# US 2026/0259858 A1 · Facilitating performance of donor-recipient disaggregated storage system workflows based on information relating to units of storage for storage space movement and ownership

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

- Number: US 2026/0259858 A1
- Document ID: US20260259858A1
- Status: Published application
- Kind: A1
- Application number: 19/184,097
- Filed: 2025-04-21
- Published: 2026-09-03
- Earliest claimed: 2025-03-05
- Assignees: NetApp, Inc.
- Applicants: NetApp, Inc.
- Inventors: Yash Hetal Trivedi; Matthew Curtis-Maury; Sushilkumar Gangadharan; William Arthur Gutknecht; Mrinal K. Bhattarcharjee; Jian Hu; Sumith Makam
- Web page: https://patentgrep.com/patent/US20260259858A1

## CPC

- G06F 3/0608: {Saving storage space on storage systems}
- G06F 3/0631: {by allocating resources to storage systems}
- G06F 3/067: {Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]}
- G06F 12/0802: Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches
- G06F 12/1458: {by checking the subject access rights}
- G06F 16/164: {File meta data generation}
- G06F 16/172: Caching, prefetching or hoarding of files
- G06F 16/182: Distributed file systems
- G06F 16/185: Hierarchical storage management [HSM] systems, e.g. file migration or policies thereof (details of archiving G06F16/11)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Systems and methods for use of information relating to units of storage space movement and ownership to facilitate performance of disaggregated storage system workflows are provided. In various examples, the unit of disaggregated storage space for purposes of movement and ownership is an allocation area (AA). AA ownership information relating to AAs owned by dynamically extensible file systems (DEFSs) of a cluster may be maintained within two different persistent data sources, including an AA label region and DEFS AA owner metafiles. A node-scoped cache may be implemented to cache the AA ownership information in-memory for DEFSs hosted by a given node to provide a multiprocessing (MP)-safe cache for AA ownership information, a mechanism to coordinate between AA movement and other subsystems needing to know whether an AA is “local” or “remote,” and a mechanism to serialize access and Input/Output (IO) operations to the persistent AA ownership information data sources.

## Claims

### Claim 1

A method comprising:
maintaining, by a distributed storage system, an in-memory cache of allocation area (AA) ownership information on each node of a plurality of nodes of a cluster, representing the distributed storage system, wherein the AA ownership information relates to a respective set of one or more dynamically extensible file systems (DEFSs) of a plurality of DEFSs of the distributed storage system that are resident on the node; and
prior to notifying, by a disaggregated workflow relating to a donor DEFS of the plurality of DEFSs, a recipient DEFS of the plurality of DEFSs regarding movement of an AA from the donor DEFS to the recipient DEFS, temporarily blocking access to metadata information of the AA by updating state information associated with the AA, wherein the state information includes persistent state information and cached state information, wherein the cached state information is contained in the in-memory cache of AA ownership information maintained on a first node of the plurality of nodes hosting the donor DEFS, and wherein the state information is indicative of whether ownership of the AA is in transition.

### Claim 2 (depends on 1)

The method of claim 1, wherein the in-memory cache of AA ownership information includes cached AA label information containing, for a given AA of a plurality of AAs, an AA label having (i) a current owner field containing a DEFS identifier (ID) identifying a first DEFS of the plurality of DEFSs that currently owns the given AA and (ii) a proposed owner field, which when ownership of the given AA is in transition contains a DEFS ID identifying a second DEFS of the plurality of DEFSs to which the ownership is to be transferred.

### Claim 3 (depends on 2)

The method of claim 2, further comprising, prior to the notifying, updating the proposed owner field of the AA label for the AA to a DEFS ID of the recipient DEFS AA.

### Claim 4 (depends on 2)

The method of claim 2, wherein the in-memory cache of AA ownership information includes cached DEFS AA owner metafile information containing, for a given DEFS of the respective set, at least a portion of an AA bitmap indicative of those AAs of the plurality of AAs owned by the given DEFS.

### Claim 5 (depends on 4)

The method of claim 4, further comprising, prior to the notifying, removing an indication of ownership of the AA from the portion of the AA bitmap for the donor DEFS.

### Claim 6 (depends on 2)

The method of claim 2, further comprising, after assimilation of the AA by the recipient DEFS, updating the current owner field of the AA label for the AA to a DEFS ID of the recipient DEFS AA.

### Claim 7 (depends on 4)

The method of claim 4, further comprising, after assimilation of the AA by the recipient DEFS, adding an indication of ownership of the AA to the portion of the AA bitmap for the recipient DEFS.

### Claim 8 (depends on 1)

The method of claim 1, further comprising, after assimilation of the AA by the recipient DEFS, unblocking access to the metadata information of the AA by updating state information associated with the AA contained in the in-memory cache of AA ownership information maintained on the first node.

### Claim 9

A non-transitory machine readable medium storing instructions, when executed by one or more processing resources of a distributed storage system, cause distributed storage system to:
maintain an in-memory cache of allocation area (AA) ownership information on each node of a plurality of nodes of a cluster representing the distributed storage system, wherein the AA ownership information relates to a respective set of one or more dynamically extensible file systems (DEFSs) of a plurality of DEFSs of the distributed storage system that are resident on the node; and
prior to notifying a recipient DEFS of the plurality of DEFSs regarding movement of an AA from a donor DEFS of the plurality of DEFSs to the recipient DEFS, temporarily block access to metadata information of the AA by updating state information associated with the AA, wherein the state information includes persistent state information and cached state information, wherein the cached state information is contained in the in-memory cache of AA ownership information maintained on a first node of the plurality of nodes hosting the donor DEFS, and wherein the state information is indicative of whether ownership of the AA is in transition.

### Claim 10 (depends on 9)

The non-transitory machine readable medium of claim 9, wherein the in-memory cache of AA ownership information includes cached AA label information containing, for a given AA of a plurality of AAs, an AA label having (i) a current owner field containing a DEFS identifier (ID) identifying a first DEFS of the plurality of DEFSs that currently owns the given AA and (ii) a proposed owner field, which when ownership of the given AA is in transition contains a DEFS ID identifying a second DEFS of the plurality of DEFSs to which the ownership is to be transferred.

### Claim 11 (depends on 10)

The non-transitory machine readable medium of claim 10, wherein the instructions further cause the distributed storage system to, prior to notifying the recipient DEFS regarding movement of the AA, update the proposed owner field of the AA label for the AA to a DEFS ID of the recipient DEFS AA.

### Claim 12 (depends on 10)

The non-transitory machine readable medium of claim 10, wherein the in-memory cache of AA ownership information includes cached DEFS AA owner metafile information containing, for a given DEFS of the respective set, at least a portion of an AA bitmap indicative of those AAs of the plurality of AAs owned by the given DEFS.

### Claim 13 (depends on 12)

The non-transitory machine readable medium of claim 12, wherein the instructions further cause the distributed storage system to, prior to notifying the recipient DEFS regarding movement of the AA, remove an indication of ownership of the AA from the portion of the AA bitmap for the donor DEFS.

### Claim 14 (depends on 10)

The non-transitory machine readable medium of claim 10, wherein the instructions further cause the distributed storage system to, after assimilation of the AA by the recipient DEFS, update the current owner field of the AA label for the AA to a DEFS ID of the recipient DEFS AA.

### Claim 15 (depends on 12)

The non-transitory machine readable medium of claim 12, wherein the instructions further cause the distributed storage system to, after assimilation of the AA by the recipient DEFS, add an indication of ownership of the AA to the portion of the AA bitmap for the recipient DEFS.

### Claim 16 (depends on 10)

The non-transitory machine readable medium of claim 10, wherein the instructions further cause the distributed storage system to, after assimilation of the AA by the recipient DEFS, unblock access to the metadata information of the AA by updating state information associated with the AA contained in the in-memory cache of AA ownership information maintained on the first node.

### Claim 17

A distributed storage system comprising:
one or more hardware processing resources; and
instructions that when executed by the one or more hardware processing resources cause the distributed storage system to:
maintain an in-memory cache of allocation area (AA) ownership information on each node of a plurality of nodes of a cluster representing the distributed storage system, wherein the AA ownership information relates to a respective set of one or more dynamically extensible file systems (DEFSs) of a plurality of DEFSs of the distributed storage system that are resident on the node; and
prior to notifying a recipient DEFS of the plurality of DEFSs regarding movement of an AA from a donor DEFS of the plurality of DEFSs to the recipient DEFS, temporarily block access to metadata information of the AA by updating state information associated with the AA, wherein the state information includes persistent state information and cached state information, wherein the cached state information is contained in the in-memory cache of AA ownership information maintained on a first node of the plurality of nodes hosting the donor DEFS, and wherein the state information is indicative of whether ownership of the AA is in transition.

### Claim 18 (depends on 17)

The distributed storage system of claim 17, wherein the in-memory cache of AA ownership information includes cached AA label information containing, for a given AA of a plurality of AAs, an AA label having (i) a current owner field containing a DEFS identifier (ID) identifying a first DEFS of the plurality of DEFSs that currently owns the given AA and (ii) a proposed owner field, which when ownership of the given AA is in transition contains a DEFS ID identifying a second DEFS of the plurality of DEFSs to which the ownership is to be transferred.

### Claim 19 (depends on 18)

The distributed storage system of claim 18, wherein the instructions further cause the distributed storage system to, prior to notifying the recipient DEFS regarding movement of the AA, update the proposed owner field of the AA label for the AA to a DEFS ID of the recipient DEFS AA.

### Claim 20 (depends on 18)

The distributed storage system of claim 18, wherein the in-memory cache of AA ownership information includes cached DEFS AA owner metafile information containing, for a given DEFS of the respective set, at least a portion of an AA bitmap indicative of those AAs of the plurality of AAs owned by the given DEFS.

### Claim 21 (depends on 20)

The distributed storage system of claim 20, wherein the instructions further cause the distributed storage system to, prior to notifying the recipient DEFS regarding movement of the AA, remove an indication of ownership of the AA from the portion of the AA bitmap for the donor DEFS.

### Claim 22 (depends on 18)

The distributed storage system of claim 18, wherein the instructions further cause the distributed storage system to, after assimilation of the AA by the recipient DEFS, update the current owner field of the AA label for the AA to a DEFS ID of the recipient DEFS AA.

### Claim 23 (depends on 20)

The distributed storage system of claim 20, wherein the instructions further cause the distributed storage system to, after assimilation of the AA by the recipient DEFS, add an indication of ownership of the AA to the portion of the AA bitmap for the recipient DEFS.

### Claim 24 (depends on 18)

The distributed storage system of claim 18, wherein the instructions further cause the distributed storage system to, after assimilation of the AA by the recipient DEFS, unblock access to the metadata information of the AA by updating state information associated with the AA contained in the in-memory cache of AA ownership information maintained on the first node.

### Claim 25 (depends on 2)

The method of claim 2, wherein the cached AA label information further contains, for the given AA, a lock flag that is used to serialize access to a corresponding persistent AA label for the given AA.

### Claim 26 (depends on 10)

The non-transitory machine readable medium of claim 10, wherein the cached AA label information further contains, for the given AA, a lock flag that is used to serialize access to a corresponding persistent AA label for the given AA.

### Claim 27 (depends on 18)

The distributed storage system of claim 18, wherein the cached AA label information further contains, for the given AA, a lock flag that is used to serialize access to a corresponding persistent AA label for the given AA.
