpointed. Processing element states are also checkpointed locally to the nodes one which the processing elements are running. Following a failure of the job manager, the job manager is reinstantiated on one of the nodes. The recovery instance of the job manger obtains state data for processing elements and jobs from the persistence mechanism and constructs an initial state for jobs and processing elements. These initial states are reconciled against the current states of the processing elements and adjustments are made accordingly.

Abstract: A related data storing unit stores a plurality of sets of related data related to a plurality of controlling units. An operation storing unit stores operation detail of each of the plurality of controlling units as an operation log. A identification data recording unit records a plurality of sets of identification data in the operation log. An abnormality data recording unit records abnormality data in the operation log. A data acquiring unit acquires an abnormality data and one of the identification data. A related data acquiring unit identifies one of the related data corresponding to the one of identification data acquired by the data acquiring unit and acquires the one of related data from the related data storing unit. A resolution data storing unit stores first resolution data to resolve the abnormality occurring in the one of control targets in association with the one of related data acquired by the related data acquiring unit and the abnormality data acquired by the data acquiring unit.

Abstract: A DBMS performs a checkpoint process for maintaining consistency of data. A snapshot acquisition control program detects the checkpoint process externally to the DBMS and creates a snapshot in an external storage according to the timing of the checkpoint. Correspondence between checkpoints and snapshots is maintained in a CP-SH correspondence management table to make it possible to restore in a short time data at the time of an arbitrary checkpoint.

Abstract: A technique enables creation and use of a writable, read-only snapshot of an active file system operating on a storage system, such as a multi-protocol storage appliance. The writable, read-only snapshot comprises a read-only “image” (file) residing in a snapshot and a writable virtual disk (vdisk) residing in the active file system. The writable vdisk is a “shadow” image of the snapshot file image and, as such, includes an attribute that specifies the snapshot file as a backing store.

Abstract: A data processing system includes at least a first storage system, a second storage system and a third storage system. The third storage system maintains a replication of data stored in the first storage system. When updating data in the first storage system, the first storage system updates the replication of data stored in the third storage system and creates a journal. The journal is formed from a copy of data used for update and update information such as a write command for update, etc. The second storage system also maintains a replication of data stored in the first storage system. The second storage system obtains the journal, and updates data stored therein corresponding to data stored in the first storage system in the order of data update performed in the first storage system. When updating data stored in the third storage system corresponding to data stored in the first storage system, the third storage system creates a journal using data update numbers created in the first storage system.

Abstract: A technique for restoring data after suspension of a communications link between two storage systems is disclosed. Upon suspension of the link, an image of the data at the first and second locations is created in a secure location. While the link is down, updates to the data at each of the first and second locations are maintained separately. Upon reestablishment of a communications link, the two locations are again synchronized.

Abstract: To provide a computer system capable of detecting a failure at an early stage while keeping down an increase in I/O load due to failure monitoring. The computer system includes plural storage systems connected in stages between a first computer and a second computer. The first computer sends control I/O to the storage systems. The second computer monitors control I/O transferred through the storage systems; and when there is control I/O that has not been transferred successfully, requests state information of the storage systems to transfer the control I/O.

Abstract: A method for providing data integrity of a database system. A standby database is selected to replace a failed primary database. At least one redo log file having at least one data transaction is selected to be applied to the selected standby database. The selected standby database is updated with the data transaction from the selected redo log file if an identification code in the redo log file matches an identification code in the standby database.

Abstract: A storage system have a plurality of control modules which control a plurality of disk storage devices. In order to read/write system information even when problems arise in paths with the plurality of disk devices, and moreover to output log data even upon occurrence of an abnormality in the control module, a plurality of control modules which control a plurality of disk storage devices, each have a built-in system disk device unit which stores log data. In equalization processing, log data of one control module is stored in a system disk of another installed control module. Even when an abnormality occurs in the one control module, log data of the one control module can be output by the other control module.

Abstract: A method and apparatus for a template based parallel checkpoint save for a massively parallel super computer system using a parallel variation of the rsync protocol, and network broadcast. In preferred embodiments, the checkpoint data for each node is compared to a template checkpoint file that resides in the storage and that was previously produced. Embodiments herein greatly decrease the amount of data that must be transmitted and stored for faster checkpointing and increased efficiency of the computer system. Embodiments are directed to a parallel computer system with nodes arranged in a cluster with a high speed interconnect that can perform broadcast communication. The checkpoint contains a set of actual small data blocks with their corresponding checksums from all nodes in the system. The data blocks may be compressed using conventional non-lossy data compression algorithms to further reduce the overall checkpoint size.

Abstract: A data preservation system for flash memory systems with a host system, the flash memory system receiving a host system power supply and energizing an auxiliary energy store therewith and communicating with the host system via an interface bus, wherein, upon loss of the host system power supply, the flash memory system actively isolates the connection to the host system power supply and isolates the interface bus and employs the supplemental energy store to continue write operations to flash memory.

Abstract: A multiple computer system incorporating redundancy is disclosed. Data to be stored (A, B, C) is distributed (A1, A2, A3, . . . B1, B2, B3, . . . C1, C2, C3, . . . ) amongst a multiplicity of computers (M1, M2, . . . Mn). A parity form (P[A], P[B], . . . ) of the stored data is created by use of a reversible encoding process. The parity form data is preferably cycled amongst the various computers. In the event of failure of one of the computers the lost data can be re-generated.

Abstract: A storage system maintains a journal and a snapshot of one or more data volumes. Two journal entry types are maintained, an AFTER journal entry and a BEFORE journal entry. Two modes of data recovery are provided: “fast” recovery and “undo-able” recovery. A combination of both recovery modes allows the user to quickly recover a targeted data state.

Abstract: A method and system for tracing and logging for a software module is provided. The method includes the steps of detecting at least one error and analyzing at least one error message corresponding to each detected error. The method further includes the step of monitoring the resources of a computer system. Further, the method includes the step of adjusting (e.g., automatically adjusting) a tracing and logging level, based on the analysis of the error messages and the availability of resources.

Abstract: Maintaining logically consistent backups using minimal data transfer. A backup, or snapshot, copy of original data is created and stored. A user designates data blocks that are to be backed up in a process of creating a subsequent snapshot copy of the data. Data blocks that are to be backed up might include those associated with active files having data of interest to the user. Data blocks that are not desired for backup might include, for example, swap files, printer buffers and temp files. The changes that have been made to the data blocks that have been designated for backup are applied to the snapshot copy after a specified time period has elapsed. Since only desired data blocks are backed up to the snapshot copy, memory, processing cycles and communication bandwidth are used more efficiently than if all data blocks were to be backed up to the snapshot copy.

Abstract: A storage system with an array of redundant storage devices places bounds on access request servicing. If a storage device is unable to service the access request within the bounds, the storage system temporarily, individually offlines the specific storage device. Access requests pending for the storage device may be serviced by other storage devices of the redundant array while the storage device is offline. The offline storage device can perform error recovery and be brought back online by the system when error recovery has completed.

Abstract: The present invention provides improved techniques for managing storage resources, such as disk drives, I/O ports, and the like in a network based storage system according to a user position within the network. Embodiments according to the present invention can provide a relatively high performance storage access environment for the mobile users moving around a wide area. For example, in one applicable environment, there are several data centers in the wide area, and each data center has a local storage system that is connected to the other storage systems through a network. Copies of a user's volume can be made in some of the storage systems. A remote copy function is utilized for making real time copies of the user's volume.

Abstract: The data up to a point of time whereat failure has occurred will be restored at high speed at a remote site without imposing any burden on a host. The first storage system on the master side processes an I/O request from the host, and as a result of I/O processing to the second storage system on the remote side, transmits the update data. The second storage system retains data received from the first storage system as update log data. The host transmits a command for settling a state of an application to the first storage system as data, and the first storage system transmits the data to the second storage system. The host and the second storage system both retain an identifier corresponding to the command, and relate the identifier to the log data. Thereby, the host designates the identifier at any given time, whereby the second storage system restores the data at any given time.

Abstract: In one embodiment, a computer accessible medium stores a plurality of instructions including instructions which, when executed: track dependencies among a plurality of assets; and responsive to an identification of an asset for potential recovery (the “selected asset”), identify an asset dependency set corresponding to the selected asset. The asset dependency set comprises at least a subset of the plurality of assets, wherein each asset in the subset has a dependency with the selected asset. In some embodiments, one or more of the following may be provided: tracking asset dependencies and presenting the asset dependency set to the user; pruning the asset dependency set to a recovery set identifying the asset dependency set; generating the recovery order (optionally optimized); initiating the recovery according to the recovery order; performing recovery steps; generating the recovery plan and/or executing recovery plans.

Abstract: A method for recovering errors on a multiple disk system. The method including the steps of (a) determining a location and type for one or more errors in a plurality of blocks on the multiple disk system, (B) determining a current error of the one or more errors that is closest to a start of the plurality of blocks, (C) recovering data for the current error using data read from drives other than the drive containing the current error and (D) determining whether any further errors are present on the drive that contained the current error.

Abstract: In one embodiment, a method is contemplated. The method includes creating a copy of a volume, wherein the copy corresponds to a first point in time. Write operations to the volume are logged separate from the volume. The method also includes recovering a state of the volume to a second point in time subsequent to the first point in time using the copy of the volume from the first point in time and at least a subset of the write operations from the log. The subset of write operations occurs subsequent to the first point in time and prior to the second point in time. In some embodiments, an end marker may be included in the log, and recovery to a write operation that is indicated as the end of a transaction (by the end marker) may be performed.

Abstract: Described is a revert preview mechanism, which gives the user a chance to temporarily remount a storage volume with the contents of a shadow copy, and then evaluate the computer system as if reverted, including allowing full I/O read and write operations to the storage volume. A temporary storage location is provided to cache data writes. Read requests are read back from the temporary storage location if the corresponding volume location has been written, or are read back from the shadow copy of the volume if not written since the revert preview operation began. In the case of a revert preview of the boot volume, an API is used to specify a correct shadow copy instance of the system registry hive, which needs to be loaded following reboot, but before the shadow copy driver is loaded. Use of the API loads the correct instance on the next reboot.

Abstract: A method and system for ordering and aggregating log streams. Log streams for events from different sources are received. If different sources have different recording cycles, or time epochs, that lead to different temporal granularities, then all of the log streams are combined into a single time epoch that is equal to the longest time epoch. Log streams from sources having shorter time epochs continue to retain information about their original time epochs, in order to retain information about the order of the events in those log streams. The log streams are re-ordered, both before and after being integrated into the aggregate log, by acquiring additional data from the different sources, thus permitting the likely cause/effect relationship between events.

Abstract: An error-handling framework is provided for business process transactions. The error-handling framework facilitates coordination of the invocation of exception and compensation handlers in response to errors. The error-handling framework includes support for custom ordering of compensation actions, data flow into and out of compensation actions, and management of the process state visible to compensation actions.

Abstract: A method and an apparatus to perform fast log replay have been disclosed. In one embodiment, the method includes preloading a buffer with data based on a catalog in response to a failure of a storage server and replaying a log as the buffer is being preloaded, wherein replaying the log comprises re-executing a set of modifying operations previously logged in a local non-volatile storage device in the storage server using the data preloaded.

Abstract: Restoration of data is facilitated in the storage system by combining data snapshots made by the storage system itself with data recovered by application programs or operating system programs. This results in snapshots which can incorporate crash recovery features incorporated in application or operating system software in addition to the usual data image provided by the storage subsystem.

Abstract: This invention is a system and method for managing recovery following failure in a data storage environment. Program logic is configured for carrying out such method steps and encoded on a computer readable medium.

Abstract: A distributed software application comprises a plurality of software components within a plurality of executables. A manager component for the distributed software application performs a recovery of two or more software components, of the plurality of software components, in an ordered sequence based on one or more dependency relationships among the plurality of software components.

Abstract: An efficient technique for performing remote asynchronous mirroring includes receiving a stream of command requests, performing the requested commands, relaying the requested commands to a target while embedding an explicitly-defined or implied task precedence graph in the relayed commands to enable increased concurrency in tasks performed by the target.

Abstract: A method and apparatus for operating a storage system is disclosed. A root node has a first pointers to a plurality of lower nodes, the lower nodes having reference through a plurality of second pointers to point to blocks of persistent storage, the blocks of persistent storage storing data of the storage system. A persistent consistency point of the storage system is created at a selected time, the persistent consistency point created by creating a partial consistency point for one or more of the first pointers and second pointers to selected blocks of data. A statutes indicator is set to indicate that an identified partial consistency point is completed. All partial consistency points are coalesced into a final completed consistency point for the selected time after all of the partial consistency points reach a status of completed.

Abstract: A method, apparatus, system, and signal-bearing medium that in an embodiment determine whether to log an exception based on whether the exception has already occurred. In an embodiment, exceptions that repeatedly occur at the same source and location within the source are logged on the first occurrence, and not logged thereafter. In this way, data can be saved about the exception, yet system resources are not consumed by repeated logging.

Abstract: An architecture and implementation for losslessly restarting subsystems in a distributed file system is described. By partitioning functionality and logging appropriately across the kernel and user-level boundaries on a client, the user-level subsystem may be made losslessly restartable. Practical mechanisms for supporting state-based recovery in replicated state machines and like replica are described. In particular, each client daemon may include an operations log and an applied log sequence number. Each client driver may include a potentially different operations log. Each client daemon may be configured to request logged operations associated with log sequence numbers in one or more ranges specified by a specification that includes the applied log sequence number. The requested logged operations may reside in the operations log maintained by a client driver.

Abstract: A method and apparatus for data backup is disclosed in which prior to actually performing a backup operation from a subscriber computer, the backup server device checks a specified server to determine if parts of the subscriber data to be backed up can be backed up or replicated from data on the specified server. If it can, the backup server uses that specified server to create a backup of the subscriber data to be backed up. If it cannot, then the data is backed up from the subscriber computer.

Abstract: An apparatus, system, and method are disclosed for automatically backing up a dynamically created resource group. One embodiment of the apparatus includes an event module, a resource group module, and a backup module. The event module receives an event notification of an unanticipated system event, such as a system failure or similar event. The resource group module dynamically creates a resource group made up of resources (files, directories, applications, databases, etc.) in response to the event notification. The resource group may be created based on which resources are within a specified classification and have a timestamp within a specified time range. The backup module initiates a backup operation to copy the resource group to a backup location. The backup module backs up as much of the resource group as possible within the time between the resource group creation and the time that the system may become unavailable.

Abstract: Various embodiments of systems and methods for preserving saved memory states to which a computer system can be restored are disclosed. In certain embodiments, the systems and methods intercept write operations to protected memory locations and redirect them to alternate memory locations. Embodiments of the systems and methods include creation of a table for each memory state. Certain embodiments additionally include a recovery capability, by which the protected memory in the computer system is capable of being restored or recovered to a recovery point that represents a saved memory state. Further embodiments relate to systems and methods for preventing protected memory locations from being overwritten that utilize a plurality of memory state values.

Abstract: In some embodiments, a computer accessible medium comprises a plurality of instructions which, when executed: cause a modification of an image of files created from a computer system having first hardware; and cause the image to be copied to a computer system having second hardware different from the first hardware. A difference between the first hardware and the second hardware necessitates that the modification of the image be performed. For example, the difference may indicate that a different device driver is to be included in the image, or that HAL or kernel code is to be changed. A similar method of modifying the image and copying the image is also contemplated.

Abstract: A method and mechanism for modifying computing resources in response to application behavior. A computing system includes a replication component configured to replicate data storage from a first data volume to a second data volume. In addition, the replication component is configured to monitor application I/O characteristics and store related statistics. I/O characteristics may include size, concurrency, locality, and frequency. I/O characteristics which are stored, and guidelines for modifying system resources based on those characteristics, may be displayed for use by an administrator in tuning system resources. Periodically, or in response to detecting an event, the replication component may automatically access the statistics and modify the system resources used by the replication system to better accommodate the application's behavior.

Abstract: A DBMS performs a checkpoint process for maintaining consistency of data. A snapshot acquisition control program detects the checkpoint process externally to the DBMS and creates a snapshot in an external storage according to the timing of the checkpoint. Correspondence between checkpoints and snapshots is maintained in a CP-SH correspondence management table to make it possible to restore in a short time data at the time of an arbitrary checkpoint.

Abstract: In a data processing system Saving a primary site and a secondary site, storage systems are connected to each other via a communication line, data update history is recorded in a storage device as a journal in the primary site, and the journal is transferred to the secondary site via the communication line. During such transfer, loads will not concentrate to a specific volume, by switching the volume that stores the journal in the primary site, while, by switching the transfer-destination volume of the journal in the secondary site. With such arrangement, in a data processing system, it is possible to ensure data consistency in a plurality of sites and prevent the system throughput capacity from being deteriorated without applying loads to a host and a network, and without causing load concentration on a specific storage device that is caused as a result of data update or recovery operations.

Abstract: An electronic computing device including at least one processing unit that implements a specific fault signal upon experiencing an associated fault, a control unit that generates a specific recovery signal upon receiving the fault signal from the at least one processing unit, and at least one input memory unit. The recovery signal initiates specific recovery processes in the at least one processing unit. The input memory buffers input data signals input to the at least one processing unit that experienced the fault during the recovery period.

Abstract: A method and computer program product for error monitoring partitions in a computer system. Provided to each partition is a partition status indicator (PSI) denoting a RUNNING or FAIL status of the partition, and an error log area (ELA) for storing partition error entries. The ELA includes a partition identifier, an entry status indicator (ESI) indicating READ/UNREAD status for the error entry, and an error identifier. An error procedure performed for each first partition whose partition status indicator indicates the FAIL status includes: copying each error entry in the ELA of the first partition whose ESI indicates the UNREAD status into the ELA of a second (running) partition; setting the ESI to the READ status for each copied error entry in the ELA of the first partition; and having the ESI set to the UNREAD status for each copied error entry in the ELA of the second partition.

Abstract: A data storage facility for transferring data from a data altering apparatus, such as a production data processing site to a remote data receiving site. The data storage facility includes a first data store for recording each change in the data generated by the data altering apparatus. A register set records each change on a track-by-track basis. A second data store has first and second operating modes. During a first operating mode the second data store becomes a mirror of the first data store. During a second operating mode the second data store ceases to act as a mirror and becomes a source for a transfer of data to the data receiving site. Only information that has been altered, i.e., specific tracks that have been altered, are transferred during successive operations in the second operating mode. Commands from the local production site initiate the transfers between the first and second operating modes.

Abstract: In general, the invention facilitates diagnosing fault conditions, such as flapping, by permitting users to request information for specific components in a network device such as a router. The invention also facilitates the diagnosis of other fault conditions, including, but not limited to, excessive numbers of dropped packets, hard drive crashes, high temperature readings, and inactive interface cards. A user may obtain a targeted log containing information relating to selected fault conditions or other network device events, rather than a system log containing information relating to all network device events, some of which may not be of interest to the user. The targeted log may be parsed and analyzed with greater ease than the system log.

Abstract: An apparatus, as well as systems, methods, and articles can operate to record the address of write operations to a memory cached by a non-volatile cache prior to executing an operating system cache driver. In an embodiment, a non-volatile cache may be implemented by creating a device option read only memory (ROM), or modifying the associated computer basic input-output system (BIOS) to trap software interrupts associated with disk and other media access requests. Associated addresses, such as logical block addresses, can be stored in a log for data that is modified. The resulting log can be stored in a non-volatile medium, including the cache itself. If the available log space is not large enough to record all write activity prior to loading operating system drivers, a flag may be set to indicate the overrun condition.

Abstract: Techniques are provided for managing caches in a system with multiple caches that may contain different copies of the same data item. Specifically, techniques are provided for coordinating the write-to-disk operations performed on such data items to ensure that older versions of the data item are not written over newer versions, and to reduce the amount of processing required to recover after a failure. Various approaches are provided in which a master is used to coordinate with the multiple caches to cause a data item to be written to persistent storage. Techniques are also provided for managing checkpoints associated with the caches, where the checkpoints are used to determine the position at which to begin processing recovery logs in the event of a failure.

Abstract: Maintaining logically consistent backups using minimal data transfer. A backup, or snapshot, copy of original data is created and stored. A user designates data blocks that are to be backed up in a process of creating a subsequent snapshot copy of the data. Data blocks that are to be backed up might include those associated with active files having data of interest to the user. Data blocks that are not desired for backup might include, for example, swap files, printer buffers and temp files. The changes that have been made to the data blocks that have been designated for backup are applied to the snapshot copy after a specified time period has elapsed. Since only desired data blocks are backed up to the snapshot copy, memory, processing cycles and communication bandwidth are used more efficiently than if all data blocks were to be backed up to the snapshot copy.

Abstract: Minimal and maximal numbers are established defining two levels of retry attempts to read system information from a storage medium. Multiple copies of the system information are stored on the storage medium. Attempts are made to successively read the copies until either the system information is successfully read or the system information is not successfully read from any copy of the system information after the minimal number of attempts on each copy. If the system information is not successfully read, attempts are made to successively read the copies until either the system information is successfully read or the system information is not successfully read from any copy of the system information after the maximal number of attempts.

Abstract: A method, apparatus, and computer instructions for managing event information in a logical partitioned data processing system. A determination is made as to whether an event for a resource is present in a first event log in a first partition in response to reallocation of the resource from the first partition to a second partition. In response to the event being present, the event is placed in a second event log in the second partition. As a result, analysis of the second event log in the second partition takes into account the event from the first partition.