摘要:
A non-disruptive upgrade (NDU) technique involves installing and activating a first copy of a new version of an application in a temporary directory to (i) obtain control from an original version of the application while the original version is installed in an application directory and (ii) shut down the original version. The technique further involves, after the first copy of the new version obtains control from the original version and the original version is shut down, installing and activating a second copy of the new version of the application in the application directory to (i) obtain control from the first copy of the new version while the first copy of the new version is installed in the temporary directory and (ii) shut down the first copy of the new version. Such operation maintains the continuity of work at each phase of the NDU technique.
摘要:
A method of registering a host bus port (HBP) of a host computer (host) at a storage bus port (SBP) of a data storage array over a storage network includes (a) acquiring a configuration instruction directing the host to process registration messages from an event processing engine, (b) receiving a registration message from the event processing engine indicating that the HBP needs to be registered with the SBP, the registration message having been generated by the event processing engine in response to receiving an event notification message indicating that a data path across the storage network between the HBP and the SBP is available, and (c) in response to receiving the registration message, processing the registration message by registering the HBP with the SBP by sending a registration command from the HBP to the SBP across the storage network, the registration command including registration information associated with the HBP.
摘要:
A method, system, and a computer program product for improving IO (input/output) performance of host systems using external storage systems. An aspect of the present invention predicts policies to be applied in the host system based on historical information. Several characteristics of a set of IO requests sent by a host system are collected and analyzed to determine a usage/IO pattern. A suitable policy is then determined based on the pattern and applied on the host system when a similar pattern of IO requests is sought to be sent again, thereby improving the IO performance of the host system.