Utilizing reinforcement learning for serverless function tuning
One or more metrics associated with performance of a serverless function chain are received. The one or more metrics are analyzed by a reinforcement learning (RL) model to determine a tuning factor in view of a goal provided to the RL model. The tuning factor is transmitted to a serverless function controller, wherein the serverless function controller is to utilize the tuning factor to tune the serverless function chain.
1. A method comprising:
receiving one or more metrics associated with performance of a serverless function chain;
analyzing, by a processing device executing a reinforcement learning (RL) model, the one or more metrics to determine a tuning factor in view of a goal provided to the RL model; and
transmitting the tuning factor to a serverless function controller, wherein the serverless function controller is to utilize the tuning factor to tune the serverless function chain.
2. The method of claim 1 , wherein the serverless function chain comprises a first serverless function having an output that is an input of a second serverless function.
3. The method of claim 1 , further comprising:
receiving one or more subsequent metrics associated with performance of the serverless function chain;
determining an impact the tuning factor has on the performance of the serverless function chain in view of the goal;
determining a subsequent tuning factor in view of the impact; and
transmitting the subsequent tuning factor to the serverless function controller.
4. The method of claim 1 , wherein the goal comprises reducing a duration of the serverless function chain.
5. The method of claim 1 , wherein the goal comprises reducing an amount of computing resources allocated to serverless function chain while satisfying a performance threshold.
6. The method of claim 1 , wherein the goal comprises adjusting a response time of the serverless function chain.
7. The method of claim 1 , wherein the serverless function chain comprises a plurality of containers.
8. The method of claim 1 , wherein the serverless function chain comprises a plurality of virtual machines.
9. The method of claim 1 , wherein the tuning factor indicates scaling a number of serverless functions of the serverless function chain that are active.
10. The method of claim 1 , wherein the tuning factor indicates computing resources to be allocated to the serverless function chain.
11. A system comprising:
a memory; and
a processing device, operatively coupled to the memory, to:
receive one or more metrics associated with a plurality of related serverless functions;
receive a goal associated with performance of the plurality of related serverless functions;
determine a tuning factor for the plurality of related serverless functions in view of the one or more metrics and the goal; and
transmit the tuning factor to a serverless function controller.
12. The system of claim 11 , wherein the plurality of related serverless functions are associated with at least one of a same user, a same project, or a same organization.
13. The system of claim 11 , wherein the serverless function controller is to tune the plurality of related serverless functions in view of the tuning factor.
14. The system of claim 11 , wherein the tuning factor indicates computing resources to be allocated to the serverless function chain.
15. The system of claim 11 , wherein the processing device executes a reinforcement learning model to determine the tuning factor.
16. The system of claim 11 , wherein the goal comprises adjusting a response time of the plurality of related serverless functions.
17. The system of claim 11 , wherein the plurality of related serverless functions comprise a serverless function chain.
18. A non-transitory computer-readable storage medium including instructions that, when executed by a processing device of a serverless function controller, cause the processing device to:
receive, by the processing device of the serverless function controller, a tuning factor associated with a serverless function chain, the tuning factor is determined in view of one or more metrics associated with the serverless function chain and a goal associated with the serverless function chain; and
tune the serverless function chain in view of the tuning factor.
19. The non-transitory computer-readable storage medium of claim 18 , wherein the serverless function chain comprises a first serverless function having an output that is an input of a second serverless function.
20. The non-transitory computer-readable storage medium of claim 18 , wherein to tune the serverless function chain, the processing device is further to:
invoke one or more serverless functions for the serverless function chain.