Dual-Memory Network Device Upgrade Latency Reduction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Traditional network device upgrades result in significant latency due to the inability to perform packet transmission during the download of new configuration information, as all memory resources are dedicated to storage, leading to traffic outages and operational limitations.

Innovation Solution

Implementing a dual-memory portion system where one portion is used for storage and another for execution during upgrades, allowing network device agents and forwarding chips to utilize both portions simultaneously, with a feature agent managing the allocation and transition between them.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If all memory resources are dedicated to storage during upgrades, then configuration information can be downloaded, but packet transmission capability is lost causing traffic outage

Engineering Contradiction:
Improveupgrade completionVSAvoidpacket transmission
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The memory resources are segmented into two distinct portions: a first portion dedicated to storage of configuration information and network device tables, and a second portion used for downloading new configuration information during upgrades. This segmentation allows packet transmission to continue using the first portion while the second portion handles the upgrade process, thereby resolving the contradiction between reliable upgrade completion and maintained packet transmission productivity.

Inventive Principle:
Principle #1Segmentation

2Adaptability or versatility

If all memory is used for downloading configuration information, then upgrade can be performed, but latency increases due to inability to transmit packets

Engineering Contradiction:
Improveupgrade executionVSAvoidupgrade latency
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system maintains continuity of useful action by enabling packet transmission to continue uninterrupted during the upgrade process. The first portion of memory preserves existing network device tables for active packet forwarding, while the second portion executes the upgrade. This eliminates downtime and reduces upgrade latency, as the network device remains operational throughout the upgrade process.

Inventive Principle:
Principle #20Continuity of useful action

3Extent of automation

If memory resources are scaled down for upgrade execution, then upgrade can proceed, but network device operability is limited

Engineering Contradiction:
Improveupgrade processVSAvoidnetwork device operability
Core Design Contradiction:
Extent of automationVSEase of operation

Solution Approach 1:

Memory resources are segmented into a first portion for storage and a second portion for upgrade execution. This segmentation enables the upgrade process to proceed automatically using the second portion while the first portion maintains full network device operability. The feature agent orchestrates this segmented memory usage, allowing automated upgrades without compromising ease of operation or network device functionality.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS11881935B2Reducing a network device upgrade outage using a reduced hardware resource scaling
Publication Date: 2024.01.23 ARISTA NETWORKS INC
  • US11881935B2 patent drawing
  • US11881935B2 patent drawing
  • US11881935B2 patent drawing

AI summary

In general, embodiments relate to a method, for managing a network device, that includes accessing, by a feature agent of the network device, an allocation data structure, wherein the allocation data structure specifies a first portion of memory and a second portion of memory, identifying, using the allocation data structure, the first portion of the memory to be used during an upgrade, wherein the second portion of memory is used for storing a network device table, wherein the network device table is used by a packet transmission component while the upgrade is being performed, and upon completion of the upgrade, updating the allocation data structure to specify that the packet transmission component use a second network device table and stop using the network device table, wherein the second network device table is initially populated during the upgrade.