SRAM Routing Table Power Management via Dynamic Hash Scaling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional routing tables in network devices, implemented using TCAMs, face challenges in power management as they consume more power than SRAMs and require rebooting to adjust power configurations, leading to system overhead and inefficiencies in smaller network infrastructures.
Innovation Solution
The implementation of routing tables using SRAMs with a power management algorithm that dynamically redistributes entries across multiple hash tables and power domains, allowing for vertical scaling and independent power management without rebooting, enabling flexible power reduction based on load conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If TCAMs are used to implement routing tables, then route lookup time is reduced, but power consumption increases
Solution Approach 1:
The routing table is divided into multiple segments or partitions that can be independently managed. The patent implements this by creating multiple routing table instances (e.g., RT0, RT1, RT2) that can be selectively activated based on load conditions, allowing the system to use only the necessary portion of the routing table capacity at any given time, thus reducing power consumption while maintaining fast lookup performance when needed.
Solution Approach 2:
The system dynamically adjusts the number of active routing table instances based on real-time load conditions. The controller monitors traffic load and automatically scales the routing table capacity by activating or deactivating instances, enabling the system to adapt power consumption to actual operational needs rather than maintaining fixed high-power TCAM operation.
2Use of energy by moving object
If power configuration is changed to save power, then power consumption is reduced, but system reboot is required causing packet loss or rerouting overhead
Solution Approach 1:
The system pre-loads and prepares multiple routing table instances in advance, so when power scaling is needed, the transition can occur immediately without rebooting. The controller has routing table instances ready to activate or deactivate based on load conditions, eliminating the need for system restart and preventing packet loss during power configuration changes.
Solution Approach 2:
The patent maintains continuous routing functionality by keeping multiple routing table instances ready in a suspended or prepared state. When power scaling is required, the system seamlessly transitions between instances without interrupting packet forwarding, ensuring continuous useful action and avoiding the downtime associated with traditional reboot-based power management.
3Use of energy by moving object
If routing table capacity is reduced for smaller network infrastructures, then power consumption is reduced, but adaptability to changing load conditions is limited
Solution Approach 1:
The system implements a universal power management approach where the same routing table infrastructure can serve multiple network scale requirements. By maintaining multiple routing table instances that can be selectively activated, the system can adapt to varying network sizes and load conditions using the same hardware platform, providing both small-network power efficiency and large-network full capacity when needed.
Solution Approach 2:
The system changes operational parameters dynamically by adjusting the number of active routing table instances based on load conditions. This parameter change approach allows the system to optimize power consumption for small networks by activating fewer instances while maintaining the capability to scale up to full capacity for larger networks, providing both power efficiency and adaptability.
Data Source
AI summary
Power management of a routing table, which comprises a plurality of hash tables, is provided by supporting various power domain configurations. Each power domain configuration can be associated with a different number of power domains than other power domain configurations. Each power domain can add vertical capacity to the entire routing table by adding a fixed number of buckets to each of the hash tables. Efficient power management can be achieved by switching between a lower power domain configuration and a higher power domain configuration during runtime based on the dynamic load conditions.