# US 2021/0334180 A1 · Network storage failover systems and associated methods

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

- Number: US 2021/0334180 A1
- Document ID: US20210334180A1
- Status: Published application
- Kind: A1
- Application number: 16/855,870
- Filed: 2020-04-22
- Published: 2021-10-28
- Earliest claimed: 2020-04-22
- Assignees: NetApp, Inc.
- Applicants: Netapp, Inc.
- Inventors: Asif Imtiyaz Pathan; Parag Sarfare; Ananthan Subramanian; Szu-Wen Kuo; Santhosh Selvaraj; Nikhil Mattankot
- Web page: https://patentgrep.com/patent/US20210334180A1

## CPC

- G06F 11/1471: involving logging of persistent data for recovery
- G06F 11/2069: {Management of state, configuration or failover}
- G06F 11/0787: {Storage of error reports, e.g. persistent data storage, storage using memory protection}
- G06F 11/1435: {using file system or storage system metadata}
- G06F 11/2094: {Redundant storage or storage space (G06F11/2056 takes precedence)}
- G06F 11/3034: {where the computing system component is a storage system, e.g. DASD based or network based (digital input from or digital output to record carriers G06F3/06; digital recording or reproducing G11B20/18; for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS], H04L67/1097)}
- G06F 16/1734: {Details of monitoring file system events, e.g. by the use of hooks, filter drivers, logs}
- G06F 16/1824: {implemented using Network-attached Storage [NAS] architecture (distributed or networked storage systems G06F3/067; protocols for distributed storage of data in a network H04L67/1097)}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Failover methods and systems for a networked storage environment are provided. In one aspect, a read request associated with a first storage object is received, during a replay of entries of a log stored in a non-volatile memory of a second storage node for a failover operation initiated in response to a failure at a first storage node. The second storage node operates as a partner node of the first storage node. The read request is processed using a filtering data structure that is generated from the log prior to the replay and identifies each log entry. The read request is processed when the log does not have an entry associated with the read request, and when the filtering data structure includes an entry associated with the read request, the requested data is located at the non-volatile memory.

## Claims

### Claim 1

A method, comprising:
receiving by a processor of a second storage node, a read request associated with a first storage object during a replay of entries of a log stored in a non-volatile memory of the second storage node for a failover operation, initiated in response to a failure at a first storage node responsible for managing the first storage object before the failure, wherein the second storage node operates as a partner node of the first storage node to mirror at the non-volatile memory one or more write requests associated with the first storage object and data associated with the one or more write requests received by the first storage node prior to the failure;
determining by the processor, whether the read request has an associated entry at a filtering data structure that is generated from the log, prior to the replay and identifies the entries in the log;
processing the read request by the processor, when the filtering data structure does not include an entry associated with the read request; and
utilizing a location data structure by the processor, to locate data associated with the read request at the non-volatile memory and providing the located data in response to the read request, when the filtering data structure includes an entry associated with the read request.

### Claim 2 (depends on 1)

The method of claim 1, further comprising: before the replay, updating the location data structure by the processor to identify each data container, and a location of the non-volatile memory where data associated with each data container is stored for each write request mirrored at the log of the second storage node after receipt by the first storage node prior to the failure.

### Claim 3 (depends on 1)

The method of claim 1, further comprising: storing by the processor in the filtering data structure, a data container and a data container offset associated with each write request mirrored at the log of the second storage node after receipt by the first storage node prior to the failure.

### Claim 4 (depends on 1)

The method of claim 1, further comprising: prior to the replay, generating by the processor, a metadata data structure to store a modification time of a data container associated with each write request mirrored at the log of the second storage node after receipt by the first storage node prior to the failure.

### Claim 5 (depends on 4)

The method of claim 4, further comprising: before the replay, persistently storing by the processor each data container modification time, and the persistently stored modification time is provided in response to the read request.

### Claim 6 (depends on 1)

The method of claim 1, further comprising: delaying by the processor, the read request processing when an error condition occurs in processing the read request.

### Claim 7 (depends on 1)

The method of claim 1, further comprising: removing by the processor, any entry added to the location structure associated with a log entry after the replay is completed.

### Claim 8

A method, comprising:
receiving by a processor of a second storage node, a write request associated with a first storage object during a replay of entries of a log stored in a non-volatile memory of the second storage node for a failover operation, initiated in response to a failure at a first storage node responsible for managing the first storage object before the failure, wherein the second storage node operates as a partner node of the first storage node to mirror at the non-volatile memory one or more write requests associated with the first storage object and data associated with the one or more write requests received by the first storage node prior to the failure;
determining by the processor, whether the write request has an entry in a filtering data structure that identifies each log entry and is generated using the log, prior to the replay;
processing the write request by the processor, when the write request is not associated with any filtering data structure entry;
determining by the processor that the write request is a re-try write request, when the write request is associated with a filtering data structure entry; and
executing the re-try write request by the processor from the second storage node, during the replay at the second storage node.

### Claim 9 (depends on 1)

The method of claim 1, further comprising: to determine that the write request is the re-try write request, comparing by the processor data for the write request and data stored at the non-volatile memory for a log entry associated with the write request.

### Claim 10 (depends on 9)

The method of claim 9, further comprising: utilizing by the processor, a location data structure to locate the data for the write request stored at the non-volatile memory.

### Claim 11 (depends on 10)

The method of claim 10, further comprising: before the replay, updating by the processor the location data structure to identify each data container, and a location of the non-volatile memory where data associated with each data container is stored at the non-volatile memory for each write request mirrored at the log of the second storage node after receipt by the first storage node prior to the failure.

### Claim 12 (depends on 11)

The method of claim 11, further comprising: after the replay is completed, removing by the processor, any entry added to the location data structure for a corresponding log entry before the replay.

### Claim 13 (depends on 1)

The method of claim 1, further comprising: identifying by the processor from the filtering data structure, a data container and a data container offset associated with each write request mirrored at the log of the second storage node after receipt by the first storage node prior to the failure.

### Claim 14 (depends on 1)

The method of claim 1, further comprising: processing by the processor, the write request after the replay, when the write request is not a re-try write request.

### Claim 15

A non-transitory machine readable medium having stored thereon instructions comprising machine executable code which when executed by a machine, causes the machine to:
receive a read request associated with a first storage object, during a replay of entries of a log stored in a non-volatile memory of a second storage node for a failover operation, initiated in response to a failure at a first storage node responsible for managing the first storage object before the failure, wherein the second storage node operates as a partner node of the first storage node to mirror at the non-volatile memory one or more write requests associated with the first storage object and data associated with the one or more write requests received by the first storage node prior to the failure;
determine whether the read request has an associated entry at a filtering data structure that is generated from the log to identify each log entry, prior to the replay;
process the read request, when the filtering data structure does not include an entry associated with the read request; and
utilize a location data structure to locate data associated with the read request at the non-volatile memory and provide the located data in response to the read request, when the filtering data structure includes an entry associated with the read request.

### Claim 16 (depends on 15)

The non-transitory machine readable medium of claim 15, wherein the machine executable code further causes the machine to: before the replay, update the location data structure to identify each data container, and a location of the non-volatile memory where data associated with each data container is stored for each write request mirrored at the log of the second storage node after receipt by the first storage node prior to the failure.

### Claim 17 (depends on 15)

The non-transitory machine readable medium of claim 15, wherein the machine executable code further causes the machine to: store in the filtering data structure, a data container and a data container offset associated with each write request mirrored at the log of the second storage node after receipt by the first storage node prior to the failure.

### Claim 18 (depends on 15)

The non-transitory machine readable medium of claim 15, wherein the machine executable code further causes the machine to: generate a metadata data structure, to store a modification time of a data container associated with each write request mirrored at the log of the second storage node after receipt by the first storage node prior to the failure.

### Claim 19 (depends on 18)

The non-transitory machine readable medium of claim 18, wherein the machine executable code further causes the machine to: prior to the replay, persistently store each data container modification time, and the persistently stored modification time is provided in response to the read request.

### Claim 20 (depends on 15)

The non-transitory machine readable medium of claim 15, wherein the machine executable code further causes the machine to: delay the read request processing, when an error condition occurs in processing the read request.
