摘要:
A method of error management in a data storage system having a target device, with the target device receiving commands from a first initiator and the target device concurrently receiving commands from a second initiator. The target device is typically a storage device operating as a PPRC secondary. A first initiator is a device which communicates with the target device through small computer systems interface (SCSI) protocol. The first initiator is typically a host computer or server. The second initiator communicates with the target device through peer-to-peer remote copy PPRC initiator mode commands. The second initiator is typically a separate storage device in a peer-to-peer remote copy (PPRC) relationship with the target device. The method consists of managing errors associated with a command sent to the target device from the first initiator independently from the management of errors associated with a command sent to the target device from the second initiator.
摘要:
Provided are a method, system and article of manufacture, wherein in certain embodiments an I/O command from a host is received at a first storage unit. An identifier is generated that identifies a destination to which the I/O command is to be transmitted from the first storage unit. The I/O command is augmented with the generated identifier at the first storage unit. The augmented I/O command is transmitted. In certain other embodiments, an I/O command is received at a storage unit, wherein the storage unit is associated with a storage unit identifier. A determination is made at the storage unit, whether the I/O command is associated with an identifier that identifies a destination for which the I/O command is intended. A further determination is made, at the storage unit, whether the identifier is the same as the storage unit identifier, in response to determining that the identifier associated with the I/O command identifies the destination for which the I/O command is intended.
摘要:
Disclosed is a technique for throttling data transfer. An amount of resources that are in use is determined. When the amount of resources reaches a high threshold, one or more primary control units are notified to temporarily stop sending data. When the amount of resources reaches a low threshold, each previously notified primary control unit is notified to resume sending data.
摘要:
Provided is a method, system and program for synchronizing sequential subtasks of a task, so that the subtasks can be dispatched to generate operations in a particular sequence. In one embodiment, a subtask which has been prepared for dispatching is queued in a queue until the queued subtask is the next subtask in sequence for dispatching. In one embodiment, the subtasks may be sorted in the queue by task and by subtask sequence.