Disclosed are a method and device for detecting an abnormal load. The method includes: collecting data of each load item in all hosts; pre-processing to obtain a second sequence corresponding to each load item; obtaining a coefficient matrix and a detail vector; computing a weighted mean of abnormal load probabilities of all the coefficient vectors, to obtain an abnormal load probability of each second sequence; comparing the abnormal load probability with a confidence interval, and judging whether there is an abnormal load, and judging that there is no abnormity in the corresponding second sequence if the abnormal load probability of each second sequence is in the confidence interval; judging whether there is an abnormal load according to data of all load items and the abnormal load probability of each second sequence; and finding a bearing host that has the abnormal load from the current online service.

An aspect includes determining a host write rate based on a number of chunks written to a storage volume during a first replication cycle and determining a target rate based on an estimated number of chunks written during a second replication cycle. The target rate is determined by dividing the number of chunks written during the second replication cycle by a recovery point objective (RPO) period. An aspect also includes transmitting chunks written during the second replication cycle at the target rate.

The rebuilding process comprises the steps of detecting a failure on a first server that stores a first data and processes input/output requests from an application, redirecting incoming input/output requests from the application to a second server storing a second data. The second data being mirrored from the first data. The process further comprises forming, by the first server, a data loss information that identifies the lost data units in the first data. The process further comprises rebuilding, by the first server, the lost data units in the first data, by using the data that is retrieved from the second data and based on the data loss information by the second server. The process further comprises syncing up data units, other than the lost data units in the first data, with corresponding data in the second data in the second server during the rebuilding process.

Methods, computer program products, and systems are presented. The methods include, for instance: analyzing a dataset associated with a service provided by the data protection service provider in order to determine a policy for when and how to replicate the respective components of the dataset corresponding to the service from a source site to a target site, such that the target site may perform the service with a minimum cost.

According to an example, a memory network includes memory nodes. The memory nodes may each include memory and control logic. The control logic may operate the memory node as a destination for a memory access invoked by a processor connected to the memory network and may operate the memory node as a router to route data or memory access commands to a destination in the memory network.

The disclosed computer-implemented method for managing replication of data to a remote storage device may include (1) maintaining a first bitmap and a second bitmap storing data acknowledging persistence of target data, respectively, at source and target gateways, where the target gateway serves the remote storage device, (2) sending replication data from a computing device to the source gateway, (3) setting a bit in the first bitmap, where the set bit corresponds to the replication data sent to the source gateway, (4) receiving a first acknowledgement indicating the source gateway received the replication data, (5) copying, in response to the first acknowledgement, the bit to the second bitmap, (6) clearing, in response to the first acknowledgement, the bit in the first bitmap, and (7) receiving a second acknowledgement indicating the target gateway received the replication data. Various other methods, systems, and computer-readable media are also disclosed.

In one embodiment, upon initiation of a consistency group, bandwidth reduction scanning logic determines whether a volume portion such as a track containing data which is to be mirrored from a primary volume to a secondary volume to form a consistency group, is allocated to the primary volume. If not, the bandwidth reduction scanning logic causes the data of the associated volume portion to not be mirrored from the primary volume to the secondary volume. As a result, the volume portion determined to not be allocated to the primary volume is bypassed by the mirroring operation, thereby reducing bandwidth usage by the mirroring and accelerating the formation of a consistency group. Other features and aspects may be realized, depending upon the particular application.

A first compute node of a plurality of compute nodes of a database cluster may receive a request for a database transaction from a client application. The client application may be located within the first compute node. A first connection may be established, without regard to whether another compute node has a lighter workload than the first compute node, between the client application and a first database of the database cluster. The first connection may be a local connection, wherein the first database is located within the first compute node. The first compute node may detect that a failure associated with the first database has occurred. The first compute node may execute a failover operation to continue servicing the request for the data. The executing of a failover operation may include establishing a second connection between the client application and a second database of the database cluster.

A storage system in one embodiment is configured to participate as a source storage system in a synchronous replication process with a target storage system. In conjunction with the synchronous replication process, the source storage system receives write requests from at least one host device. Responsive to a given write request being a multi-page write request, an entry is created in a first journal, where the first journal is utilized to ensure that the given write request is completed for all of the pages or for none of the pages. Responsive to the write request being a single-page write request, an entry is created in a second journal different than the first journal. An address-to-signature table is updated utilizing write data of the write request, and if the corresponding entry for the write request was created in the first journal, the entry is swapped from the first journal into the second journal, and the write data of the write request is sent to the target storage system.

Provided are techniques for delayed consistent point-in-time copy from a secondary device in an asynchronous mirror relationship. A consistent asynchronous mirror copy that includes an asynchronous mirror copy from a primary volume to a secondary volume and a point-in-time copy from the secondary volume to a tertiary volume is performed. A point-in-time copy is created from the secondary volume to an accessible consistent copy volume. In response to receiving a request to access a track of the accessible consistent copy volume, it is determined whether to access the track of one of the secondary volume, the tertiary volume, and the accessible consistent copy volume. A response to the request is provided with data accessed from the determined one of the secondary volume, the tertiary volume, and the accessible consistent copy volume.