Search

EP-4740435-A1 - SYSTEM AND METHOD FOR UNIFORM DISTRIBUTION OF ONE OR MORE DATA PACKETS

EP4740435A1EP 4740435 A1EP4740435 A1EP 4740435A1EP-4740435-A1

Abstract

The present disclosure relates to a system (108) and a method (400) for uniform distribution of one or more data packets The system (108) includes a receiving unit (210) to receive one or more data packets from one or more User Equipment (UE) (102). The system (108) includes a retrieving unit (212) to retrieve an Internet Protocol (IP) address of the one or more data packets from one of a source address of a PDU of an IP header and a destination address of the IP header. The system (108) includes a hashing unit (214) to perform hashing operation on the IP address of each of the one or more retrieved IP addresses. The system (108) includes a mapping unit (218) to map the hash value (406) with at least one core from the plurality of cores (410), and thereby distributing the one or more data packets across the plurality of data cores.

Inventors

  • BHATNAGAR, AAYUSH
  • JHA, ADITYAKAR
  • Ranjan, Anu
  • MALHOTRA, PANKAJ
  • Sengupta, Swarup
  • Mamgain, Ranjan
  • VASHISHTH, Yog

Assignees

  • Jio Platforms Limited

Dates

Publication Date
20260513
Application Date
20240627

Claims (16)

  1. 1. A method (600) of uniform distribution of one or more data packets across a plurality of cores (410), the method (500) comprising the steps of: receiving, by one or more processors (202), the one or more data packets from one or more User Equipments (UE) (102); retrieving, by the one or more processors (202), an Internet Protocol (IP) address of the one or more data packets from one of a source address of a Protocol Data Unit (PDU) of an IP header and a destination address of the IP header; performing, by the one or more processors (202), hashing operation on the IP address of each of the one or more retrieved IP addresses to receive a hash value of the IP address of each of the one or more retrieved IP addresses; and mapping, by the one or more processors (202), of the hash value with at least one core from the plurality of cores (410), and thereby distributing the one or more data packets across the plurality of data cores.
  2. 2. The method (600) as claimed in claim 1 , wherein the one or more data packets is one of an uplink data packet and a downlink data packet.
  3. 3. The method (600) as claimed in claim 2, wherein the uplink data packet is received via a first interface and the downlink data packet is received via a second interface, and wherein the first interface is an N3 interface and the second interface is an N6 interface.
  4. 4. The method (600) as claimed in claim 1, wherein the one or more processors (202) is configured to retrieve the IP address of the one or more data packets from the PDU of the IP header if the one or more data packets is the uplink data packet.
  5. 5. The method (600) as claimed in claim 1, wherein the one or more processors (202) is configured to retrieve the IP address of the one or more data packets from the destination address of the IP header if the one or more data packets is the downlink data packet.
  6. 6. The method (600) as claimed in claim 1, wherein the method (400) comprises the steps of: generating, by the one or more processors (202), a query list based on the hash value, wherein the query list includes a hash to a Rx queue table; and transmitting, by the one or more processors (202), queries from the query list to the at least one mapped core of the plurality of cores (410).
  7. 7. The method (600) as claimed in claim 1, wherein the step of mapping is performed based on a redundancy check performed on processing history of a previously received data packets.
  8. 8. A system (108) for uniform distribution of one or more data packets across a plurality of cores (410), the system (108) comprising: a receiving unit (210) configured to receive, the one or more data packets from one or more User Equipments (UE) (102); a retrieving unit (212) configured to retrieve, an Internet Protocol (IP) address of the one or more data packets from one of a source address of a Protocol Data Unit (PDU) of an IP header and a destination address of the IP header; a hashing unit (214) configured to perform, hashing operation on the IP address of each of the one or more retrieved IP addresses to receive a hash value of the IP address of each of the one or more retrieved IP addresses; and a mapping unit (218) configured to map, the hash value (406) with at least one core from the plurality of cores (410), and thereby distributing the one or more data packets across the plurality of data cores.
  9. . The system (108) as claimed in claim 8, wherein the one or more data packets is one of an uplink data packet and a downlink data packet.
  10. 10. The system (108) as claimed in claim 9, wherein the uplink data packet is received via a first interface and the downlink data packet is received via a second interface, and wherein the first interface is an N3 interface and the second interface is an N6 interface.
  11. 11. The system (108) as claimed in claim 8, wherein the retrieving unit (212) is configured to retrieve the IP address of the one or more data packets from the PDU of the IP header if the one or more data packets is the uplink data packet.
  12. 12. The system (108) as claimed in claim 8, wherein the retrieving unit (212) is configured to retrieve the IP address of the one or more data packets from the destination address of the IP header if the one or more data packets is the downlink data packet.
  13. 13. The system (108) as claimed in claim 8, wherein the system (108) comprising: a generating unit (216) configured to generate, a query list based on the hash value (406), wherein the query list includes a hash to a Rx queue table; and a transmitting unit (220) configured to transmit, queries from the query list to the at least one mapped core of the plurality of cores (410).
  14. 14. The system (108) as claimed in claim 8, wherein the mapping unit (218) is configured to map based on a redundancy check performed on processing history of previously received data packets.
  15. 15. A non-transitory computer-readable medium having stored thereon computer- readable instructions that, when executed by a processor (202), cause the processor (202) to: receive, the one or more data packets from one or more User Equipments (UE) (102); retrieve, an Internet Protocol (IP) address of the one or more data packets from one of a source address of a Protocol Data Unit (PDU) of an IP header and a destination address of the IP header; perform, hashing operation on the IP address of each of the one or more retrieved IP addresses to receive a hash value (406) of the IP address of each of the one or more retrieved IP addresses; and map, the hash value (406) with at least one core from the plurality of cores (410), and thereby distributing the one or more data packets across the plurality of data cores.
  16. 16. A User Equipment (UE) (102), comprising: one or more primary processors (302) communicatively coupled to one or more processors (202), the one or more primary processors (302) coupled with a memory (304), wherein said memory (304) stores instructions which when executed by the one or more primary processors (302) causes the UE (102) to: transmit, one or more data packets to the one or more processers (202); wherein the one or more processors (202) is configured to perform the steps as claimed in claim 1.

Description

SYSTEM AND METHOD FOR UNIFORM DISTRIBUTION OF ONE OR MORE DATA PACKETS FIELD OF THE INVENTION [0001] The present invention relates to user plane packet processing, more particularly relates to a system and method for uniform distribution of data traffic using user plane packet processing on a multi-core computer processing unit. BACKGROUND OF THE INVENTION [0002] Exchange of information between end-user devices and network infrastructure is facilitated through the use of packets in current telecommunications networks. These packets contain data, such as voice, video, and other forms of digital information, which are transmitted over the network to reach their intended destinations. [0003] Further to the current, network architectures are designed to handle different types of data traffic, such as control plane traffic and user plane traffic. The control plane is responsible for managing signaling and control functions, while the user plane is responsible for the transmission of user data packets. [0004] The emergence of 5th Generation (5G) networks has increased the demand for high-speed, low-latency communication with respect to the user data packets. To achieve the high speed and the low latency, efficient handling of user data traffic is required. Thus, the need for significant changes to the network architecture arises. [0005] The User Plane Function (UPF) technology is configured to handle the user data traffic within 5G and beyond network architectures. Hence the evolution of the UPF plays an important role, since UPF acts as a crucial component within the 5G core network, responsible for various tasks, including packet forwarding, traffic management, quality of service (QoS) enforcement, and network slicing. Further the User Plane Function (UPF) enables efficient data handling, supports diverse service requirements, and ensures a seamless user experience in highly dynamic and heterogeneous network environments. [0006] Further the UPF in a service provider is configured to host multiple user/UE session and it applies different policies (rate limit, barring, quota, forwarding policies etc) on user packets flowing through the network. UPF in case of such service provider performs inter networking between the 5G network and the data network, and may have N3 interface defined towards gNodeB and N6 interface defined towards the data network. For UPF, running on a multi-core CPU/processor, to optimize the performance, multiple Rx queues are configured which are associated with the multiple CPU cores. The network interface card (NIC) receives the uplink/downlink traffic and if the default 5-tuple RSS based packet distribution is configured, which uses source IP, destination IP, source port, destination port, protocol in deciding that on which Rx queue the packet will land to, and based on that classifies/distributes the traffic to the Rx queues. This leads to packets from the same user/UE landing onto different Rx queues in downlink and all traffic from the same gNodeB landing onto the same Rx queue. That leads to a skewed load balancing and also impacts performance as it reduces cache localization and efficiency, reduced scalability across the CPU cores and moreover the control plane data plane synchronization requires locking all the data plane cores resulting in a sub-optimal implementation. [0007] Hence there is a need in the art to further optimize the handling of requests and queries received by the UPF, for uniform distribution of data traffic. In particular, for uniform distribution of one or more data packets. SUMMARY OF THE INVENTION [0008] One or more embodiments of the present disclosure provide a system and a method for uniform distribution of one or more data packets. [0009] In one aspect of the present invention, the system for uniform distribution of one or more data packets is disclosed. The system includes a receiving unit configured to receive one or more data packets from one or more User Equipments (UE). The system further includes a retrieving unit configured to retrieve, an Internet Protocol (IP) address of the one or more data packets from one of a source address of a Protocol Data Unit (PDU) of an IP header and a destination address of the IP header. The system further includes a hashing unit configured to perform, a hashing operation on the IP address of each of the one or more retrieved IP addresses to receive a hash value of the IP address of each of the one or more retrieved IP addresses. The system further includes a mapping unit configured to map, the hash value with at least one core from a plurality of cores, and thereby distributing the one or more data packets across the plurality of data cores. [0010] In an embodiment, the one or more data packets is one of an uplink data packet and a downlink data packet. In an embodiment, the uplink data packet is received via a first interface and the downlink data packet is received via a second interface, and wherein the first int