Multicast miss notification for a distributed network switch

• US 8,787,373 B2
• Filed: 01/19/2012
• Issued: 07/22/2014
• Est. Priority Date: 01/19/2012
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Cors, Josep, Greenfield, Todd A., Shedivy, David A., Walk, Bruce M.
• Primary Examiner(s): Pham, Chi
• Assistant Examiner(s): Rivas, Raul
• Application Number:
  US13/353,737
• Publication Number:
  US 20130188637A1
• Time in Patent Office: 915 Days
• Field of Search: None
• US Class Current: 370/390
• CPC Class Codes: H04L 12/1886 with traffic restrictions for efficiency improvement, e.g. involving subnets or subdomains
• CPC Class Codes: H04L 45/16 Multipoint routing

Abstract

Techniques are provided for multicast miss notification for a distributed network switch. In one embodiment, a bridge element in the distributed network switch receives a frame destined for a multicast group on a network. If a local multicast forwarding table of the bridge element does not include any forwarding entry for the multicast group, a forwarding entry is selected from the local multicast forwarding table as a candidate for being replaced. An indication of the candidate is sent to a management controller in the distributed network switch.

Claims

1. A computer program product, comprising a computer-readable memory having computer-readable program code embodied therewith for multicast miss notification in a distributed network switch that includes a first switch module, the computer-readable program code executable to:

receive, by a bridge element of the first switch module, a frame destined for a multicast group on a network, wherein the first switch module includes a management controller associated with a global multicast forwarding table that includes a plurality of forwarding entries, wherein the bridge element is associated with a local multicast forwarding table specific to the bridge element and that includes a subset of the plurality of forwarding entries;

determine that the local multicast forwarding table associated with the bridge element does not include a forwarding entry for the multicast group for which the frame is addressed;

select a first forwarding entry from the local multicast forwarding table as a candidate for replacing with a forwarding entry for the multicast group for which the frame is destined; and

send, to the management controller, an indication that the first forwarding entry is the candidate for replacing with the forwarding entry for the multicast group for which the frame is destined, wherein the indication conforms to a predefined frame format comprising a central controlling bridge MAC address field, a source MAC address field, a key field, and a multicast hint field,

thereby providing multicast miss notification in the distributed network switch and reducing an incidence of multicast groups, to which frames are destined, not being found in the local multicast forwarding table, relative to not sending the management controller any indication of candidate forwarding entries for replacement.

2. The computer program product of claim 1, wherein the management controller is configured to:

retrieve, from the global multicast forwarding table, the forwarding entry for the multicast group, and wherein the management controller; and

store the retrieved forwarding entry in the local multicast forwarding table, based on the indication.

3. The computer program product of claim 1, wherein the predefined selection criteria comprises a time that the forwarding entry was last accessed in processing a multicast frame.

4. The computer program product of claim 1, wherein the bridge element comprises a distributed virtual Ethernet bridge (dVEB), and wherein the indication serves as a hint to the management controller which multicast forwarding entry is to replace.

5. The computer program product of claim 1, wherein the indication comprises an index of the first forwarding entry in the local multicast forwarding table, and wherein the forwarding entry for the multicast group for which the frame is destined comprises at least one of a logical network of the multicast group, a virtual local area network (VLAN) of the multicast group, and a Media Access Control (MAC) address for the multicast group.

6. The computer program product of claim 1, wherein the computer-readable program code is further executable to:

prior to sending the indication to the management controller, send the frame to a broadcast domain associated with the network.

7. The computer program product of claim 1, wherein the bridge element is configured to, upon determining that the local multicast forwarding table associated with the bridge element includes a forwarding entry for a second multicast group for which a second frame is destined, sending the second frame to the second multicast group based on the forwarding entry.

8. A system to provide multicast miss notification in a distributed network switch that includes a first switch module, the system comprising:

one or more computer processors;

a memory containing a program, which when executed by the one or more computer processors is configured to perform an operation comprising;

receiving, by a bridge element of the first switch module, a frame destined for a multicast group on a network, wherein the first switch module includes a management controller associated with a global multicast forwarding table that includes a plurality of forwarding entries, wherein the bridge element is associated with a local multicast forwarding table specific to the bridge element and that includes a subset of the plurality of forwarding entries;

determining that the local multicast forwarding table associated with the bridge element does not include a forwarding entry for the multicast group for which the frame is addressed;

selecting a first forwarding entry from the local multicast forwarding table as a candidate for replacing with a forwarding entry for the multicast group for which the frame is destined; and

sending, to the management controller, an indication that the first forwarding entry is the candidate for replacing with the forwarding entry for the multicast group for which the frame is destined, wherein the indication conforms to a predefined frame format comprising a central controlling bridge MAC address field, a source MAC address field, a key field, and a multicast hint field,

thereby providing multicast miss notification in the distributed network switch and reducing an incidence of multicast groups, to which frames are destined, not being found in the local multicast forwarding table, relative to not sending the management controller any indication of candidate forwarding entries for replacement.

9. The system of claim 8, wherein the management controller is configured to:

retrieve, from the global multicast forwarding table, the forwarding entry for the multicast group, and wherein the management controller; and

store the retrieved forwarding entry in the local multicast forwarding table, based on the indication.

10. The system of claim 8, wherein the predefined selection criteria comprises a time that the forwarding entry was last accessed in processing a multicast frame.

11. The system of claim 8, wherein the bridge element comprises a distributed virtual Ethernet bridge (dVEB), and wherein the indication serves as a hint to the management controller which multicast forwarding entry is to replace.

12. The system of claim 8, wherein the indication comprises an index of the first forwarding entry in the local multicast forwarding table, and wherein the forwarding entry for the multicast group for which the frame is destined comprises at least one of a logical network of the multicast group, a virtual local area network (VLAN) of the multicast group, and a Media Access Control (MAC) address for the multicast group.

13. The system of claim 8, wherein the operation further comprises:

prior to sending the indication to the management controller, sending the frame to a broadcast domain associated with the network.

14. The system of claim 8, wherein the predefined selection criteria comprises a time that the forwarding entry was last accessed in processing a multicast frame, wherein the management controller is configured to:

retrieve, from the global multicast forwarding table, the forwarding entry for the multicast group, and wherein the management controller; and

store the retrieved forwarding entry in the local multicast forwarding table, based on the indication.

15. The system of claim 14, wherein the bridge element comprises a distributed virtual Ethernet bridge (dVEB), wherein the indication serves as a hint to the management controller which multicast forwarding entry is to replace, wherein the indication comprises an index of the first forwarding entry in the local multicast forwarding table, and wherein the forwarding entry for the multicast group for which the frame is destined comprises at least one of a logical network of the multicast group, a virtual local area network (VLAN) of the multicast group, and a Media Access Control (MAC) address for the multicast group.

16. The system of claim 15, wherein the bridge element is configured to, upon determining that the local multicast forwarding table associated with the bridge element includes a forwarding entry for a second multicast group for which a second frame is destined, sending the second frame to the second multicast group based on the forwarding entry, wherein the operation further comprises:

prior to sending the indication to the management controller, sending the frame to a broadcast domain associated with the network.

17. The system of claim 16, wherein the local multicast forwarding table is associated with a plurality of predefined data structures including a delayed tracking table, a broadcast table, a multicast tree table, a logical network-VLAN table, an uplink table, a physical link state table, a query pending data structure, a forwarding cache data structure, and a set of next-previous data structures;

wherein the delayed tracking table maintains state information used by a multicast replication engine for operations queued for subsequent processing, whereby the processing of the operations is delayed only upon determining that multicast group information is not available in the local multicast forwarding table, wherein the operations include replicating multicast frames and sending the multicast frames;

wherein the broadcast table is indexed by logical network and virtual local area network and stores a bitmap of switch modules from which to receive broadcast frames for a given broadcast domain;

wherein the multicast tree table stores a bitmap of dVEBs in the distributed network switch, wherein a first bit in the bitmap represents a dVEB containing a port that is a member of a given multicast group.

18. The system of claim 17, wherein the physical link state table stores status information of whether a given physical link is operational;

wherein the query pending data structure maintains a pointer back to an entry in the delayed tracking table, that initiated a query to the management controller, wherein the pointer in effect serves as a breadcrumb back to a source of invoking the query;

wherein the forwarding cache data structure maintains a key for a cached forwarding entry, wherein the key includes a logical network, a VLAN, and a MAC address, wherein the forwarding cache data structure comprises a ternary content addressable memory data structure;

wherein the set of next-previous data structures comprise control structures configured to maintain both used forwarding entries and unused forwarding entries;

wherein the local multicast forwarding table includes the plurality of predefined data structures.

19. The system of claim 18, wherein the central controlling bridge comprises a firmware component that functions as a switch control point configured to receive packets for additional processing by the distributed network switch;

wherein the central controlling bridge MAC address field stores a six-byte MAC address of the central controlling bridge, wherein the source MAC address field stores a six-byte MAC address of a dVEB generating the multicast miss notification, wherein the key field stores a key not found in the forwarding cache data structure, wherein the multicast hint field provides a suggestion as to which entry in the multicast tree table should be replaced upon determining that an entry is to be added to the table responsive to a multicast miss, wherein the key multicast hint field in a given instance specifies an entry least recently used for forwarding;

wherein the predefined frame format further includes a VLAN protocol ID, a VLAN tag, and an ether type field, a control operation code type field, and a frame check sequence, and a plurality of pad fields each storing a respective, predetermined count of bytes of 0×

0 values, wherein the pad fields are not contiguous with one another, wherein each entry comprises a forwarding entry.