Virtualized QoS support in software defined networks

Patent metadata

Field	Value
Publication number	US-11799784-B2
Application number	US-202217569276-A
Country	US
Kind code	B2
Filing date	Jan 5, 2022
Priority date	Jun 8, 2021
Publication date	Oct 24, 2023
Grant date	Oct 24, 2023

Abstract

A network system that implements quality of service (QoS) by rate limiting at a logical network entity is provided. The logical network entity includes multiple transport nodes for transporting network traffic in and out of the logical network entity. The system monitors traffic loads of the multiple transport nodes of the logical network entity. The system allocates a local CR and a local BS to each of the multiple transport nodes. The allocated local CR and the local BS are determined based on the CR and BS parameters of the logical network entity and based on the monitored traffic loads. Each transport node of the logical network entity in turn controls an amount of data being processed by the transport node based on a token bucket value that is computed based on the local CR and the local BS of the transport node.

First claim

We claim:

1. A method comprising:
for a logical network entity in a logical network, specifying, at a computing device, a quality of service (QoS) requirement in terms of a committed rate (CR) parameter and a burst size (BS) parameter, the logical network entity comprising a plurality of transport nodes that process network traffic of the logical network entity;
monitoring traffic loads of the plurality of transport nodes of the logical network entity; and
allocating a local CR and a local BS to each of the plurality of transport nodes, wherein the local CR and the local BS are determined based on the CR and BS parameters of the logical network entity and based on the monitored traffic loads,
wherein each transport node of the logical network entity controls an amount of data being processed by the transport node based on a token bucket value that is computed based on the local CR and the local BS of the transport node.

2. The method of claim 1 further comprising allocating the CR and the BS of the logical network entity evenly among the transport nodes of the logical network entity prior to a time interval for monitoring the traffic loads at the plurality of transport nodes.

3. The method of claim 1 , wherein a local token value of a transport node specifies a current amount of data that the transport node is capable of processing, wherein controlling the amount of data being processed by the transport node comprises:
adding to the local token value of the transport node an amount of data allowed to be processed by the transport node during a monitoring interval based on the local CR; and
subtracting from the local token value of the transport node an amount of data already processed by the transport node.

4. The method of claim 3 , wherein the amount of data allowed to be processed by the transport node is capped according to the local BS.

5. The method of claim 1 , further comprising maintaining a QoS data structure of the logical network entity, the QoS data structure comprising the CR and the BS of the logical network entity.

6. The method of claim 5 , wherein the QoS data structure further comprises the local CR and the local BS of each transport node.

7. The method of claim 1 , wherein the CR and the BS of the logical network entity are determined according to a QoS policy of the logical network entity.

8. The method of claim 1 , wherein the logical network entity is in a virtualized shard based on a particular QoS class, wherein different virtualized shards support different QoS classes.

9. The method of claim 1 , wherein monitoring the traffic load of the logical network entity comprises periodically collecting traffic load information from each transport node of the plurality of transport nodes.

10. The method of claim 1 , wherein the plurality of transport nodes comprises one or more edge nodes for controlling network traffic to and from the logical network.

11. The method of claim 1 , wherein the plurality of transport nodes comprises a plurality of managed forwarding elements in the logical network.

12. The method of claim 1 , wherein the plurality of managed forwarding elements are implemented by virtualization software running in a plurality of different host computing devices.

13. The method of claim 12 , wherein the plurality of different host computing devices comprises host computing devices in multiple different public cloud datacenters.

14. The method of claim 1 , wherein the logical network spans multiple public cloud datacenters.

15. A system comprising:
a logical network entity in a logical network comprising a plurality of transport nodes that process network traffic of the logical network entity; and
a computing device implementing a central control plane (CCP) node of the logical network,
wherein the CCP node specifies a quality of service (QoS) requirement in terms of a committed rate (CR) parameter and a burst size (BS) parameter for a logical network entity,
wherein the CCP node monitors traffic loads of the plurality of transport nodes of the logical network entity,
wherein the CCP node allocates a local CR and a local BS to each of the plurality of transport nodes based on the CR and BS parameters of the logical network entity and the monitored traffic loads,
wherein each transport node of the logical network entity controls an amount of data being processed by the transport node based on a token bucket value that is computed based on the local CR and the local BS of the transport node.

16. The system of claim 15 , wherein the CR and the BS of the logical network entity are allocated evenly among the transport nodes of the logical network entity prior to a time interval for monitoring the traffic loads at the plurality of transport nodes.

17. The system of claim 15 , wherein a local token value of a transport node specifies a current amount of data that the transport node is capable of processing, wherein each transport node controls the amount of data being processed by the transport node by (i) adding to the local token value of the transport node an amount of data allowed to be processed by the transport node during a monitoring interval based on the local CR and (ii) subtracting from the local token value of the transport node an amount of data already processed by the transport node.

18. The system of claim 17 , wherein the amount of data allowed to be processed by the transport node is capped according to the local BS.

19. A computing device comprising:
one or more processors; and
a computer-readable storage medium storing a plurality of computer-executable components that are executable by the one or more processors to perform a plurality of actions, the plurality of actions comprising:
specifying a quality of service (QoS) requirement in terms of a committed rate (CR) parameter and a burst size (BS) parameter for a logical network entity in a logical network, the logical network entity comprising a plurality of transport nodes that process network traffic of the logical network entity;
monitoring traffic loads of the plurality of transport nodes of the logical network entity; and
allocating a local CR and a local BS to each of the plurality of transport nodes, wherein the local CR and the local BS are determined based on the CR and BS parameters of the logical network entity and based on the monitored traffic loads,
wherein each transport node of the logical network entity controls an amount of data being processed by the transport node based on a token bucket value that is computed based on the local CR and the local BS of the transport node.

20. The computing device of claim 19 , wherein the plurality of actions further comprise periodically collecting traffic load information from each transport node of the plurality of transport nodes.

Assignees

• Vmware Inc

Inventors

• Wang Dexiang
• Ravinoothala Sreeram Kumar
• Wang Yong
• Catrouillet Jerome

Classifications

• H04L47/2416 Primary

  Real-time traffic · CPC title

• H04L43/0888

  Throughput · CPC title

• H04L47/122

  by diverting traffic away from congested entities · CPC title

• H04L47/125

  by balancing the load, e.g. traffic engineering · CPC title

• H04L47/2433

  Allocation of priorities to traffic types · CPC title