Computing node management system and method for managing a plurality of computing nodes
View Patent ↗A computing node management system includes a central offload node and a plurality of computing nodes. A riser card is inserted into each computing node. Each riser card is connected to the central offload node. Each riser card establishes a communication channel between the central offload node and the computing node into which the riser card is inserted. The central offload node is configured to provide resources for the plurality of computing nodes through the communication channels.
1 . A system comprising:
a central offload node;
a plurality of riser cards; and
a plurality of computing nodes,
wherein a first riser card of the plurality of riser cards is inserted into a first computing node of the plurality of computing nodes, and the first riser card is connected to the central offload node,
wherein a first inter-node communication sub-channel is established between the first riser card and the central offload node,
wherein a first intra-node communication sub-channel is established between the first riser card and the computing node into which the first riser card is inserted,
wherein the central offload node is connected to a storage device that provides a first storage resource,
wherein a first virtual device is deployed on the first riser card of the plurality of riser cards,
wherein a first cloud instance in a first computing node into which the first riser card is inserted is bound to the first virtual device,
wherein the central offload node allocates, to the first virtual device through the first inter-node communication sub-channel, the first storage resource of the storage device connected to the central offload node,
wherein the first cloud instance accesses, through the first intra-node communication sub-channel, the first virtual device to which the first storage resource is allocated, and
wherein the central offload node is further configured to forward an input/output (I/O) request between the storage device and the first cloud instance.
2 . The system of claim 1 , wherein the central offload node is further configured to perform processing on the I/O request, and wherein the processing comprises at least one of data encryption and decryption, data verification, data transmission speed control, or data quality-of-service control.
3 . The system of claim 1 , wherein a second riser card in the plurality of riser cards is inserted into a second computing node of plurality of computing nodes, and the second riser card is connected to the central offload node, wherein a second inter-node communication sub-channel is established between the second riser card of the plurality of riser cards and the central offload node, wherein a first intra-node communication sub-channel is established between the second riser card and the computing node into which the second riser card is inserted, wherein the central offload node is connected to a computing device that provides a computing resource, wherein a second virtual device is deployed on the second riser card of the plurality of riser cards, wherein a second cloud instance in the second computing node of the plurality of computing nodes into which the second riser card is inserted is bound to the second virtual device, wherein the central offload node allocates, to the second virtual device through the second inter-node communication sub-channel, the computing resource of the computing device connected to the central offload node, and wherein the second cloud instance accesses, through the second intra-node communication sub-channel, the second virtual device to which the computing resource is allocated.
4 . The system of claim 3 , wherein the computing device is a processor configured for heterogeneous computing.
5 . The system of claim 1 , wherein a third riser card in the plurality of riser cards is inserted into a third computing node of plurality of computing nodes, and the third riser card is connected to the central offload node, wherein a third inter-node communication sub-channel is established between the third riser card of the plurality of riser cards and the central offload node, wherein a third intra-node communication sub-channel is established between the third riser card and the computing node into which the third riser card is inserted, wherein the central offload node is connected to a network device that provides a network resource, wherein a third virtual device is deployed on the third riser card of the plurality of riser cards, wherein a third cloud instance in a third computing node into which the third riser card is inserted is bound to the third virtual device, wherein the central offload node allocates, to the third virtual device through the third inter-node communication sub-channel, the network resource of the network device connected to the central offload node, and wherein the third cloud instance accesses, through the third intra-node communication sub-channel, the third virtual device to which the network resource is allocated.
6 . The system of claim 5 , wherein the central offload node is further configured to forward a network packet between the network device and the third cloud instance.
7 . The system of claim 5 , wherein the central offload node is further configured to forward network packets between cloud instances in the computing nodes.
8 . The system of claim 1 , wherein the first riser card is further configured to establish the first inter-node communication sub-channel using a high-speed communication bus, and wherein the high-speed communication bus is a Peripheral Component Interconnect Express (PCIE) bus, a serializer/deserializer (SERDES) bus, a remote direct memory access (RDMA) bus, and a RDMA over converged ethernet (RoCE) bus.
9 . The system of claim 1 , wherein the first riser card is further configured to establish the first intra-node communication sub-channel using a Peripheral Component Interconnect Express (PCIE) bus.
10 . The system of claim 1 , wherein the computing nodes are disposed in a same subrack.
11 . The system of claim 1 , wherein the computing nodes comprise groups of computing nodes, and wherein each group of the computing nodes is disposed in a same subrack.
12 . The system of claim 1 , wherein the central offload node is a server.
13 . The system of claim 1 , wherein the central offload node is an offload card.
14 . The system of claim 1 , wherein the first virtual device is a virtual function (VF) device.
15 . The system of claim 1 , wherein the first virtual device is a physical function (PF) device.
16 . The system of claim 1 , wherein the first riser card supports a single-root input/output (I/O) virtualization (SRIOV) function.
17 . The system of claim 1 , wherein the first riser card is further configured to create the first virtual device based on a virtio protocol.
18 . The system of claim 1 , wherein a second riser card in the plurality of riser cards is inserted into a second computing node of plurality of computing nodes, and the second riser card is connected to the central offload node, wherein a second inter-node communication sub-channel is established between the second riser card of the plurality of riser cards and the central offload node, wherein a second intra-node communication sub-channel is established between the second riser card and the computing node into which the second riser card is inserted, wherein the storage device provides a second storage resource, wherein a second virtual device is deployed on the second riser card of the plurality of riser cards, wherein a second cloud instance in the second computing node of the plurality of computing nodes into which the second riser card is inserted is bound to the second virtual device, wherein the central offload node allocates, to the second virtual device through the second inter-node communication sub-channel, the second storage resource of the storage device connected to the central offload node, and wherein the second cloud instance accesses, through the second intra-node communication sub-channel, the second virtual device to which the second storage resource is allocated.
19 . The system of claim 18 , wherein the second riser card is further configured to create the second virtual device based on a virtio protocol.
20 . The system of claim 1 , wherein the central offload node is of at least two central offload nodes of the system, and wherein a quantity of the at least two central offload nodes for the plurality of computing nodes is adjustable.