Dynamic Packet Flow Path Switching via Inactivity Intervals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In cloud-based data centers, packet flows often experience bandwidth exceeding, leading to dropped packets due to static assignment of paths, where the utilization of paths is measured between flowlets, causing inefficient network traffic throughput.
Innovation Solution
Implementing techniques to dynamically move packet flows between network paths based on inactivity intervals and latency skews, allowing packets to be forwarded along paths with lower utilization without causing reordering, thereby preventing dropped packets and improving network throughput.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If packet flows are statically assigned to network paths, then path utilization measurement is simplified, but network throughput is reduced due to bandwidth exceeding and packet drops
Solution Approach 1:
The patent implements dynamic path assignment by monitoring inactivity intervals of packet flows and switching paths when the inactivity interval exceeds the latency skew between paths. This dynamic approach allows the system to adapt to changing network conditions and utilize underloaded paths, thereby increasing network throughput while maintaining manageable complexity through automated decision-making based on measurable parameters.
2Productivity
If packet flows are dynamically moved between paths, then network throughput is improved, but packet reordering may occur
Solution Approach 1:
The patent changes the operational parameter from static path assignment to dynamic path selection based on inactivity interval measurements. By comparing the inactivity interval against the latency skew between paths, the system determines when path switching is safe without causing packet reordering. This parameter-based decision mechanism enables throughput improvement while preserving packet delivery reliability.
3Reliability
If path utilization is measured continuously, then bandwidth exceeding is prevented, but measurement precision requirements increase
Solution Approach 1:
The patent extracts the essential measurement requirement from continuous utilization monitoring by focusing specifically on inactivity intervals between packet flow bursts. Instead of measuring continuous path utilization, the system only measures the time between flowlets, which is sufficient to determine when path switching is appropriate. This extraction simplifies the measurement requirement while maintaining reliable bandwidth management.
Data Source
AI summary
In one example, a network device is configured as a leaf node of an interconnected topology that defines a plurality of network paths from the network device to each of a plurality of other leaf nodes of the interconnected topology. The network device includes one or more processing units configured to forward a first packet of a packet flow along a first network path of the plurality of network paths, after receiving a second packet of the packet flow, determine an inactivity interval for the packet flow that represents an amount of time between receipt of the first packet and receipt of the second packet, compare the inactivity interval to a threshold, and when the inactivity interval is greater than the threshold, forward the second packet along a second network path of the plurality of network paths, wherein the second network path is different than the first network path.