Heartbeat Communication Randomization for Distributed Database Partition Groups

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In multi-partitioned distributed databases, the increasing number of heartbeat communications due to the Raft consensus algorithm can lead to congestion and unnecessary leader elections, particularly as the system scales up, affecting the reliability and performance of the system.

Innovation Solution

Randomizing the timing of heartbeat communications across partition groups based on a maximum duration heartbeat communication interval, which is partly derived from the heartbeat timeout interval, to minimize the number of concurrent heartbeat communications and prevent unnecessary leader elections.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If the number of computing nodes and partitions is increased to achieve horizontal scalability, then data access performance is improved, but the number of heartbeat communications increases causing network congestion

Engineering Contradiction:
Improvedata access performanceVSAvoidnetwork congestion
Core Design Contradiction:
ProductivityVSObject-affected harmful factors

Solution Approach 1:

The patent applies dynamics by making the heartbeat communication interval variable rather than fixed. Each partition group dynamically adjusts its heartbeat interval based on its position in a randomized sequence, transforming the static periodic communication into a dynamic adaptive system that distributes communication load over time

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent changes the parameter of heartbeat communication interval from a fixed value to a variable value drawn from a probability distribution. This parameter change allows the system to maintain the necessary heartbeat functionality while varying the timing to avoid synchronized communications across all partition groups

Inventive Principle:
Principle #35Parameter changes

2Reliability

If periodic heartbeat communications are sent according to a pre-determined schedule, then leader detection is maintained, but unnecessary leader elections are triggered due to congestion

Engineering Contradiction:
Improveleader detectionVSAvoidleader election stability
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The patent maintains periodic action by ensuring heartbeats are sent at regular intervals within each partition group, but applies a twist by randomizing the phase offset of these periodic actions across different partition groups. This preserves the reliability of leader detection within each group while preventing system-wide synchronization issues

Inventive Principle:
Principle #19Periodic action

Solution Approach 2:

The patent applies preliminary action by pre-assigning randomized heartbeat intervals to partition groups before the system operates. This preliminary randomization prevents congestion and unnecessary elections from occurring in the first place, rather than reacting to them after they happen

Inventive Principle:
Principle #10Preliminary action

3Reliability

If the number of heartbeat communications is increased to maintain consistency across more partitions, then data consistency is improved, but computational resource consumption increases

Engineering Contradiction:
Improvedata consistencyVSAvoidcomputational resource consumption
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent applies segmentation by dividing the system into partition groups that communicate heartbeats independently with randomized intervals. This segmentation allows each group to maintain consistency without contributing to system-wide communication storms, reducing overall computational resource consumption while preserving data consistency within each segment

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP4189534B1Randomization of heartbeat communications among multiple partition groups
Publication Date: 2024.12.11 HITACHI VANTARA LLC
  • EP4189534B1 patent drawingFigure 1
  • EP4189534B1 patent drawingFigure 2
  • EP4189534B1 patent drawingFigure 3

AI summary

In some examples, a first computing device of a plurality of computing devices may be a member of a first partition group. For example, the first partition group may correspond to a first partition of multiple partitions of a metadata database. The first partition group may include at least one other computing device. Furthermore, each of the plurality of computing devices may maintain at least one partition of the metadata database so that the metadata database is partitioned into multiple partitions distributed across the computing devices. The first computing device may determine a first time threshold for a heartbeat communication to be sent to the other computing device(s) in the first partition group, and may select a random time before the first time threshold. The first computing device may send, based on the selected random time, the heartbeat communication to the other computing device(s) in the first partition group.