Granted Patent B2

US 12,613,751 · App. 18/093,273 · Granted Apr 28, 2026

Inventors: Ming Fang (Sammamish, WA); Xinyue Yu (Seattle, WA); Michal Piotr Prussak (Kirkland, WA); Vladislavs Dovgalecs (Bellevue, WA); Wei Gao (Bellevue, WA)

Assignee: Oracle International Corporation

G06F9/505G06F2209/503

Abstract

Claims (79)

1 . A method, comprising:

receiving, by a computing device, a first message from a first message stream, the first message comprising a job request from a tenant and a tenant identifier;

detecting, by the computing device, a base number of units permissible to be processed for the tenant over a unit of time;

detecting, by the computing device, a processing speed of a downstream processor of an asynchronous pipeline;

detecting, by the computing device, a number of messages in a second message stream, the downstream processor configured to receive messages from the second message stream;

determining, by the computing device, a target throughput for the tenant based at least in part on a mathematical operation using the base number, the number of messages in the second message stream, and the processing speed on the downstream processor;

determining, by the computing device, a historical throughput for the tenant based at least in part on an average number of units processed over the unit of time;

comparing, by the computing device, the target throughput with the historical throughput to determine whether to process the job request; and

scheduling, by the computing device, the job request for processing based at least in part on the comparison, wherein scheduling the job request comprises:

creating a second message comprising a job identifier, a job identifier index value, and an address of data to be used to process the job request; and

transmitting the second message to a preprocessing processor using a third message stream.

2 . The method of claim 1 , wherein the mathematical operation comprises:

determining a quotient of the number of messages in the second message stream over the processing speed of the downstream processor; and

determining a product of the quotient and the base number, wherein the target throughput is the product.

3 . The method of claim 1 , wherein the method further comprises:

detecting a weight associated with the tenant;

determining a quotient of the number of messages in the second message stream over the processing speed of the downstream processor; and

determining a product of the quotient, the base number, and the weight, wherein the target throughput is the product.

4 . The method of claim 1 , wherein scheduling the job request from the tenant based at least in part on the comparison comprises determining that the target throughput is greater than the historical throughput.

5 . The method of claim 1 , wherein the first message is received at first point in time, and wherein scheduling the job request from the tenant based at least in part on the comparison comprises:

determining that the historical throughput is greater than the target throughput;

transmitting the first message back into the first message stream based on the determination;

receiving the first message at a second point in time;

determining that the target throughput is greater than the historical throughput; and

scheduling the job request based on the determination that the target throughput is greater than the historical throughput.

6 . The method of claim 1 , wherein the method further comprises determining the historical output comprises matching the tenant identifier of the first message with tenants identifiers associated with the units of the average number of units.

7 . A computing device, comprising:

a processor; and

a computer-readable medium including instructions that, when executed by the processor, cause the processor to perform operations comprising:

receiving a first message from a first message stream, the first message comprising a job request from a tenant and a tenant identifier;

detecting a base number of units permissible to be processed for the tenant over a unit of time;

detecting a processing speed of a downstream processor of an asynchronous pipeline;

detecting a number of messages in a second message stream, the downstream processor configured to receive messages from the second message stream;

determining a target throughput for the tenant based at least in part on a mathematical operation using the base number, the number of messages in the second message stream, and the processing speed on the downstream processor;

determining a historical throughput for the tenant based at least in part on an average number of units processed over the unit of time;

comparing the target throughput with the historical throughput to determine whether to process the job request; and

scheduling the job request for processing based at least in part on the comparison, wherein scheduling the job request comprises:

creating a second message comprising a job identifier, a job identifier index value, and an address of data to be used to process the job request; and

transmitting the second message to a preprocessing processor using a third message stream.

8 . The device of claim 7 , wherein the mathematical operation comprises:

determining a quotient of the number of messages in the second message stream over the processing speed of the downstream processor; and

determining a product of the quotient and the base number, wherein the target throughput is the product.

9 . The device of claim 7 , wherein the instructions that, when executed by the processor, further cause the processor to perform operations comprising:

detecting a weight associated with the tenant;

determining a quotient of the number of messages in the second message stream over the processing speed of the downstream processor; and

determining a product of the quotient, the base number, and the weight, wherein the target throughput is the product.

10 . The device of claim 7 , wherein scheduling the job request from the tenant based at least in part on the comparison comprises determining that the target throughput is greater than the historical throughput.

11 . The device of claim 7 , wherein the first message is received at first point in time, and wherein scheduling the job request from the tenant based at least in part on the comparison comprises:

determining that the historical throughput is greater than the target throughput;

transmitting the first message back into the first message stream based on the determination;

receiving the first message at a second point in time;

determining that the target throughput is greater than the historical throughput; and

scheduling the job request based on the determination that the target throughput is greater than the historical throughput.

12 . The device of claim 7 , wherein the instructions that, when executed by the processor, further cause the processor to perform operations comprising matching the tenant identifier of the first message with tenants identifiers associated with the units of the average number of units.

13 . A non-transitory computer-readable medium having stored thereon a sequence of instructions that, when executed by a processor, causes the processor to perform operations comprising:

receiving a first message from a first message stream, the first message comprising a job request from a tenant and a tenant identifier;

detecting a base number of units permissible to be processed for the tenant over a unit of time;

detecting a processing speed of a downstream processor of an asynchronous pipeline;

detecting a number of messages in a second message stream, the downstream processor configured to receive messages from the second message stream;

determining a target throughput for the tenant based at least in part on a mathematical operation using the base number, the number of messages in the second message stream, and the processing speed on the downstream processor;

determining a historical throughput for the tenant based at least in part on an average number of units processed over the unit of time;

comparing the target throughput with the historical throughput to determine whether to process the job request; and

scheduling the job request for processing based at least in part on the comparison, wherein scheduling the job request comprises:

creating a second message comprising a job identifier, a job identifier index value, and an address of data to be used to process the job request; and

transmitting the second message to a preprocessing processor using a third message stream.

14 . The non-transitory computer-readable medium of claim 13 , wherein the mathematical operation comprises:

determining a quotient of the number of messages in the second message stream over the processing speed of the downstream processor; and

determining a product of the quotient and the base number, wherein the target throughput is the product.

15 . The non-transitory computer-readable medium of claim 13 , wherein the instructions that, when executed by the processor, further cause the processor to perform operations comprising:

detecting a weight associated with the tenant;

determining a quotient of the number of messages in the second message stream over the processing speed of the downstream processor; and

determining a product of the quotient, the base number, and the weight, wherein the target throughput is the product.

16 . The non-transitory computer-readable medium of claim 13 , wherein scheduling the job request from the tenant based at least in part on the comparison comprises determining that the target throughput is greater than the historical throughput.

17 . The non-transitory computer-readable medium of claim 13 , wherein the first message is received at first point in time, and wherein scheduling the job request from the tenant based at least in part on the comparison comprises:

determining that the historical throughput is greater than the target throughput;

transmitting the first message back into the first message stream based on the determination;

receiving the first message at a second point in time;

determining that the target throughput is greater than the historical throughput; and

scheduling the job request based on the determination that the target throughput is greater than the historical throughput.

Assignments (1)

Continuity (1)

References Cited (15)