Abstract: A method, system, apparatus, and computer-readable medium are described for providing distributed hot-spare storage in a redundant storage cluster. According to one method, a portion of the unutilized space on the storage cluster is utilized as a distributed hot-spare storage node. Through this mechanism, a redundant storage cluster with N storage nodes may be contracted to a redundant array with N?1 nodes. Thin provisioning and intelligent data placement may also be utilized to implement the distributed hot-spare storage node. Through repeated application of such methods and systems, the failure of any storage node or the sequential failure of multiple storage nodes within a redundant storage cluster results in the recreation of the cluster as a redundant storage array with one fewer node, but with the same redundancy.

Abstract: A method, system, apparatus, and computer-readable medium are described for the background movement of data between nodes in a storage cluster. According to one method, exception tables are generated that include data identifying the areas on each node that need to be migrated to another node and the areas on each node that are to be migrated from another node. The exception tables may be generated in response to the failure of a node in the storage cluster or in other circumstances. A background resynchronization thread utilizes the contents of the exception tables to migrate data between the nodes of the cluster, thereby synchronizing the data stored on the nodes. Input/output operations directed to an area that is to be migrated from another node are redirected to the other node in accordance with a timeout period associated with the input/output operations.

Abstract: Technologies are described for implementing a migration mechanism in a data storage system containing multiple tiers of storage with each tier having different cost and performance parameters. Access statistics can be collected for each territory, or storage entity, within the storage system. Data that is accessed more frequently can be migrated toward higher performance storage tiers while data that is accessed less frequently can be migrated towards lower performance storage tiers. Each tier can be associated with a range of ILM statistics referred to as the bucket for that tier. A pivot table may be provided that relates the tiers and the buckets. Operations on the pivot table can provide counts of how many territories may be promoted or demoted between any two pairs of tiers.

Abstract: Technologies are described herein for providing networked RAID in a virtualized storage cluster. The storage capacity of a storage cluster having two or more storage nodes is organized into tiers. A portion of the available storage capacity is allocated to one tier that is organized using chained declustering. Another portion of the available storage capacity is allocated to another tier that is organized using a networked RAID configuration. The storage cluster monitors the frequency at which data in the storage cluster is accessed. Frequently used data that is stored in the network RAID-configured tier is promoted to the chained declustered-configured tier. Infrequently used data that is stored in the chained declustered-configured tier is demoted to the network RAID-configured tier. The zone size for zones stored in the chained declustered-configured tier may be different than for zones stored in the network RAID-configured tier.

Abstract: A system, method, apparatus, and computer-readable medium are described for providing redundancy in a storage system. According to one method, maps are generated and stored that define stripe patterns for storing data on the storage nodes of a storage cluster. The maps are defined such that when a new storage node is added to the cluster, no movement of data occurs between two storage nodes that existed in the cluster prior to the addition of the new storage node during re-striping, and such that the data stored on each storage node is mirrored on another storage node. Storage nodes may also be designated as an owner or a peer for each storage zone. Input/output operations received at an owner node are fielded directly and mirrored to the peer node, while input/output operations received at a peer node are redirected to the owner node for processing.

Abstract: A method, system, apparatus, and computer-readable medium are provided for improved maintenance of metadata relating to a mass storage array. The metadata may comprise the data structures utilized by a thin provisioning system. When the metadata changes, such as in response to the modification of the underlying data, changed metadata is created in the memory. A parity block is then read from the row of the array where the changed metadata is to be stored. A new parity is calculated for the row using only the old metadata, the changed metadata, and the parity read from the stripe. The old metadata need not be read from disk expressly, as is usually done. Instead, the value that is present in memory before the metadata change is utilized directly to calculate the new parity. The changed metadata and the new parity are then written to the array.

Abstract: A method, system, apparatus, and computer-readable medium are provided for taking snapshots of a storage volume. According to aspects of one method, each snapshot is represented as a unique sequence number. Every fresh write access to a volume in a new snapshot lifetime is allocated a new section in the disk, called a provision, which is labeled with the sequence number. Read-modify-write operations are performed on a sub-provision level at the granularity of a chunk. Because each provision contains chunks with valid data and chunks with invalid data, a bitmap is utilized to identify the valid and invalid chunks with each provision. Provisions corresponding to different snapshots are arranged in a linked list. Branches from the linked list can be created for storing writable snapshots. Provisions may also be deleted and rolled back by manipulating the contents of the linked lists.

Abstract: A system, method, apparatus, and computer-readable medium are provided for expanding the data storage capacity of a virtualized storage system, such as a storage cluster. According to one method, maps are generated and stored that define a stripe pattern for storing data on the storage nodes of a storage cluster. The stripe pattern for each map is defined such that when a storage node is added to a cluster and the data is re-striped according to the new map, only the data that will subsequently reside in the new storage node is moved to the new storage cluster during re-striping. The stripe pattern may be further defined so that during re-striping no movement of data occurs between two storage nodes that existed in the cluster prior to the addition of the new storage node. The stripe pattern may be further defined such that during re-striping an equal amount of data is moved from each of the storage nodes that existed in the cluster prior to the addition of the new storage node to the new storage node.

Abstract: Techniques for maintaining mirrored storage cluster data consistency on systems with write back cache can employ write-intent logging and periodic log clearing. The techniques can track any outstanding I/Os, data in caches, and data that has gone out of sync between mirrored nodes due to link failures. The techniques can ensure that a power failure on any of the storage nodes does not result in inconsistent data among the storage nodes. The techniques can use gate bitmaps to log outstanding I/Os. The gate bitmaps may be periodically cleared. The clearing period may be selected as to allow enough time for all caches to be flushed and for all synchronizing I/Os to complete. Efficient queuing of I/O requests in conjunction with the efficient operation of multiple gate bitmaps can reduce performance impacts of the gating or logging operations.

Abstract: System and methods are disclosed for gathering debug information of a storage system of a computer system without requiring additional external hardware directly connected to the controller of the storage system.

Abstract: Technologies are provided herein for asynchronous data replication. A primary server maintains and exposes a storage volume for use by storage clients. The primary server receives write operations directed toward the storage volume and performs the writes on the storage volume. The primary server also creates buckets containing each of the write operations. The buckets are opened at a first point in time and closed at a second point in time that may be selected based upon the contents of the buckets, a predefined time period, or based upon an indication from an application program. The buckets are transmitted to a second server computer asynchronously. When each bucket is received completely by the second server, its contents are written to a storage volume maintained by the second computer. The buckets may be created from pages of a write-back cache utilizing a zero buffer copy mechanism.

Abstract: A method, system, apparatus, and computer-readable medium are provided for improving storage in a disk array are provided. According to aspects of the invention, a redundant disk array is combined with a mechanism for thin provisioning of the array. Thin provisioning refers to a process of allocating physical capacity to logical volumes on an as-needed basis. Data structures containing a mapping between the logical location of stored data and its actual location on a physical device are maintained. Through the use of the thin provisioning mechanism, physical storage space can be allocated sequentially, regardless of the order of logical writes. In this manner, the data stored on the array grows in a linear manner. The data structures maintained by the thin provisioning mechanism can be used to identify the portions of a device or an array that have been previously written.

Abstract: A method, system, apparatus, and computer-readable medium are described for the background movement of data between nodes in a storage cluster. According to one method, exception tables are generated that include data identifying the areas on each node that need to be migrated to another node and the areas on each node that are to be migrated from another node. The exception tables may be generated in response to the failure of a node in the storage cluster or in other circumstances. A background resynchronization thread utilizes the contents of the exception tables to migrate data between the nodes of the cluster, thereby synchronizing the data stored on the nodes. Input/output operations directed to an area that is to be migrated from another node are redirected to the other node. The methods, systems, apparatus, and computer-readable medium may be utilized with operations including the rebuilding, expansion, contraction, and compaction of a storage cluster.

Abstract: Technologies are presented herein for synchronization of I/O operations in a data storage system. Multiple reader and writer locks may be acquired by calling processes at two different granularities. Locks may be acquired for an area of storage equivalent to the logical unit of allocation or for a sub-provision area equivalent to a unit of snapshot read-modify-write. Each lock may be represented by a lock data structure that represents the same amount of logical address space as the logical unit of allocation. A request that arrives to the lock data structure may be placed in a lock wait queue until the request can be honored. A round robin technique may be utilized to respond to requests for locks so that one lock does not starve out other locks.

Abstract: A method, system, and apparatus for expanding the storage capacity of a data storage system are provided. According to one method, the physical storage devices that store the data and metadata for one or more logical disks are organized into a container. A logical disk segment is created within the container for each logical disk. When storage capacity is added through the addition of logical disks, a new logical disk segment is added to the end of the container for the new logical disk. When storage capacity is added through the addition of capacity to an existing logical disk, a new logical disk segment is added to the end of the container for the new logical disk segment within the logical disk. The devices within a container may be migrated between server computers or between CPUs with their associated mass storage controllers.

Abstract: A system, method, apparatus, and computer-readable medium are provided for expanding the data storage capacity of a virtualized storage system, such as a storage cluster. According to one method, maps are generated and stored that define a stripe pattern for storing data on the storage nodes of a storage cluster. The stripe pattern for each map is defined such that when a storage node is added to a cluster and the data is re-striped according to the new map, only the data that will subsequently reside in the new storage node is moved to the new storage cluster during re-striping. The stripe pattern may be further defined so that during re-striping no movement of data occurs between two storage nodes that existed in the cluster prior to the addition of the new storage node. The stripe pattern may be further defined such that during re-striping an equal amount of data is moved from each of the storage nodes that existed in the cluster prior to the addition of the new storage node to the new storage node.

Abstract: A method, system, apparatus, and computer-readable medium are provided for improving storage in a disk array are provided. According to aspects of the invention, a redundant disk array is combined with a mechanism for thin provisioning of the array. Thin provisioning refers to a process of allocating physical capacity to logical volumes on an as-needed basis. Data structures containing a mapping between the logical location of stored data and its actual location on a physical device are maintained. Through the use of the thin provisioning mechanism, physical storage space can be allocated sequentially, regardless of the order of logical writes. In this manner, the data stored on the array grows in a linear manner. The data structures maintained by the thin provisioning mechanism can be used to identify the portions of a device or an array that have been previously written.

Abstract: A method, system, apparatus, and computer-readable medium are provided for integrating a caching module into a data storage system architecture. According to one method, a request to perform an I/O operation is received at the caching module from an initiator. In response to the request, the caching module provides a notification to a storage driver that the request will be delivered to the storage driver in the future. In response to receiving the notification, the storage driver determines whether the request can be satisfied. If the storage driver determines that it will be unable to satisfy the forthcoming I/O request, the storage driver may provide an error message to the caching module. If the storage driver determines that it will be able to satisfy the I/O request, the storage driver can optimize the allocation and placement of the I/O request prior to receiving the actual I/O request.

Abstract: A method, system, apparatus, and computer-readable medium for logging metadata modifications in a storage system are provided. According to one method, modifications to storage system metadata are detected and described in a log string data structure. The log strings are collected and periodically committed to a mass storage device in the data storage system. The log strings may be collected in a log buffer data structure that includes the collected log strings and one or more unique, constantly increasing timestamps. The time stamps are written at the end of each sector of the log buffer. The log buffer may be committed to the mass storage device when the log buffer is full, when a predefined period of time has elapsed since the previous commitment of the log strings to disk, or in a manner designed to ensure that one write of the log buffer is always outstanding. A logger module is operative to collect the log strings, build the log buffer, and to commit the log buffer to disk.

Abstract: Technologies are described herein for providing file-level CDP of files stored on a remote storage system. A client module executing on a client computer monitors for modifications made at the client computer to files or folders stored on a virtual storage volume provided by the remote storage system. Upon detecting a modification of a monitored file, the client module sends a message to the remote storage system identifying the file. A server module executing in the remote storage system receives the message identifying the modified file and copies a version of the file containing the modification from the virtual storage volume to a backup volume located in the remote storage system.