Mitigating oversubscription of traffic to edge nodes in a data center

Patent metadata

Field	Value
Publication number	US-12015539-B2
Application number	US-202217726453-A
Country	US
Kind code	B2
Filing date	Apr 21, 2022
Priority date	Apr 21, 2022
Publication date	Jun 18, 2024
Grant date	Jun 18, 2024

Abstract

An example method of mitigating oversubscription of traffic to edge services gateways in a data center includes: receiving, by a host of the data center, traffic metrics corresponding to the ESGs; determining traffic congestion at a first active edge of the ESGs in response to the traffic metrics; dividing, in response to the traffic congestion, a classless inter-domain routing (CIDR) block assigned to the first active edge into a first CIDR block and a second CIDR block; and creating, in a routing table of a router, a first route between an internet protocol (IP) address of the first active edge and the first CIDR block, and a second route between an IP address of a second active edge of the ESGs and the second CIDR block.

First claim

What is claimed is:

1. A method of mitigating oversubscription of traffic to edge services gateways (ESGs) in a data center, a router in the data center including a first route between an internet protocol (IP) address of a first active edge of the ESGs and a first classless inter domain routing (CIDR) block assigned to the first active edge and a second route between an IP address of a second active edge of the ESGs and a second CIDR block assigned to the second active edge, the method comprising:
receiving, by a host of the data center, traffic metrics corresponding to the ESGs;
determining traffic congestion at the first active edge of the ESGs in response to the traffic metrics;
dividing, in response to the traffic congestion, the first CIDR block into a first CIDR sub-block and a second CIDR sub-block;
modifying, in a routing table of the router, the first route to be between the IP address of the first active edge and the first CIDR sub-block;
creating, in the routing table of the router, a third route between an IP address of the second active edge of the ESGs and the second CIDR sub-block; and
creating, in the routing table of the router, a fourth route between the IP address of the second active edge and a third CIDR block, the third CIDR block being an aggregation of CIDR blocks of a plurality of under-utilized routes.

2. The method of claim 1 , wherein the host executes a standby edge of the ESGs.

3. The method of claim 1 , wherein the host is configured to determine the traffic congestion by requesting the traffic metrics from a control plane of a cloud in which the data center is provisioned.

4. The method of claim 3 , wherein the router comprises an underlay router in a physical network of the cloud.

5. The method of claim 1 , further comprising:
determining the second active edge of the ESGs to be under-utilized based on the traffic metrics.

6. The method of claim 1 , further comprising:
determining the plurality of under-utilized routes in the routing table of the router;
aggregating the CIDR blocks of the plurality of under-utilized routes into the third CIDR block; and
removing the plurality of under-utilized routes from the routing table.

7. The method of claim 6 , wherein the host is configured to determine the plurality of under-utilized routes in the routing table in response to the traffic metrics and tags on the plurality of under-utilized routes.

8. A non-transitory computer readable medium comprising instructions to be executed in a computing device to cause the computing device to carry out a method of mitigating oversubscription of traffic to edge services gateways (ESGs) in a data center, a router in the data center including a first route between an internet protocol (IP) address of the first active edge of the ESGs and a first classless inter domain routing (CIDR) block assigned to the first active edge and a second route between an IP address of the second active edge of the ESGs and a second CIDR block assigned to the second active edge, the method comprising:
receiving, by a host of the data center, traffic metrics corresponding to the ESGs;
determining traffic congestion at the first active edge of the ESGs in response to the traffic metrics;
dividing, in response to the traffic congestion, the first CIDR block into a first CIDR sub-block and a second CIDR sub-block;
modifying, in a routing table of the router, the first route to be between the IP address of the first active edge and the first CIDR sub-block;
creating, in the routing table of the router, a third route between an IP address of the second active edge of the ESGs and the second CIDR sub-block; and
creating, in the routing table of the router, a fourth route between the IP address of the second active edge and a third CIDR block, the third CIDR block being an aggregation of CIDR blocks of a plurality of under-utilized routes.

9. The non-transitory computer readable medium of claim 8 , wherein the host executes a standby edge of the ESGs.

10. The non-transitory computer readable medium of claim 8 , wherein the host is configured to determine the traffic congestion by requesting the traffic metrics from a control plane of a cloud in which the data center is provisioned.

11. The non-transitory computer readable medium of claim 10 , wherein the router comprises an underlay router in a physical network of the cloud.

12. The non-transitory computer readable medium of claim 8 , further comprising:
determining the second active edge of the ESGs to be under-utilized based on the traffic metrics.

13. The non-transitory computer readable medium of claim 8 , further comprising:
determining the plurality of under-utilized routes in the routing table of the router;
aggregating the CIDR blocks of the plurality of under-utilized routes into the third CIDR block; and
removing the plurality of under-utilized routes from the routing table.

14. The non-transitory computer readable medium of claim 13 , wherein the host is configured to determine the plurality of under-utilized routes in the routing table in response to the traffic metrics and tags on the plurality of under-utilized routes.

15. A computing system, comprising:
edge services gateways (ESGs) of a data center including a first active edge and a second active edge;
a router including a first route between an internet protocol (IP) address of the first active edge and a first classless inter domain routing (CIDR) block assigned to the first active edge, and a second route between an IP address of the second active edge and a second CIDR block assigned to the second active edge;
a host in the data center having a hardware platform; and
the host configured to:
receive traffic metrics corresponding to the ESGs;
determine traffic congestion at the first active edge of the ESGs in response to the traffic metrics;
divide, in response to the traffic congestion, the first CIDR block into a first CIDR sub-block and a second CIDR sub-block;
modify, in a routing table of the router, the first route to be between the IP address of the first active edge and the first CIDR sub-block;
create, in the routing table of the router, a second route between the IP address of a second active edge of the ESGs and the second CIDR sub-block;
create, in the routing table of the router, a fourth route between the IP address of the second active edge and a third CIDR block, the third CIDR block being an aggregation of CIDR blocks of a plurality of under-utilized routes.

16. The computing system of claim 15 , wherein the host executes a standby edge of the ESGs.

17. The computing system of claim 15 , wherein the host is configured to determine the traffic congestion by requesting the traffic metrics from a control plane of a cloud in which the data center is provisioned.

18. The computing system of claim 17 , wherein the router comprises an underlay router in a physical network of the cloud.

19. The computing system of claim 15 , wherein the host is configured to:
determine the second active edge of the ESGs to be under-utilized based on the traffic metrics.

20. The computing system of claim 15 , wherein the host is configured to:
determine the plurality of under-utilized routes in the routing table of the router;
aggregate the CIDR blocks of the plurality of under-utilized routes into the third CIDR block; and
remove the plurality of under-utilized routes from the routing table.

Assignees

• Vmware Inc
• VMware LLC

Inventors

• Parmar Ankit
• Gaviyappa Harish Kumar
• Shukla Pawan
• Parikh Ravi
• Tiwari Ritesh

Classifications

• H04L45/38

  Flow based routing · CPC title

• H04L45/42

  Centralised routing · CPC title

• H04L47/122 Primary

  by diverting traffic away from congested entities · CPC title

• H04L45/123

  Evaluation of link metrics (techniques for monitoring network metrics H04L43/08) · CPC title

• H04L45/02 Primary

  Topology update or discovery · CPC title