System and method for supporting heterogeneous and asymmetric dual rail fabric configurations in a high performance computing environment
Systems and methods for supporting heterogeneous and asymmetric dual rail fabric configurations in a high performance computing environment. A method can provide, comprising at one or more computers each including one or more microprocessors, a plurality hosts, each of the plurality of hosts comprising at least one dual port adapter, a private fabric, the private fabric comprising two or more switches, and a public fabric, the public fabric comprising a cloud fabric. A workload can be provisioned at a host of the plurality of hosts. A placement policy can be assigned to the provisioned workload. Then, network traffic between peer nodes of the provisioned workload can be assigned to one or more of the private fabric and the public fabric in accordance with the placement policy.
1 . A system for supporting redundant independent networks in a high performance computing environment, comprising:
a computer, the computer comprising one or more microprocessors;
a plurality of hosts provided at the computer;
wherein a host of the plurality of hosts is connected, by a first host port, to a private network fabric, wherein the host is further connected, via a second host port, to a public cloud network, and wherein the private network fabric and the public cloud network each respectively comprise an independent rail;
wherein a workload is provisioned at the host of the plurality of hosts, the host of the plurality of hosts being respectively connected to each independent rail via a different port of a plurality of ports associated with the host;
wherein the workload is assigned to one of the private network fabric and the public cloud network.
2 . The system of claim 1 ,
wherein the private network fabric independently provides full connectivity between the plurality of hosts.
3 . The system of claim 2 ,
wherein the public cloud network independently provides full connectivity between the plurality of hosts.
4 . The system of claim 3 ,
wherein the assignment of the workload to one of the private network fabric and the public cloud network is based on a service level agreement associated with the workload.
5 . The system of claim 4 ,
wherein the private network fabric comprises a plurality of switches.
6 . The system of claim 5 ,
wherein, based upon the service level agreement associated with the workload, communication associated with the workload between the plurality takes place within the public cloud network.
7 . The system of claim 5 ,
wherein, based upon the service level agreement associated with the workload, communication associated with the workload between the plurality takes place within the private network fabric.
8 . A method for supporting redundant independent networks in a high performance computing environment, comprising:
providing, at a computer, the computer comprising one or more microprocessors,
a plurality of hosts;
wherein a host of the plurality of hosts is connected, by a first host port, to a private network fabric,
wherein the host is further connected, via a second host port, to a public cloud network, and
wherein the private network fabric and the public cloud network each respectively comprise an independent rail;
wherein a workload is provisioned at a host of the plurality of hosts, the host of the plurality of hosts being respectively connected to each independent rail via a different port of a plurality of ports associated with the host;
wherein the workload is assigned to one of the private network fabric and the public cloud network.
9 . The method of claim 8 ,
wherein the private network fabric independently provides full connectivity between the plurality of hosts.
10 . The method of claim 9 ,
wherein the public cloud network independently provides full connectivity between the plurality of hosts.
11 . The method of claim 10 ,
wherein the assignment of the workload to one of the private network fabric and the public cloud network is based on a service level agreement associated with the workload.
12 . The method of claim 11 ,
wherein the private network fabric comprises a plurality of switches.
13 . The method of claim 12 ,
wherein, based upon the service level agreement associated with the workload, communication associated with the workload between the plurality takes place within the public cloud network.
14 . The method of claim 13 ,
wherein, based upon the service level agreement associated with the workload, communication associated with the workload between the plurality takes place within the private network fabric.
15 . A non-transitory computer readable storage medium comprising instructions for supporting redundant independent networks in a high performance computing environment, comprising:
providing, at the computer, the computer comprising one or more microprocessors,
a plurality of hosts;
wherein a host of the plurality of hosts is connected, by a first host port, to a private network fabric, wherein the host is further connected, via a second host port, to a public cloud network, and wherein the private network fabric and the public cloud network each respectively comprise an independent rail;
wherein a workload is provisioned at a host of the plurality of hosts, the host of the plurality of hosts being respectively connected to each independent rail via a different port of a plurality of ports associated with the host;
wherein the workload is assigned to one of the private network fabric and the public cloud network.
16 . The non-transitory computer readable storage medium of claim 15 ,
wherein the private network fabric independently provides full connectivity between the plurality of hosts.
17 . The non-transitory computer readable storage medium of claim 16 ,
wherein the public cloud network independently provides full connectivity between the plurality of hosts.
18 . The non-transitory computer readable storage medium of claim 17 ,
wherein the assignment of the workload to one of the private network fabric and the public cloud network is based on a service level agreement associated with the workload.
19 . The non-transitory computer readable storage medium of claim 18 ,
wherein the private network fabric comprises a plurality of switches.
20 . The non-transitory computer readable storage medium of claim 19 ,
wherein, based upon the service level agreement associated with the workload, communication associated with the workload between the plurality takes place within the public cloud network; and
wherein, based upon the service level agreement associated with the workload, communication associated with the workload between the plurality takes place within the private network fabric.