Abstract: A cache page management method can include paging out a memory page to an input/output controller, paging the memory page from the input/output controller into a real memory, modifying the memory page in the real memory to an updated memory page and purging the memory page paged to the input/output controller.

Abstract: The present invention relates to the use of RFID technology to identify the specific location of cable ends in a network configuration. An end of a cable has an attached RFID tag capable of storing cable identification information. The cable end is connected to an endpoint adapter having a means for communicating with the identification adapter in the cable end. A database stores the cable identification information read by the communication means within the endpoint adapter.

Abstract: A storage area network cable apparatus can include a cable, an identification adaptor disposed in the cable, an illuminator disposed in the identification adaptor, an endpoint adaptor disposed at an end of the cable and an integrated device disposed in the endpoint adapter and configured to generate a frequency in the cable.

Abstract: A cache page management method can include paging out a memory page to an input/output controller, paging the memory page from the input/output controller into a real memory, modifying the memory page in the real memory to an updated memory page and purging the memory page paged to the input/output controller.

Abstract: Disclosed are a method, information processing system, and computer readable medium for resource recovery. The method comprises associating at least one bit with at least one block of memory. The bit denotes a borrow status for the block of memory. The bit is set for resource recovery. A resource recovery event is detected and in response to the bit being enabled for resource recovery, the block of memory is borrowed for a given duration of time. The block is borrowed to temporarily store information associated with the resource recovery there into until the information is written to persistent storage.

Abstract: A method, data processing system and program product for protecting against stale page overlays which includes executing a process in memory of the data processing system. A storage controller pages data from the memory to a disk in pages when the memory is constrained by other processes being executed by the data processing system. Data is then paged from the disk into memory in a one or more paged-in pages. The paged-in page is updated with updated data by the process, and the version on the disk is marked as stale. The storage controller commands the disk to make the stale disk version of the updated paged-in page as write-only, thereby providing that the disk version may be overwritten with new data while providing that the disk version cannot be read.

Abstract: Disclosed are a method, information processing system, and computer readable medium for resource recovery. The method comprises associating at least one bit with at least one block of memory. The bit denotes a borrow status for the block of memory. The bit is set for resource recovery. A resource recovery event is detected and in response to the bit being enabled for resource recovery, the block of memory is borrowed for a given duration of time. The bit is borrowed to temporarily store information associated with the resource recovery there into until the information is written to persistent storage.

Abstract: Disclosed are a method, system and computer program for purging data in a data storage system comprising a plurality of hosts one or more data storage devices and a controller, the controller including a cache. In accordance with the present invention, a communication interface is implemented between operating systems (OS) and the storage controller, of a multi-host data storage system, to signal the storage controller when the host is being shutdown. When the storage controller gets the signal, the controller purges the controller cache of any pages belonging to that host and puts those pages back into the free pool.

Abstract: A memory management method is disclosed. In response to a process running in a first memory and the first memory becoming constrained by demands from another process, information in the first memory is paged out to a second memory. In response to a request to further run the process, the information from the second memory is paged into a read cache and then into the first memory, while a copy of the information is left the read cache. In response to the information in the first memory then being updated and the copy of the information in the read cache now becoming stale, the now stale copy of the information in the read cache is checked for and purged, and indication is provided that the read cache has been purged.