Abstract: Multi-site distributed storage systems and computer-implemented methods are described for improving a resumption time of input/output (I/O) operations during a common snapshot process for storage objects. A computer-implemented method comprises performing a baseline transfer from at least one storage object of a first storage node to at least one replicated storage object of a second storage node, starting the common snapshot process including stop processing of I/O operations, performing a snapshot create operation on the primary storage site for the at least one storage object of the first storage node, resuming processing of I/O operations, and assigning a new universal unique identifier (UUID) to the at least one storage object of the second storage node after resuming processing of I/O operations with the new UUID to identify when file system contents are different than the baseline transfer.

Abstract: Multi-site distributed storage systems and computer-implemented methods are described for improving a resumption time of input/output (I/O) operations during a common snapshot procedure for storage objects. A computer-implemented method includes initiating a snap create handler operation for a storage object of a batch of storage objects having a plurality of replicated datasets with each replicated dataset having a synchronous replication relationship between at least one storage object of the first storage node and at least one replicated storage object of the second storage node, determining whether a consistency point is currently in progress or not, and providing a hint to accelerate a currently in progress consistency point when the consistency point is currently in progress.

Abstract: A method for managing data storage using a distributed file system. A file system volume associated with a write request received at a data management subsystem is identified. A logical block device associated with the file system volume is identified. A plurality of data blocks is formed based on the write request. The plurality of data blocks is distributed across a plurality of node block stores in a distributed block layer of a storage management subsystem of the distributed file system. Each of the plurality of node block stores corresponds to a different node of a plurality of nodes in the distributed storage system. The storage management subsystem operates separately from but in communication with the data management subsystem.

Abstract: Multi-site distributed storage systems and computer-implemented methods are described for improving a resumption time of input/output (I/O) operations during a common snapshot procedure for storage objects. A computer-implemented method includes initiating a snapshot multi create operation to selectively form a batch of first and second synchronous replicated datasets that belong to a first group of storage disks at the primary storage site and corresponding second group of storage disks at the secondary storage site, performing a batch snapshot create operation on the primary storage site by executing snapshots of storage objects on the primary storage site of the batch of first and second synchronous replicated datasets in parallel multiple threads to effectively utilize processing resources on the primary storage site, and initiating an independent workflow and state machine for each storage object of the batch of first and second synchronous replicated datasets.

Abstract: Data traffic management in a computing environment utilizing direct memory access functionality is disclosed. A management agent is configured to operate within a storage node. The management agent includes a storage interface to communicate with a first set of storage devices, a management memory interface to communicate with a first management memory, and an interconnect (IC) interface to communicate with a remote peer node. The management agent controls data traffic between the storage node and the peer node to provide at least mirroring of the first management memory to the peer node and mirroring of a second management memory on the peer node to the storage node. The management agent further controls the data traffic using a traffic control approach selected based on at least a performance evaluation of an IC fabric accessible via the IC interface.

Abstract: Systems and methods for performing a fast resynchronization of a mirrored aggregate of a distributed storage system using disk-level cloning are provided. According to one embodiment, responsive to a failure of a disk of a plex of the mirrored aggregate utilized by a high-availability (HA) pair of nodes of a distributed storage system, disk-level clones of the disks of the healthy plex may be created external to the distributed storage system and attached to the degraded HA partner node. After detection of the cloned disks by the degraded HA partner node, mirror protection may be efficiently re-established by assimilating the cloned disks within the failed plex and then resynchronizing the mirrored aggregate by performing a level-1 resync of the failed plex with the healthy plex based on a base file system snapshot of the healthy plex. In this manner, a more time-consuming level-0 resync may be avoided.

Abstract: Computing technology for managing support requests are provided. The technology includes a processor executable application programming interface (API) that receives a support case indicating a problem associated with a device. The API utilizes a training model to predict a problem category for the support case. The training model predicts the problem category based on a feature extracted from information included in the support case. The training model further identifies a plurality of proximate support cases based on a distance between the support case and the proximate support cases within a virtual space assigned to the predicted problem category; determines relevance of each proximate support case to the support case; and outputs a resolution code for the support case based on the determined relevance of each proximate support case.

Abstract: Various embodiments are directed to techniques for coordinating at least partially parallel performance and cancellation of data access commands between nodes of a storage cluster system. An apparatus may include a processor component of a first node coupled to a first storage device storing client device data; an access component to perform replica data access commands of replica command sets on the client device data, each replica command set assigned a set ID; a communications component to analyze a set ID included in a network packet to determine whether a portion of a replica command set in the network packet is redundant, and to reassemble the replica command set from the portion based if the portion is not redundant; and an ordering component to provide the communications component with set IDs of replica command sets of which the access component has fully performed the set of replica data access commands.

Abstract: Techniques are provided for implementing a defragmentation process during a merge operation performed by a re-compaction process upon a log structured merge tree. The log structured merge tree is used to store keys of key-value pairs within a key-value store. As the log structured merge tree fills with keys over time, the re-compaction process is performed to merge keys down to lower levels of the log structured merge tree to re-compact the keys. Re-compaction can result in fragmentation because there is a lack of spatial locality of where the re-compaction operations re-writes the keys within storage. Fragmentation increases read and write amplification when accessing the keys stored in different locations within the storage. Accordingly, the defragmentation process is performed during a last merge operation of the re-compaction process in order to store keys together within the storage, thus reducing read and write amplification when accessing the keys.

Abstract: The disclosed technology relates determining a first subset of a plurality drives having a first zone size and a second subset of the plurality of drives having a second zone size different from the first zone size, within a redundant array of independent disks (RAID) group. A prevailing zone size between the first zone size and the second zone size is determined. One or more logical zones within the determined first subset of the plurality of drives and the determined second subset of the plurality of drives for a received input-output operation is reserved based on the determined prevailing zone size. The received input-output operation is completed within the reserved one or more logical zones within the determined first subset of the plurality of drives and the determined second subset of the plurality of drives.

Abstract: A system, method, and machine-readable storage medium for restoring a data object for a specified active time period are provided. In some embodiments, the method includes receiving, by a storage device from a client, a request specifying an active time period for a data object to remain stored on an accessible tier. The method also includes determining, by the storage device, that the active time period has elapsed. The method further includes responsive to a determination that the active time period has elapsed, sending, by the storage device, a request to a server storing the data object to move the data object from the accessible tier to an archive tier. Data objects that are stored on the accessible tier are accessible by the client, and data objects that are stored on the archive tier are inaccessible by the client.

Abstract: An application may store data to a dataset comprising a plurality of volumes stored on a plurality of storage systems. The application may request a dataset image of the dataset, the dataset image comprising a volume image of each volume of the dataset. A dataset image manager operates with a plurality of volume image managers in parallel to produce the dataset image, each volume image manager executing on a storage system. The plurality of volume image managers respond by performing requested operations and sending responses to the dataset image manager in parallel. Each volume image manager on a storage system may manage and produce a volume image for each volume of the dataset stored to the storage system. If a volume image for any volume of the dataset fails, or a timeout period expires, a cleanup procedure is performed to delete any successful volume images.

Abstract: Systems and methods for re-aligning data replication configuration of a cross-site storage solution after a failover are provided. According to one embodiment, after a failover, the new primary distributed storage system orchestrates flipping of the data replication configuration of a peered consistency group (CG) to reestablish zero RPO and zero RTO protections for the peered CG. The primary causes the secondary distributed storage system to perform an atomic database operation on its remote configuration database to (i) delete an existing source configuration that identifies the secondary as a source of data replication; and (ii) persist a new destination configuration identifying the secondary as a destination of data replication.

Abstract: With a forever incremental snapshot configuration and a typical caching policy (e.g., least recently used), a storage appliance may evict stable data blocks of an older snapshot, perhaps unchanged data blocks of the snapshot baseline. If stable data blocks have been evicted, restore of a recent snapshot will suffer the time penalty of downloading the stable blocks for restoring the recent snapshot. Creating synthetic baseline snapshots and refreshing eviction data of stable data blocks can avoid eviction of stable data blocks and reduce the risk of violating a recovery time objective.

Abstract: Systems and methods for automated remediation of issues arising in a data management storage system are provided. Deployed assets of a storage solution vendor may deliver telemetry data to the vendor on a regular basis. The received telemetry data may be processed by an AIOps platform to perform predictive analytics and arrive at “community wisdom” from the vendor's installed user base. In one embodiment, an insight-based approach is used to facilitate risk detection and remediation including proactively addressing issues before they turn into more serious problems. For example, based on continuous learning based on the community wisdom and making one or both of a rule set and a remediation set derived therefrom available for use by cognitive computing co-located with a customer's storage system, a risk to which the storage system is exposed may be determined and a corresponding remediation may be deployed to address or mitigate the risk.

Abstract: Systems and methods for automated remediation of issues arising in a data management storage system are provided. Deployed assets of a storage solution vendor may deliver telemetry data to the vendor on a regular basis. The received telemetry data may be processed by an AIOps platform to perform predictive analytics and arrive at “community wisdom” from the vendor's installed user base. In one embodiment, an insight-based approach is used to facilitate risk detection and remediation including proactively addressing issues before they turn into more serious problems. For example, based on continuous learning based on the community wisdom and making one or both of a rule set and a remediation set derived therefrom available for use by cognitive computing co-located with a customer's storage system, a risk to which the storage system is exposed may be determined and a corresponding remediation may be deployed to address or mitigate the risk.

Abstract: Asynchronous snapshot invalidation techniques are described. According to various such techniques, an enhanced file handle structure may be defined that includes a snapshot generation ID that is to comprise a value that singularly identifies a snapshot performed at a particular point in time. In some embodiments, when a snapshot ID assigned to that snapshot is reused at a subsequent point in time, a different snapshot generation ID may be assigned to that subsequent snapshot. With respect to an in-core cache, the differing snapshot generation IDs may eliminate unacceptable ambiguity regarding respective file information sets corresponding to the initial and subsequent snapshots sharing the same snapshot ID. As a result, obsolete file information sets may be cleared from the in-core cache asynchronously, enabling improved performance. The embodiments are not limited in this context.

Abstract: Techniques are provided for implementing a unified object format. The unified object format is used to format data in a performance tier (e.g., infrequently accessed data, snapshot data, etc.) into objects that are stored into an object store for low cost, scalable, long term storage compared to storage of the performance tier. With the unified object format, compression of the data may be retained when the data is stored as the objects into the object store. Additional compression may also be provided for the data in the objects. The unified object format includes slot header metadata used to track the location of the data within the object notwithstanding the data being compressed and/or stored at non-fixed boundaries. The slot header metadata may be cached at the performance tier for improved read performance and may be repaired by a repair subsystem (a slot header repair subsystem).

Abstract: A method performed by one or more processing resources of one or more computer systems is disclosed. The method comprises receiving an object at a first of a plurality of nodes from a second of the plurality of storage nodes within a cluster switch fabric, examining a value associated included within the received object, wherein the value is associated with a clock value of the second node and updating a clock operating at the first node with the received value.

Abstract: According to one embodiment, a computer implemented method comprises providing multiple channels between a first storage node and a second storage node with each channel having a separate network connection for packets of a transport layer session, assigning packets from each channel to a group of receive queues of the second storage node, continuously monitoring whether two or more channels of the multiple channels share a same receive queue of the second storage node, and sending a communication via a channel to the first storage node to indicate a dynamic change in a hash input field (e.g., a source port, a destination port, a source internet protocol (IP) address, and a destination IP address) when two or more channels of the multiple channels share a same receive queue of the second storage node.