Abstract: Techniques for managing metadata storage units involve: in response to receiving, from a client, a request for allocating a target number of metadata storage units, determining a first number of available metadata storage units remaining in a metadata storage space of a storage system after the allocation is performed; and if the first number is not less than a reserved number, allocating the target number of metadata storage units from the metadata storage space for the client to use, wherein the reserved number is associated with a usage condition of the metadata storage units in the storage system. Accordingly, such techniques can effectively manage metadata and improve the performance of a system.

Abstract: Techniques for replicating data involve: determining overwritten probabilities of a plurality of data blocks of a source storage device. The techniques further involve: classifying the plurality of data blocks as cold data blocks or hot data blocks based on the overwritten probabilities in the plurality of data blocks. The techniques further involve: replicating at least a portion of the cold data blocks to a target storage device prior to the hot data blocks. Accordingly, transmission resources used to re-replicate overwritten data during an initial replication period can be reduced, thereby achieving efficient data replication.

Abstract: A method of initializing a data storage system (DSS) is provided. The method includes (a) in response to the DSS booting, reading data from a first plurality of disks marked as part of a raw mirror which mirrors configuration data of the DSS between the first plurality of disks; (b) comparing sequence numbers from the read data read and selecting data from a disk of the first plurality having a latest sequence number; (c) obtaining configuration data of the DSS from the selected data; (d) using the configuration data to construct a topology of the DSS which includes information describing a relationship between a second plurality of disks of the DSS, RAID groups of the DSS, and logical disks presented to users, the second plurality of disks being larger than and including the first plurality of disks; and (e) initializing the RAID groups and the logical disks described by the topology based on the information of the topology.

Abstract: Methods and apparatus are provided for real-time ad hoc querying of data records, such as call detail records.

Abstract: A computer program product, system, and method for generating and storing a parity chunk using at least a first chunk and a second chunk; detecting at least one unused segment within the first chunk; generating a new chunk as a third chunk; associating one or more used segments from the first chunk to the third chunk; filling an unused segment within the third chunk with new data; calculating a delta parity between the first chunk and the third chunk; and updating the stored parity chunk using the delta parity.

Abstract: A method and system for implementing enhanced indexing in a backup system as well as manage file recovery. The method implemented at a backup server receives a filename from a client to be retrieved from a backup system and queries the filename on a directory records database. As a query return, a directory record is received including a savetime identifying a backup instance and an inode of a directory for the filename of the requested file. The process then queries the inode on a node records database and receives at least one node record where the node record has the inode of the directory record as a parent.