# US 2019/0173739 A1 · Method, device and computer program product for managing distributed system

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

- Number: US 2019/0173739 A1
- Document ID: US20190173739A1
- Status: Published application
- Kind: A1
- Application number: 16/173,099
- Filed: 2018-10-29
- Published: 2019-06-06
- Earliest claimed: 2017-10-27
- Assignees: EMC IP Holding Company LLC
- Applicants: EMC IP Holding Company LLC
- Inventors: Wei Cui; Junping Zhao; Huan Chen; Brown Zan Liu
- Web page: https://patentgrep.com/patent/US20190173739A1

## CPC

- H04L 41/0668: by dynamic selection of recovery network elements, e.g. replacement by the most appropriate element after failure
- H04L 43/0817: by checking functioning
- H04L 43/10: Active monitoring, e.g. heartbeat, ping or trace-route
- H04L 45/02: Topology update or discovery
- H04L 41/0893: Assignment of logical groups to network elements
- H04L 43/16: Threshold monitoring
- H04L 45/037: Routes obligatorily traversing service-related nodes
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Embodiments of the present disclosure relate to a method, a device and a computer program product for managing a distributed system. The method comprises sending heartbeat messages from a master node to a plurality of slave nodes, the master node and the plurality of slave nodes being included in a plurality of nodes in the distributed system, and the plurality of nodes being divided into one or more partitions. The method further comprises, in response to receiving a response to the heartbeat messages from a portion of slave nodes in the plurality of slave nodes, determining respective states of the one or more partitions. In addition, the method further comprises a state of a first slave node in the plurality of slave nodes at least based on the respective states of the one or more partitions, the master node failing to receive a response to the heartbeat messages from the first slave node.

## Claims

### Claim 1

A method for managing a distributed system (300), the method (400) comprising:
sending heartbeat messages from a master node (310-4) to a plurality of slave nodes (310-1, 310-2, 310-3, 310-4), the master node (310-4) and the plurality of slave nodes (310-1, 310-2, 310-3, 310-4) being included in a plurality of nodes (320) in the distributed system (300), and the plurality of nodes (320) being divided into one or more partitions;
in response to receiving a response to the heartbeat messages from a part (310-2, 310-3, 310-5) of the plurality of slave nodes (310-1, 310-2, 310-3, 310-5), determining (420) respective states of the one or more partitions; and
determining (430) a state of a first slave node (310-1) in the plurality of slave nodes (310-1, 310-2, 310-3, 310-4) at least based on the respective states of the one or more partitions, the master node (310-4) failing to receive a response to the heartbeat messages from the first slave node (310-1).

### Claim 2 (depends on 1)

The method (400) according to claim 1, wherein determining (420) the respective states of the one or more partitions comprises:
determining, based on the response received from the part (310-2, 310-3, 310-5) of the plurality of slave nodes, at least one partition where the part (310-2, 310-3, 310-5) of the plurality of slave nodes locate; and
determining a respective state of the at least one partition as an active state, the active state indicating that the at least one partition is not isolated from more than a predetermined number of nodes in the plurality of nodes (320).

### Claim 3 (depends on 2)

The method (400) according to claim 2, wherein the response received from the part (310-2, 310-3, 310-5) of the plurality of slave nodes includes first information on the at least one partition, and determining the at least one partition comprises:
determining the at least one partition based on the first information, the first information including at least one of second information on a subnet mask, and a gateway address.

### Claim 4 (depends on 2)

The method (400) according to claim 2, wherein determining (430) the state of the first slave node (310-1) comprises:
in response to determining that the first slave node (310-1) is located in the at least one partition, determining the state of the first slave node as a first state (430), the first state indicating that the first slave node (310-1) is not isolated from more than the predetermined number of nodes in the plurality of nodes (320).

### Claim 5 (depends on 4)

The method (400) according to claim 4, wherein determining (430) the state of the first slave node (310-1) further comprises:
in response to determining that a first duration of the first slave node (310-1) in the first state (430) exceeds a first threshold, determining the state of the first slave node (310-1) as a failed state (440).

### Claim 6 (depends on 4)

The method (400) according to claim 4, wherein determining (430) the state of the first slave node (310-1) comprises:
in response to determining that the first slave node (310-1) is outside the at least one partition, determining the state of the first slave node (310-1) as a second state (420), the second state indicating that the first slave node (310-1) is isolated from more than the predetermined number of nodes in the plurality of nodes (320).

### Claim 7 (depends on 6)

The method (400) according to claim 6, wherein the part (310-2, 310-3, 310-5) of the plurality of slave nodes include a second slave node (310-2) in the failed state (440), and the method (400) further comprises:
in response to determining that a second duration of the second slave node (310-2) in the failed state (440) fails to exceed a second threshold, determining (430) a state of the second slave node (310-2) as the second state (420).

### Claim 8 (depends on 7)

The method (400) according to claim 7, wherein the distributed system (300) further includes at least one node (330) in a standby state (410) for replacing a failed node in the plurality of nodes (320), and the method (400) further comprises:
replacing a slave node in the plurality of slave nodes (320) with the at least one node (330), wherein a duration of the slave node in the failed state (440) exceeds the second threshold.

### Claim 9 (depends on 8)

The method (400) according to claim 8, further comprising:
in response to the second duration exceeding the second threshold, determining (430) the state of the second slave node (310-2) as the standby state (410).

### Claim 10

An electronic device (600), comprising:
at least one processing unit (601);
at least one memory (602, 603) coupled to the at least one processing unit (601) and storing instructions for execution by the at least one processing unit (601), the instructions, when executed by the at least one processing unit (601), causing the device (600) to perform acts comprising:
sending heartbeat messages to a plurality of slave nodes (310-1, 310-2, 310-3, 310-4), a master node (310-4) including the device (600) and the plurality of slave nodes (310-1, 310-2, 310-3, 310-4) being included in a plurality of nodes (320) in the distributed system (300), the device (600) being included in the master node (310-4), and the plurality of nodes (320) being divided into one or more partitions;
in response to receiving a response to the heartbeat messages from a part (310-2, 310-3, 310-5) of the plurality of slave nodes (310-1, 310-2, 310-3, 310-5), determining (420) respective states of the one or more partitions; and
determining (430) a state of a first slave node (310-1) in the plurality of slave nodes (310-1, 310-2, 310-3, 310-4) at least based on the respective states of the one or more partitions, the device (600) failing to receive a response to the heartbeat messages from the first slave node (310-1).

### Claim 11 (depends on 10)

The device (600) according to claim 10, wherein determining (420) the respective states of the one or more partitions comprises:
determining, based on the response received from the part (310-2, 310-3, 310-5) of the plurality of slave nodes, at least one partition where the part (310-2, 310-3, 310-5) of the plurality of slave nodes locate; and
determining a respective state of the at least one partition as an active state, the active state indicating that the at least one partition is not isolated from more than a predetermined number of nodes in the plurality of nodes (320).

### Claim 12 (depends on 11)

The device (600) according to claim 11, wherein the response received from the part (310-2, 310-3, 310-5) of the plurality of slave nodes includes first information on the at least one partition, and determining the at least one partition comprises:
determining the at least one partition based on the first information, the first information including at least one of second information on a subnet mask, and a gateway address.

### Claim 13 (depends on 11)

The device (600) according to claim 11, wherein determining (430) the state of the first slave node (310-1) comprises:
in response to determining that the first slave node (310-1) is located in the at least one partition, determining the state of the first slave node as a first state (430), the first state indicating that the first slave node (310-1) is not isolated from more than the predetermined number of nodes in the plurality of nodes (320).

### Claim 14 (depends on 13)

The device (600) according to claim 13, wherein determining (430) the state of the first slave node (310-1) further comprises:
in response to determining that a first duration of the first slave node (310-1) in the first state (430) exceeds a first threshold, determining the state of the first slave node (310-1) as a failed state (440).

### Claim 15 (depends on 13)

The device (600) according to claim 13, wherein determining (430) the state of the first slave node (310-1) comprises:
in response to determining that the first slave node (310-1) is outside the at least one partition, determining the state of the first slave node (310-1) as a second state (420), the second state indicating that the first slave node (310-1) is isolated from more than the predetermined number of nodes in the plurality of nodes (320).

### Claim 16 (depends on 15)

The device (600) according to claim 15, wherein the part (310-2, 310-3, 310-5) of the plurality of slave nodes include a second slave node (310-2) in the failed state (440), and the acts further comprise:
in response to determining that a second duration of the second slave node (310-2) in the failed state (440) fails to exceed a second threshold, determining (430) a state of the second slave node (310-2) as the second state (420).

### Claim 17 (depends on 16)

The device (600) according to claim 16, wherein the distributed system (300) further includes at least one node (330) in a standby state (410) for replacing a failed node in the plurality of nodes (320), and the acts further comprise:
replacing a slave node in the plurality of slave nodes (320) with the at least one node (330), wherein a duration of the slave node in the failed state (440) exceeds the second threshold.

### Claim 18 (depends on 17)

The device (600) according to claim 17, wherein the acts further comprise:
in response to the second duration exceeding the second threshold, determining (430) the state of the second slave node (310-2) as the standby state (410).

### Claim 19

A computer program product that is tangibly stored on a non-transient computer readable medium and includes machine-executable instructions, the machine-executable instructions, when being executed by a device, causing the device to manage a distributed system by performing:
sending heartbeat messages from a master node (310-4) to a plurality of slave nodes (310-1, 310-2, 310-3, 310-4), the master node (310-4) and the plurality of slave nodes (310-1, 310-2, 310-3, 310-4) being included in a plurality of nodes (320) in the distributed system (300), and the plurality of nodes (320) being divided into one or more partitions;
in response to receiving a response to the heartbeat messages from a part (310-2, 310-3, 310-5) of the plurality of slave nodes (310-1, 310-2, 310-3, 310-5), determining (420) respective states of the one or more partitions; and
determining (430) a state of a first slave node (310-1) in the plurality of slave nodes (310-1, 310-2, 310-3, 310-4) at least based on the respective states of the one or more partitions, the master node (310-4) failing to receive a response to the heartbeat messages from the first slave node (310-1).

### Claim 20 (depends on 19)

The computer program product of claim 19, wherein determining (420) the respective states of the one or more partitions comprises:
determining, based on the response received from the part (310-2, 310-3, 310-5) of the plurality of slave nodes, at least one partition where the part (310-2, 310-3, 310-5) of the plurality of slave nodes locate; and
determining a respective state of the at least one partition as an active state, the active state indicating that the at least one partition is not isolated from more than a predetermined number of nodes in the plurality of nodes (320).
