System and method for supporting a scalable flooding mechanism in a middleware machine environment

• US 9,641,350 B2
• Filed: 07/11/2012
• Issued: 05/02/2017
• Est. Priority Date: 07/11/2011
• Status: Active Grant

• Current Assignee: Oracle International Corporation (Oracle Corporation)
• Original Assignee: Oracle International Corporation (Oracle Corporation)
• Inventors: Johnsen, Bjrn Dag, Mayhead, Martin Paul, Trudbakken, Ola
• Primary Examiner(s): Chu, Wutchung
• Application Number:
  US13/546,261
• Publication Number:
  US 20130016719A1
• Time in Patent Office: 1,756 Days
• Field of Search: 709203, 709217, 709227, 709229, 709250, 709226, 709208, 709224, 709223, 370390, 370400
• CPC Class Codes: H04L 12/1836 with heterogeneous network architecture
• CPC Class Codes: H04L 12/1863 comprising mechanisms for improved reliability, e.g. status reports arrangements for detecting or preventing errors by carrying supervisory signal the return channel H04L1/16
• CPC Class Codes: H04L 12/4641 Virtual LANs, VLANs, e.g. virtual private networks [VPN] LAN interconnection over a bridge based backbone H04L12/462; encapsulation techniques H04L12/4633; routing of packets H04L45/00; packet switches H04L49/00; virtual private networks for security H04L63/0272
• CPC Class Codes: H04L 12/64 Hybrid switching systems
• CPC Class Codes: H04L 12/6402 Hybrid switching fabrics
• CPC Class Codes: H04L 12/66 Arrangements for connecting between networks having differing types of switching systems, e.g. gateways
• CPC Class Codes: H04L 45/245 Link aggregation, e.g. trunking
• CPC Class Codes: H04L 45/32 Flooding denial of service attacks H04L63/1458
• CPC Class Codes: H04L 49/00 Packet switching elements
• CPC Class Codes: H04L 49/10 characterised by the switching fabric construction
• CPC Class Codes: H04L 49/111 Switch interfaces, e.g. port details
• CPC Class Codes: H04L 49/30 Peripheral units, e.g. input or output ports
• CPC Class Codes: H04L 49/358 Infiniband Switches
• CPC Class Codes: H04L 67/563 Data redirection of data network streams

Abstract

A system and method can support a scalable packet forwarding mechanism in a middleware machine environment. The middleware machine environment can comprise one or more network switch instances, wherein each network switch instance is associated with one or more external ports that are adapted to receive data packets from an external network. Furthermore, the middleware machine environment can comprise a plurality of packet dispatching components, each of which is responsible for forwarding a data packet to a virtual machine on a host server that operates to process the data packet. Additionally, a link aggregation component can combine multiple external ports into a logical port, and wherein the bandwidth of the logical port is linearly scaled accordingly to a total number of the multiple external ports.

Claims

1. A system for supporting scalable packet intermediate forwarding in a middleware machine environment operable on one or more microprocessors, comprising:

a network switch instance connected with a plurality of host servers, wherein said network switch instance is associated with a plurality of external ports, each of which is adapted to receive one or more data packets from an external network, and

wherein each of the plurality of host servers is connected to the network switch via a host channel adapter (HCA) port and associated with one or more virtual machines, and

wherein each of the plurality of host servers is configured to communicate directly with each other of the plurality of host servers via a respective HCA port;

a link aggregation component that combines the plurality of external ports into a logical port, and wherein bandwidth of the logical port is linearly scaled accordingly to a number of the plurality of external ports; and

one or more packet dispatching components, each of which is associated with a different host server from the plurality of host servers that acts as an intermediate forwarding destination for incoming data packets without hardware context received at an external port;

wherein a number of the one or more packet dispatching components is such that each of the one or more packet dispatching components acts as the intermediate forwarding destination for a subset of the plurality of host servers that does not exceed a number of the plurality of external ports;

wherein each of the one or more packet dispatching components is responsible for forwarding a data packet without hardware context to a virtual machine that operates to process the data packet, the virtual machine residing on a host server associated with the packet dispatching component; and

wherein the host servers associated with the one or more packet dispatching components comprise a flood multicast group.

2. The system according to claim 1, further comprising:

a hardware context table that contains a plurality of contexts, which can be used to forward an incoming data packet to a host channel adapter port.

3. The system according to claim 1, wherein:

at least one said intermediate forwarding destination in the multicast group operate to use a packet dispatching component from the one or more packet dispatching components to forward a data packet received at the multicast group to a said host server in the subset of said host servers.

4. The system according to claim 1, wherein:

the plurality of host server shares multiple link aggregation component instances.

5. The system according to claim 4, wherein:

each said link aggregation component instance is associated with a packet dispatch component associated with an intermediate forwarding destination, and wherein the packet dispatch component operates to forward a packet received at said link aggregation component instance to a destination host server.

6. The system according to claim 5, wherein:

the destination host server operates to receive only one copy of a single multicast packet.

7. A method for supporting scalable packet intermediate forwarding in a middleware machine environment operable on one or more microprocessors, comprising:

providing a network switch instance connected with a plurality of host servers, wherein said network switch instance is associated with a plurality of external ports, and

wherein each of the plurality of host servers is connected to the network switch via a host channel adapter (HCA) port and associated with one or more virtual machines,

wherein each of the plurality of host servers is configured to communicate directly with each other of the plurality of host servers via a respective HCA port;

providing a link aggregation component that combines the plurality of external ports into a logical port, and wherein bandwidth of the logical port is linearly scaled accordingly to a number of the plurality of external ports;

receiving, at the plurality of external ports, one or more data packets without hardware context from an external network; and

forwarding, via one or more packet dispatching components each associated with a different host server from the plurality of host servers that acts as an intermediate forwarding destination for incoming data packets without hardware context received at an external port, each said data packet without hardware context to a virtual machine that operates to process the data packet;

wherein a number of the one or more packet dispatching components is such that each of the one or more packet dispatching components acts as the intermediate forwarding destination for a subset of the plurality of host servers that does not exceed a number of the plurality of external ports; and

wherein the host servers associated with the one or more packet dispatching components comprise a flood multicast group.

8. The method according to claim 7, further comprising:

providing a hardware context table that contains a plurality of contexts, which can be used to forward an incoming data packet to a host channel adapter port.

9. The method according to claim 7, further comprising:

allowing at least one said intermediate forwarding destination in the multicast group to use a packet dispatching component from the one or more packet dispatching components to forward a data packet received at the multicast group to a host server in the subset of said host servers.

10. The method according to claim 7, further comprising:

allowing the plurality of host server to share multiple link aggregation component instances.

11. The method according to claim 10, further comprising:

associating each said link aggregation component instance with a packet dispatch component associated with an intermediate forwarding destination, and wherein the packet dispatch component operates to forward a packet received at said link aggregation component instance to a destination host server.

12. A non-transitory machine readable storage medium having instructions stored thereon for supporting scalable packet intermediate forwarding in a middleware machine environment that when executed cause a system to perform the steps comprising:

providing a network switch instance connected with a plurality of host servers, wherein said network switch instance is associated with a plurality of external ports, and

wherein each of the plurality of host servers is connected to the network switch via a host channel adapter (HCA) port and associated with one or more virtual machines,

wherein each of the plurality of host servers is configured to communicate directly with each other of the plurality of host servers via a respective HCA port;

providing a link aggregation component that combines the plurality of external ports into a logical port, and wherein bandwidth of the logical port is linearly scaled accordingly to a number of the plurality of external ports;

receiving, at the plurality of external ports, one or more data packets without hardware context from an external network; and

forwarding, via one or more packet dispatching components each associated with a different host server from the plurality of host servers that acts as an intermediate forwarding destination for incoming data packets without hardware context received at an external port, each said data packet without hardware context to a virtual machine that operates to process the data packet;

wherein a number of the one or more packet dispatching components is such that each of the one or more packet dispatching components acts as the intermediate forwarding destination for a subset of the plurality of host servers that does not exceed a number of the plurality of external ports; and

wherein the host servers associated with the one or more packet dispatching components comprise a flood multicast group.