International Business Machines Corporation

Anthony D Hooten

Keith E Duvall

Todd A Smith

Larry K Loucks

John C O'Quin, Iii

A memory management system method increases the size of a segment in blocks of 64K virtual pages in response to the system detecting that the requested page has been protected. The conventional UNIX type System Calls create and open files in virtual memory. All pages are protected 'read only' until a SHMAT type System Call is made to operate on a page at a specific address. At that point in the process, a protection exception is recognized by the system and the UNIX kernel takes control to remove the protection and update the appropriate data structures to reflect the new status of the page and the addresses in real memory where the page may be found. Segments containing mapped files are also extended by the method.

Method to automatically increase the segment size of unix files in a

A method for accessing information in a page segmented virtual memory data processing system in which virtual machines running UNIX type operating systems are concurrently established, and in which a memory manager controls the transfer of information between primary and secondary storage devices in response to the occurrence of page faults. The method establishes a plurality of data structures in a dynamic manner in response to a Supervisor call to 'map' a file. The mapping process assigns a new segment of virtual memory to the mapped file and correlates, in one data structure, the virtual address of each page of data in the new segment to a disk file address where that page is actually stored. A UNIX system call by an application program for a specific virtual page is handled by the page fault hanger, and not the UNIX kernel, since the application can supply the real address of the page on the disk file from the data structure that was created by the mapped page range Supervisor call. Simple load and store type of instructions are employed for the data transfer, which avoids much of the overhead that normally accompanies conventional UNIX read and write system calls to the storage subsystem.

Method to control I/O accesses in a multi-tasking virtual memory virtual

A method for facilitating the interchange of data in a UNIX* file between two UNIX processes being run concurrently on two virtual machines in a page segmented virtual memory virtual machine type data processing system. A Shared Copy-On-Write (SCOW) command is created for the UNIX type operating system which when executed in response to a system call from one processes causes the specified UNIX file to be mapped to a unique segment of the virtual memory. A map node data structure is established for storing the ID of the unique segment and for maintaining a count value of the number of user sharing the unique segment. A system call to the SCOW command by the second process involving the same UNIX file checks the map node data structure to see if the file is currently mapped for the SCOW mode. Subsequent instructions in the application programs which are run concurrently on the virtual machines operate on the copy of the file in the unique segment so that any data that is changed, i.e. written by one process, is available to be read by the second process.

Growing community of inventors

Round Rock, TX, United States of America

Anthony D Hooten