Data Transfer Engine Offloads Database Transfers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing communication network elements face inefficiencies in transferring large databases between processors and packet processing hardware, leading to increased latency and potential packet dropping due to slow data transfer speeds.
Innovation Solution
The implementation of data-transfer circuitry and work queues allows for the translation and execution of communication packets and databases between processors and packet processing hardware, utilizing PCIe for fast data transfer and minimizing CPU intervention, enabling efficient and high-speed database transfers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If traditional CPU-based data transfer methods are used between processor and packet processing hardware, then data transfer can be performed, but transfer speed is slow and causes increased latency
Solution Approach 1:
The patent replaces the traditional CPU-based data transfer mechanism with a dedicated data transfer engine (DTE) that operates independently. The DTE translates CPU requests into hardware-level operations and manages data movement between the processor and packet processing hardware without CPU intervention, achieving speeds comparable to packet routing operations.
Solution Approach 2:
The patent introduces a data transfer engine as an intermediary component between the CPU and packet processing hardware. This DTE includes translation circuitry that converts CPU data transfer requests into work elements, and execution circuitry that performs the actual data movement, effectively mediating the transfer process and eliminating CPU bottlenecks.
2Productivity
If CPU is used for data transfer operations, then data can be transferred, but CPU resources are consumed and packet processing may be delayed
Solution Approach 1:
The patent extracts data transfer operations from the CPU's responsibility and assigns them to a dedicated data transfer engine. The CPU only needs to post work elements to queues, while the DTE independently executes data transfer operations, freeing CPU resources for packet processing and eliminating delays caused by CPU involvement in data movement.
Solution Approach 2:
The data transfer engine operates autonomously without requiring CPU intervention during execution. It self-manages the translation of work elements into data transfer operations, performs the actual data movement between memory and packet processing hardware, and handles completion signaling, allowing the CPU to focus entirely on packet processing.
3Quantity of substance
If databases are transferred between processor and packet processing hardware using conventional methods, then data transfer occurs, but transfer size is limited and causes packet dropping
Solution Approach 1:
The patent implements dynamic database transfer capabilities where the DTE can handle variable-sized database transfers based on actual needs. The work element mechanism allows flexible specification of transfer parameters including source/destination addresses and transfer sizes, enabling the system to transfer complete databases when needed without arbitrary limitations, thereby preventing packet dropping due to insufficient data availability.
Data Source
AI summary
A network element includes one or more ports for communicating over a network, a processor and packet processing hardware. The packet processing hardware is configured to transfer packets to and from the ports, and further includes data-transfer circuitry for data transfer with the processor. The processor and the data-transfer circuitry are configured to transfer between one another (i) one or more communication packets for transferal between the ports and the processor and (ii) one or more databases for transferal between the packet processing hardware and the processor, by (i) translating, by the processor, the transferal of both the communication packets and the databases into work elements, and posting the work elements on one or more work queues in a memory of the processor, and (ii) using the data-transfer circuitry, executing the work elements so as to transfer both the communication packets and the databases.