Managing both baseline and burst I/O request rates

US12197736B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-12197736-B2
Application numberUS-202318150425-A
CountryUS
Kind codeB2
Filing dateJan 5, 2023
Priority dateJan 5, 2023
Publication dateJan 14, 2025
Grant dateJan 14, 2025

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

A technique of managing the rate of I/O (Input/Output) request processing includes a token-bucket arrangement having first, second, and third token buckets. The first token bucket is provided with sufficient tokens to accommodate an expected baseline level of I/O requests, whereas the second token bucket is provided with sufficient tokens to accommodate an expected excess level of I/O requests during bursts. The third token bucket is provided with tokens at predefined intervals and limits a total amount of bursting available during those intervals.

First claim

Opening claim text (preview).

What is claimed is: 1. A method of managing I/O request processing rate, comprising: receiving a plurality of I/O requests, the I/O requests including read requests and/or write requests; processing the plurality of I/O requests in exchange for tokens, such that each I/O request is processed only if sufficient tokens are available to process the I/O request; and managing the tokens using first, second, and third token buckets, the first token bucket provided with sufficient tokens to accommodate an expected baseline level of I/O requests, the second token bucket provided with sufficient tokens to accommodate an expected excess level of I/O requests during bursts, and the third token bucket provided with tokens at predefined intervals and limiting an overall amount of bursting available during the predefined intervals, wherein the method further comprises calculating a respective number of tokens needed for each I/O request of the plurality of I/O requests and, for each I/O request of the plurality of I/O requests for which the first token bucket contains fewer than the respective number of tokens but the second and third token buckets each contain at least a balance of tokens not found in the first token bucket, decrementing the first token bucket by the number of tokens in the first token bucket and decrementing each of the second and third token buckets by the balance of tokens not found in the first token bucket. 2. The method of claim 1 , further comprising: for each I/O request of the plurality of I/O requests for which the first token bucket contains at least the respective number of tokens, decrementing the first token bucket by the respective number of tokens. 3. The method of claim 2 , further comprising, for each I/O request of the plurality of I/O requests for which the first token bucket contains fewer than the respective number of tokens and at least one of the second and third token buckets contains fewer than a balance of tokens not found in the first token bucket, enqueue the respective I/O request for later processing or fail the respective I/O request. 4. The method of claim 3 , further comprising replenishing tokens in the first bucket at a first rate determined to accommodate the expected baseline level of I/O requests. 5. The method of claim 4 , further comprising replenishing tokens in the second bucket at a second rate determined to accommodate the expected excess level of I/O requests during bursts. 6. The method of claim 5 , wherein the first rate and the second rate are each constant. 7. The method of claim 3 , further comprising replenishing tokens in the third bucket at the regular intervals, wherein numbers of tokens provided at the regular intervals are based on a total excess level of I/O requests allowed during the regular intervals. 8. The method of claim 1 , further comprising calculating respective numbers of tokens needed for respective I/O requests of the plurality of I/O requests based on at least one of (i) a constant number of tokens for each I/O request, (ii) whether each I/O request is a read or a write, and/or (iii) amounts of data specified to be written and/or read by each I/O request. 9. The method of claim 1 , further comprising, in response to receipt of a first I/O request: calculating a number N 1 of tokens for the first I/O request; determining that the first token bucket has only M 1 tokens, where M 1 is less than N 1 ; determining that the second and third token buckets each have at least N 1 -M 1 tokens; and processing the first I/O request by, in any order, (i) decrementing the first token bucket by M 1 tokens, (ii) decrementing each of the second and third token buckets by N 1 -M 1 tokens, and (iii) forwarding the first I/O request to subsequent processing layers. 10. The method of claim 1 , further comprising, in response to receipt of a second I/O request: calculating a number N 2 of tokens for the second I/O request; determining that the first token bucket has only M 2 tokens, where M 2 is less than N 2 ; determining that at least one of the second and third token buckets has fewer than N 2 -M 2 tokens; and queuing or failing the second I/O request in response to the determination that at least one of the second and third token buckets has fewer than N 2 -M 2 tokens. 11. The method of claim 1 , further comprising, in response to receipt of a third I/O request: calculating a number N 3 of tokens for the third I/O request; determining that the first token bucket has at least N 3 tokens; and processing the third I/O request by, in any order, (i) decrementing the first token bucket by Ns tokens and (ii) forwarding the third I/O request to subsequent processing layers. 12. A computerized apparatus, comprising control circuitry that includes a set of processors coupled to memory, the control circuitry constructed and arranged to: receive a plurality of I/O requests, the I/O requests including read requests and/or write requests; process the plurality of I/O requests in exchange for tokens, such that each I/O request is processed only if sufficient tokens are available to process the I/O request; and manage the tokens using first, second, and third token buckets, the first token bucket provided with sufficient tokens to accommodate an expected baseline level of I/O requests, the second token bucket provided with sufficient tokens to accommodate an expected excess level of I/O requests during bursts, and the third token bucket provided with tokens at predefined intervals and limiting an overall amount of bursting available during the predefined intervals, wherein the control circuitry is further constructed and arranged to calculate a respective number of tokens needed for each I/O request of the plurality of I/O requests and, for each I/O request of the plurality of I/O requests for which the first token bucket contains fewer than the respective number of tokens but the second and third token buckets each contain at least a balance of tokens not found in the first token bucket, decrement the first token bucket by the number of tokens in the first token bucket and decrement each of the second and third token buckets by the balance of tokens not found in the first token bucket. 13. A computer program product including a set of non-transitory, computer-readable media having instructions which, when executed by control circuitry of a computerized apparatus, cause the computerized apparatus to perform a method of managing I/O request processing rate, the method comprising: receiving a plurality of I/O requests, the I/O requests including read requests and/or write requests; processing the plurality of I/O requests in exchange for tokens, such that each I/O request is processed only if sufficient tokens are available to process the I/O request; and managing the tokens using first, second, and third token buckets, the first token bucket provided with sufficient tokens to accommodate an expected baseline level of I/O requests, the second token bucket provided with sufficient tokens to accommodate an expected excess level of I/O requests during bursts, and the third token bucket provided with tokens at predefined intervals and limiting an overall amount of bursting available during the predefined intervals, wherein the method further comprises calculating a respective number of tokens needed for each I/O request of the plurality of I/O requests and, for each I/O request of the plurality of I/O requests for which the first token bucket contains fewer than the respective number of tokens but the second and third token buckets each contain at least a balance of tokens not found in the

Assignees

Inventors

Classifications

  • Improving or facilitating administration, e.g. storage management · CPC title

  • Command handling arrangements, e.g. command buffers, queues, command scheduling · CPC title

  • G06F3/067Primary

    Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS] · CPC title

  • G06F3/0613Primary

    in relation to throughput · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US12197736B2 cover?
A technique of managing the rate of I/O (Input/Output) request processing includes a token-bucket arrangement having first, second, and third token buckets. The first token bucket is provided with sufficient tokens to accommodate an expected baseline level of I/O requests, whereas the second token bucket is provided with sufficient tokens to accommodate an expected excess level of I/O requests …
Who is the assignee on this patent?
Dell Products Lp
What technology area does this patent fall under?
Primary CPC classification G06F3/067. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue Jan 14 2025 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 7 related publications on this page (citations in our corpus or others sharing the same primary CPC).