摘要:
An apparatus, program product and method of replacing a failed hardware device in a computer each rely solely on program code and/or other computer facilities that are ensured of being available in the computer during a concurrent maintenance operation, so that, even in the event that a failure occurs in such a hardware device, successful performance of the concurrent maintenance operation is ensured. For example, the initiation of power up and power down functions necessary to permit replacement of a failed device may be performed through a control panel or other similar facility in a computer that is continuously available when a computer is in a fully or partially active and powered-on state. Also, a concurrent replacement operation may be supported that automatically detects a lock-up condition resulting from a failed attempt to access data using a failed hardware device, and that, upon replacement of the device with a suitable replacement device, automatically associates a resource that was previously associated with the failed device with the replacement device such that the failed attempt to access data may be automatically resumed, thereby automating the recovery from the lock-up condition.
摘要:
An apparatus, clustered computer system, program product and method assist in the distribution of configuration data such as VPD for a switchable resource to multiple nodes within a clustered computer system. Program code operating as a resource manager is used to enroll a node to receive updates to a switchable resource in the clustered computer system, and, in response to an update to the switchable resource, to notify each enrolled node of the update. Moreover, configuration data is communicated along with the notification to each enrolled node, such that any data required to initiate acquisition of functional ownership of a switchable resource by any such node will be locally available to such node.
摘要:
An apparatus, program product and method of managing computer resources each facilitate concurrent maintenance operations by automatically re-associating existing resources in a computer, when suitable, with appropriate hardware devices installed into the computer after a concurrent maintenance operation has been performed. An existing resource is re-associated with an installed hardware device by updating at least one of a device identifier and a location identifier associated with the resource based upon that of the installed hardware device. A resource identifier for the resource, however, is preserved so that any computer application that relies on the resource can still access the resource without additional manual reconfiguration of the resource or the computer application. Consequently, maintenance operations are substantially simplified and expedited, thereby facilitating system maintenance and minimizing computer downtime.
摘要:
An apparatus, program product and method to dynamically control the bindings between Input/Output Adaptors (IOA's) and Input/Output Processors (IOP's) in a hierarchical I/O interface of a computer, such that an IOA can be dynamically reassigned from one IOP to another IOP such that the latter IOP takes over management of data transfer between the processing complex of the computer and the IOA from the former IOP. At least partial system availability is maintained in the computer during dynamic reassignment to minimize system downtime and simplify maintenance operations on the computer.
摘要:
A resource and partition manager of the preferred embodiments includes a lock mechanism that operates on a plurality of locks that control access to individual I/O slots. The resource and partition manager uses the lock mechanism to obtain a lock on an I/O slot when transferring control of the I/O slot to a logical partition that is powering on and when removing the I/O slot from a logical partition that is powering off. The resource and partition manager uses the lock mechanism to remove control of an I/O slot from, or return control to, an operating logical partition in order to facilitate hardware service operations on that I/O slot or on the physical enclosure in which it is contained.
摘要:
A low-level logical partitioning function associates partitions, partitionable entities, and location codes. Partitionable entities are hardware components, not necessarily individually replaceable. The location code reflects the physical topology of the system packaging. It is preferably a string of concatenated elements, each element representing a device in a hierarchical level of devices which may contain other devices. A respective location code is likewise associated with each of multiple physical indicators. The location code of partitionable entities allocated to a partition is compared with the indicator's location code to determine whether a process executing within a partition can access the indicator. Preferably, each partition has a virtual indicator corresponding to a physical indicator, the state of the physical indicator being derived as a function of the states of multiple virtual indicators for multiple partitions.
摘要:
Systems and methods are provided for performing maintenance on a multiple-slot device having multiple adapters in a computer system including a peripheral interface having a plurality of device connection slots. The invention includes determining that a selected slot on the peripheral interface is associated with an adapter of a multiple-slot device, identifying a further slot associated with the multiple-slot device based on the selected slot, and providing power to, or removing power from, the selected slot and the identified further slot. Numerous other aspects are provided.
摘要:
A low-level logical partitioning function associates partitions, partitionable entities, and location codes. Partitionable entities are hardware components, not necessarily individually replaceable. The location code reflects the physical topology of the system packaging. It is preferably a string of concatenated elements, each element representing a device in a hierarchical level of devices which may contain other devices. A respective location code is likewise associated with each of multiple physical indicators. The location code of partitionable entities allocated to a partition is compared with the indicator's location code to determine whether a process executing within a partition can access the indicator. Preferably, each partition has a virtual indicator corresponding to a physical indicator, the state of the physical indicator being derived as a function of the states of multiple virtual indicators for multiple partitions.
摘要:
A method, apparatus and computer program product are provided for detecting and powering off unused I/O slots in a computer system. For each of the I/O slots, the current slot is checked to determine if the slot is powered on and unlocked. When the current slot is powered on and unlocked, the current slot is checked to determine if the current slot is a candidate for being powered off. When the current slot is determined to be a candidate for being powered off, then the current slot is powered off and the checking continues with a next one of the I/O slots. Recording the slot as a candidate for being powered off before the slot is actually powered off ensures a proper delay to avoid powering off a slot that is about to be locked, which could cause slot power cycles in quick succession.
摘要:
A resource and partition manager of the preferred embodiments includes a lock mechanism that operates on a plurality of locks that control access to individual I/O slots. The resource and partition manager uses the lock mechanism to obtain a lock on an I/O slot when transferring control of the I/O slot to a logical partition that is powering on and when removing the I/O slot from a logical partition that is powering off. The resource and partition manager uses the lock mechanism to remove control of an I/O slot from, or return control to, an operating logical partition in order to facilitate hardware service operations on that I/O slot or on the physical enclosure in which it is contained.