Provided are a computer program product, system, and method for using a cascade flag to process a copy relationship having a backward cascade copy relationship. Each of a plurality of copy relationships indicates to copy source data to target data and has a cascade flag. The cascade flag for a forward copy relationship of the copy relationships is set to a first value in response to determining that the source data for the forward copy relationship comprises target data for a backward copy relationship and that a background copy operation specified to copy source data to target data of the backward copy relationship has not completed. The cascade flag for the forward copy relationship is set to a second value in response to determining that the backward copy relationship does not have an uncompleted background copy operation.

Disclosed herein are systems and methods for providing on-the-fly padding to feature maps of convolutional neural networks (CNNs). In an implementation, a processor first identifies a padding schema for a feature map based on a type of convolution to be performed on the feature map. Next the processor identifies a feature vector from the feature map currently in an associated memory. Then, the processor determines a padding for the feature vector based on the padding schema. Finally, the processor applies the padding to the feature vector while the feature vector is transferred from the associated memory to registers of the suitable computer.

A command to transfer data in a portion of a memory component to a recovery portion of a different memory component is received from a host system, wherein the portion of the memory component is associated with a portion of the memory component that has failed, and the data in the portion of the memory component is recovered and transferred to the recovery portion of the different memory component without moving or processing the data through the host system responsive to receipt of the command.

A technique is directed to processing metadata changes. The technique involves designating a first tablet to ingest metadata changes and a second tablet to destage previously ingested metadata changes, the first tablet being partitioned into a first reserved space and a first regular space that form a first memory pool, and the second tablet being partitioned into a second reserved space and a second regular space that form a second memory pool. The technique further involves, while the first tablet is designated to ingest metadata changes and the second tablet is designated to destage previously ingested metadata changes, ingesting metadata changes into the first tablet and destaging the previously ingested metadata changes from the second tablet. The technique further involves, when the first tablet becomes full, performing a switch operation that designates the second tablet to ingest metadata changes and the first tablet to destage previously ingested metadata changes.

Systems and methods for securely and remotely storing data in a remote, distributed redundant array of independent drives (RAID) is provided. RAID storage is accomplished through a series of mapped drives, non-routable Internet protocol (IP) addresses, and routable IP addresses. In addition, authorization to access a RAID controller, network address translation (NAT) system, and domain name system (DNS) system may all be separated, increasing security and allowing storage to be securely distributed among a variety of dispersed storage locations.

A main data storage system has a main computer-implemented storage control and data storage, and a user interface, the main storage control in communication with a local computer-implemented storage control of a local data storage system with local data storage. In response to a request to increase data storage from the user interface, the main storage control determines whether the main data storage is out of space. If so, the main storage control sends a command to the local storage control to create data space in local data storage. The local storage control creates the data space and associates the data space with the main storage control; and, in response to a command from the user interface to rebalance data storage, the local storage control sends the command to the main storage control to search for storage space sufficient for the data space in the main storage.

The system includes a plurality of storage volumes, a data synchronization module, a space-efficient storage module, and a heat data module. A second storage volume of the plurality of storage volumes includes a backup storage location for a first storage volume. The data synchronization module, coupled to the first storage volume and the second storage volume, provides a backup by synchronizing information from the first storage volume to the second storage volume during a synchronization event. The information includes data chunks, heat map data, and first metadata. The space-efficient storage module receives the information from the data synchronization module and allocates the information to the second storage volume in accordance with a space-efficient storage model. The heat data module reads the first metadata and the heat map data and adjusts a location of the data chunks in the second storage volume based on the heat map data.

Apparatuses and methods are disclosed for protection of data servers configured for data replication of a database. As an example, one apparatus includes at least one processing circuit configured to receive records indicating respective modifications performed on a first version of the database stored in a first data server of the plurality of data servers. The at least one processing circuit is configured to delay replication of the modification in one or more additional servers in the plurality of data servers for a respective length of time specified for the servers in a security profile. While delaying replication of the modification, the processing circuit determines a probability that the modification is malicious based on a first set of factors indicated in a security profile. If the probability is greater than a threshold specified in the security profile, the processing circuit prevents the modification from being performed.

A method, storage control system and information handling system (IHS) provides copying of a first directory containing a first plurality of files from a client to a target server. The method includes receiving, via a first processor of the client, a request to copy the first directory containing the first plurality of files from a first storage device to the target server. The first directory is parsed into a first i-node tree. Metadata corresponding to the first i-node tree is generated and transmit from the client to the target server. A second processor at the target server is triggered to generate a second directory based on the metadata corresponding to the first i-node tree. The first plurality of files contained in the first directory from the first storage device is transmitted to the target server.

A memory system includes a memory device comprising a plurality of memory blocks each memory block having N word line groups, N being a natural number equal to or more than 2; and a controller suitable for: selecting bad memory blocks among the memory blocks; arranging normal word line groups of the selected bad memory blocks into one or more memory-block-word-line groups each including non-conflicting N normal word line groups; and managing each of the memory-block-word-line groups as a reused memory block, the controller manages a reused block mapping table including a plurality of entries respectively corresponding to the memory-block-word-line groups, the reused block mapping table includes a plurality of logical addresses respectively corresponding to the entries, and each of the entries includes a plurality of physical address values respectively corresponding to the selected bad memory blocks having the normal word line groups included in the corresponding memory-block-word-line group.