# US 2021/0240529 A1 · Scheduler for handling io requests of different priorities

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

- Number: US 2021/0240529 A1
- Document ID: US20210240529A1
- Status: Published application
- Kind: A1
- Application number: 17/162,169
- Filed: 2021-01-29
- Published: 2021-08-05
- Earliest claimed: 2020-01-31
- Assignees: Rubrik, Inc.
- Applicants: Rubrik, Inc.
- Inventors: Vivek Sanjay Jain; Aravind Menon; Junyong Lee; Connie Xiao Zeng
- Web page: https://patentgrep.com/patent/US20210240529A1

## CPC

- G06F 9/4881: {Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues}
- G06F 9/4887: {involving deadlines, e.g. rate based, periodic}
- G06F 13/18: based on priority control (G06F13/1605 takes precedence)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

In some examples, a data management and storage (DMS) system comprises peer DMS nodes in a node cluster, a distributed data store comprising local and cloud storage, and an IO request scheduler comprising at least one processor configured to perform operations in a method of scheduling IO requests. Example operations comprise implementing a kernel scheduler to schedule a flow of IO requests in the DMS system, and providing an adjustment layer to adjust the kernel scheduler based on an IO request prioritization. A flow of IO requests is identified and some examples implement an IO request prioritization based on the adjustments made by the adjustment layer.

## Claims

### Claim 1

In a data management and storage (DMS) system accessing a cluster comprising peer DMS nodes and a distributed data store, a computer-implemented method of scheduling IO requests including:
implementing a kernel scheduler to schedule a flow of IO requests in the DMS system;
providing an adjustment layer to adjust the kernel scheduler based on an IO request prioritization;
identifying a flow of IO requests; and
implementing an IO request prioritization based on the adjustments made by the adjustment layer.

### Claim 2 (depends on 1)

The method of claim 1, wherein the IO request prioritization includes, by the kernel scheduler, providing or implementing a grace period for IO requests having a higher priority in the IO request flow, based on a IO request priority threshold value or event.

### Claim 3 (depends on 2)

The method of claim 2, further comprising disallowing, by the kernel scheduler, a passage or processing of at least some IO requests of lower priority during the grace period.

### Claim 4 (depends on 1)

The method of claim 1, wherein implementing the IO request prioritization includes, by the kernel scheduler, allowing a passage or processing of concurrent IO requests for a response, the concurrent IO requests being of a same or a different priority based on an IO request priority threshold value or event, the implementing of the IO request prioritization further including allowing the kernel scheduler to implement a balancing of the concurrent IO requests.

### Claim 5 (depends on 4)

The method of claim 4, wherein implementing the IO request prioritization further includes, by the kernel scheduler, enforcing a limit on an IO request concurrency and/or throughput.

### Claim 6 (depends on 1)

The method of claim 1, wherein the IO request prioritization includes enforcing, by the kernel scheduler, a dynamic minimum throughput for IO requests having a lower or lowest priority based on a IO request priority threshold value or event, such that the lower or lowest priority IO requests are not completely starved of a response thereto.

### Claim 7

A data management and storage (DMS) system, comprising:
peer DMS nodes in a node cluster;
a distributed data store comprising local and cloud storage; and
an IO request scheduler comprising at least one processor configured to perform operations in a method of scheduling IO requests, the operations comprising, at least:
implementing a kernel scheduler to schedule a flow of IO requests in the DMS system;
providing an adjustment layer to adjust the kernel scheduler based on an IO request prioritization;
identifying a flow of IO requests; and
implementing an IO request prioritization based on the adjustments made by the adjustment layer.

### Claim 8 (depends on 7)

The DMS system of claim 7, wherein the implemented IO request prioritization includes, by the kernel scheduler, providing or implementing a grace period for IO requests having a higher priority in the IO request flow, based on a IO request priority threshold value or event.

### Claim 9 (depends on 8)

The DMS system of claim 8, wherein the operations further comprise disallowing, by the kernel scheduler, a passage or processing of at least some IO requests of lower priority during the grace period.

### Claim 10 (depends on 7)

The DMS system of claim 7, wherein implementing the IO request prioritization includes, by the kernel scheduler, allowing a passage or processing of concurrent IO requests for a response, the concurrent IO requests being of a same or a different priority based on an IO request priority threshold value or event, the implementing of the IO request prioritization further including allowing the kernel scheduler to implement a balancing of the concurrent IO requests.

### Claim 11 (depends on 10)

The DMS system of claim 10, wherein implementing the IO request prioritization further includes, by the kernel scheduler, enforcing a limit on an IO request concurrency and/or throughput.

### Claim 12 (depends on 7)

The DMS system of claim 7, wherein the IO request prioritization includes enforcing, by the kernel scheduler, a dynamic minimum throughput for IO requests having a lower or lowest priority based on a IO request priority threshold value or event, such that the lower or lowest priority IO requests are not completely starved of a response thereto.

### Claim 13

A non-transitory machine-readable medium comprising instructions which, when read by a machine of a data management and storage (DMS) system comprising peer DMS nodes in a node cluster and a distributed data store comprising local and cloud storage DMS system, cause the machine to implement operations in a method of scheduling IO requests, the operations comprising, at least:
implementing a kernel scheduler to schedule a flow of IO requests in the DMS system;
providing an adjustment layer to adjust the kernel scheduler based on an IO request prioritization;
identifying a flow of IO requests; and
implementing an IO request prioritization based on the adjustments made by the adjustment layer.

### Claim 14 (depends on 13)

The medium of claim 13, wherein the implemented IO request prioritization includes, by the kernel scheduler, providing or implementing a grace period for IO requests having a higher priority in the IO request flow, based on a IO request priority threshold value or event.

### Claim 15 (depends on 14)

The medium of claim 14, wherein the operations further comprise disallowing, by the kernel scheduler, a passage or processing of at least some IO requests of lower priority during the grace period.

### Claim 16 (depends on 13)

The medium of claim 13, wherein implementing the IO request prioritization includes, by the kernel scheduler, allowing a passage or processing of concurrent IO requests for a response, the concurrent IO requests being of a same or a different priority based on an IO request priority threshold value or event, the implementing of the IO request prioritization further including allowing the kernel scheduler to implement a balancing of the concurrent IO requests.

### Claim 17 (depends on 16)

The medium of claim 16, wherein implementing the IO request prioritization further includes, by the kernel scheduler, enforcing a limit on an IO request concurrency and/or throughput.

### Claim 18 (depends on 13)

The medium of claim 13, wherein the IO request prioritization includes enforcing, by the kernel scheduler, a dynamic minimum throughput for IO requests having a lower or lowest priority based on a IO request priority threshold value or event, such that the lower or lowest priority IO requests are not completely starved of a response thereto.
