Granted Patent B1

US 12,273,264 · App. 18/434,618 · Granted Apr 8, 2025

Inventors: Dipankar Barman (Bangalore, IN); Chin Man Kim (Cupertino, CA)

Assignee: Juniper Networks, Inc.

H04L45/38H04L45/02H04L45/566H04L45/60H04L67/1023H04L2101/663

Abstract

Claims (92)

1. A network device comprising:

processing circuitry in communication with storage media;

at least one service physical interface card (PIC) comprising at least one processing unit, wherein the at least one processing unit comprises a plurality of cores;

a forwarding engine executing on the processing circuitry, wherein the forwarding engine is configured to:

partially assemble fragmented packet data for traffic flows to obtain 5-tuple information for each of the respective traffic flows;

generate, from the 5-tuple information for each of the respective traffic flows, a 5-tuple hash for each of the respective traffic flows;

modify the fragmented packet data for the traffic flows to include metadata specifying the 5-tuple information and the 5-tuple hash for each of the respective traffic flows; and

loopback the modified fragmented packet data for the traffic flows to the forwarding engine for forwarding to a first core of a core group, of one or more core groups, to which the respective traffic flow is assigned to obtain packets for the respective traffic flows; and

a routing engine executing on the processing circuitry, wherein the routing engine is configured to assign each of the traffic flows to a respective core group of the one or more core groups, wherein each of the one or more core groups comprises a subset of the plurality of cores of the at least one processing unit of the at least one service PIC, the subset comprising at least the first core,

wherein, for each of the traffic flows, the first core of the core group to which the respective traffic flow is assigned is configured to apply a network service to the packets for the respective traffic flow, and

wherein, for each of the traffic flows, the forwarding engine is further configured to forward, after application of the network service, the packets for the respective traffic flow toward a destination of the traffic flow.

2. The network device of claim 1 ,

wherein the routing engine is configured to assign each of the respective traffic flows to the respective core group of the one or more core groups based at least in part on the 5-tuple information of the respective traffic flow.

3. The network device of claim 2 , wherein the 5-tuple information for each of the respective traffic flows comprises:

a source address;

a destination address;

one of a source port and destination port or a security port index (SPI); and

a protocol for the traffic flow.

4. The network device of claim 1 , wherein the first core of the core group comprises a 5-tuple core.

5. The network device of claim 1 ,

wherein the forwarding engine is configured to obtain, from an initial fragment of the fragmented packet data for the traffic flows, a core identifier for each of the corresponding traffic flows, and

wherein the routing engine is configured to assign each of the traffic flows to the respective core group of the one or more core groups based at least in part on the core identifier obtained for the corresponding traffic flow of the traffic flows.

6. The network device of claim 1 ,

wherein the forwarding engine is configured to obtain, for the fragmented packet data for the traffic flows, a non-fragmented route for each of the corresponding traffic flows, and

wherein the routing engine is configured to assign each of the traffic flows to the respective core group of the one or more core groups based at least in part on the non-fragmented route for the corresponding traffic flow of the traffic flows.

7. The network device of claim 1 , wherein the service PIC is configured to implement a service plane for the network device.

8. A network device comprising:

processing circuitry in communication with storage media;

at least one service physical interface card (PIC) comprising at least one processing unit, wherein the at least one processing unit comprises a plurality of cores;

a forwarding engine executing on the processing circuitry, wherein the forwarding engine is configured to:

obtain, from fragmented packet data for traffic flows, 5-tuple information for each of the respective traffic flows;

generate, from the 5-tuple information for each of the respective traffic flows, a 5-tuple hash for each of the respective traffic flows;

fully assemble the fragmented packet data for the traffic flows to obtain packets for each of the respective traffic flows;

modify the packets for each of the respective traffic flows to include metadata specifying the 5-tuple information and the 5-tuple hash for each of the respective traffic flows; and

loopback the modified packets for the traffic flows to the forwarding engine for forwarding to a first core of a core group, of one or more core groups, to which the respective traffic flow is assigned to obtain packets for the respective traffic flows; and

a routing engine executing on the processing circuitry, wherein the routing engine is configured to assign each of the traffic flows to a respective core group of the one or more core groups, wherein each of the one or more core groups comprises a subset of the plurality of cores of the at least one processing unit of the at least one service PIC, the subset comprising at least the first core,

wherein, for each of the traffic flows, the first core of the core group to which the respective traffic flow is assigned is configured to apply a network service to the packets for the respective traffic flow, and

wherein, for each of the traffic flows, the forwarding engine is further configured to forward, after application of the network service, the packets for the respective traffic flow toward a destination of the traffic flow.

9. The network device of claim 8 , wherein the routing engine is configured to assign each of the respective traffic flows to the respective core group of the one or more core groups based at least in part on 5-tuple information for each of the respective traffic flows.

10. A method comprising:

executing, by processing circuitry of a network device, a forwarding engine configured to:

partially assemble fragmented packet data for traffic flows to obtain 5-tuple information for each of the respective traffic flows;

generate, from the 5-tuple information for each of the respective traffic flows, a 5-tuple hash for each of the respective traffic flows;

modify the fragmented packet data for the traffic flows to include metadata specifying the 5-tuple information and the 5-tuple hash for each of the respective traffic flows; and

loopback the modified fragmented packet data for the traffic flows to the forwarding engine for forwarding to a first core of a core group, of one or more core groups, to which the respective traffic flow is assigned to obtain packets for the respective traffic flows;

executing, by the processing circuitry of the network device, a routing engine configured to assign each of the traffic flows to a respective core group of the one or more core groups, wherein each of the one or more core groups comprises a subset of a plurality of cores of at least one processing unit of at least one service physical interface card (PIC) of the network device, the subset comprising at least the first core;

applying, for each of the traffic flows and by the first core of the core group to which the respective traffic flow is assigned, a network service to the packets for the respective traffic flow, and

forwarding, for each of the traffic flows, by the forwarding engine, and after application of the network service, the packets for the respective traffic flow toward a destination of the traffic flow.

11. The method of claim 10 ,

wherein assigning each of the respective traffic flows to the respective core group of the one or more core groups is based at least in part on the 5-tuple information of the respective traffic flow.

12. The method of claim 11 , wherein the 5-tuple information for each of the respective traffic flows comprises:

a source address;

a destination address;

one of a source port and destination port or a security port index (SPI); and

a protocol for the traffic flow.

13. The method of claim 10 , wherein the first core of the core group comprises a 5-tuple core.

14. The method of claim 10 ,

wherein the method further comprises obtaining, by the forwarding engine, from an initial fragment of the fragmented packet data for the traffic flows, a core identifier for each of the corresponding traffic flows, and

wherein assigning each of the traffic flows to the respective core group of the one or more core groups is based at least in part on the core identifier obtained for the corresponding traffic flow of the traffic flows.

15. The method of claim 10 ,

wherein the method further comprises obtaining, by the forwarding engine and for the fragmented packet data for the traffic flows, a non-fragmented route for each of the corresponding traffic flows, and

wherein assigning each of the traffic flows to the respective core group of the one or more core groups is based at least in part on the non-fragmented route for the corresponding traffic flow of the traffic flows.

16. A method comprising:

executing, by processing circuitry of a network device, a forwarding engine configured to:

obtain, from fragmented packet data for traffic flows, 5-tuple information for each of the respective traffic flows;

generate from the 5-tuple information for each of the respective traffic flows, a 5-tuple hash for each of the respective traffic flows;

fully assemble the fragmented packet data for the traffic flows to obtain packets for each of the respective traffic flows;

modify the packets for each of the respective traffic flows to include metadata specifying the 5-tuple information and the 5-tuple hash for each of the respective traffic flows; and

loop back the modified packets for the traffic flows to the forwarding engine for forwarding to a first core of a core group, of one or more core groups, to which the respective traffic flow is assigned to obtain packets for the respective traffic flows;

executing, by the processing circuitry of the network device, a routing engine configured to assign each of the traffic flows to a respective core group of the one or more core groups, wherein each of the one or more core groups comprises a subset of a plurality of cores of at least one processing unit of at least one service physical interface card (PIC) of the network device, the subset comprising at least the first core;

applying, for each of the traffic flows and by the first core of the core group to which the respective traffic flow is assigned, a network service to the packets for the respective traffic flow, and

forwarding, for each of the traffic flows, by the forwarding engine, and after application of the network service, the packets for the respective traffic flow toward a destination of the traffic flow.

17. The method of claim 16 , wherein assigning each of the respective traffic flows to the respective core group of the one or more core groups is based at least in part on 5-tuple information for each of the respective traffic flows.

18. Non-transitory computer-readable media comprising instructions that, when executed, are configured to cause processing circuitry to:

execute a forwarding engine configured to:

partially assemble fragmented packet data for traffic flows to obtain 5-tuple information for each of the respective traffic flows;

generate, from the 5-tuple information for each of the respective traffic flows, a 5-tuple hash for each of the respective traffic flows;

modify the fragmented packet data for the traffic flows to include metadata specifying the 5-tuple information and the 5-tuple hash for each of the respective traffic flows; and

loopback the modified fragmented packet data for the traffic flows to the forwarding engine for forwarding to a first core of a core group, of one or more core groups, to which the respective traffic flow is assigned to obtain packets for the respective traffic flows; and

execute a routing engine configured to assign each of the traffic flows to a respective core group of the one or more core groups, wherein each of the one or more core groups comprises a subset of a plurality of cores of at least one processing unit of at least one service physical interface card (PIC) of a network device, the subset comprising at least the first core;

wherein the instructions are further configured to cause, for each of the traffic flows, the first core of the core group to which the respective traffic flow is assigned to apply a network service to the packets for the respective traffic flow, and

wherein, for each of the traffic flows, the forwarding engine is further configured to forward, after application of the network service, the packets for the respective traffic flow toward a destination of the traffic flow.

19. Non-transitory computer-readable media comprising instructions that, when executed, are configured to cause processing circuitry to:

execute a forwarding engine configured to:

obtain, from fragmented packet data for traffic flows, 5-tuple information for each of the respective traffic flows;

generate, from the 5-tuple information for each of the respective traffic flows, a 5-tuple hash for each of the respective traffic flows;

fully assemble the fragmented packet data for the traffic flows to obtain packets for each of the respective traffic flows;

modify the packets for each of the respective traffic flows to include metadata specifying the 5-tuple information and the 5-tuple hash for each of the respective traffic flows; and

loopback the modified packets for the traffic flows to the forwarding engine for forwarding to a first core of a core group, of one or more core groups, to which the respective traffic flow is assigned to obtain packets for the respective traffic flows;

execute a routing engine configured to assign each of the traffic flows to a respective core group of the one or more core groups, wherein each of the one or more core groups comprises a subset of a plurality of cores of at least one processing unit of at least one service physical interface card (PIC) of a network device, the subset comprising at least the first core;

wherein the instructions are further configured to cause, for each of the traffic flows, the first core of the core group to which the respective traffic flow is assigned to apply a network service to the packets for the respective traffic flow, and

wherein, for each of the traffic flows, the forwarding engine is further configured to forward, after application of the network service, the packets for the respective traffic flow toward a destination of the traffic flow.

Assignments (2)

Continuity (2)

References Cited (16)