US 11,531,569 B2Granted

System and method for scaling provisioned resources

AssigneeCore Scientific Operating Company

InventorsAlbert Hse-Lin Chen, Max Alt, Jesse Barnes

Life of this patent

Estimating the term…

Loading patent…

Abstract

Systems and apparatuses for provisioning computer services or resources and methods for making and using the same. In one embodiment, an exemplary method for performing an iterative search can include selecting a service from a group of available services for adjustment. An application associated with the selected service can be run, and an amount of resources consumed while the application is run can be captured. A provision level for the selected service, a provision type for the selected service or both can be adjusted based upon the captured amount of resources consumed. The method then can determine whether provision levels of the available services, provision types of the available services or both require further adjustment to be most performant. The approaches described herein advantageously can be applied, for example, to “right-size” or “scale” multiple resources.

Claims20

Dependent claims

A method comprising:

preparing a list, for each available service, of provision levels of computer resources provided by each available service;
sorting each list of provision levels based on at least one of a power, a capacity, and a performance of each computer resource, wherein at least one service of the each available service is a remotely provided service;
selecting, from a sorted list, a first computer resource provided by the remotely provided service from a group of available computer resources for adjustment, wherein the first computer resource includes at least one of storage, compute, memory, network bandwidth, and central processing unit (CPU) capacity;
optimizing, based on a user preference, a cost to performance ratio of running an application via the remotely provided service, wherein the optimizing of the cost to performance ratio comprises:
running, in real time, the application at least in part via the selected first computer resource;
capturing an amount of the first computer resource consumed during the running;
and
adjusting a first provision for the selected first computer resource based on the amount of the first computer resource consumed and the user preference, wherein the first provision includes at least one of available input/output operations per second (IOPS), available compute cores, available threads, available memory, available throughput, available terra operations per second (TOPS), and type of memory storage;
and
optimizing the cost to performance ratio of running the application based on a different user preference.

7 more elements

A computer program product being encoded on one or more non-transitory machine-readable storage media and comprising:

instruction for preparing a list, for each available service, of provision levels of computer resources provided by each available service, wherein each available service is provided remotely;
instruction for sorting each list of provision levels based on at least one of a power, a capacity, and a performance of each computer resource in the list for each available service, wherein sorting at least one list is also at least partially based on an Abstract Compute Unit (ACU) to measure an effectiveness of compute power provision levels;
instruction for selecting a first computer resource from a group of available computer resources for adjustment, wherein the first computer resource includes at least one of storage, compute, memory, network bandwidth, and central processing unit (CPU) capacity;
instruction for optimizing, based on a user preference, a cost to performance ratio of running an application via one available service, wherein the optimizing of the cost to performance ratio comprises:
instruction for running the application at least in part via with the selected first computer resource;
instruction for capturing, while the application is running, a first amount of resources consumed by the application during the running;
instruction for adjusting a first provision for the selected first computer resource to a different provision based on the first amount of resources consumed and the user preference to optimize the cost to performance ratio, wherein the first provision includes at least one of available input/output operations per second (IOPS), available compute cores, available threads, available memory, available throughput, available terra operations per second (TOPS), and type of memory storage;
and
instruction for running the application via the selected first computer resource provisioned to the different provision;
and
optimizing the cost to performance ratio of running the application based on a different user preference.

8 more elements

A system comprising a processor configured to carry out:

preparing a list, for each available service, of provision levels of computer resources provided by each available service
sorting each list of provision levels for computer resources based on at least one of a power, a capacity, and a performance of each computer resource in the list for each available service, wherein sorting at least one list is also at least partially based on an Abstract Compute Unit (ACU) to measure an effectiveness of compute power provision levels, and wherein at least one service of the each available service is provided by a remote service provider;
selecting a first computer resource provided by the remote service provider from a group of available computer resources for adjustment, wherein the first computer resource includes at least one of storage, compute, memory, network bandwidth, and central processing unit (CPU) capacity;
optimizing, based on a user preference, a cost to performance ratio of running an application via the remote service provider, wherein the optimizing of the cost to performance ratio comprises:
running the application at least in part via the selected first computer resource;
capturing, while the application is running, an amount of the selected first computer resource consumed by the application during the running;
adjusting a first provision for the selected first computer resource to a different provision based on the amount of the first computer resource consumed and the user preference, wherein the first provision includes at least one of available input/output operations per second (IOPS), available compute cores, available threads, available memory, available throughput, available terra operations per second (TOPS), and type of memory storage;
and
running the application via the first computer resource provisioned to the different provision to optimize the cost to performance ratio based on the user preference;
and
optimizing the cost to performance ratio of running the application based on a different user preference.

8 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/185,762Filed 9 Nov 2018 · us provisional application
Priority: 10 Nov 2017
Published: US 2019/0272200 A15 Sep 2019
Granted: 20 Dec 2022
Term ends: Not estimatedThe source records don’t support an estimate.

Classification5 codes

G06F 9/5027
To service a request: the resource being a machine, e.g. CPUs, Servers, Terminals
G06F 9/5061
Allocation of resources, e.g. of the central processing unit [CPU]: partitioning or combining of resources
G06F 9/4881
By program, e.g. task dispatcher, supervisor, operating system: scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
G06F 9/50
Multiprogramming arrangements: allocation of resources, e.g. of the central processing unit [CPU]