The disclosed technology relates to a system configured to detect a modification to a node in a tree data structure. The node is associated with a content item managed by a content management service as well as a filename. The system may append the filename and a separator to a filename array, determine a location of the filename in the filename array, and store the location of the filename in the node.

A computer-implemented method may comprise providing a first executed agreement cache in a first data center and a second executed agreement cache in a second data center; receiving agreements on proposals to create or make changes to files stored in the first and second data centers; storing metadata of the files referred to by the received agreements the first and/or second executed agreement caches; maintaining the first and second executed agreement caches synchronous with one another before the files referred to by the received agreements are created or changed; creating or making changes to the file referred to by the received agreements only after the first and second executed agreement caches have been synchronized; and searching the first and/or second executed agreement caches for updated metadata whenever requests for data of files stored in the first or second data centers are received in the first or the second data centers and, responsive to the received requests, providing data corresponding to the updated metadata when updated metadata is found.

A computer-implemented method may comprise providing a first executed agreement cache in a first data center and a second executed agreement cache in a second data center; receiving agreements on proposals to create or make changes to files stored in the first and second data centers; storing metadata of the files referred to by the received agreements the first and/or second executed agreement caches; maintaining the first and second executed agreement caches synchronous with one another before the files referred to by the received agreements are created or changed; creating or making changes to the file referred to by the received agreements only after the first and second executed agreement caches have been synchronized; and searching the first and/or second executed agreement caches for updated metadata whenever requests for data of files stored in the first or second data centers are received in the first or the second data centers and, responsive to the received requests, providing data corresponding to the updated metadata when updated metadata is found.

A file storage include: a processor that receives a write request for a file from an application, writes data of the file to a storage unit, then compresses the data of the written file, and writes the compressed data to the storage unit. The processor determines a compression algorithm to be used for the compression according to an amount of data, which is written during a predetermined time, of one or more written files.

A file storage include: a processor that receives a write request for a file from an application, writes data of the file to a storage unit, then compresses the data of the written file, and writes the compressed data to the storage unit. The processor determines a compression algorithm to be used for the compression according to an amount of data, which is written during a predetermined time, of one or more written files.

A system for provisioning resources includes a processor and a memory. The processor is configured to receive a time series of past usage data. The past usage data comprises process usage data and instance usage data. The processor is further configured to determine an upcoming usage data based at least in part on the time series of the past usage data, and provision a computing system according to the upcoming usage data.

A system for provisioning resources includes a processor and a memory. The processor is configured to receive a time series of past usage data. The past usage data comprises process usage data and instance usage data. The processor is further configured to determine an upcoming usage data based at least in part on the time series of the past usage data, and provision a computing system according to the upcoming usage data.

A file system and a related method are presented. The file system includes an object storage configured to store file data for one or more files and a plurality of namespace entries corresponding to file data and/or metadata of the one or more files as one or more objects. Each namespace entry of the plurality of namespace entries includes an operation type conducted on the file data and/or metadata captured in a particular snapshot and a version number corresponding to the particular snapshot. The file system further includes an indexing system configured to generate the plurality of namespace entries; store the plurality of namespace entries as one or more objects in the object storage; and identify, in response to a search query, one or more files for retrieval from the object storage based on a list of the plurality of namespace entries sorted on the version numbers.

Embodiments of small file restore process in deduplication file system wherein restoration requires issuing a read request within an I/O request to the file system. The process places the files in a prefetch queue such that a combined size of the files meets or exceeds a size of the prefetch queue as defined by a prefetch horizon. A file handler disassociates prefetch streams from read streams. The handler prefetches the read operations and stores them in memory. The stream corresponding to a read will only open as the read requests hit the queue processor. As a result, the stream usage is very low, since the I/O, worker threads and the read streams are disassociated from each other.

Embodiments of small file restore process in deduplication file system wherein restoration requires issuing a read request within an I/O request to the file system. The process places the files in a prefetch queue such that a combined size of the files meets or exceeds a size of the prefetch queue as defined by a prefetch horizon. A file handler disassociates prefetch streams from read streams. The handler prefetches the read operations and stores them in memory. The stream corresponding to a read will only open as the read requests hit the queue processor. As a result, the stream usage is very low, since the I/O, worker threads and the read streams are disassociated from each other.