Concurrent Hashing Controller for Packet Stream Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current Internet protocols, such as IP and Ethernet, are location-based, making them inadequate for the evolving network demands, particularly in content-centric networks (CCN) where efficient processing of multiple hashes over data streams is challenging due to the need for state transfer between hashes.
Innovation Solution
A system and method that facilitate concurrent hashing operations using a controller to manage multiple packet streams in parallel, employing hashing operations like SipHash, SHA-2, SHA-3, and FNV hashes, with a flexible ruleset to determine appropriate hashing based on packet status, and cross-connecting packet streams to an array of hashing modules for efficient processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple hashing operations are performed sequentially on the same data stream, then each hash can be computed accurately, but the processing time and system throughput are significantly reduced
Solution Approach 1:
The patent divides the hashing computation into multiple parallel segments by implementing separate hashing modules (first hashing module, second hashing module, etc.) that simultaneously compute different hash functions on the same data stream. Each module operates independently with its own computation units, enabling concurrent hash generation without sequential bottlenecks.
Solution Approach 2:
The patent transitions from sequential single-dimension processing to parallel multi-dimension processing by deploying multiple hashing modules operating in parallel. The system uses a controller to coordinate multiple computation units across different modules, effectively adding a temporal parallelism dimension to the hashing operation.
2Productivity
If multiple hashing modules operate concurrently on packet streams, then processing efficiency is improved, but the risk of errors and faults increases
Solution Approach 1:
The patent implements a feedback mechanism where the controller continuously monitors the operational status of each hashing module and computation unit. When an error or fault is detected in any module, the controller receives status feedback and automatically adjusts by discontinuing the faulty module or redistributing workloads to healthy modules, ensuring system reliability.
Solution Approach 2:
The system prepares backup hashing modules that can immediately take over when a primary module fails. The controller is pre-configured to detect faults and switch to alternative modules, providing a cushion against failures before they impact overall system operation.
3Adaptability or versatility
If a flexible ruleset is used to determine hashing operations based on packet status, then adaptability to different packet types is improved, but the control logic complexity increases
Solution Approach 1:
The patent pre-configures multiple hashing modules with different hash function capabilities (SipHash, SHA-2, SHA-3, FNV) before runtime. The controller has pre-established rules that map specific packet types or statuses to appropriate hashing modules, eliminating the need for complex runtime decision-making and reducing control logic complexity during operation.
Solution Approach 2:
The controller is designed as a universal coordination unit that can manage multiple types of hashing modules through a unified interface. The single controller handles diverse packet types by selecting from its array of specialized hashing modules, concentrating control complexity in one component while keeping individual modules simple and specialized.
Data Source
AI summary
One embodiment of the present invention provides a system for performing concurrent hashing of packet streams. During operation, the system receives a stream of packets at a controller. The controller then identifies types and parameters for a plurality of different hashing operations based on a received packet. The controller further sends the packet concurrently to corresponding different hashing modules to produce different hash values, which can be used to facilitate packet forwarding.