IP Library Granted Patent US 10,013,358
Granted Patent B2
US 10,013,358 · App. 15/112,740 · Granted Jul 3, 2018

Computer system and memory allocation management method

Inventors: Sachie Tajima (Tokyo, JP); Tadashi Takeuchi (Tokyo, JP)
Assignee: HITACHI, LTD.
G06F12/0891G06F12/0815G06F12/0871G06F2212/1021G06F2212/1044G06F2212/152G06F2212/608G06F2212/657
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,013,358
App. No.
15/112,740
Granted
Jul 3, 2018
Kind
B2
Abstract

A computer system includes: a physical resource including a memory; a virtualization mechanism that provides a virtual computer to which the physical resource is allocated; and a cache state management mechanism that manages a cache state of the virtual computer. The virtualization mechanism provides a first virtual computer and a second virtual computer. The cache state management mechanism manages the cache state of each of the first virtual computer and the second virtual computer. When the cache state management mechanism detects transition of the cache state in a state where a memory area allocated to a cache of the first virtual computer and a memory area allocated to a cache of the second virtual computer include duplicated areas storing same data, the virtualization mechanism releases the duplicated area in one of the first virtual computer and the second virtual computer.

Claims (29)

1. A computer system comprising:

a physical resource including a memory;

a virtualization mechanism that provides a virtual computer to which the physical resource is allocated; and

a cache state management mechanism that manages a cache state of the virtual computer, wherein

the virtualization mechanism provides a first virtual computer and a second virtual computer,

the cache state management mechanism manages the cache state of each of the first virtual computer and the second virtual computer,

when the cache state management mechanism detects transition of the cache state, in a state where a memory area allocated to a cache of the first virtual computer and a memory area allocated to a cache of the second virtual computer include duplicated areas storing same data, the virtualization mechanism releases the duplicated area in one of the first virtual computer and the second virtual computer,

wherein

the computer system has a configuration in which the first virtual computer is an application-executing virtual computer, the second virtual computer is an IO-issuing virtual computer that issues to a target device an IO request based on an IO request from the first virtual computer, and the virtualization mechanism notifies the second virtual computer of the IO request issued by the first virtual computer and notifies the target device of the IO request from the second virtual computer, and

when there are the duplicated areas, the virtualization mechanism releases the duplicated area in the first virtual computer and allocates the duplicated area in the second virtual computer to the cache of the first virtual computer.

2. The computer system according to claim 1 , wherein when the cache states of the first virtual computer and the second virtual computer are both clean or when the cache state of the first virtual computer is clean and the cache state of the second virtual computer is dirty, the virtualization mechanism determines that there are the duplicated areas.

3. The computer system according to claim 1 , wherein the cache state management mechanism detects the transition of the cache state, when read for reading data, write for writing data, destage for notifying a backend-side device of data in the cache, or free for releasing the cache occurs in the first virtual computer or the second virtual computer.

4. The computer system according to claim 1 , wherein

a state where the cache states of the first virtual computer and the second virtual computer are both clean or where the cache state of the first virtual computer is clean and the cache state of the second virtual computer is dirty is defined as a duplication state, a state where the cache states of the first virtual computer and the second virtual computer are not the state is defined as a non duplication state, and

when the cache state management mechanism detects the transition of the cache states, the virtualization mechanism releases the duplicated area in the first virtual computer and allocates the duplicated area in the second virtual computer to the cache in the first virtual computer when transition from the non duplication state to the duplication state has occurred, and allocates another area to the cache in the first virtual computer, to which the duplicated area in the second virtual computer has been allocated, when the transition from the duplication state to the non duplication state has occurred.

5. The computer system according to claim 1 , wherein

the cache state management mechanism stores information indicating the cache state of the first virtual computer in a cache state table, and

when an operation system of the first virtual computer is started, the virtualization mechanism restores the cache in the first virtual computer based on the information stored in the cache state table.

6. The computer system according to claim 1 , wherein

the first virtual computer is an application-executing virtual computer and the second virtual computer is an IO-issuing virtual computer that issues to a target device an IO request based on an IO request from the first virtual computer, and a mechanism that manages memory allocation to the second virtual computer is configured to be independent from other mechanisms.

7. A memory allocation management method in a computer system including a physical resource including a memory, a virtualization mechanism that provides a virtual computer to which the physical resource is allocated, and a cache state management mechanism that manages a cache state of the virtual computer, the method managing memory allocation to a cache of the virtual computer, and the method comprising:

operating the virtualization mechanism to provide a first virtual computer and a second virtual computer;

operating the cache state management mechanism to manage , a cache state of each of the first virtual computer and the second virtual computer; and

operating the virtualization mechanism to release, when the cache state management mechanism detects transition of the cache state in a state where a memory area allocated to a cache of the first virtual computer and a memory area allocated to a cache of the second virtual computer include duplicated areas storing same data, one of the duplicated areas in the first virtual computer and the second virtual computer,

wherein

the computer system has a configuration in which the first virtual computer is an application-executing virtual computer, the second virtual computer is an IO-issuing virtual computer that issues to a target device an IO request based on an IO request from the first virtual computer, and the virtualization mechanism notifies the second virtual computer of the TO request issued by the first virtual computer and notifies the target device the TO request from the second virtual computer, and

when there are the duplicated areas, the virtualization mechanism releases the duplicated area in the first virtual computer and allocates the duplicated area in the second virtual computer to the cache in the first virtual computer.

8. The memory allocation management method according to claim 7 , wherein the cache state management mechanism stores information indicating the cache state of the first virtual computer in a cache state table, and

when an operation system of the first virtual computer is started, the virtualization mechanism restores the cache in the first virtual computer based on the information stored in the cache state table.

Assignments (2)
COMPANY SPLIT Recorded Aug 20, 2024
From: HITACHI, LTD.
To: HITACHI VANTARA, LTD.
Reel/Frame 069518/0761 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 20, 2016
From: TAJIMA, SACHIE; TAKEUCHI, TADASHI
To: HITACHI, LTD.
Reel/Frame 039197/0031 →
Continuity (1)
Related Publication 20160335192A1 · Nov 17, 2016