Resource allocation and provisioning in a multi-tier edge-cloud virtualization environment
Techniques are provided for resource allocation and provisioning in a multi-tier edge-cloud virtualization environment. An exemplary method comprises: obtaining an application request for processing a given data type in a multi-tier environment; processing application requests received within a decision window to allocate resources for virtual nodes to process the application requests received within the decision window, wherein the allocated resources for each virtual node is on a corresponding one of cloud resources and a given edge node; instantiating the allocated virtual nodes to process the application requests; and providing the application requests to the instantiated virtual nodes, wherein the instantiated virtual nodes obtain the data of the given data type from a data repository. The virtual node waits to process a given application request for output data of any predecessor requests and sends the output data of the given application request to any additional virtual nodes holding successor requests to the given application request.
1. A method, comprising:
obtaining at least one application request, from one or more of a user and a first application, to access a second application, wherein the second application processes data of a given data type in a multi-tier environment comprising cloud resources and a plurality of edge nodes, wherein said application request comprises (i) the given data type, and (ii) a data freshness constraint indicating a time elapsed since an acquisition from a source of the data;
processing, using at least one processing device, one or more application requests received within a decision window to allocate resources for one or more virtual nodes to process the one or more application requests received within the decision window, wherein the allocated resources for each of the one or more virtual nodes are on a corresponding one of: said cloud resources and a given one of said plurality of edge nodes, wherein the resources for the one or more virtual nodes to process the one or more application requests are provisioned to satisfy said data freshness constraint specified for the one or more application requests;
instantiating, using the at least one processing device, the one or more virtual nodes to process the one or more application requests; and
providing the one or more application requests to the one or more instantiated virtual nodes for processing by the one or more instantiated virtual nodes, wherein the one or more instantiated virtual nodes obtain from a data repository at least some of the data needed to compute the given data type indicated in said application request.
2. The method of claim 1 , wherein the virtual node waits to process a given application request for output data of one or more predecessor requests.
3. The method of claim 1 , wherein, upon completion of processing a given application request, the respective virtual node sends the output data of the given application request to one or more additional virtual nodes holding one or more successor requests to the given application request.
4. The method of claim 1 , further comprising the step of updating the data based on an evaluation of a time-stamp of the data from the data repository with respect to the data freshness constraint.
5. The method of claim 1 , further comprising the step of instantiating a copy of a workflow described by the given data type that is used to form the given data type.
6. The method of claim 1 , wherein the data comprises data from one or more Internet of Things devices.
7. The method of claim 1 , wherein the allocating employs a utility function based on one or more of a substantially minimum cost and a substantially maximum profit.
8. A system, comprising:
a memory; and
at least one processing device, coupled to the memory, operative to implement the following steps:
obtaining at least one application request, from one or more of a user and a first application, to access a second application, wherein the second application processes data of a given data type in a multi-tier environment comprising cloud resources and a plurality of edge nodes, wherein said application request comprises (i) the given data type, and (ii) a data freshness constraint indicating a time elapsed since an acquisition from a source of the data;
processing, using the at least one processing device, one or more application requests received within a decision window to allocate resources for one or more virtual nodes to process the one or more application requests received within the decision window, wherein the allocated resources for each of the one or more virtual nodes are on a corresponding one of: said cloud resources and a given one of said plurality of edge nodes, wherein the resources for the one or more virtual nodes to process the one or more application requests are provisioned to satisfy said data freshness constraint specified for the one or more application requests;
instantiating, using the at least one processing device, the one or more virtual nodes to process the one or more application requests; and
providing the one or more application requests to the one or more instantiated virtual nodes for processing by the one or more instantiated virtual nodes, wherein the one or more instantiated virtual nodes obtain from a data repository at least some of the data needed to compute the given data type indicated in said application request.
9. The system of claim 8 , wherein the virtual node waits to process a given application request for output data of one or more predecessor requests.
10. The system of claim 8 , wherein, upon completion of processing a given application request, the respective virtual node sends the output data of the given application request to one or more additional virtual nodes holding one or more successor requests to the given application request.
11. The system of claim 8 , further comprising the step of updating the data based on an evaluation of a time-stamp of the data from the data repository with respect to the data freshness constraint.
12. The system of claim 8 , further comprising the step of instantiating a copy of a workflow described by the given data type that is used to form the given data type.
13. The system of claim 8 , wherein the data comprises data from one or more Internet of Things devices.
14. The system of claim 8 , wherein the allocating employs a utility function based on one or more of a substantially minimum cost and a substantially maximum profit.
15. A computer program product, comprising a non-transitory machine-readable storage medium having encoded therein executable code of one or more software programs, wherein the one or more software programs when executed by at least one processing device perform the following steps:
obtaining at least one application request, from one or more of a user and a first application, to access a second application, wherein the second application processes data of a given data type in a multi-tier environment comprising cloud resources and a plurality of edge nodes, wherein said application request comprises (i) the given data type, and (ii) a data freshness constraint indicating a time elapsed since an acquisition from a source of the data;
processing, using at least one processing device, one or more application requests received within a decision window to allocate resources for one or more virtual nodes to process the one or more application requests received within the decision window, wherein the allocated resources for each of the one or more virtual nodes are on a corresponding one of: said cloud resources and a given one of said plurality of edge nodes, wherein the resources for the one or more virtual nodes to process the one or more application requests are provisioned to satisfy said data freshness constraint specified for the one or more application requests;
instantiating, using the at least one processing device, the one or more virtual nodes to process the one or more application requests; and
providing the one or more application requests to the one or more instantiated virtual nodes for processing by the one or more instantiated virtual nodes, wherein the one or more instantiated virtual nodes obtain from a data repository at least some of the data needed to compute the given data type indicated in said application request.
16. The computer program product of claim 15 , wherein the virtual node waits to process a given application request for output data of one or more predecessor requests.
17. The computer program product of claim 15 , wherein, upon completion of processing a given application request, the respective virtual node sends the output data of the given application request to one or more additional virtual nodes holding one or more successor requests to the given application request.
18. The computer program product of claim 15 , further comprising the step of updating the data based on an evaluation of a time-stamp of the data from the data repository with respect to the data freshness constraint.
19. The computer program product of claim 15 , further comprising the step of instantiating a copy of a workflow described by the given data type that is used to form the given data type.
20. The computer program product of claim 15 , wherein the allocating employs a utility function based on one or more of a substantially minimum cost and a substantially maximum profit.