Data center management with rack-controllers

Abstract

Provided is a process, including: receiving, with a rack-controller, via a first network, an application program interface (API) request; based on the API request, selecting, with the rack-controller, one of a plurality of routines to effectuate control via the second network of at least some of the plurality of rack-mounted computing devices; executing, with the rack-controller, the selected routine and, as a result, sending one or more commands via the second network encoded in a second protocol different from the first protocol to effectuate an action indicated by the API request.

What is claimed is: 
     
         1 . A tangible, non-transitory, machine-readable medium storing instructions that when executed by one or more processors effectuate operations comprising:
 executing a plurality of peer nodes of a distributed orchestration application, the distributed orchestration application orchestrating a plurality of containers to implement a distributed workload application;   determining a first hierarchical arrangement of the peer nodes with a consensus protocol executed by the peer nodes, the first hierarchical arrangement indicating that a first peer node among the plurality of peer nodes is designated as a leader node;   determining, by at least some of the plurality of peer nodes, that a heartbeat signal has not been received from the first peer node within a threshold duration of time while the first peer node is designated as the leader node and, in response, electing a second peer node among the plurality of peer nodes as the leader node with the consensus protocol to determine a second hierarchical arrangement of the peer nodes; and   propagating configuration data of at least some of the plurality of containers that implement the distributed workload application from the second peer node, while the second peer node is designated as the leader node, to other peer nodes among the plurality of peer nodes.   
     
     
         2 . The medium of  claim 1 , wherein the distributed orchestration application is configured to implement control and updates to the plurality of containers in a distributed, concurrent fashion by distributing commands through a through a hierarchical tree structure network graph established at least in part on an ad hoc, peer-to-peer, distributed basis. 
     
     
         3 . The medium of  claim 1 , wherein:
 the plurality of peer nodes execute in at least some of the containers; and   the orchestration application is configured to carry out at least three of the following tasks:
 service discovery, 
 file synchronization, 
 configuration synchronization, 
 physical or logical mapping of management components based on role, 
 device bootstrap, 
 configuration management, 
 file management, 
 container management, 
 operating system update management, or 
 user interface management. 
   
     
     
         4 . The medium of  claim 1 , wherein the orchestration application is configured to carry out each of the following tasks:
 service discovery,   file synchronization,   configuration synchronization,   physical or logical mapping of management components based on role,   device bootstrap,   configuration management,   file management,   container management,   operating system update management, and   user interface management.   
     
     
         5 . The medium of  claim 1 , wherein the operations comprise:
 steps for container management for workload orchestration.   
     
     
         6 . The medium of  claim 1 , wherein the operations comprise:
 steps for containing network traffic to a local branch of a data center management network.   
     
     
         7 . The medium of  claim 1 , wherein the operations comprise:
 steps for configuring rack control units in a data center.   
     
     
         8 . The medium of  claim 1 , wherein the operations comprise:
 changing configurations of at least some of the containers or servers upon which the at least some of the containers execute via a data center management computing device coupled to an out-of-band network.   
     
     
         9 . A computer-implemented method, comprising:
 executing a plurality of peer nodes of a distributed orchestration application, the distributed orchestration application orchestrating a plurality of containers to implement a distributed workload application;   determining a first hierarchical arrangement of the peer nodes with a consensus protocol executed by the peer nodes, the first hierarchical arrangement indicating that a first peer node among the plurality of peer nodes is designated as a leader node;   determining, by at least some of the plurality of peer nodes, that a heartbeat signal has not been received from the first peer node within a threshold duration of time while the first peer node is designated as the leader node and, in response, electing a second peer node among the plurality of peer nodes as the leader node with the consensus protocol to determine a second hierarchical arrangement of the peer nodes; and   propagating configuration data of at least some of the plurality of containers that implement the distributed workload application from the second peer node, while the second peer node is designated as the leader node, to other peer nodes among the plurality of peer nodes.   
     
     
         10 . The method of  claim 9 , wherein the distributed orchestration application is configured to implement control and updates to the plurality of containers in a distributed, concurrent fashion by distributing commands through a through a hierarchical tree structure network graph established at least in part on an ad hoc, peer-to-peer, distributed basis. 
     
     
         11 . The method of  claim 9 , wherein:
 the plurality of peer nodes execute in at least some of the containers; and   the orchestration application is configured to carry out at least three of the following tasks:
 service discovery, 
 file synchronization, 
 configuration synchronization, 
 physical or logical mapping of management components based on role, 
 device bootstrap, 
 configuration management, 
 file management, 
 container management, 
 operating system update management, or 
 user interface management. 
   
     
     
         12 . The method of  claim 9 , wherein the orchestration application is configured to carry out each of the following tasks:
 service discovery,   file synchronization,   configuration synchronization,   physical or logical mapping of management components based on role,   device bootstrap,   configuration management,   file management,   container management,   operating system update management, and   user interface management.   
     
     
         13 . The method of  claim 9 , further comprising:
 steps for container management for workload orchestration.   
     
     
         14 . The method of  claim 9 , further comprising:
 steps for containing network traffic to a local branch of a data center management network.   
     
     
         15 . The method of  claim 9 , further comprising:
 steps for configuring rack control units in a data center.   
     
     
         16 . The method of  claim 9 , further comprising:
 changing configurations of at least some of the containers or servers upon which the at least some of the containers execute via a data center management computing device coupled to an out-of-band network.   
     
     
         17 . A system, comprising:
 a plurality of data center management computing devices, wherein each of the data center management computing devices is configured to:
 provide a gateway between an out-of-band network and a respective plurality of local managed computing devices, the managed computing devices being configured to execute a workload application on data exchanged via an in-band network; 
 receive automated provisioning commands from a remote centralized data center management computing device and automatically provision the respective plurality of managed computing devices responsive to the automated provisioning commands; 
 receive automated configuration commands from the remote centralized data center management computing device and automatically configure the respective plurality of managed computing devices responsive to the automated configuration commands; and 
 automatically scan or enumerate the respective plurality of local managed computing devices to discover the respective plurality of local managed computing devices for which the respective data center management computing devices is to provide a gateway; and 
   the remote centralized data center management computing device.   
     
     
         18 . The system of  claim 17 , wherein:
 the plurality of data center management computing devices and the remote centralized data center management computing device comprise means for providing a management and control system;   the means for providing the management and control system is configured to push an operating system image out to the respective pluralities of local managed computing devices via the plurality of data center management computing devices;   the plurality of data center management computing devices are configured to manage and control the respective plurality of local managed computing devices via secure shell communications;   the out-of-band network is a cellular communications network;   the plurality of data center management computing devices are configured to report readings from temperature and humidity sensors associated with the respective pluralities of local managed computing devices to the remote centralized data center management computing device; and   the system comprises the in-band network and the respective pluralities of local managed computing devices.