Abstract: A mechanism is provided for identifying data that can be removed from a cache memory by determining a memory region of the cache that is less recently accessed than other memory regions in the cache. A tree data structure is used to store a mapping of storage volume data locations to cache data locations. A counter reflecting recency of access to the cache data location is associated with each entry. The counter is incremented, along with counters associated with keys leading to a node including the entry, with each access to the associated cache memory location, while other counters in each affected node are decremented. Advantages of the tree data structure are used to efficiently locate a cache memory location associated with a counter reflecting a less recently accessed state in order to make that cache memory location available for storage of recently accessed data from the storage volume.

Abstract: A computer-implemented method for efficient sequential logging on caching-enabled storage devices may include 1) identifying a storage device with a cache, 2) allocating space on the storage device for a sequential log, 3) calculating a target size for the sequential log based at least in part on an input/output load directed to the sequential log, and then 4) restricting the sequential log to a portion of the allocated space corresponding to the target size. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: A method for storing data in a storage system. In one embodiment, implementation of a method for storing data in compliance with a compression handling instruction includes: at a storage controller, receiving an object for storage within a data storage, wherein the object is in an original state; determining whether a compression handling instruction is received in association with the object; and executing the compression handling instruction when storing the object.

Abstract: A host-based replication snapshot method. The method includes synchronizing a set of data objects stored at both a replication source node and a secondary node. The method further includes identifying changed data objects out of the set of data objects from the replication source node that have been modified during a time period between a first time and a subsequent second time. Metadata indicating the changed data objects from the replication source node is transmitted to the secondary node. A snapshot is then generated at the second time on the secondary node by using the metadata.

Abstract: Systems and methods for fault handling are presented. In one embodiment, a fault handling method includes: performing an information collection process, wherein the information collection process includes collecting information regarding guest operating system files of a virtual machine; performing a selective replication region identification process, wherein the selective replication region identification process includes identifying regions associated with a selective amount of the guest operating system files; and performing a replication process based upon result of the replication region identification process. In one embodiment, the selective replication region identification process includes identifying regions associated with files of interest. The selective replication region identification process can include identifying regions associated with temporary files.

Abstract: A computer-implemented method for efficient sequential logging on caching-enabled storage devices may include 1) identifying a storage device with a cache, 2) allocating space on the storage device for a sequential log, 3) calculating a target size for the sequential log based at least in part on an input/output load directed to the sequential log, and then 4) restricting the sequential log to a portion of the allocated space corresponding to the target size. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: Incremental checkpoint, for use in data replication, track the changes made to a file system after a point in time at which the incremental checkpoint is created. Data replication techniques using the incremental checkpoints may include taking a regular checkpoint of the file system and creating the first time full copy on remote node using the regular checkpoint. Changes made to the file system are then tracked in an incremental checkpoint that are stored on the remote node. The processes of taking the incremental checkpoint and storing the incremental checkpoint are iteratively performed. The first time fully copy and the incremental checkpoints may then be used for data replication, backup, continuous data protection (CDP), or the like.

Abstract: A method for implementing continuous data replication in a distributed computer system. The method includes receiving a forwarded data object write I/O from a data server. The method further includes examining attribute information of the data object to determine a consistency group for the data object. A replication policy is examined in view of the consistency group of the data object to determine a destination redundancy server. The data object write I/O is forwarded to the destination redundancy server for storage. An acknowledgment is then sent to the data server upon storage of the data object in the destination redundancy server.

Abstract: A method, in one embodiment, can include receiving a key and associated data via a computing device. Furthermore, the method can include searching a B+ tree data structure using the key to find a leaf node. The B+ tree data structure is stored by a persistent storage coupled to the computing device. The B+ tree data structure can include a first plurality of nodes that each contains a key-value entry that is not maintained in a sorted order based on its key. In addition, the key and associated data are appended to the leaf node. A sector that includes the leaf node and the key and associated data can be flushed to the persistent storage.

Abstract: A computer-implemented method for enabling replication targets to reclaim unused storage space on thin-provisioned storage systems may include: 1) replicating data from a replication source to a replication target, 2) identifying unused storage space within the replicated data, 3) generating a reclamation request for reclaiming the unused storage space from a thin-provisioned storage system that provides thin-provisioned storage for the replication target, and then 4) issuing the reclamation request to the thin-provisioned storage system in order to reclaim the unused storage space from the thin-provisioned storage system. Various other related systems, methods, and configured computer-readable media are also disclosed.

Abstract: A periodic checkpoint method for a file system replication source. The method comprises generating a first checkpoint at a first time on a file system replication source and identifying a set of data objects from the replication source that have been modified during a time period between the first time and a subsequent second time. A periodic checkpoint is then generated at the second time on the file system replication source by using the set of data objects.

Abstract: Network fabric events may be utilized to proactively handle network path outages. A storage network virtualization manager may receive a network fabric event indicating a failure along a network path to a storage device and in response may initiate a proactive error handling mechanism. A storage network virtualization manager may proactively handle a network path failure before I/O requests via that network path fail. The proactive error handling mechanism may be initiated and completed prior to or without a host receiving an indication that an access request to a storage device on the network path has failed. Proactive error handling in response to network fabric events may reduce the number of I/O failures and retries and may also reduce the length of time access requests to storage devices affected by a network fabric path failure must be quiesced.

Abstract: A system for volume replication in a distributed block virtualization environment includes a first and a second set of one or more physical block devices, a first and a second volume server, one or more volume clients, and a replication manager. The first volume server may be configured to aggregate storage in the first set of one or more physical block devices into one or more logical volumes, and to make the one or more logical volumes accessible to the one or more volume clients. The replication manager may be configured to operate in cooperation with the first and second volume servers and the one or more volume clients to maintain a replica of at least a subset of the one or more logical volumes at the second set of one or more physical block devices.