Abstract: Embodiments of the present disclosure provide a method, device and computer program product for storing data. The method comprises creating a first data file having a naming identification at a first node in a Redundant Array of Independent Nodes (RAIN), and creating a second data file having the naming identification at a second node in the RAIN. The method further comprises creating, at a third node in the RAIN, a parity file having the naming identification, wherein the parity file is a parity result of a plurality of data files. According to embodiments of the present disclosure, files in the same parity group are configured with the same or partially the same file name.

Abstract: Embodiments of the present disclosure relate to a method, an electronic device and a computer program product for creating metadata index. The method disclosed herein comprises: generating a first-level index to index a metadata item; inserting a first indication into the first-level index to indicate a position of the metadata item in a set of metadata; generating a second-level index to index a set of first-level indexes; and inserting a second indication into the second-level index to indicate a set of positions of the set of metadata. In this way, embodiments of the present disclosure can create an index structure which can indicate the position of the metadata item, so as to rapidly determine the position of the metadata item.

Abstract: The present disclosure provides a solution for migrating data. In the solution, a migration tool first receives, from a source server, an index having index values corresponding to a plurality of files stored at the source server. The migration tool then retrieves a location of an index value corresponding to key information file in the index. The migration tool sorts the index based on the retrieved location. The migration tool processes the plurality of files based the sorted index, such that the sorted index causes the key information file to be processed last.

Abstract: Embodiments of the present disclosure a method, device and computer program product for storage management. The method comprises: determining, from a storage system, a plurality of storage areas corresponding to a plurality of files; selecting, from the plurality of storage areas, a pair of first storage area and second storage area, both the first storage area and the second storage area having non-empty available space; moving at least part of data stored in used space of the first storage area to available space of the second storage area; and in response to determining that the used space of the first storage area becomes empty after the moving, releasing the first storage area. In this way, the storage space can be effectively released and the storage efficiency is accordingly improved.

Abstract: According to example embodiments of the present disclosure, provided is a method, device and computer program product for backing up data. The method comprises: determining a first number of data streams for sending target data; causing the target data to be sent to a buffer via the first number of data streams; determining a second number of data streams for sending the target data from the buffer to a server based on a transmission parameter associated with transmission of the target data to the buffer and a capability of the server for receiving data from the buffer; and causing the target data to be sent from the buffer to the server via the second number of data streams. Thereby, the present solution can improve the performance of sending data in a backup client.

Abstract: Embodiments of the present disclosure provide a method, device and computer program product for storing data. The method comprises creating a first data file having a naming identification at a first node in a Redundant Array of Independent Nodes (RAIN), and creating a second data file having the naming identification at a second node in the RAIN. The method further comprises creating, at a third node in the RAIN, a parity file having the naming identification, wherein the parity file is a parity result of a plurality of data files. According to embodiments of the present disclosure, files in the same parity group are configured with the same or partially the same file name.

Abstract: Embodiments of the present disclosure relate to a method, device and computer program product for backing up data. The method comprises determining, for a data backup to be performed, a first deduplication rate related to a first target server and a second deduplication rate related to a second target server. The method comprises selecting a suitable target server from the first target server and the second target server according to the first deduplication rate and the second deduplication rate. In addition, the method further comprises replicating a portion of data in the data backup to the selected suitable target server.

Abstract: According to example embodiments of the present disclosure, provided is a method, device and computer program product for backing up data. The method comprises: determining a first number of data streams for sending target data; causing the target data to be sent to a buffer via the first number of data streams; determining a second number of data streams for sending the target data from the buffer to a server based on a transmission parameter associated with transmission of the target data to the buffer and a capability of the server for receiving data from the buffer; and causing the target data to be sent from the buffer to the server via the second number of data streams. Thereby, the present solution can improve the performance of sending data in a backup client.

Abstract: Embodiments of the present disclosure provide a method, device and computer program product for managing backup data. The method comprising: obtaining historical information of a plurality of historical operations on target data in a backup storage device during a first time period, the historical information indicating at least types and time of occurrences of the plurality of historical operations; determining, based on the historical information, whether the target data is to be rewritten to the backup storage device within a second time period after the first time period; and in response to determining that the target data is to be written to the backup storage device within the second time period, adjusting an expiration time of the target data in the backup storage device. Based on such a manner, efficiency of the backup system can be increased.

Abstract: Embodiments of the present disclosure relate to a method, device and computer readable storage medium for data collection. The method includes: determining, based on a flag associated with at least some nodes in a tree representation in the backup system, whether a node in the tree representation is associated with a valid backup or an invalid backup; in response to determining that the node is associated with a valid backup, keeping the node and nodes referred to by the node; and in response to determining that the node is associated with an invalid backup, deleting the node.

Abstract: A unified distributed real-time quota limitation system limits use of shared networked resources in distributed networked environment (DNE). A dispatch center determines an amount of shared resources available to client devices in the DNE. The dispatch center determines an amount of the shared resources to allocate for use by the clients, and sends the clients one or more policies having a resource usage quota that limits the amount of the resource that the client can use. When a client receives a request to perform a task that requires a shared resource, before running the task, the client determines its own usage of the resource and terminates the task if running the task will exceed the quota limit of the shared resource.

Abstract: Embodiments of the present disclosure provide to a method, a device and a computer program product for backing up data. The method comprises receiving a request for determining whether a data chunk is backed up and, determining a first identifier of a backup node associated with the data chunk based on a first set of the multiple sets of bits, in response to the first identifier matching the second identifier of the storage node, and determining a file identifier of an index file associated with the data chunk based on a second set of the multiple sets of bits. The method further comprises determining a location, in the index file, associated with the hash value based on a third set of the multiple sets of bits and in response to the index file storing the mapping at the location, sending an indication that the data chunk has been backed up.

Abstract: Embodiments of the present disclosure a method, device and computer program product for storage management. The method comprises: determining, from a storage system, a plurality of storage areas corresponding to a plurality of files; selecting, from the plurality of storage areas, a pair of first storage area and second storage area, both the first storage area and the second storage area having non-empty available space; moving at least part of data stored in used space of the first storage area to available space of the second storage area; and in response to determining that the used space of the first storage area becomes empty after the moving, releasing the first storage area. In this way, the storage space can be effectively released and the storage efficiency is accordingly improved.

Abstract: Embodiments of the present disclosure relate to a method, an electronic device and a computer program product for a creating metadata index. The method disclosed herein comprises: generating a first-level index to index a metadata item; inserting a first indication into the first-level index to indicate a position of the metadata item in a set of metadata; generating a second-level index to index a set of first-level indexes; and inserting a second indication into the second-level index to indicate a set of positions of the set of metadata. In this way, embodiments of the present disclosure can create an index structure which can indicate the position of the metadata item, so as to rapidly determine the position of the metadata item.

Abstract: A unified distributed real-time quota limitation system limits use of shared networked resources in distributed networked environment (DNE). A dispatch center determines an amount of shared resources available to client devices in the DNE. The dispatch center determines an amount of the shared resources to allocate for use by the clients, and sends the clients one or more policies having a resource usage quota that limits the amount of the resource that the client can use. When a client receives a request to perform a task that requires a shared resource, before running the task, the client determines its own usage of the resource and terminates the task if running the task will exceed the quota limit of the shared resource.

Abstract: The present disclosure provides a solution for migrating data. In the solution, a migration tool first receives, from a source server, an index having index values corresponding to a plurality of files stored at the source server. The migration tool then retrieves a location of an index value corresponding to key information file in the index. The migration tool sorts the index based on the retrieved location. The migration tool processes the plurality of files based the sorted index, such that the sorted index causes the key information file to be processed last.