# US 2020/0403930 A1 · Dynamic allocation of resources while considering resource reservations

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

- Number: US 2020/0403930 A1
- Document ID: US20200403930A1
- Status: Published application
- Kind: A1
- Application number: 16/912,070
- Filed: 2020-06-25
- Published: 2020-12-24
- Earliest claimed: 2013-06-21
- Assignees: Microsoft Technology Licensing, LLC
- Applicants: Microsoft Technology Licensing, LLC
- Inventors: Sudipto Das; Vivek Narasayya; Feng Li; Manoj Syamala
- Web page: https://patentgrep.com/patent/US20200403930A1

## CPC

- H04L 47/72: using reservation actions during connection setup
- H04L 67/10: in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Described herein are technologies relating to computing resource allocation among multiple tenants. Each tenant may have a respective absolute reservation for rate-based computing resources, which is independent of computing resource reservations of other tenants. The multiple tenants vie for the rate-based computing resources, and tasks are scheduled based upon which tenants submit the tasks and the resource reservations of such tenants.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

A computing system comprising a processor and memory, wherein the memory stores instructions that, when executed by the processor, cause the processor to perform acts comprising:
scheduling a task of a tenant of a cloud computing system to be completed by a computing device of the cloud computing system, wherein the task is scheduled to be completed based upon a reservation of the tenant for a rate-based computing resource, wherein the reservation is indicative of an amount of the rate-based computing resource that is to be allocated to the tenant over a window of time; and
causing the computing device of the cloud computing system to perform the task of the tenant in accordance with the scheduling of the task of the tenant.

### Claim 22 (depends on 21)

The computing system of claim 21, the acts further comprising:
scheduling a second task of a second tenant of the cloud computing system to be completed by the computing device of the cloud computing system, wherein the second task is scheduled to be completed based upon a second reservation of the second tenant for the rate-based computing resource, wherein the second reservation is indicative of a second amount of the rate-based computing resource that is to be allocated to the second tenant over the window of time; and
causing the computing device of the cloud computing system to perform the second task of the tenant in accordance with the scheduling of the second task of the tenant.

### Claim 23 (depends on 21)

The computing system of claim 21, wherein the task of the tenant of the cloud computing system is scheduled to be completed based further upon a second reservation of the tenant for a second rate-based computing resource, wherein the second reservation is indicative of an amount of the second rate-based computing resource that is to be allocated to the tenant over the window of time.

### Claim 24 (depends on 21)

The computing system of claim 21, the acts further comprising:
scheduling a second task of a second tenant of the cloud computing system to be completed by the computing device of the cloud computing system, wherein the second task is scheduled to be completed based upon a reservation of the second tenant for a second rate-based computing resource, wherein the reservation of the second tenant is indicative of an amount of the second rate-based computing resource that is to be allocated to the second tenant over the window of time; and
causing the computing device of the cloud computing system to perform the second task of the tenant in accordance with the scheduling of the second task of the tenant.

### Claim 25 (depends on 21)

The computing system of claim 21, wherein the window of time is amongst several windows of time, and further wherein the reservation indicates that the tenant is to be allocated the amount of the rate-based computing resource for each window of time in the several windows of time.

### Claim 26 (depends on 21)

The computing system of claim 21, wherein the task of the tenant is scheduled based further upon a second reservation for the rate-based computing resource for a second tenant of the cloud computing environment over the window of time.

### Claim 27 (depends on 21)

The computing system of claim 21, wherein the rate-based computing resource is CPU time of the computing device.

### Claim 28 (depends on 21)

The computing system of claim 21, wherein the computing system schedules tasks for tenants across several computing devices of the cloud computing environment based upon reservations of the tenants for the rate-based computing resource.

### Claim 29 (depends on 21)

The computing system of claim 21, wherein the rate-based computing resource pertains to a number of I/O operations during the window of time.

### Claim 30 (depends on 21)

The computing system of claim 21, wherein the rate-based computing resource is a number of processing cycles during the window of time.

### Claim 31

A method performed by a computing system in a cloud computing environment that comprises several computing devices that are configured to execute tasks of tenants of the cloud computing environment, the method comprising:
scheduling a task of a tenant for execution on a computing device in the computing devices of the cloud computing environment, wherein a portion of the task is scheduled to be executed within a window of time, wherein the task is scheduled for execution based upon a reservation of the tenant for a rate-based computing resource of the computing device, wherein the reservation indicates an amount of the rate-based computing resource that is to be allocated to the tenant within the window of time; and
causing the computing device to execute the tenant in accordance with reservation of the tenant for the rate-based computing resource.

### Claim 32 (depends on 31)

The method of claim 31, wherein the task of the tenant is scheduled based further upon a second reservation of a second tenant for the rate-based computing resource, wherein the second reservation indicates a second amount of the rate-based computing resource that is to be allocated to the tenant over the window of time.

### Claim 33 (depends on 31)

The method of claim 31, wherein the resource reservation indicates an amount of a second rate-based computing resource that is to be allocated to the tenant over the window of time.

### Claim 34 (depends on 31)

The method of claim 31, further comprising:
scheduling a second task of a second tenant for execution on the computing device, wherein a portion of the second task is scheduled to be executed within the window of time, wherein the second task is scheduled for execution based upon a second reservation of the second tenant for the rate-based computing resource of the computing device, wherein the second reservation indicates an amount of the rate-based computing resource that is to be allocated to the second tenant within the window of time; and
causing the computing device to execute the second tenant in accordance with the second reservation of the second tenant for the rate-based computing resource.

### Claim 35 (depends on 31)

The method of claim 31, wherein the window of time is amongst several windows of time, wherein each window of time in the several windows of time is of the same length, and further wherein the reservation indicates that the tenant is to be allocated the amount of the rate-based computing resource during each window of time in the several windows of time.

### Claim 36 (depends on 31)

The method of claim 31, wherein the rate-based computing resource is CPU time of the computing device.

### Claim 37

A client computing device comprising a processor and memory, wherein the memory stores instructions that, when executed by the processor, cause the processor to perform acts comprising:
causing a tenant to be instantiated on at least one computing device in a cloud computing system, wherein the cloud computing system schedules a task set forth by the tenant to be computed by the at least one computing device, wherein the task is scheduled to be completed based upon a reservation of the tenant for a rate-based computing resource, wherein the reservation is indicative of an amount of the rate-based computing resource that is to be allocated to the tenant over a window of time, and further wherein the task is performed by the at least one computing device in accordance with the scheduling of the task of the tenant.

### Claim 38 (depends on 37)

The client computing device of claim 37, wherein the task of the tenant of is scheduled to be completed based further upon a second reservation of the tenant for a second rate-based computing resource, wherein the second reservation is indicative of an amount of the second rate-based computing resource that is to be allocated to the tenant over the window of time.

### Claim 39 (depends on 37)

The client computing device of claim 37, wherein the window of time is amongst several windows of time, and further wherein the reservation indicates that the tenant is to be allocated the amount of the rate-based computing resource for each window of time in the several windows of time.

### Claim 40 (depends on 37)

The client computing device of claim 37, wherein the task of the tenant is scheduled based further upon a second reservation for the rate-based computing resource for a second tenant of the cloud computing environment over the window of time.
