# US 2025/0165359 A1 · Methods and systems to improve input/output (i/o) resumption time during a non-disruptive automatic unplanned failover from a primary copy of data at a primary storage system to a mirror copy of the data at a cross-site secondary storage system

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

- Number: US 2025/0165359 A1
- Document ID: US20250165359A1
- Status: Published application
- Kind: A1
- Application number: 19/033,913
- Filed: 2025-01-22
- Published: 2025-05-22
- Earliest claimed: 2022-07-28
- Assignees: NetApp, Inc.
- Applicants: NetApp, Inc.
- Inventors: Anoop Vijayan; Akhil Kaushik; Dhruvil Shah
- Web page: https://patentgrep.com/patent/US20250165359A1

## CPC

- G06F 11/2025: {using centralised failover control functionality}
- G06F 11/0727: {in a storage system, e.g. in a DASD or network based storage system (drivers for digital recording or reproducing units G06F3/06; circuits for error detection or correction within digital recording or reproducing units 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 11/0757: {by exceeding a time limit, i.e. time-out, e.g. watchdogs}
- G06F 11/0772: {Means for error signaling, e.g. using interrupts, exception flags, dedicated error registers}
- G06F 11/2041: {with more than one idle spare processing component}
- G06F 11/2046: {where the redundant components share persistent storage (G06F11/2043 takes precedence)}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Multi-site distributed storage systems and computer-implemented methods are described for improving a resumption time of input/output (I/O) operations during an automatic unplanned failover (AUFO). A computer-implemented method includes monitoring, with a second cluster, heartbeat information received at ultra-short time intervals from a first connection of one or more storage objects of the first cluster, determining, with the second cluster, whether the heartbeat information from the first connection is received during an ultra-short time interval, and intelligently routing heartbeat information from the one or more storage objects of the first cluster from the first connection to a second connection when the heartbeat information from the first connection is not received during the ultra-short time interval.

## Claims

### Claim 1

A computer-implemented method performed by one or more processing resources of a multi-site distributed storage system with a primary storage site having a first cluster and a secondary storage site having a second cluster, the computer-implemented method comprising:
monitoring, with the second cluster, heartbeat information received at ultra-short time intervals from a first connection between a first logical network interface of the first cluster and a first logical network interface of the second cluster; and
intelligently routing heartbeat information from the one or more storage objects of the first cluster from the first connection to a different second connection between a second logical network interface of the first cluster and a second logical network interface of the second cluster when the heartbeat information from the first connection is not received during the ultra-short time interval.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the intelligently routing heartbeat information further comprises:
sending, with the second cluster, a time-out message to a heartbeat module of the first cluster when the heartbeat information from the first connection is not received during the ultra-short time interval; and
in response to the time-out message, sending, with the first cluster, heartbeat information to the second connection.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein the first connection is associated with a first logical network interface of the first cluster and a first logical network interface of the second cluster, wherein the second connection is associated with a second logical network interface of the first cluster and a second logical network interface of the second cluster.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein the first logical network interface of the first cluster is migrating to a different logical network interface.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein the ultra-short time interval is less than one second.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, further comprising:
determining, with the second cluster, whether the heartbeat information from the first connection is received during an ultra-short time interval.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, further comprising:
determining whether the heartbeat information is received during a time period of three ultra-short time intervals;
sending a heartbeat response from the second cluster to the first cluster;
issuing, with the second cluster, an abort notification upon expiration of the time period with no heartbeat information being received during this time period;
initiating an out of sync (OOS) state for a relationship between the first and a second cluster of the secondary storage site when the secondary storage site fails to receive the heartbeat information during the time period; and
performing an automatic unplanned failover based on the OOS state and whether the primary storage site has a failure.

### Claim 8

A multi-site distributed storage system having a primary storage site with a first cluster and a secondary storage site with a second cluster comprising:
one or more processing resources; and
a non-transitory computer-readable medium coupled to the one or more processing resources, having stored therein instructions, which when executed by the one or more processing resources cause the one or more processing resources to:
monitor, with the second cluster, heartbeat information received at ultra-short time intervals from a first connection between a first logical network interface of the first cluster and a first logical network interface of the second cluster; and
intelligently routing heartbeat information from the one or more storage objects of the first cluster from the first connection to a different second connection between a second logical network interface of the first cluster and a second logical network interface of the second cluster when the heartbeat information from the first connection is not received during the ultra-short time intervals.

### Claim 9 (depends on 8)

The multi-site distributed storage system of claim 8, wherein the intelligently routing heartbeat information further comprises:
send, with the second cluster, a time-out message to a heartbeat module of the first cluster when the heartbeat information from the first connection is not received during the ultra-short time interval; and
in response to the time-out message, send, with the first cluster, heartbeat information to the second connection.

### Claim 10 (depends on 9)

The multi-site distributed storage system of claim 9, wherein the first connection is associated with a first logical network interface of the first cluster and a first logical network interface of the second cluster, wherein the second connection is associated with a second logical network interface of the first cluster and a second logical network interface of the second cluster.

### Claim 11 (depends on 8)

The multi-site distributed storage system of claim 8, wherein the first logical network interface of the first cluster is migrating to a different port.

### Claim 12 (depends on 8)

The multi-site distributed storage system of claim 8, wherein the ultra-short time interval is less than one second.

### Claim 13 (depends on 8)

The multi-site distributed storage system of claim 8, further comprising:
determine, with the second cluster, whether the heartbeat information from the first connection is received during an ultra-short time interval.

### Claim 14 (depends on 8)

The multi-site distributed storage system of claim 8, wherein the instructions when executed by the one or more processing resources cause the one or more processing resources to:
determine whether the heartbeat information is received during a time period of three ultra-short time intervals;
send a heartbeat response from the second cluster to the first cluster;
issue, with the second cluster, an abort notification upon expiration of the time period with no heartbeat information being received during this time period;
initiate an out of sync (OOS) state for a relationship between the first and a second cluster of the secondary storage site when the secondary storage site fails to receive the heartbeat information during the time period; and
perform an automatic unplanned failover based on the OOS state and whether the primary storage site has a failure.

### Claim 15 (depends on 14)

The multi-site distributed storage system of claim 14, wherein the instructions when executed by the one or more processing resources cause the one or more processing resources to:
initiate an out of sync (OOS) state of the second cluster for a relationship between a primary copy of data of a consistency group in the first cluster and a secondary mirror copy of the data in the second cluster when the secondary storage site fails to receive the heartbeat information during the time period.

### Claim 16

A non-transitory computer-readable storage medium embodying a set of instructions, which when executed by one or more processing resources of a multi-site distributed storage system cause the one or more processing resources to:
initiate an out of sync notification for a data replication relationship between a first storage cluster of a first storage site and a second storage cluster of a second storage site based on an inter-cluster heartbeat communication miss; and
initiate, with a mediator agent of the second cluster of the second storage site of the multi-site distributed storage system, a health check to determine a condition of the first cluster of the first storage site of the multi-site distributed storage system based on the out of sync notification.

### Claim 17 (depends on 16)

The non-transitory computer-readable storage medium of claim 16, wherein the instructions when executed by the one or more processing resources cause the one or more processing resources to:
perform an external mediator-based health check operation of a third site and logical network interface (LIF) based heath check operation in parallel for a first level of parallelization by sending a message from the health check module of the second cluster of the second storage site to an external mediator of the third site to cause a polling communication to be sent from the external mediator to storage nodes of the first cluster of the first storage site to determine a health condition of the storage nodes of the first cluster of the first storage site and simultaneously sending one or more communications to intercluster LIFs of each storage node of the first cluster of the first storage site across communication links between the first cluster and the second cluster of the second storage site to determine a health condition of each storage node of the first cluster of the first storage site, wherein the health check includes a second level of parallelization to perform health check operations simultaneously on all the storage nodes of the first cluster.

### Claim 18 (depends on 17)

The non-transitory computer-readable storage medium of claim 17, wherein the health check includes a third level of parallelization to perform these health check operations simultaneously across all the LIFs on a specific node.

### Claim 19 (depends on 17)

The non-transitory computer-readable storage medium of claim 17, wherein the instructions when executed by the one or more processing resources cause the one or more processing resources to:
receive responses from one or more storage nodes that have been polled;
receive one or more reply messages from available LIFs; and
collate results of these health check operations and determine a health condition of the storage nodes and the LIFs of the first cluster.

### Claim 20 (depends on 16)

The non-transitory computer-readable storage medium of claim 16, wherein the instructions when executed by the one or more processing resources cause the one or more processing resources to:
determine whether a first received response or reply message from a first consistency group (CG) of the first cluster indicates a failure;
cache, with the second cluster, a result indicating the failure of the first CG of the second cluster; and
utilize the result for additional CGs with no health check operations being performed for additional CGs of the first cluster, wherein the first cluster has a primary copy of data in the first CG that is initially assigned a leader role, wherein the second cluster has a mirrored copy of the data in a second consistency group that is initially assigned a follower role.
