Scalable partition memory mapping system

• US 20070067366A1
• Filed: 10/07/2004
• Published: 03/22/2007
• Est. Priority Date: 10/08/2003
• Status: Abandoned Application

• Current Assignee: Unisys Corporation
• Original Assignee: Unisys Corporation
• Inventors: Landis, John
• Application Number:
  US10/575,394
• Publication Number:
  US 20070067366A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 12/1009 using page tables, e.g. page table structures
• CPC Class Codes: G06F 12/1036 for multiple virtual address spaces, e.g. segmentation G06F12/1045 takes precedence
• CPC Class Codes: G06F 12/109 for multiple virtual address spaces, e.g. segmentation G06F12/1036 takes precedence
• CPC Class Codes: G06F 2212/652 Page size control
• CPC Class Codes: G06F 9/455 Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines

Abstract

A virtualization infrastructure that allows multiple guest partitions to run within a host hardware partition. The host system is divided into distinct logical or virtual partitions and special infrastructure partitions are implemented to control resource management and to control physical I/O device drivers that are, in turn, used by operating systems in other distinct logical or virtual guest partitions. Host hardware resource management runs as a tracking application in a resource management “ultravisor” partition, while host resource management decisions are performed in a higher level command partition based on policies maintained in a separate operations partition. The conventional hypervisor is reduced to a context switching and containment element (monitor) for the respective partitions, while the system resource management functionality is implemented in the ultravisor partition. The ultravisor partition maintains the master in-memory database of the hardware resource allocations and serves a command channel to accept transactional requests for assignment of resources to partitions. It also provides individual read-only views of individual partitions to the associated partition monitors. Host hardware I/O management is implemented in special redundant I/O partitions. A scalable partition memory mapping system is implemented in the ultravisor partition so that the virtualized system is scalable to a virtually unlimited number of pages. A log (2¹⁰) based allocation allows the virtual partition memory sizes to grow over multiple generations without increasing the overhead of managing the memory allocations. Each page of memory is assigned to one partition descriptor in the page hierarchy and is managed by the ultravisor partition.

Claims

1. A resource management system for a host computer, comprising:

a resource database for storing indices to system resources of said host computer;

a resource management software application that assigns system resources of said host computer and maintains a memory allocation page map of said resource database including indices to the assigned system resources in said resource database,

wherein said memory allocation page map is organized according to a tiered page size model including a hierarchy of scales using 2^x as a scaling factor whereby an index page at each tiered page size level may allocate 2^x memory blocks at a size of the next lower tiered page size level.

2. The resource management system of claim 1, wherein said resource management software application stores a descriptor for each assigned system resource at an index [G,M,K] in said memory allocation page map defined as Mem(G,M,K)=((G*2¹⁰+M)*2¹⁰+K)*2¹⁰*(word size), where word size is a power of 2.

3. The resource management system of claim 2, wherein x=10 and wherein a descriptor is stored in said memory allocation page map as a 32 bit index (2, 10, 10, 10) into a map of 4k pages that identifies the descriptor with said index, where a first bit indicates suballocation in smaller pages and three successive 2¹⁰ values identify scaled pages.

4. A method of managing memory of a host computer, comprising the steps of:

storing indices to system resources of said host computer in a resource database;

maintaining a memory allocation page map of said resource database including indices to assigned system resources in said resource database; and

organizing said memory allocation page map according to a tiered page size model including a hierarchy of scales using 2^x as a scaling factor whereby an index page at each tiered page size level may allocate 2^x memory blocks at a size of the next lower tiered page size level.

5. The method of claim 4, further comprising the step of storing a descriptor for each assigned system resource at an index [G,M,K] in said memory allocation page map defined as Mem(G,M,K)=((G*2¹⁰+M)*2¹⁰+K)*2¹⁰*(word size), where word size is a power of 2.

6. The method of claim 5, wherein x=10 and said storing step comprises storing a descriptor in said memory allocation page map as a 32 bit index (2, 10, 10, 10) into a map of 4k pages that identifies the descriptor with said index, where a first bit indicates suballocation in smaller pages and three successive 2¹⁰ values identify scaled pages.