System and method for autonomous and dynamic resource allocation in storage systems
US-11018991-B1 · May 25, 2021 · US
US11899633B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-11899633-B2 |
| Application number | US-202016928155-A |
| Country | US |
| Kind code | B2 |
| Filing date | Jul 14, 2020 |
| Priority date | Jul 14, 2020 |
| Publication date | Feb 13, 2024 |
| Grant date | Feb 13, 2024 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
From among physical storage devices (PSDs) of a storage system, a set of two or more of the PSDs that are eligible for scrubbing may be determined; and from among the set, a relative eligibility of the PSDs may be determined. Conformance prediction analysis may be applied to determine the set and the relative eligibility of PSDs of the set. The conformance prediction analysis may determine a scrubbing eligibility classification (e.g., label), and a confidence value for the classification, which may serve as the relative eligibility of the PSD. The eligible PSDs may be ranked in an order according to determined confidence values, and may be further classified according to such order. The future workload of the storage system may be forecasted, and the scrubbing of PSDs may be scheduled based on the forecasted workload of the system and the relative eligibilities of the set of PSDs.
Opening claim text (preview).
What is claimed is: 1. For a storage system including a plurality PSDs (physical storage devices), a method comprising: selecting, using a processor, an eligible set of two or more of the plurality of PSDs that are eligible for scrubbing, wherein said selecting the eligible set includes using a processor to select each PSD of the eligible set based on a similarity between characteristics of said each PSD and characteristics of PSDs previously determined to be eligible for scrubbing; responsive to said selecting, storing, in a memory using a processor, the eligible set of the two or more PSDs eligible for scrubbing; receiving, using a processor, a health score set of health scores for the two or more PSDs in the eligible set, wherein the health score set identifies, for each PSD in the eligible set, a corresponding health score in the health score set; receiving, using a processor and in accordance with the health score set, a relative eligibility for each PSD of the eligible set relative to other PSDs of the eligible set; receiving, using a processor, a table defining PSD health categories with associated health score ranges and associated scrub frequency categories, wherein each PSD health category is associated with a corresponding one of the associated health score ranges and is associated with a corresponding one of the associated scrub frequency categories; for each PSD of the eligible set, mapping, using a processor, said each PSD to one of the PSD health categories and one of the scrub frequency categories associated with said one PSD health category, wherein said mapping is performed in accordance with the health score set and in accordance with the table, wherein a first of the PSD health categories is associated with a first of the scrub frequency categories and a second of the PSD health categories is associated with a second of the scrub frequency categories, wherein the first PSD health category denotes a healthier PSD state than the second PSD health category, and wherein the second scrub frequency denotes a higher scrub frequency than the first scrub frequency, wherein a first PSD of the eligible set has a first health score of the health score set which is mapped by said mapping to the first PSD health category, wherein a second PSD of the eligible set has a second health score of the health score set which is mapped by said mapping to the second PSD health category, and wherein the first PSD is healthier than the second PSD as indicated by the first health score of the first PSD being greater than the second health score of the second PSD; scheduling, using a processor and in accordance with a schedule, scrubbing of the eligible set of PSDs, including, for each PSD of the eligible set, scheduling a scrubbing of said each PSD based on the relative eligibility of said each PSD and based on a particular one of the scrub frequency categories mapped to said each PSD by said mapping, wherein the schedule indicates to scrub the second PSD, which is less healthy than the first PSD, more frequently than said first PSD; and scrubbing, using a processor, the eligible set of PSDs according to the schedule, wherein said scrubbing scrubs the second PSD, which is less healthy than the first PSD, more frequently than said first PSD, and wherein said scrubbing includes detecting a media error and corrupted data, and reconstructing the corrupted data into a corresponding proper form. 2. The method of claim 1 , wherein said scheduling the scrubbing of the eligible set of PSDs includes, for each PSD of the set, scheduling a frequency of scrubbing of said each PSD based on the relative eligibility of said each PSD. 3. The method of claim 1 , further comprising: predicting, using a processor, amounts of workload activity on the storage system during future time periods, wherein the scrubbing of the eligible set of PSDs is scheduled based on the predicted amounts of workload activity. 4. The method of claim 1 , further comprising: ranking, using a processor, the PSDs of the eligible set in an order according to the relative eligibility of the PSDs, wherein the scrubbing of the eligible set of PSDs is based on the order. 5. The method of claim 1 , further comprising: performing, using a processor, conformal prediction analysis on the plurality of PSDs, which includes determining the eligible set using a processor. 6. The method of claim 5 , wherein said determining the eligible set includes, for each PSD of the plurality of PSDs, classifying said each PSD using a processor as either eligible for scrubbing or not eligible for scrubbing. 7. The method of claim 6 , wherein said performing conformal prediction analysis includes calculating, using a processor for each PSD of the eligible set of PSDs, a confidence in the classification of said each PSD as eligible for scrubbing, wherein the calculated confidence serves as the health score and the relative eligibility of said each PSD. 8. A storage system comprising: a plurality PSDs (physical storage devices); one or more processors; and one or more memories comprising code stored thereon, that when executed by at least one of the one or more processors, performs a method including: selecting an eligible set of two or more of the plurality of PSDs that are eligible for scrubbing, wherein said selecting the eligible set includes selecting each PSD of the eligible set based on a similarity between characteristics of said each PSD and characteristics of PSDs previously determined to be eligible for scrubbing; responsive to said selecting, storing in a memory, the eligible set of the two or more PSDs eligible for scrubbing; receiving a health score set of health scores for the two or more PSDs in the eligible set, wherein the health score set identifies, for each PSD in the eligible set, a corresponding health score in the health score set; receiving, in accordance with the health score set, a relative eligibility for each PSD of the eligible set relative to other PSDs of the eligible set; receiving a table defining PSD health categories with associated health score ranges and associated scrub frequency categories, wherein each PSD health category is associated with a corresponding one of the associated health score ranges and is associated with a corresponding one of the associated scrub frequency categories; for each PSD of the eligible set, mapping said each PSD to one of the PSD health categories and one of the scrub frequency categories associated with said one PSD health category, wherein said mapping is performed in accordance with the health score set and in accordance with the table, wherein a first of the PSD health categories is associated with a first of the scrub frequency categories and a second of the PSD health categories is associated with a second of the scrub frequency categories, wherein the first PSD health category denotes a healthier PSD state than the second PSD health category, and wherein the second scrub frequency denotes a higher scrub frequency than the first scrub frequency, wherein a first PSD of the eligible set has a first health score of the health score set which is mapped by said mapping to the first PSD health category, wherein a second PSD of the eligible set has a second health score of the health score set which is mapped by said mapping to the second PSD health category, and wherein the first PSD is healthier than the second PSD as indicated by the first health score of the first PSD being greater than the second health score of the second PSD; scheduling, in accordance with a schedule, scrubbing of the eligible set of PSDs, including, for each PSD of the eligible set, scheduling a scrubbing of said each PSD based on the relative eligibility of said each PSD and based o
Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors · CPC title
Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues · CPC title
by facilitating the interaction with a user or administrator · CPC title
Erasing, e.g. deleting, data cleaning, moving of data to a wastebasket · CPC title
Command handling arrangements, e.g. command buffers, queues, command scheduling · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.