Hash Table Flow Identification for IP Fragmented Packets
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Data center fabrics struggle to accurately identify and manage fragmented IP packets, leading to inaccurate analytics and quality of service for multi-destination traffic, which affects efficiency and performance.
Innovation Solution
Implementing a dynamic flow hash table (DFHT) in network devices to store and retrieve tuple information associated with IP fragmented packets, enabling accurate identification of traffic flows and enabling data center fabrics to provide proper services for fragmented traffic.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If fragmented packets are routed through the data center fabric, then large packets can be transmitted by splitting them into smaller units, but the fabric becomes unable to accurately identify which traffic flow the fragmented traffic belongs to
Solution Approach 1:
The patent applies preliminary action by storing the complete tuple information from the initial fragmented packet in a hash table before subsequent fragments arrive. When later fragments are received, the system retrieves the stored tuple information to identify the traffic flow, eliminating the need for the later fragments to contain the complete identification data.
Solution Approach 2:
The patent introduces a hash table as an intermediary data structure that stores tuple information associated with fragmented packets. This hash table acts as a mediator between the fragmented packets and the traffic flow identification process, allowing the system to accurately identify traffic flows even when individual fragments lack complete identification information.
2Adaptability or versatility
If fragmented traffic is supported in data center fabrics, then flexibility in packet transmission is improved, but analytics accuracy, quality of service and load balancing become significantly impacted
Solution Approach 1:
The system performs preliminary action by capturing and storing complete tuple information from the initial fragmented packet in a hash table before subsequent fragments are processed. This allows analytics, QoS, and load balancing functions to access accurate traffic flow identification data even when individual fragments lack complete information.
Solution Approach 2:
The hash table serves as an intermediary that bridges the gap between fragmented packets and analytics/QoS functions. It stores the complete tuple information needed for accurate measurement and analysis, enabling these functions to operate correctly on fragmented traffic without requiring each fragment to contain complete identification data.
3Quantity of substance
If fragmented packets are reassembled after exiting the fabric, then large data transmission is enabled, but the fabric cannot perform proper load balancing and quality of service during transmission
Solution Approach 1:
The patent applies preliminary action by storing complete tuple information from the initial fragment in a hash table before the fragmented packets traverse the fabric. This enables load balancing and QoS management functions to access accurate traffic flow identification data during transmission, eliminating the need to wait for reassembly at the egress point.
Data Source
AI summary
A network device receives a fragmented packet of an internet protocol (IP) packet. The fragmented packet is subsequently received relative to an initial fragmented packet of the IP packet and includes a first set of tuple information. The network device determines an entry of a hash table associated with the IP packet, based on the first set of tuple information and a fragment identifier (ID) within the fragmented packet. The network device retrieves a second set of tuple information associated with the fragmented packet from the hash table entry, and transmits an indication of the first and second sets of tuple information.