Message diversion method and network equipment
A technology for message and message reception, applied in the field of communication, can solve the problems of inability to realize message distribution, consumption of resources, and high computational complexity, and achieve the effect of improving the efficiency of message distribution and reducing resource consumption.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0047] The packet distribution method in Embodiment 1 can be applied to include 2 K -In a network device with 1 data core, the queue number is 0 to 2 K 1 to 2 in the queue for -1 K -1 for the queue with the 2 K - 1 data core corresponds one by one, the queue whose queue number is 0 corresponds to the data core corresponding to the queue whose queue number is Q, where 1≤Q≤2 K -1, Q is a natural number; 2 K -1 data core processes messages in its corresponding queue.
[0048] Among them, Q is 1 to 2 in specific implementation K Any natural number between -1, but one of them needs to be specified in advance. When a queue with queue number 0 is matched, the message will be fixedly assigned to the queue with the queue number Q, so that the corresponding message will eventually be sent to the same data core. Processing is performed to prevent messages with the same tuple information from being assigned to different data cores for processing.
[0049] Embodiment 2 of the present...
Embodiment 2
[0056] The packet distribution method in Embodiment 2 can be applied to include 2 K -In a network device with 1 data core, the queue number is 1 to 2 K -1 for the queue with the 2 K -1 data core one-to-one correspondence; the 2 K -1 data core processes messages in its corresponding queue.
[0057] In Embodiment 1 and Embodiment 2, the method of dividing the equalization calculation value according to the number of K bits per share is as follows: the equalization calculation value can be divided according to the number of K bits per share from the low bit to the high bit, and when the highest bit is not enough for the number of K bits, it can be supplemented. When 0 is K bits or not enough for K bits, the highest bit is not counted; it can also be divided according to the number of bits per share from high to low. share.
[0058] In the number of shares divided by the balanced operation value, get M 1 The method for the number of K bits is: randomly select M 1 The number ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 