System and method for providing bandwidth congestion control in a private fabric in a high performance computing environment
Systems and methods for providing bandwidth 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, and a plurality of host channel adapters, wherein each of the host channel adapters comprise at least one host channel adapter port, and wherein the plurality of host channel adapters are interconnected via the plurality of switches, and a plurality of end nodes. The method can provide, at a host channel adapter, an end node ingress bandwidth quota associated with an end node attached to the host channel adapter. The method can receive, at the end node of the host channel adapter, ingress bandwidth, the ingress bandwidth exceeding the ingress bandwidth quota of the end node.
1. A system for providing bandwidth congestion control in a private fabric in a high performance computing environment, comprising:
a computer comprising one or more microprocessors;
a first subnet provided at the computer, 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 plurality of target groups are defined within the subnet, each target group being defined at a specific portion of the subnet;
wherein each target group, respectively, defines a bandwidth limit for the associated specific portion of the subnet;
wherein a record of each of the plurality of target groups is stored at a target group repository of a host channel adapter of the plurality of host channel adapters; and
wherein two or more concurrent flows, each having a respective flow rate, are subjected to a bandwidth limit of at least one target group simultaneously.
2. The system of claim 1 ,
wherein at least two of the target groups define a different bandwidth restriction for each respective specific portion of the subnet.
3. The system of claim 2 ,
wherein the different bandwidth restrictions are defined based upon a quality of service class defined for the respective associated specific portion of the subnet.
4. The system of claim 1 ,
wherein at least a portion of the plurality of target groups comprise a hierarchy of target groups.
5. The system of claim 4 ,
wherein a maximum bandwidth is defined for the hierarchy of target groups, the maximum bandwidth being at least a most limited rate capacity among the at least a portion of the plurality of target groups.
6. The system of claim 1 ,
wherein at least one of the respective flow rates of the two or more concurrent flows is modified based upon the bandwidth limitation of the at least one target group.
7. A method for providing bandwidth congestion control in a private fabric in a high performance computing environment, comprising:
providing, at computer 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,
defining a plurality of target groups within the subnet, each target group being defined at a specific portion of the subnet;
defining, by each target group, respectively, a bandwidth limit for the associated specific portion of the subnet;
storing a record of each of the plurality of target groups at a target group repository of a host channel adapter of the plurality of host channel adapters; and
wherein two or more concurrent flows, each having a respective flow rate, are subjected to a bandwidth limit of at least one target group simultaneously.
8. The method of claim 7 ,
wherein at least two of the target groups define a different bandwidth restriction for each respective specific portion of the subnet.
9. The method of claim 8 ,
wherein the different bandwidth restrictions are defined based upon a quality of service class defined for the respective associated specific portion of the subnet.
10. The method tem of claim 7 ,
wherein at least a portion of the plurality of target groups comprise a hierarchy of target groups.
11. The method of claim 10 ,
wherein a maximum bandwidth is defined for the hierarchy of target groups, the maximum bandwidth being at least a most limited rate capacity among the at least a portion of the plurality of target groups.
12. The method of claim 7 ,
wherein at least one of the respective flow rates of the two or more concurrent flows is modified based upon the bandwidth limitation of the at least one target group.
13. A non-transitory computer readable storage medium having instructions thereon for providing bandwidth congestion control in a private fabric in a high performance computing environment, which when read and executed cause a computer to perform steps comprising:
providing, at computer 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,
defining a plurality of target groups within the subnet, each target group being defined at a specific portion of the subnet;
defining, by each target group, respectively, a bandwidth limit for the associated specific portion of the subnet;
storing a record of each of the plurality of target groups at a target group repository of a host channel adapter of the plurality of host channel adapters; and
wherein two or more concurrent flows, each having a respective flow rate, are subjected to a bandwidth limit of at least one target group simultaneously.
14. The non-transitory computer readable storage medium of claim 13 ,
wherein at least two of the target groups define a different bandwidth restriction for each respective specific portion of the subnet.
15. The non-transitory computer readable storage medium of claim 14 ,
wherein the different bandwidth restrictions are defined based upon a quality of service class defined for the respective associated specific portion of the subnet.
16. The non-transitory computer readable storage medium of claim 13 ,
wherein at least a portion of the plurality of target groups comprise a hierarchy of target groups.
17. The non-transitory computer readable storage medium of claim 16 ,
wherein a maximum bandwidth is defined for the hierarchy of target groups, the maximum bandwidth being at least a most limited rate capacity among the at least a portion of the plurality of target groups.
18. The non-transitory computer readable storage medium of claim 13 ,
wherein at least one of the respective flow rates of the two or more concurrent flows is modified based upon the bandwidth limitation of the at least one target group.