Abstract: A system can maintain information indicative of prohibited computer operations, wherein the information is accessible to respective computing clusters of a group of computing clusters, and wherein the information is stored separately from the group of computing clusters. The system can obtain, by a service of a first computing cluster of the group of computing clusters, the information. The system can, in response to receiving, at the first computing cluster, a request to perform an operation on a first computer of the first computing cluster, in response to determining, based on the information, that the operation is prohibited, prevent the operation from occurring; and, in response to determining, based on the information, that the operation is not prohibited, permit the operation to occur.

Abstract: An archival job is assessed to calculate loss of data reduction efficiency due to block-level data deduplication. Archivable data, or individual storage objects or data structures therein, are moved to archival storage contingent upon satisfaction of a predetermined condition related to data reduction efficiency. Archivable data, or individual storage objects or data structures therein, that fail to satisfy the predetermined condition are maintained in primary storage. The loss of data reduction efficiency and the predetermined condition may be expressed as a percentage of maximum possible data reduction that would result in the absence of data deduplication.

Abstract: A system can maintain information indicative of prohibited computer operations, wherein the information is accessible to respective computing clusters of a group of computing clusters, and wherein the information is stored separately from the group of computing clusters. The system can obtain, by a service of a first computing cluster of the group of computing clusters, the information. The system can, in response to receiving, at the first computing cluster, a request to perform an operation on a first computer of the first computing cluster, in response to determining, based on the information, that the operation is prohibited, prevent the operation from occurring; and, in response to determining, based on the information, that the operation is not prohibited, permit the operation to occur.

Abstract: A system can determine to perform a replication of data from first computing equipment to second computing equipment, wherein the data is stored within a path in a file system of the first computing equipment. The system can determine the path from a replication policy for the replication. The system can, while tree-walking the path, in response to determining that a first file is marked for priority replication, adding the first file to a priority queue, and in response to determining that a second file lacks a marking for priority replication, adding the second file to a normal queue. The system can, in response to determine that the priority queue contains files, replicating the files from the priority queue instead of replicating other files from the normal queue.

Abstract: A system can determine to perform a replication of data from first computing equipment to second computing equipment, wherein the data is stored within a path in a file system of the first computing equipment. The system can determine the path from a replication policy for the replication. The system can, while tree-walking the path, in response to determining that a first file is marked for priority replication, adding the first file to a priority queue, and in response to determining that a second file lacks a marking for priority replication, adding the second file to a normal queue. The system can, in response to determine that the priority queue contains files, replicating the files from the priority queue instead of replicating other files from the normal queue.

Abstract: A system can determine to perform a replication of data from first computing equipment to second computing equipment, the data being stored as part of a path in a file system. The system can determine that a change log of file operations on files in the path identifies a file operation on a file that is made by a user account that has priority for replications. The system can replicate the file. The system can, after processing the change log for file operations made by first user accounts that have priority for replications, replicating other files in the path associated with second user accounts that do not have priority for replications.

Abstract: A system can to perform a replication of data from first computing equipment to second computing equipment, the data being stored as part of a path in a file system. The system can, from a replication policy for the replication, a priority sub-path of the path. The system can add a first set of files to a transfer queue comprising tree-walking the priority sub-path. The system can, after adding the first set of files, adding a second set of files to the transfer queue comprising tree-walking a portion of the path that is different from the priority sub-path. The system can replicate files in the transfer queue from the first computing equipment to the second computing equipment.

Abstract: Techniques are provided for identifying and deleting idle remote sessions in a distributed file system. In an example, a server that serves a plurality of server message block (SMB) sessions analyzes those sessions to determine which sessions are idle. Of the idle sessions, the server can determine which possess a lock on a computer file. Where another, active session is waiting for that resource, the server can terminate the idle session and release the lock so that the active session acquires access to the requested computer file.

Abstract: Techniques are provided for predicting and deleting idle remote sessions in a distributed file system. In an example, a server that serves a plurality of server message block (SMB) sessions analyzes with linear regression techniques those sessions to determine which sessions will become idle. In some examples, the server can then proactively close a SMB session that it predicts that an administrator would choose to close after a given idle period of time, or recommend to an administrator that the SMB session can be closed.

Abstract: Efficient configuration replication using a configuration change log is described herein. A method as described herein can include identifying, by a device operatively coupled to a processor, modified configurations from among a group of configurations associated with a first computing cluster; fetching, by the device, the modified configurations from the first computing cluster; and replicating, by the device, the modified configurations from the first computing cluster to a second computing cluster that is distinct from the first computing cluster and omitting replication of one or more unmodified configurations from among the group of configurations associated with the first computing cluster.

Abstract: Efficient configuration replication using a configuration change log is described herein. A method as described herein can include identifying, by a device operatively coupled to a processor, modified configurations from among a group of configurations associated with a first computing cluster; fetching, by the device, the modified configurations from the first computing cluster; and replicating, by the device, the modified configurations from the first computing cluster to a second computing cluster that is distinct from the first computing cluster and omitting replication of one or more unmodified configurations from among the group of configurations associated with the first computing cluster.

Abstract: Techniques are provided for predicting and deleting idle remote sessions in a distributed file system. In an example, a server that serves a plurality of server message block (SMB) sessions analyzes with linear regression techniques those sessions to determine which sessions will become idle. In some examples, the server can then proactively close a SMB session that it predicts that an administrator would choose to close after a given idle period of time, or recommend to an administrator that the SMB session can be closed.

Abstract: Techniques are provided for identifying and deleting idle remote sessions in a distributed file system. In an example, a server that serves a plurality of server message block (SMB) sessions analyzes those sessions to determine which sessions are idle. Of the idle sessions, the server can determine which possess a lock on a computer file. Where another, active session is waiting for that resource, the server can terminate the idle session and release the lock so that the active session acquires access to the requested computer file.

Abstract: Implementations are provided herein for optimizing the usage of cluster resources in a cluster of nodes operating as a distributed file system. A node relative capacity table can be generated that inventories the total capacity of each node within the cluster of nodes. Each node can then be dynamically monitored for usage of node resources. A node available capacity table can be dynamically populated with the amount of available capacity each node has for compute, memory usage, and network bandwidth. When clients connect to the distributed file system, they can be directed to have their requests serviced by nodes with greater available capacity based on policy.