Abstract: A second data source may retrieve metadata for one or more versions of a set of versions of a file stored at the first data source. In some examples, the metadata for the one or more versions of the file may include at least an identifier of the file, a timestamp, and a cryptographic signature. In some examples, generation of the cryptographic signature may be based on the identifier of the file, the timestamp, and a cryptographic key. The second data source may identify a set of versions of the file that were uploaded from a trusted data source to the first data source based on a comparison of the cryptographic signature to a computed cryptographic signature. The second data source may then determine a targeted version of the file and retrieve the targeted version of the file from the first data source.

Abstract: A data management system (DMS) may receive entries corresponding to files and directories of a storage system that changed within a time period. The received entries may include metadata associated with the changed files and directories. The DMS may identify one or more directories that were renamed or deleted within the time period by analyzing the metadata from the received entries. The DMS may identify descendent directories and descendent files corresponding to the one or more renamed or deleted directories. The DMS may update path identifiers associated with the descendent directories and the descendent files based on the metadata from the received entries. The DMS may generate an updated index file based on updating the path identifiers for the descendent directories and the descendent files. The described techniques may enable the DMS to identify renames and deletions with greater efficiency, among other benefits.

Abstract: A second data source may retrieve metadata for one or more versions of a set of versions of a file stored at the first data source. In some examples, the metadata for the one or more versions of the file may include at least an identifier of the file, a timestamp, and a cryptographic signature. In some examples, generation of the cryptographic signature may be based on the identifier of the file, the timestamp, and a cryptographic key. The second data source may identify a set of versions of the file that were uploaded from a trusted data source to the first data source based on a comparison of the cryptographic signature to a computed cryptographic signature. The second data source may then determine a targeted version of the file and retrieve the targeted version of the file from the first data source.

Abstract: A data management system (DMS) may receive entries corresponding to files and directories of a storage system that changed within a time period. The received entries may include metadata associated with the changed files and directories. The DMS may identify one or more directories that were renamed or deleted within the time period by analyzing the metadata from the received entries. The DMS may identify descendent directories and descendent files corresponding to the one or more renamed or deleted directories. The DMS may update path identifiers associated with the descendent directories and the descendent files based on the metadata from the received entries. The DMS may generate an updated index file based on updating the path identifiers for the descendent directories and the descendent files. The described techniques may enable the DMS to identify renames and deletions with greater efficiency, among other benefits.

Abstract: A second data source may retrieve metadata for one or more versions of a set of versions of a file stored at the first data source. In some examples, the metadata for the one or more versions of the file may include at least an identifier of the file, a timestamp, and a cryptographic signature. In some examples, generation of the cryptographic signature may be based on the identifier of the file, the timestamp, and a cryptographic key. The second data source may identify a set of versions of the file that were uploaded from a trusted data source to the first data source based on a comparison of the cryptographic signature to a computed cryptographic signature. The second data source may then determine a targeted version of the file and retrieve the targeted version of the file from the first data source.

Abstract: A second data source may retrieve metadata for one or more versions of a set of versions of a file stored at the first data source. In some examples, the metadata for the one or more versions of the file may include at least an identifier of the file, a timestamp, and a cryptographic signature. In some examples, generation of the cryptographic signature may be based on the identifier of the file, the timestamp, and a cryptographic key. The second data source may identify a set of versions of the file that were uploaded from a trusted data source to the first data source based on a comparison of the cryptographic signature to a computed cryptographic signature. The second data source may then determine a targeted version of the file and retrieve the targeted version of the file from the first data source.

Abstract: The embodiments disclosed herein relate to intelligent configuration of a cloud-service gateway based on a pattern recognition algorithm. A machine-learning model is trained to learn the patterns of correlation among many configuration parameters affecting the performance of the system when processing an observed or estimated workload. Training the model may be performed off-line with performance data observed during experiments performed with a variety of configurations and workloads. Once trained, the model may be used to recommend: (a) new configuration parameter values based on constraints of the system being configured, (b) an amount of work that can be performed at a certain performance level when the system is configured with certain parameter values, or (c) the expected performance level when running a certain workload on the system configured with certain configuration parameter values.

Abstract: The embodiments disclosed herein relate to intelligent configuration of a cloud-service gateway based on a pattern recognition algorithm. A machine-learning model is trained to learn the patterns of correlation among many configuration parameters affecting the performance of the system when processing an observed or estimated workload. Training the model may be performed off-line with performance data observed during experiments performed with a variety of configurations and workloads. Once trained, the model may be used to recommend: (a) new configuration parameter values based on constraints of the system being configured, (b) an amount of work that can be performed at a certain performance level when the system is configured with certain parameter values, or (c) the expected performance level when running a certain workload on the system configured with certain configuration parameter values.

Abstract: The embodiments disclosed herein relate to intelligent configuration of a cloud-service gateway based on a pattern recognition algorithm. A machine-learning model is trained to learn the patterns of correlation among many configuration parameters affecting the performance of the system when processing an observed or estimated workload. Training the model may be performed off-line with performance data observed during experiments performed with a variety of configurations and workloads. Once trained, the model may be used to recommend: (a) new configuration parameter values based on constraints of the system being configured, (b) an amount of work that can be performed at a certain performance level when the system is configured with certain parameter values, or (c) the expected performance level when running a certain workload on the system configured with certain configuration parameter values.

Abstract: The embodiments disclosed herein relate to intelligent configuration of a cloud-service gateway based on a pattern recognition algorithm. A machine-learning model is trained to learn the patterns of correlation among many configuration parameters affecting the performance of the system when processing an observed or estimated workload. Training the model may be performed off-line with performance data observed during experiments performed with a variety of configurations and workloads. Once trained, the model may be used to recommend: (a) new configuration parameter values based on constraints of the system being configured, (b) an amount of work that can be performed at a certain performance level when the system is configured with certain parameter values, or (c) the expected performance level when running a certain workload on the system configured with certain configuration parameter values.

Abstract: A system and method for determining a status of a connection path. For example, the method can include receiving a control message at a first node of a number of nodes that are configured to form a cluster, identifying a second node of the nodes as a node from which the control message was received, identifying a storage device to which the second node is coupled; and determining a status of a connection path. The connection path is between the first node and the second node, and the second node and the storage device. The first node includes a first computer system, and the second node includes a second computer system.

Abstract: A system and method for discovering multiple paths to a disk device are disclosed. For example, the method can include discovering a plurality of paths that exist from a first host computer to a storage device. The plurality of paths includes at least one local path and at least one network path from the first host computer to the storage device. In addition, the first host computer is one of several host computers in a cluster. Once the paths have been discovered, a representation of the paths from the first host computer to the storage device is generated. Such a method can be performed, for example, without user intervention.