# US 2022/0019457 A1 · Hardware placement and maintenance scheduling in high availability systems

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0019457 A1
- Document ID: US20220019457A1
- Status: Published application
- Kind: A1
- Application number: 17/490,247
- Filed: 2021-09-30
- Published: 2022-01-20
- Earliest claimed: 2019-01-23
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: RICHARD E. HARPER; HARIGOVIND V. RAMASAMY; VALENTINA SALAPURA; SANDHYA KAPOOR; LONG WANG
- Web page: https://patentgrep.com/patent/US20220019457A1

## CPC

- G06F 9/45558: {Hypervisor-specific management and integration aspects}
- G06F 9/5077: {Logical partitioning of resources; Management or configuration of virtualized resources (specific details on emulation or internal functioning of virtual machines G06F9/455)}
- G06F 8/65: Updates (security arrangements therefor G06F21/57)
- G06F 9/505: {considering the load}
- G06F 9/5072: {Grid computing}
- G06F 9/5083: {Techniques for rebalancing the load in a distributed system}
- G06F 2009/4557: {Distribution of virtual machine instances; Migration and load balancing}
- G06F 2009/45595: {Network integration; Enabling network access in virtual machine instances}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method of organizing computer resources includes receiving a specification defining a plurality of quiescence groups of independent component instances for each of at least two services, and performing a first load balancing of the quiescence groups across a plurality of physical servers to define a plurality of supergroups while assigning each of the physical servers across the supergroups.

## Claims

### Claim 1

A method of organizing resources of a computer system, the computer system being organized into a plurality of supergroups, each of the supergroups including at least one quiescence group of independent component instances executing on different physical servers comprising:
determining a minimum achievable number of supergroups needed to perform a service of the computer system;
sorting the quiescence groups in a plurality of services by resource consumption;
sorting the supergroups by resource utilization; and
selecting each of the quiescence groups sequentially beginning with a quiescence group having a heaviest resource consumption, and placing a currently selected quiescence group on a supergroup having a lowest resource utilization among the supergroups and into which the currently selected quiescence group fits, and within the supergroup having the lowest resource utilization placing the currently selected quiescence group on a physical service having a lowest resource utilization among the physical servers, and resorting the supergroups by resource utilization upon placing the currently selected quiescence group.

### Claim 2 (depends on 1)

The method of claim 1, wherein placing the currently selected quiescence group on the supergroup having the lowest resource utilization among the supergroups and into which the currently selected quiescence group fits further comprises:
determining that the currently selected quiescence group does not fit in any of the supergroups;
adding a physical server to one of the supergroups having a highest resource utilization; and
placing the selected group on the physical server added to the supergroup having the highest resource utilization.

### Claim 3 (depends on 1)

The method of claim 1, wherein the placement of the quiescence groups into the supergroups uses a minimum number of the physical servers.

### Claim 4 (depends on 1)

The method of claim 1, wherein anti-collocation of dependent ones of the component instances to the physical servers is enforced by the placement of the quiescence groups into the supergroups.

### Claim 5 (depends on 1)

The method of claim 1, further comprising assigning the physical servers such that no two supergroups have component instances coexisting on a same one of the physical servers.

### Claim 6 (depends on 1)

The method of claim 1, further comprising performing a maintenance function on portions of the computer system supporting sequential ones of the supergroups without interrupting the services.

### Claim 7 (depends on 6)

The method of claim 6, wherein performing the maintenance function includes taking down, simultaneously, the independent component instances of the quiescence groups within a given supergroup.
