# US 2023/0066848 A1 · Method and system for granular dynamic quota-based congestion management

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

- Number: US 2023/0066848 A1
- Document ID: US20230066848A1
- Status: Published application
- Kind: A1
- Application number: 17/410,492
- Filed: 2021-08-24
- Published: 2023-03-02
- Earliest claimed: 2021-08-24
- Assignees: Hewlett Packard Enterprise Development LP
- Applicants: Hewlett Packard Enterprise Development LP
- Inventors: Ryan Dean Menhusen; Darel Neal Emmot; Daniel William Dauwe
- Web page: https://patentgrep.com/patent/US20230066848A1

## CPC

- H04L 47/122: by diverting traffic away from congested entities
- H04L 47/17: Interaction among intermediate nodes, e.g. hop by hop
- H04L 47/30: in combination with information about buffer occupancy at either end or at transit nodes
- H04L 47/35: by embedding flow control information in regular packets, e.g. piggybacking
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

A system for facilitating sender-side granular congestion control is provided. During operation, the first and second processes of an application can run on sender and receiver nodes, respectively. A first buffer on the sender node can be allocated to the first process. For the first process, the system can then identify a second buffer at a last-hop switch of the receiver node. The system can determine, based on in-flight packets, the utilization of the second buffer. The system can also determine a fraction of available space in the second buffer for packets from the first buffer based on the utilization. Subsequently, the system can determine whether the fraction of the available space can accommodate the next packet from the first buffer. If the fraction of the available space can accommodate the next packet, the system can allow the first process to send the next packet to the second process.

## Claims

### Claim 1

A method for facilitating sender-side granular congestion control, the method comprising:
for a first process of an application on a sender node, wherein a first buffer on the sender node is allocated to the first process, identifying a second buffer, at a last-hop switch of a receiver node, wherein the second buffer is allocated for packets to a second process of the application on the receiver node, and wherein the receiver node is reachable from the sender node via the last-hop switch;
determining, based on in-flight packets to the second buffer, utilization of the second buffer;
determining a fraction of available space in the second buffer for packets from the first buffer based on the utilization of the second buffer;
determining whether the fraction of the available space in the second buffer can accommodate a next packet from the first buffer while avoiding congestion at the last-hop switch; and
in response to determining that the fraction of the available space in the second buffer can accommodate the next packet, allowing the first process to send the next packet to the second process.

### Claim 2 (depends on 1)

The method of claim 1, further comprising determining a number of sender processes sending packets to the second buffer based on the utilization of the second buffer and the in-flight packets to the second buffer.

### Claim 3 (depends on 2)

The method of claim 2, further comprising determining the fraction of the available space based further on the number of sender processes.

### Claim 4 (depends on 2)

The method of claim 2, further comprising updating the number of sender processes based on a response rate from the second buffer.

### Claim 5 (depends on 1)

The method of claim 1, wherein allowing the first process to send the next packet to the second process further comprises:
determining a request rate from the first buffer to the second buffer based on the next packet; and
determining whether the request rate is within a response rate from the second buffer.

### Claim 6 (depends on 1)

The method of claim 1, wherein determining the utilization of the second buffer further comprises determining a steady-state utilization of the second buffer based on a queuing delay between the first and second buffers.

### Claim 7 (depends on 1)

The method of claim 1, further comprising, in response to determining that sending the next packet can cause congestion at the second buffer, buffering the next packet at the sender node, thereby avoiding triggering congestion control for the second process at the receiver node.

### Claim 8 (depends on 1)

The method of claim 1, wherein determining the utilization of the second buffer further comprises:
monitoring a set of triggering events; and
in response to detecting at least one triggering event, determining information associated with the utilization of the second buffer.

### Claim 9 (depends on 8)

The method of claim 8, wherein the set of triggering events comprises one or more of:
initiating a transaction request by the first process;
injecting a packet by the first process;
receiving a response from the second buffer; and
detecting a packet drop.

### Claim 10 (depends on 1)

The method of claim 1, wherein the first buffer resides on a network interface controller (NIC) of the sender node.

### Claim 11

A computer system, comprising:
a processor;
a network interface controller (NIC);
a non-transitory computer-readable storage medium storing instructions, which when executed by the processor causes the processor to perform a method for facilitating sender-side granular congestion control, the method comprising:
for a first process of an application on the computer system, wherein a first buffer is allocated to the first process, identifying a second buffer at a last-hop switch of a remote computer system, wherein the second buffer is allocated for packets to a second process of the application, and wherein the remote computer system is reachable from the computer system via the last-hop switch;
determining, based on in-flight packets to the second buffer, utilization of the second buffer;
determining a fraction of available space in the second buffer for packets from the first buffer based on the utilization of the second buffer determining whether the fraction of the available space in the second buffer can accommodate a next packet from the first buffer while avoiding congestion at the last-hop switch; and
in response to determining that the fraction of the available space in the second buffer can accommodate the next packet, allowing the first process to send the next packet to the second process.

### Claim 12 (depends on 11)

The computer system of claim 11, wherein the method further comprises determining a number of sender processes sending packets to the second buffer based on the utilization of the second buffer and the in-flight packets to the second buffer.

### Claim 13 (depends on 12)

The computer system of claim 12, wherein the method further comprises determining the fraction of the available space based further on the number of sender processes.

### Claim 14 (depends on 12)

The computer system of claim 12, wherein the method further comprises updating the number of sender processes based on a response rate from the second buffer.

### Claim 15 (depends on 11)

The computer system of claim 11, wherein allowing the first process to send the next packet to the second process further comprises:
determining a request rate from the first buffer to the second buffer based on the next packet; and
determining whether the request rate is within a response rate from the second buffer.

### Claim 16 (depends on 11)

The computer system of claim 11, wherein determining the utilization of the second buffer further comprises determining a steady-state utilization of the second buffer based on a queuing delay between the first and second buffers.

### Claim 17 (depends on 11)

The computer system of claim 11, wherein the method further comprises, in response to determining that sending the next packet can cause congestion at the second buffer, buffering the next packet at the computer system, thereby avoiding triggering congestion control for the second process at the remote computer system.

### Claim 18 (depends on 11)

The computer system of claim 11, wherein determining the utilization of the second buffer further comprises:
monitoring a set of triggering events; and
in response to detecting at least one triggering event, determining information associated with the utilization of the second buffer.

### Claim 19 (depends on 18)

The computer system of claim 18, wherein the set of triggering events comprises one or more of:
initiating a transaction request by the first process;
injecting a packet by the first process;
receiving a response from the second buffer; and
detecting a packet drop.

### Claim 20 (depends on 11)

The computer system of claim 11, wherein the first buffer is on the NIC of the computer system.
