US 12,750,323 B2 · Low latency queuing system

Abstract

Disclosed herein are methods and apparatuses for processing network traffic by a queuing system which may include: receiving pointers to chunks of memory allocated responsive to receipt of network traffic, the chunks of memory each including a portion of a queue batch, wherein the queue batch includes a plurality of queue requests; generating a data structure including the pointers and a reference count; assigning the queue request to a second core; generating a first structured message for the first queue request; and storing the first structured message in a structured message passing queue associated with the second core, wherein a second processing thread associated with the second core, responsive to receiving the structured message, processes the first queue request by retrieving the first queue request from at least one of the chunks of memory.

Claims20

Dependent claims

A method for processing requests by a computing device having a plurality of cores, the method comprising:

receiving a first request by a first processing thread associated with a first core of the computing device by storing references to memory chunks generated by an electronic communication unit in a data structure, the memory chunks including non-executable data elements associated with the first request received by the electronic communication unit from a remote computing device;
determining an assignment of the first request to a second processing thread associated with a second core of the first computing device based on a comparison between an identifier associated with the first request in the data structure and a partition routing table stored in a memory location associated with the first core;
routing the first request to the second processing thread using a pointer referencing memory associated with the data structure.

A non-transitory computer readable medium including a processor that includes a first core and a second core, and a memory that includes instructions that when executed causes the processor to:

receive a first request by the first core including storing references to memory chunks generated by an electronic communication unit in a data structure, the memory chunks including non-executable data elements associated with the first request received by the electronic communication unit from a remote computing device;
determine an assignment of the first request to the second core based on a comparison between an identifier associated with the first request in the data structure and a partition routing table stored in a memory location associated with the first core;
route the first request to the second core using a pointer referencing memory associated with the data structure.

Dependencies are inferred from the claim text.

Low latency queuing system

Life of this patent

Low latency queuing system

Life of this patent

Abstract

Claims20