摘要:
Described are techniques for indicating a state associated with a device. A request is received over a path for information about a device. A response to the request is sent. The response indicates a state regarding the device on the path. The response has a response status of good and a payload of a varying size. The payload is truncated at a location prior to that at which a device identifier for the device is expected. In accordance with the response, a state regarding the device on the path is determined.
摘要:
Described are techniques for indicating a state associated with a device. A request is received over a path for information about a device. A response to the request is sent. The response indicates a state regarding the device on the path. The response has a response status of good and a payload of a varying size. The payload is truncated at a location prior to that at which a device identifier for the device is expected. In accordance with the response, a state regarding the device on the path is determined.
摘要:
Described are techniques for indicating a state associated with a device. A request is received over a path for information about a device. A response to the request is sent. The response indicates a state regarding the device on the path. The response has a response status of good and a payload of a varying size. The payload is truncated at a location prior to that at which a device identifier for the device is expected. In accordance with the response, a state regarding the device on the path is determined.
摘要:
An in-band protocol transport carries command-response protocol communications between first and second functional components of a storage input/output (I/O) interface stack, for example to control encryption-related processing of storage I/O commands. A storage read command used as a protocol transport message has protocol data in a read data buffer, and predetermined read address information, such as a prime-numbered starting block address and a small, odd-valued length value, unlikely to occur in normal (non-transport) storage read commands. The second functional component determines that the storage read command contains the predetermined read address information, indicating that the storage read command is a protocol transport message rather than a normal read. For greater confidence, it also determines that the protocol data in the read data buffer includes protocol identification data such as a protocol signature. The protocol data is used to control a processing action for subsequent normal storage I/O commands, such as encryption-related processing, and a protocol response is returned by creating and storing response data in the read data buffer and signaling completion of the storage read command to the first functional component.
摘要:
A system shares encryption-related metadata between layers of a storage I/O stack. Additionally, a detection mechanism ensures that certain layers within the storage I/O stack are present and cooperate with a particular protocol. Along these lines, functional components engage in an in-band communications protocol, such as a data encryption key (DEK) management protocol. The in-band communications protocol employs protocol commands and responses carried along the data path as contents of in-band transport messages and responses, such as special SCSI read commands and their responses. The protocol commands and responses include a handshake command and a handshake response used during an initial handshake operation. Each protocol command and response has a protocol signature field carrying one of distinct first and second signature values which are used to identify the presence of the protocol command or response in the transport messages and responses at different locations along the data path.
摘要:
A method of performing data migration from a source storage device to a target storage device in a failover cluster includes use of a roll-forward flag to signal successful completion of a migration operation from a migration node to failover nodes of the cluster, reliably controlling host access to the target storage device to ensure that it is used only when it has been successfully synchronized to the source storage device and a commit operation has occurred that ensures that subsequent read and write operations are directed exclusively to the target storage device.
摘要:
A computer of a data processing system includes a software encryption engine and path circuitry that initially provides one or more paths for conveying data of storage I/O requests to and from a storage device, the paths including an encrypting path having a hardware encrypting component. According to a failover technique, in a first operating state, (a) the data of the storage I/O requests is conveyed via the encrypting path with encryption and decryption of the data being performed by the hardware encrypting component, and (b) monitoring is performed for occurrence of an event indicating that the hardware encrypting component has become unavailable for encrypting and decrypting the data of the storage I/O requests. Upon occurrence of the event, if the path circuitry provides a non-encrypting path for conveying the data of the storage I/O requests to and from the storage device, then operation is switched to a second operating state in which the data of the storage I/O requests is conveyed via the non-encrypting path and is encrypted and decrypted by the software encryption engine. A failback technique provides for reverting to hardware-assisted encryption under proper circumstances.
摘要:
An improved technique migrating data from a source LUN (logical unit) to a target LUN manages control I/O's in a manner that depends on the current state of data migration and on whether the control I/O's specify that reservation information for a LUN is to be set or queried. Control I/O's specifying reservation settings during the different states of migration are treated the same way as data WRITEs during those respective states, and control I/O's specifying reservation queries during different migration states are treated the same way as data READs during those respective states.
摘要:
Methods and systems for preserving disk geometry when relabeling a data volume encapsulated in a virtual storage device that presents a different disk geometry than the data volume. An exemplary method includes maintaining information from a label of the data volume in a memory associated with the virtual storage device and intercepting a request for information related to a disk geometry of the encapsulated data volume that is normally answered without reference to the label. The request may be associated with a command to relabel the encapsulated data volume. The method also includes reporting the information from the label of the data volume related to the disk geometry of the data volume if the label is associated with an operating system that considers a geometry of a data volume when partitioning.
摘要:
Described are techniques for overriding an existing device reservation. Discovery processing is performed by a first data storage system to locate a specified device. The discovery processing includes determining whether there is a reservation conflict for said device of a second data storage system. If there is a reservation conflict for the device, a command is issued from the first data storage system to the second data storage system during said discovery processing to create an override for said reservation conflict. The override causes processing to be performed at a subsequent point in time so that an existing reservation associated with the reservation conflict is overridden in connection with performing a first process on said first data storage system.