Abstract: Techniques are provided for implementing asynchronous checkpointing of in-memory data in a distributed computing system. For example, a method includes processing a stream of data records by an operator executing on a computing node, maintaining in a system memory, an operator state which is generated in response to the operator processing the stream of data records, and performing an asynchronous checkpointing process. The asynchronous checkpointing process includes enqueuing a checkpoint of the operator state in a first queue, wherein the first queue is maintained in the system memory, and executing a background worker thread to dequeue the checkpoint of the operator state from the first queue and store the checkpoint of the operator state in a data store. The operator continues with processing the stream of data records during the asynchronous checkpointing process.

Abstract: Functionality is disclosed for throughput and latency optimized volume initialization. Data blocks used for boot processes of multiple virtual machine (VM) instances are identified, for example, where the multiple VM instances are created from a specific VM image. A load order document is generated that identifies the data blocks, and also identifies an order in which the data blocks are used for the boot process. The identified data blocks are coalesced to generated a coalesced boot volume. Subsequently, each time a VM instance is created from the specific VM image, the coalesced boot volume (e.g., instead of the individual data blocks) is transmitted from a data store to the a block storage service in the order specified by the load order document. The block storage service exposes a storage volume to the VM instance that can be used to initialize the VM instance.

Abstract: A method and system for direct memory transfers between memory modules are described that includes sending a request to a first memory module and storing the data sent on a memory bus by the first memory module into a second memory module. The direct transfer of data between the first and second memory modules reduces power consumption and increases performance.

Abstract: The invention relates to a method for storing data, wherein the method, in order to store a file (101), comprises: —automatic generation (602) of a distribution schedule (416); —performance (604) of an error correction method, which is specified in the distribution schedule, for generating file fragments from the file by a user computer system; —sending (606) of an authorisation enquiry (420) for storing the file fragments in the memory services (SD2, SD4-SD6) identified in the distribution schedule from the user computer system to a file management server via a network; —in response to reception of the authorisation enquiry by the file management server, requesting (608, 424) of an authorisation token by the file management server from each of the memory services identified in the distribution schedule and forwarding (610) of the authorisation token (428) obtained in response to the request to the user computer system by the file management server; and —storage (612) of the generated file fragments in the st

Abstract: A system, method, and computer readable medium for hybrid kernel-mode and user-mode checkpointing of multi-process applications. The computer readable medium includes computer-executable instructions for execution by a processing system. A multi-process application runs on primary hosts and is checkpointed by a checkpointer comprised of a kernel-mode checkpointer module and one or more user-space interceptors providing barrier synchronization, checkpointing thread, resource flushing, and an application virtualization space. Checkpoints may be written to storage and the application restored from said stored checkpoint at a later time. Checkpointing is transparent to the application and requires no modification to the application, operating system, networking stack or libraries. In an alternate embodiment the kernel-mode checkpointer is built into the kernel.

Abstract: A system that implements a data storage service may store data on behalf of clients in multiple replicas on respective computing nodes. The system may employ an external service to select a master replica for a replica group. The master replica may service consistent read operations and/or write operations that are directed to the replica group (or to a data partition stored by the replica group). The master replica may employ a quorum based mechanism for performing replicated write operations, and a local lease mechanism for determining the replica authorized to perform consistent reads, even when the external service is unavailable. The master replica may propagate local leases to replica group members as replicated writes. If another replica assumes mastership for the replica group, it may not begin servicing consistent read operations that are directed to the replica group until the lease period for a current local lease expires.

Abstract: Described herein is a network device configured to determine and provide alerts of communication link failures across layers of a communication stack of the network device. The network device determines at a radio link layer of the communication stack that a communication link between the network device and a network has failed. The network device then alerts one or more components associated with another layer of the communication stack of the determination that the communication link has failed.

Abstract: A distributed storage network (DSN) stores encoded data slices in storage units based on DSN address ranges. A rebuilding module selects a range of addresses for potential rebuilding activities. A rebuilding activity capacity level for the address range is determined, and using that information a maximum number of rebuilding modules to be assigned to the selected address range is determined. Distributed agreement protocol (DAP) function weights of the plurality of potential rebuilding modules are determined, and those weights are used by the DAP function to produce a rank ordered list of rebuilding module identifiers. Top ranked rebuilding modules are selected for use in rebuilding activities within the selected address range.

Abstract: In one example, mapping information corresponding to a container running on a private data center may be generated in a public cloud by a processor-based disaster recovery manager. Further, volume data associated with the container may be synchronized to the public cloud based on the mapping information by the disaster recovery manager. Furthermore, a failure of the container running on the private data center may be determined by the disaster recovery manager. In response to the failure of the container running on the private data center, the container may be deployed in the public cloud using the synchronized volume data and the mapping information by the disaster recovery manager.

Abstract: In one embodiment, a system includes a processor and logic integrated with and/or executable by the processor, the logic being configured to cause the processor to: collect, by the processor, workload information for a computing/storage device for a present time period and one or more previous time periods; determine, by the processor, a maximum workload parameter for the present time period and the one or more previous time periods; determine, by the processor, a maximum workload threshold that corresponds to the maximum workload parameter; compute, by the processor, a difference between the maximum workload threshold and the maximum workload parameter; and determine, by the processor, an amount of workload to move to the computing/storage device based on the difference. Other methods and computer program products are presented in additional embodiments.

Abstract: In a virtualized computer system, guest memory pages are mapped to disk blocks that contain identical contents and the mapping is used to improve management processes performed on virtual machines, such as live migration and snapshots. These processes are performed with less data being transferred because the mapping data of those guest memory pages that have identical content stored on disk are transmitted instead of the their contents. As a result, live migration and snapshots can be carried out more quickly. The mapping of the guest memory pages to disk blocks can also be used to optimize other tasks, such as page swaps and memory error corrections.

Abstract: A system determines a topology of a distributed system and determines, based on the topology, one or more injection points in the distributed system to inject failure scenarios. Each failure scenario including one or more faults and parameters for each of the faults. The system prioritizes the failure scenarios and injects a failure scenario from the prioritized failure scenarios into the distributed system via the one or more injection points. The system determines whether the injected failure scenario causes a response of the distributed system to fall below a predetermined level. The system determines resiliency of the distributed system to one or more faults in the injected failure scenario based on whether the injected failure scenario causes the response of the distributed system to fall below the predetermined level.

Abstract: Storage device groups are formed with respect to data consistency policies and/or quantified probabilities. A method embodiment commences upon identifying a computing system having a plurality of storage devices that are accessed by a plurality of computing nodes. A user interface serves for collecting policies, data loss parameters, and data rebuild parameters. Based on the policies and/or values of the data loss parameters, and values of the data rebuild parameters, sets of storage device groups are formed to achieve particular data loss and rebuild time properties. Data storage containers such as files or virtual disks that hold persistent datasets are assigned to respective storage device groups that are appropriate to the nature of the dataset. The objective pertaining to an acceptable likelihood of data loss as well as the objective of an acceptable time for rebuild are achieved as a result of assignments of certain storage devices into a group.

Abstract: A software and hardware facility persistently maintains metrics on directories at different levels within a tree of a filesystem. The facility hierarchically aggregates attributes of files contained by directories and stores them as metric values in each directory within a tree. The stored values represent summed or otherwise aggregated data from the descendant directories and files. The metric values represent aggregated attributes such as total space consumed by a directory and all the descendant directories and files, total number of files within a directory, total data blocks used by a directory and its descendant directories and data files, etc.

Abstract: Generally described, one or more aspects of the present application correspond to a highly distributed replica of a volume stored in a networked elastic computing environment. First and second replicas of the volume can be synchronously replicated, and some implementations of the tertiary replica can be asynchronously replicated. The highly distributed nature of the tertiary replica supports parallel data transfer of the data of the volume, resulting in faster creation of backups and new copies of the volume.

Abstract: A storage device including a first memory that stores a plurality of pieces of data a second memory that stores first state information indicating a state of update of the plurality of pieces of data, and a processor coupled to the first memory and the second memory and the processor configured to receive a update request for the plurality of pieces of data stored in the first memory, update a part of the plurality of pieces of data corresponding to the update request in response to an update of a second storage device coupled to the storage device, and update the first state information in response to the update of the plurality of pieces of data.

Abstract: The present disclosure relates to a method and system for determining automation sequences for resolution of an incident ticket by an automation system. The automation system retrieves data associated with plurality of incident tickets received from a ticketing system during predefined time duration and groups the plurality of incident tickets into one or more clusters based on the data. The automation system receives a plurality of user actions associated with the plurality of incident tickets performed across a plurality of user devices and identifies similarity among sequences of the plurality of user actions for each ticket cluster. Based on the similarity, the automation system groups the sequences of the plurality of user actions into one or more bucket and determines automation sequences for resolution of the incident ticket by correlating the data associated with plurality of incident tickets with one or more buckets of the sequences.

Abstract: Secondary nodes may detect failover operations for applications performing at a primary node. Application state indications may be collected at a primary node and reported to a monitor for the primary node. A secondary node may obtain the state indications from the monitor in order to evaluate whether the application is performing correctly at the primary and if not, trigger a failover operation to switch performance of the application to the secondary node. In some embodiments, the state information may be encoded into a single metric that can be obtained by the secondary node and evaluated to detect failover events.

Abstract: Provided is an electronic apparatus for which an increase in cost due to an increase in the size of the electronic device and an increase in the number of parts is suppressed. A system-control unit manages each of the partitions of a HDD and a SSD (storage device) that has a smaller storage capacity than the HDD by a mounting process. When it becomes impossible to read data from or write data to any one of the partitions, the system-control unit moves data of the other partitions to the SSD (storage device). Moreover, the system-control unit, together with disconnecting the disabled partition, replaces the disabled partition with the partition to which the data is moved.

Abstract: Techniques disclosed herein provide an approach for creating snapshots and reverting to the same for virtual machine (VM) guest operating systems (OSes). In one embodiment, a snapshot module in a guest OS receives blocks for a snapshot of a guest OS volume. In turn, the snapshot module creates a snapshot file in a repository external to a virtual disk of the VM, and writes the received blocks to the external repository. By storing snapshot content outside the virtual disks of VMs, disk space limitations in local VM disks can be overcome, and it is also more difficult for malicious software to modify the snapshots and infect them. To reduce storage space requirements, snapshots stored in the external repository may be deduplicated with other snapshots stored therein, including snapshots from guest OSes running in other VMs and/or a host OS on which a hosted hypervisor runs.

Abstract: The present disclosure provides a mobile game data processing method and apparatus. The method includes: acquiring a target running state, currently triggered for execution, of a mobile game; searching at least one to-be-processed data operation involved in the target running state; and determining, when the at least one to-be-processed data operation has a to-be-processed data operation of a non-transmission type, the to-be-processed data operation of a non-transmission type as a first data operation, and executing the first data operation at a local client of the mobile game; wherein the first data operation includes an operation of displaying interface association information, the interface association information including at least one of progress information, associated animation information, and operation result information. Thus, a waste of network bandwidths can be avoided during a mobile game, to improve network smoothness of the mobile game.

Abstract: Featured are a method and apparatus for managing various point-in-time copies of workloads or applications using a software system called workload manager. An aspect of the invention is to receive backup images of point-in-time backup images of workload from a backup client and realize corresponding virtual resource from backup image on the cloud platform that is part of the workload manager appliance. Workload manager maintains catalog of point-in-time copies of workloads. Each item in the catalog refers resource entries on the cloud platform. When user wishes to instantiate a point-in-time copy, workload manager instantiates all the resources identified in the catalog entry. User can also restore a particular point-in-time workload to production system or migrate a particular point-in-time workload to remote application.

Abstract: When a particular event record requires a particular service, but that service has failed for the event, an error record that includes an aggregate identifier (AgID) is stored for the event in an error queue. Storing an error record in the error queue causes the service to notify a remediation team to fix the failed event. All events with the AgID in the error record are put on hold and an error record is created for each of these events. The remediation team generates a fixed version of the event record and causes the system to retry the failed service for the event based on the fixed version. If the fixed version of the event is successfully processed, then any other events with the same AgID that have error records in the error queue, are routed in order of enqueue time through the event processor to be handled.

Abstract: Various embodiments are generally directed to an apparatus, method and other techniques to receiving a sequence of transactions, each transaction including a request to write data to a memory device, processing the sequence of transactions, and communicating a response to a host after the sequence of transaction have been completed.

Abstract: Rolling back data on tape in a file system is provided. A management tape is prepared. The management tape has only index files recorded thereon. The index files contain information about start positions and lengths of corresponding data files recorded on normal tapes. The index files further contain identification information for the normal tapes. A first index file of the management tape is read. The first index file is related to a data file to be rolled back. The first index file is read out from the management tape mounted on a first tape drive. The data file to be rolled back is read out of a first normal tape. The first normal tape is identified based on information in the first index file. The first normal tape is mounted on a second tape drive.

Abstract: A method includes encoding, via the processing system, data using first level dispersal parameters to produce a set of first level encoded data slices, wherein the first level dispersal parameters includes a first level write threshold; outputting the set of first level encoded data slices to a set of distributed storage and task (DST) processing units, wherein each DST processing unit of the set of DST processing units encodes a corresponding one of the set of first level encoded data slices using second level dispersal parameters to produce a set of second level encoded data slices; determining, via the processing system, when a first level write threshold number of favorable storage responses is received from a subset of the set of DST processing units; and generating and outputting, via the processing system, a cancellation message to other DST processing units of the set of DST processing units.

Abstract: Techniques are disclosed which allow a secondary storage system to provide data to non-production workloads in conjunction with performing data backup and protection tasks. As disclosed, a secondary storage system exposes backup data stored by the secondary storage system to other workloads, such as test and development applications, data analytics, etc. These non-production workloads can run at the same time the secondary storage system provides backup services to a primary storage system. This consolidation eliminates the need for an enterprise to deploy separate storage clusters for analytics, test and development applications, etc. and eliminates unnecessary copies of data.

Abstract: A system, method, and computer program product are provided for web testing and automation offline storage and analysis. In operation, an automated testing flow of a system under test is monitored by a testing system. Further, an instruction is received by the testing system to capture a snapshot of the system under test during the automated testing flow of the system under test. In response to receiving the instruction to capture the snapshot of the system under test, a complete snapshot of the system under test is saved by the testing system. The complete snapshot includes an appearance of the system under test, digital assets being utilized in association with the automated testing flow of the system under test, and current code associated with the automated testing flow of the system under test, such that full client-side functionality of the system under test is available to a tester offline.

Abstract: Provided are a computer program product, system, and method for determining space to release in a target volume to which tracks from a source volume are mirrored. A copy of a source volume table for the source volume providing a state of the tracks in the source volume for a consistency group is received. Tracks received from the source volume are written to the target volume to form the consistency group of tracks in the source volume at the target volume. A determination is made of tracks available to release from the copy of the source volume table and space allocated to the determined tracks is replaced. A point-in-time copy is created of the target volume for the consistency group. Complete is returned to forming the consistency group in response to releasing the space and creating the point-in-time copy.

Abstract: Apparatus and methods are disclosed for implementing bad jump detection in block-based processor architectures. In one example of the disclosed technology, a block-based processor includes one or more block-based processing cores configured to fetch and execute atomic blocks of instructions and a control unit configured to, based at least in part on receiving a branch signal indicating a target location is received from one of the instruction blocks, verify that the target location is a valid branch target.

Abstract: Systems and methods for switching to different states of electronic content being developed in a content creation application. This involves storing different states of the electronic content using a content-addressable data store, where individual states are represented by identifiers that identify items of respective states stored in the content-addressable data store. Identical items that are included in multiple states are stored once in the content-addressable data store and referenced by common identifiers. Input is received to change the electronic content to a selected state of the different states and the electronic content is displayed in the selected state based on identifiers for the selected state. In this way, undo, redo, and other commands to switch to different states of electronic content being developed are provided.

Abstract: Provided are a computer program product, system, and method for determining tracks to release in a source volume being copied to a target volume. A consistency group is formed of tracks in the source volume to copy to the target volume. A volume table providing information on the tracks allocated to the source volume is copied to a volume table copy in a memory providing a state of the tracks in the source volume as of a consistency group time. A determination is made of tracks in the source volume to release for tracks that are indicated in the volume table copy as available to release excluding tracks in the source volume that are written after the consistency group time. Space allocated to the determined tracks is released.

Abstract: The present disclosure provides for information handling systems and methods to configure and manage any number of heterogeneous devices. In various embodiments, a shared device configuration is simultaneously applied to a selected group of otherwise incompatible heterogeneous devices that may use different communication protocols and operating systems. Certain embodiments create and maintain a database of configuration and operational information that is accessible across platforms. A group device configuration may be automatically applied to all devices in the selected group via a batch command. Some embodiments allow independent heterogeneous devices that have similar functionality to have different device configuration settings.

Abstract: A method, computer program product, and computing system for establishing a data communication channel between a first virtual storage appliance and a second virtual storage appliance within a storage system, wherein the data communication channel includes a network-based data communication path. A heartbeat communication channel is established between the first virtual storage appliance and the second virtual storage appliance within the storage system, wherein the heartbeat communication channel includes a network-based heartbeat communication path. A tie breaker node is coupled to the network-based heartbeat communication path to monitor one or more heartbeat signals present on the network-based heartbeat communication path.

Abstract: An apparatus in one embodiment comprises a distributed processing system including a plurality of processing nodes. The processing nodes implement respective ones of a plurality of operators for a processing a data stream in the distributed processing system. Responsive to a detected fault in a given one of the operators processing the data stream, other ones of the operators processing the data stream are partitioned into one or more upstream operators, one or more immediately downstream operators, and one or more further downstream operators, relative to the given faulted operator. The given faulted operator is recovered from a checkpoint of that operator. In parallel with recovering the given faulted operator, different sets of operations are performed for respective ones of the upstream operators, immediately downstream operators and further downstream operators. A given such set of operations may be performed utilizing window metadata maintained for respective buffers of the processing nodes.

Abstract: Provided are a computer program product, system, and method for determining tracks to release in a target volume mirroring tracks from a source volume. Tracks received from the source volume are written to the target volume to form a consistency group of tracks in the source volume at the target volume. A determination is made of tracks available to release from a volume table providing a state of the tracks in the target volume and space allocated to the determined tracks is released. A point-in-time copy of the target volume is crated and complete is returned to forming the consistency group in response to releasing the space and creating the point-in-time copy.

Abstract: Multi-tenant access to respective isolated data sets organized using different application schemas is disclosed. Multiple tenants store respective data sets in separate datastores. The datastores are organized using different application schemas, each derived from a same base schema. However, the tenants share access to a same application. The application receives a first request from a first tenant and a second request from a second tenant. The application serves the first request by accessing a first data set organized using a first application schema. The application serves the second request by accessing a second data set using a second application schema.

Abstract: Examples disclosed herein relate to processing transaction logs for storage nodes. Multiple nodes manage transactions for storage units including transaction logs. A node assumes control over a set of storage units and blocks host access requests to the storage units. Transaction logs are processed to determine a subset of the set to perform recovery for. In this example, the subset of storage units are locked. Host access requests are resumed.

Abstract: The present disclosure relates to error recovery in a virtual machine-based development environment. An example method generally includes monitoring for an error event in a virtual machine managed within a development environment. The development environment attempts to recover the virtual machine from the error event by performing a first error remediation procedure on the virtual machine. Upon determining that the first error remediation procedure failed to recover the virtual machine from the error event, the development environment attempts to recover the virtual machine from the error event by performing a second error remediation procedure on the virtual machine. The second remediation procedure may be a procedure that is more severe than the first error remediation procedure.

Abstract: An operating method of a storage device that includes a nonvolatile memory device and a controller configured to control the nonvolatile memory device, the method including: detecting, by the controller, a fault of the nonvolatile memory device or the controller, notifying, by the controller, a host device of the fault, notifying, by the controller, the host device of one or more recovery schemes for recovering the fault, and recovering, by the controller, the fault in response to a recovery scheme selected by the host device.

Abstract: A system and a method to manage a data center, the method including, for example, retrieving a physical topology of a service; determining from the physical topology a concrete type of a resource for the service; and selecting an actual instance of the resource in the data center. The actual instance having the concrete type and the actual instance selected such that a consumption of the actual instance does not violate at least one of a constraint and a policy.

Abstract: A command processing method and a storage controller using the same are provided. The command processing method includes: receiving a plurality of I/O commands; categorizing the I/O commands into a plurality of groups according to a processor effort index of the I/O commands; selecting a first group from the groups, resetting a timer and obtaining an expiration time corresponding to the first group according to the I/O commands of the first group, and executing the I/O commands of the first group; and selecting a second group from the groups and resetting the timer when the expiration time of the first group expires, wherein when the processor effort index of the first group is less than a threshold, a clock frequency of the processor is lowered before the expiration time expires.

Abstract: A variable checkpoint mechanism in a streams manager checkpoints a streaming application based on periodic time periods for checkpoints. The variable checkpoint mechanism can take a checkpoint early before a periodic time period ends or late after the periodic time period ends based on predicted size of one or more tuple windows in the streaming application. The time for taking the checkpoint can be selected based on multiple checkpoint timing criteria, which include storage requirement for the checkpoint and predicted backpressure in the flow graph. In this manner the checkpoint timing of the variable checkpoint mechanism can be adjusted real-time to minimize the negative impact of checkpointing on the performance of the streaming application.

Abstract: An electronic device includes a volatile memory; a non-volatile memory which is for storing firmware; and a circuit, wherein the firmware includes firmware body and loader which is for rewriting the non-volatile memory, and the circuit, judges whether the firmware is being rewritten or not based on a first mark when activating, judges whether the loader is being rewritten or not based on a second mark when it judges that the firmware is being rewritten, copies the loader which is copied to the other position of the non-volatile memory to the volatile memory when it judges that the loader is being rewritten, and executes the loader which is copied to the volatile memory and rewrites the firmware which is stored in the non-volatile memory.

Abstract: A system, method, and computer readable medium for asynchronous live migration of applications between two or more servers. The computer readable medium includes computer-executable instructions for execution by a processing system. Primary applications runs on primary hosts and one or more replicated instances of each primary application run on one or more backup hosts. Asynchronous live migration is provided through a combination of process replication, logging, barrier synchronization, checkpointing, reliable messaging and message playback. The live migration is transparent to the application and requires no modification to the application, operating system, networking stack or libraries.

Abstract: A computer-implemented method for repairing corrupted data segments in deduplicated data systems may include (1) identifying a corrupted data segment within a deduplicated data system, (2) locating backed up versions of a first file and backed up versions of a second file, (3) analyzing a first pattern with which the backed up versions of the first file reference the corrupted data segment and a second pattern with which the backed up versions of the second file reference the corrupted data segment, (4) determining that a first location within an instance of the first file is more likely to include a non-corrupt instance of the corrupted data segment than is a second location within an instance of the second file, (6) retrieving the non-corrupt instance of the corrupted data segment from the first location, and (7) repairing the corrupted data segment. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: A management system coupled to an operation target system including one or more operation target apparatuses creates or edits a service template for operation automation, the service template being associated with one or more components. A processor (1) receives a version upgrade request that designates a service template; and (2) causes a version of a target component associated with the designated service template or a copy of the designated service template to be different from a version of a target component already associated with the designated service template, in response to the version upgrade request.

Abstract: A single instruction is received to read a read address in storage in order to obtain read data and write the read data to a write address in the storage. Error correction decoding is performed in order to obtain user data. Error correction parity information is generated based at least in part on (1) the user data and (2) new metadata associated with the write address, without buffering the user data between the error correction decoding and the generation of the error correction parity information. The user data, the new metadata, and the error correction parity information are stored in the write address in the storage.

Abstract: Techniques are disclosed relating to clause-based execution of program instructions, which may be single-instruction multiple data (SIMD) computer instructions. In some embodiments, an apparatus includes execution circuitry configured to receive clauses of instructions and SIMD groups of input data to be operated on by the clauses. In some embodiments, the apparatus further includes one or more storage elements configured to store state information for clauses processed by the execution circuitry. In some embodiments, the apparatus further includes scheduling circuitry configured to send instructions of a first clause and corresponding input data for execution by the execution circuitry and indicate, prior to sending instruction and input data of a second clause to the execution circuitry for execution, whether the second clause and a first clause are assigned to operate on groups of input data corresponding to the same instruction stream.

Abstract: In one embodiment, a computer-implemented method for performing deduplication in conjunction with random read and write operations across a namespace that is divided into a plurality of disjoint regions is disclosed. The method includes: maintaining a metadata structure for each of the plurality of disjoint regions via the respective region manager, each metadata structure comprising metadata indicating a physical storage location of one or more data chunks associated with the respective region; and performing a deduplicated write operation. The deduplicated write operation includes: determining whether the disjoint regions comprise a second data chunk identical in content to a first data chunk; and in response to determining one or more of the plurality of disjoint regions other than the first region includes the second data chunk, establishing a reference from the first data chunk to the second data chunk. Corresponding systems and computer program products are also disclosed.