Large receive offload (LRO) processing in virtualized computing environments

• US 10,313,926 B2
• Filed: 05/31/2017
• Issued: 06/04/2019
• Est. Priority Date: 05/31/2017
• Status: Active Grant

• Current Assignee: Nicira Incorporated (Broadcom, Inc.)
• Original Assignee: Nicira Incorporated (Broadcom, Inc.)
• Inventors: Mehta, Rishi, Ang, Boon, Yang, Guolin, Jiang, Wenyi, Jain, Jayant
• Primary Examiner(s): Abelson, Ronald B
• Application Number:
  US15/609,037
• Publication Number:
  US 20180352474A1
• Time in Patent Office: 734 Days
• CPC Class Codes: G06F 2009/45595 Network integration; Enabling network access in virtual machine instances
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects
• CPC Class Codes: H04L 49/90 Buffering arrangements
• CPC Class Codes: H04L 49/9057 Arrangements for supporting packet reassembly or resequencing
• CPC Class Codes: H04L 69/161 Implementation details of TCP/IP or UDP/IP stack architecture; Specification of modified or new header fields
• CPC Class Codes: H04W 28/065 using assembly or disassembly of packets

Abstract

Example methods are provided for a host to perform large receive offload (LRO) processing in a virtualized computing environment. The method may comprise receiving, via a physical network interface controller (NIC), incoming packets that are destined for the virtualized computing instance, and processing the incoming packets to generate at least one processed packet using a networking service pipeline that includes a packet aggregation service and multiple networking services. The packet aggregation service may be configured to aggregate the incoming packets into an aggregated packet and enabled at a service point along the networking service pipeline based on an LRO capability of at least one of the multiple networking services to process the aggregated packet. The method may also comprise forwarding the at least one processed packet generated by the networking service pipeline to the virtualized computing instance.

Claims

1. A method for a host to perform large receive offload (LRO) processing in a virtualized computing environment, wherein the host includes a physical network interface controller (NIC) and a networking service pipeline having a packet aggregation service and multiple networking services and supports a virtualized computing instance, and the method comprises:

receiving, via the physical NIC, incoming packets that are destined for the virtualized computing instance, wherein prior to receiving the incoming packets, enabling a packet splitting service at another service point along the networking service pipeline based on an LRO capability of the virtualized computing instance, or an LRO capability of at least one of the multiple networking services, or both;

processing the incoming packets to generate at least one processed packet using the networking service pipeline,

wherein the packet aggregation service is configured to aggregate the incoming packets into an aggregated packet, and enabled at a service point along the networking service pipeline based on an LRO capability of at least one of the multiple networking services to process the aggregated packet, and

wherein the aggregated packet is split by the packet splitting service at the another service point into multiple non-aggregated packets; and

forwarding the at least one processed packet generated by the networking service pipeline to the virtualized computing instance.

2. The method of claim 1, wherein processing the incoming packets comprises:

splitting, by the packet splitting service, the aggregated packet based on packet boundary information associated with the incoming packets.

3. The method of claim 2, wherein processing the incoming packets comprises:

linking, by the packet aggregation service, the aggregated packet with the packet boundary information that includes memory address information associated with the incoming packets.

4. The method of claim 1, wherein receiving the incoming packets comprises:

retrieving the incoming packets from a NIC queue that belongs to a pool of multiple NIC queues at the physical NIC that are configured to hold incoming packets destined for multiple virtualized computing instances that have LRO capability.

5. The method of claim 4, wherein the method further comprises:

prior to receiving the incoming packets, enabling the packet aggregation service at the service point along the networking service pipeline associated with the NIC queue.

6. A non-transitory computer-readable storage medium that includes a set of instructions which, in response to execution by a processor of a host, cause the processor to implement a method of large receive offload (LRO) processing in a virtualized computing environment, wherein the host includes a physical network interface controller (NIC) and a networking service pipeline having a packet aggregation service and multiple networking services and supports a virtualized computing instance, and the method comprises:

receiving, via the physical NIC, incoming packets that are destined for the virtualized computing instance, wherein prior to receiving the incoming packets, enabling a packet splitting service at another service point along the networking service pipeline based on an LRO capability of the virtualized computing instance, or an LRO capability of at least one of the multiple networking services, or both;

processing the incoming packets to generate at least one processed packet using the networking service pipeline,

wherein the packet aggregation service is configured to aggregate the incoming packets into an aggregated packet and enabled at a service point along the networking service pipeline based on an LRO capability of at least one of the multiple networking services to process the aggregated packet, and

wherein the aggregated packet is split by the packet splitting service at the another service point into multiple non-aggregated packets; and

forwarding the at least one processed packet generated by the networking service pipeline to the virtualized computing instance.

7. The non-transitory computer-readable storage medium of claim 6, wherein processing the incoming packets comprises:

splitting, by the packet splitting service, the aggregated packet based on packet boundary information associated with the incoming packets.

8. The non-transitory computer-readable storage medium of claim 7, wherein processing the incoming packets comprises:

linking, by the packet aggregation service, the aggregated packet with the packet boundary information that includes memory address information associated with the incoming packets.

9. The non-transitory computer-readable storage medium of claim 6, wherein receiving the incoming packets comprises:

retrieving the incoming packets from a NIC queue that belongs to a pool of multiple NIC queues at the physical NIC that are configured to hold incoming packets destined for multiple virtualized computing instances that have LRO capability.

10. The non-transitory computer-readable storage medium of claim 9, wherein the method further comprises:

prior to receiving the incoming packets, enabling the packet aggregation service at the service point along the networking service pipeline associated with the NIC queue.

11. A host configured to perform large receive offload (LRO) processing in a virtualized computing environment, wherein the host comprises:

a processor;

a physical network interface controller (NIC);

a networking service pipeline having a packet aggregation service and multiple networking services; and

a non-transitory computer-readable medium having stored thereon instructions that, when executed by the processor, cause the processor to;

receive, via the physical NIC, incoming packets that are destined for a virtualized computing instance supported by the host, wherein prior to receiving the incoming packets, enabling a packet splitting service at another service point along the networking service pipeline based on an LRO capability of the virtualized computing instance, or an LRO capability of at least one of the multiple networking services, or both;

process the incoming packets to generate at least one processed packet using the networking service pipeline,

wherein the packet aggregation service is configured to aggregate the incoming packets into an aggregated packet and enabled at a service point along the networking service pipeline based on an LRO capability of at least one of the multiple networking services to process the aggregated packet, and

wherein the aggregated packet is split by the packet splitting service at the another service point into multiple non-aggregated packets; and

forward the at least one processed packet generated by the networking service pipeline to the virtualized computing instance.

12. The host of claim 11, wherein the instructions for processing the incoming packets cause the processor to:

split, by the packet splitting service, the aggregated packet based on packet boundary information associated with the incoming packets.

13. The host of claim 12, wherein the instructions for processing the incoming packets cause the processor to:

link, by the packet aggregation service, the aggregated packet with the packet boundary information that includes memory address information associated with the incoming packets.

14. The host of claim 11, wherein the instructions for receiving the incoming packets cause the processor to:

retrieve the incoming packets from a NIC queue that belongs to a pool of multiple NIC queues at the physical NIC that are configured to hold incoming packets destined for multiple virtualized computing instances that have LRO capability.

15. The host of claim 14, wherein the instructions further cause the processor to:

prior to receiving the incoming packets, enable the packet aggregation service at the service point along the networking service pipeline associated with the NIC queue.