Abstract: Systems and methods are provided for computationally configuring computing devices and performing multi-layer cluster analysis. For example, the system can identify multiple layers of clusters of devices (e.g., shared hardware configuration, shared application configuration, number of applications, etc.) in a large scale infrastructure environment automatically. For each layer of the clusters of devices, parameters of these devices are provided to a machine learning model to produce an objective function (e.g., minimum number of devices, utilization under 80%, etc.), whose output can be provided to a datacenter operator or other user in the large scale infrastructure environment so they can make further configuration changes to the devices in each cluster.

Abstract: Systems and methods are provided for computationally configuring computing devices and performing multi-layer cluster analysis. For example, the system can identify multiple layers of clusters of devices (e.g., shared hardware configuration, shared application configuration, number of applications, etc.) in a large scale infrastructure environment automatically. For each layer of the clusters of devices, parameters of these devices are provided to a machine learning model to produce an objective function (e.g., minimum number of devices, utilization under 80%, etc.), whose output can be provided to a datacenter operator or other user in the large scale infrastructure environment so they can make further configuration changes to the devices in each cluster.

Abstract: The present disclosure provides a method and a system for migrating a virtual file server. In an example of a method, a virtual file server is migrated from a first storage to a second storage, wherein the virtual file server comprises a server layer and a data layer. Identity information is retrieved from the server layer from the server layer for the second storage. The identity information is updated so instantiation of the virtual file server on the second storage appears the same as on the first storage.

Abstract: The present disclosure provides a method and a system for migrating a virtual file server. In an example of a method, a virtual file server is migrated from a first storage to a second storage, wherein the virtual file server comprises a server layer and a data layer. Identity information is retrieved from the server layer from the server layer for the second storage. The identity information is updated so instantiation of the virtual file server on the second storage appears the same as on the first storage.

Abstract: In some examples, a system determines, based on information relating to access of objects in storage segments by requester devices, an affinity between access devices and the storage segments that are managed by respective controllers of a plurality of controllers, the access devices comprising the requester devices or the controllers. The system selects, based on the affinity between the access devices and the storage segments, a controller of the plurality of controllers for serving requests of a first requester device of the requester devices to access objects.

Abstract: Examples of data management for tenants are described herein. In an example, a storage system includes a management tree for each of a plurality of tenants associated with the storage system. The management tree includes data management policies defined by the tenant. Further, the management tree includes a storage tree, which is mapped to a storage domain. The storage domain may hold data pertaining to the tenant. The data may be managed based on the data management policies defined by one of the management tree and the storage tree.

Abstract: In some examples, a system determines, based on information relating to access of objects in storage segments by requester devices, an affinity between access devices and the storage segments that are managed by respective controllers of a plurality of controllers, the access devices comprising the requester devices or the controllers. The system selects, based on the affinity between the access devices and the storage segments, a controller of the plurality of controllers for serving requests of a first requester device of the requester devices to access objects.

Abstract: Examples of data management for tenants are described herein. In an example, a storage system includes a management tree for each of a plurality of tenants associated with the storage system. The management tree includes data management policies defined by the tenant. Further, the management tree includes a storage tree, which is mapped to a storage domain, The storage domain may hold data pertaining to the tenant. The data may be managed based on the data management policies defined by one of the management tree and the storage tree.

Abstract: The present disclosure provides a method and a system for migrating a virtual file server. In an example of a method, a virtual file server is migrated from a first storage to a second storage, wherein the virtual file server comprises a server layer and a data layer. Identity information is retrieved from the server layer from the server layer for the second storage. The identity information is updated so instantiation of the virtual file server on the second storage appears the same as on the first storage.

Abstract: An exemplary embodiment of the present invention provides a method of processing a file system transaction in a distributed file system. The method includes receiving a transaction request from a computer, wherein the transaction request includes file data to be stored and a first segment identifier that determines a destination of the file data. The method also includes generating a first distributed journal record corresponding to the file data. The method also includes generating a first file operation request based, at least in part, on the transaction request. The method also includes sending the first file operation request to a first segment server corresponding to the first segment identifier, wherein the first segment server generates a second distributed journal record corresponding to the file data on a memory device associated with the first segment server.

Abstract: An exemplary embodiment of the present invention provides a method of processing a file system transaction in a distributed file system. The method includes receiving a transaction request from a computer, wherein the transaction request includes file data to be stored and a first segment identifier that determines a destination of the file data. The method also includes generating a first distributed journal record corresponding to the file data. The method also includes generating a first file operation request based, at least in part, on the transaction request. The method also includes sending the first file operation request to a first segment server corresponding to the first segment identifier, wherein the first segment server generates a second distributed journal record corresponding to the file data on a memory device associated with the first segment server.

Abstract: A system includes storage configured to store file system entities, including directories and files, residing in segments of a distributed, segmented single file system, file servers configured to implement the single file system with separate ones of the file servers controlling metadata of separate ones of the segments, and a controller configured to control storage of files in the file system such that for a master file stored in a first segment, a first replica of the master file will be stored in a second segment that is physically separate from the first segment, the controller being further configured to control storage of directories in the file system such that a single directory will include identifiers for the master file and the first replica.

Abstract: The SCSI and iSCSI layers over the TCP/IP layers of the protocol stack in an IP network client and in an IP network-attached storage server are replaced with a thin network block services layer. The network block services layer 71 implements a network block services protocol having a very reduced set of commands transmitted between the client and the storage server. The network block services protocol is used in a configuration process in which logical volumes of the network-attached storage are exported to the client and become local pseudo-disk instances. The client's operating system and application programs access the local pseudo-disk instances with what appears to be a standard device driver for a local disk device. The device driver maintains a TCP connection to each open device, and responds to connection failure by re-connecting with an alternative server IP port.

Abstract: Internally, a production file system and each of its related snapshot file systems have a common file system identifier (fid?) and a unique respective file system identifier (fsid?). Externally, the production file system and each of its related snapshot file systems has a common file system identifier (fsid) and a unique respective file identifier (fid). For example, the “fsid” and “fid” for the production and snapshot file systems are interchanged between a client-server protocol layer and a logical volume layer in a file server. Moreover, the file handle for an object indicates whether an object is in either a production file system that is not configured to have related snapshots, a production file system that is configured to have related snapshots, or a snapshot file system. When the object is in a snapshot file system, the file handle also indicates the related production file system.

Abstract: File system cells are linked together to form a meta file system that appears to a user or application program to be a single file system. The meta file system permits concurrent access by multiple processors in a file server wherein each file system cell is managed by a respective one of the processors. The file server responds to a directory access request by returning a file handle containing a file system cell ID and a pointer to a file in the file system cell. The file server responds to a subsequent file access request including the file handle by extracting the file system cell ID and the pointer to the file, searching a routing table for an entry having a file system cell ID matching the file system cell ID extracted from the file handle, and routing the request to the processor managing the file system cell.

Abstract: Internally, a production file system and each of its related snapshot file systems have a common file system identifier (fid′) and a unique respective file system identifier (fsid′). Externally, the production file system and each of its related snapshot file systems has a common file system identifier (fsid) and a unique respective file identifier (fid). For example, the “fsid” and “fid” for the production and snapshot file systems are interchanged between a client-server protocol layer and a logical volume layer in a file server. Moreover, the file handle for an object indicates whether an object is in either a production file system that is not configured to have related snapshots, a production file system that is configured to have related snapshots, or a snapshot file system. When the object is in a snapshot file system, the file handle also indicates the related production file system.

Abstract: The SCSI and iSCSI layers over the TCP/IP layers of the protocol stack in an IP network client and in an IP network-attached storage server are replaced with a thin network block services layer. The network block services layer 71 implements a network block services protocol having a very reduced set of commands transmitted between the client and the storage server. The network block services protocol is used in a configuration process in which logical volumes of the network-attached storage are exported to the client and become local pseudo-disk instances. The client's operating system and application programs access the local pseudo-disk instances with what appears to be a standard device driver for a local disk device. The device driver maintains a TCP connection to each open device, and responds to connection failure by re-connecting with an alternative server IP port.

Abstract: File system cells are linked together to form a meta file system that appears to a user or application program to be a single file system. The meta file system permits concurrent access by multiple processors in a file server wherein each file system cell is managed by a respective one of the processors. The file server responds to a directory access request by returning a file handle containing a file system cell ID and a pointer to a file in the file system cell. The file server responds to a subsequent file access request including the file handle by extracting the file system cell ID and the pointer to the file, searching a routing table for an entry having a file system cell ID matching the file system cell ID extracted from the file handle, and routing the request to the processor managing the file system cell.

Abstract: To reorganize a striped file system, data blocks are sequentially moved from storage locations in original data storage to storage locations in an array including the original data storage and additional data storage. If the new striping has the same precedence order as the original striping, then temporary storage is not needed for the block movement. Otherwise, stripes of the data blocks are sequentially moved to a stripe of temporary storage locations, and moved from the stripe of the temporary locations to storage locations in the array. Once a pivot point is reached, however, there is no need to use the temporary storage. Moreover, there is an increasing separation between the read and write pointers. Once this separation exceeds the stripe length, the file system metadata can be synchronized at decreasing intervals and still permit concurrent read access.

Abstract: Mirrored data is contained in a first data storage device array and also in a second data storage device array. However, devices in the first array are not simply mirrors of devices in the second array. Instead, each data storage device in the second array contains a respective share of the mirrored data contained in each data storage device in the first array, and each data storage device in the first array contains a respective share of the mirrored data contained in each data storage device in the second array. Therefore, when a data storage device in one array fails, the failure load is spread over the data storage devices of the other array. For disk storage devices, the mirrored data can be arranged in the first and second arrays so that the mirrored data is contained at the same disk track radius in both arrays in order to equalize seek time for write access or sequential read access to both arrays.