System and method for supporting SMA level handling to ensure subnet integrity in a high performance computing environment
US-10148567-B2 · Dec 4, 2018 · US
US11838217B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-11838217-B2 |
| Application number | US-202217744517-A |
| Country | US |
| Kind code | B2 |
| Filing date | May 13, 2022 |
| Priority date | Nov 19, 2019 |
| Publication date | Dec 5, 2023 |
| Grant date | Dec 5, 2023 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Systems and methods for supporting target groups for congestion control in a private fabric in a high performance computing environment. An exemplary method can provide, at one or more microprocessors, a first subnet, the first subnet comprising a plurality of switches, a plurality of host channel adapters, and a plurality of end nodes, including a plurality of virtual machines. The method can define a target group on one of an inter-switch link or at a port of a switch of the plurality of switches, wherein the target group defines a bandwidth limit on the at least one of an inter-switch link between two switches of the plurality of switches or at a port of a switch of the plurality of switches. The method can provide a target group repository stored in a memory of the host channel adapter where the defined target group in the target group repository is recorded.
Opening claim text (preview).
What is claimed is: 1. A system for supporting target groups for congestion control in a private fabric in a high performance computing environment, comprising: one or more microprocessors; a first subnet, the first subnet comprising a plurality of switches, and a plurality of host channel adapters, wherein the plurality of host channel adapters are interconnected via the plurality of switches; wherein a target group is defined within the subnet, wherein a host channel adapter comprises a target group repository stored in a memory of the host channel adapter; wherein the target group is associated with two or more bandwidth limitations, each of the two or more bandwidth limitations being associated with a different quota priority class; wherein the target group repository queries the target group defined within the subnet to determine the two or more bandwidth limitations associated with the target group; and wherein upon querying the target group, the target group repository stores the two or more bandwidth limitations as host channel adapter objects. 2. The system of claim 1 , wherein the defined target group is recorded in the target group repository. 3. The system of claim 2 , wherein the target group is defined at an inter-switch link between two switches of the plurality of switches. 4. The system of claim 3 , wherein the target group defines, based upon the associated two or more bandwidth limitations, two or more bandwidth limits on the inter-switch link between two switches of the plurality of switches. 5. The system of claim 2 , wherein the target group is defined at port of a switch of the plurality of switches. 6. The system of claim 5 , wherein the target group defines, based upon the associated two or more bandwidth limitations, two or more bandwidth limits at the port of the switch of the plurality of switches. 7. The system of claim 1 , wherein the target group is decoupled from any specific destination address. 8. A method for supporting target groups for congestion control in a private fabric in a high performance computing environment, comprising: providing a first subnet, the first subnet comprising a plurality of switches, and a plurality of host channel adapters, wherein the plurality of host channel adapters are interconnected via the plurality of switches; wherein a target group is defined within the subnet, wherein a host channel adapter comprises a target group repository stored in a memory of the host channel adapter; wherein the target group is associated with two or more bandwidth limitations, each of the two or more bandwidth limitations being associated with a different quota priority class; wherein the target group repository queries the target group defined within the subnet to determine the two or more bandwidth limitations associated with the target group; and wherein upon querying the target group, the target group repository stores the two or more bandwidth limitations as host channel adapter objects. 9. The method of claim 8 , wherein the defined target group is recorded in the target group repository. 10. The method of claim 9 , wherein the target group is defined at an inter-switch link between two switches of the plurality of switches. 11. The method of claim 10 , wherein the target group defines, based upon the associated two or more bandwidth limitations, two or more bandwidth limits on the inter-switch link between two switches of the plurality of switches. 12. The method of claim 9 , wherein the target group is defined at port of a switch of the plurality of switches. 13. The method of claim 12 , wherein the target group defines, based upon the associated two or more bandwidth limitations, two or more bandwidth limits at the port of the switch of the plurality of switches. 14. The method of claim 8 , wherein the target group is decoupled from any specific destination address. 15. A non-transitory computer readable storage medium having instructions thereon for supporting target groups for congestion control in a private fabric in a high performance computing environment, which when read and executed cause a computer to perform a method comprising: a first subnet, the first subnet comprising a plurality of switches, and a plurality of host channel adapters, wherein the plurality of host channel adapters are interconnected via the plurality of switches; wherein a target group is defined within the subnet, wherein a host channel adapter comprises a target group repository stored in a memory of the host channel adapter; wherein the target group is associated with two or more bandwidth limitations, each of the two or more bandwidth limitations being associated with a different quota priority class; wherein the target group repository queries the target group defined within the subnet to determine the two or more bandwidth limitations associated with the target group; and wherein upon querying the target group, the target group repository stores the two or more bandwidth limitations as host channel adapter objects. 16. The non-transitory computer readable storage medium of claim 15 , wherein the defined target group is recorded in the target group repository. 17. The non-transitory computer readable storage medium of claim 16 , wherein the target group is defined at an inter-switch link between two switches of the plurality of switches. 18. The non-transitory computer readable storage medium of claim 17 , wherein the target group defines, based upon the associated two or more bandwidth limitations, two or more bandwidth limits on the inter-switch link between two switches of the plurality of switches. 19. The non-transitory computer readable storage medium of claim 16 , wherein the target group is defined at port of a switch of the plurality of switches. 20. The non-transitory computer readable storage medium of claim 15 , wherein the target group is decoupled from any specific destination address.
Avoiding congestion; Recovering from congestion · CPC title
Discovery or management of network topologies · CPC title
sent by intermediate network nodes · CPC title
Infiniband Switches · CPC title
using explicit feedback to the source, e.g. choke packets · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.