INFRASTRUCTURE DRIVEN AUTO-SCALING OF WORKLOADS
The disclosure provides a method for scaling workloads. The method includes receiving information regarding resources of one or more host machines running one or more virtual machines. The method further includes determining, based on the information, to change a quantity of the one or more virtual machines running on the one or more host machines. The method further includes determining an amount to change the quantity of the one or more virtual machines running on the one or more host machines based on utilization of one or more resource types of the one or more host machines, the utilization indicated by the information. The method further includes causing a change in the quantity of the one or more virtual machines running on the one or more host machines by the determined amount.
1 . A method for scaling workloads, the method comprising:
receiving information regarding resources of one or more host machines running one or more virtual machines;
determining, based on the information, to change a quantity of the one or more virtual machines running on the one or more host machines;
determining an amount to change the quantity of the one or more virtual machines running on the one or more host machines based on utilization of one or more resource types of the one or more host machines, the utilization indicated by the information; and
causing a change in the quantity of the one or more virtual machines running on the one or more host machines by the determined amount.
2 . The method of claim 1 , further comprising, based on the change in the quantity of the one or more virtual machines running on the one or more host machines, causing a change to a quantity of containers running or permitted to run in the one or more virtual machines.
3 . The method of claim 2 , further comprising, based on the change to the quantity of containers running or permitted to run in the one or more virtual machines, changing a capacity configuration of a distributed computational framework executing on at least one container running in the one or more virtual machines.
4 . The method of claim 1 , wherein determining to change the quantity of the one or more virtual machines running on the one or more host machines is based on one or more of:
a change in a number of the one or more host machines,
a change in utilization of the one or more resource types of the one or more host machines,
a change in a policy governing an amount of the one or more resource types assignable to the one or more virtual machines, or
a change in date or time triggering a schedule based policy determining maximum utilization of the one or more resource types assignable to the one or more virtual machines.
5 . The method of claim 1 , wherein the one or more virtual machines are assigned to a first priority pool that has a lower priority than one or more other virtual machines running on the one or more host machines.
6 . The method of claim 1 , wherein determining the amount to change the quantity of the one or more virtual machines is further based on a configuration of the one or more virtual machines, the configuration indicating an amount of resources allocated to each of the one or more virtual machines.
7 . The method of claim 1 , wherein determining the amount to change the quantity of the one or more virtual machines is further based on an oversubscription amount of resources of the one or more virtual machines to the one or more resources types of the one or more host machines.
8 . The method of claim 1 , wherein determining the amount to change the quantity of the one or more virtual machines is further based on which of the one or more resource types is a limiting resource type for running of the one or more virtual machines on the one or more hosts.
9 . The method of claim 1 , wherein the utilization comprises a predicted utilization for a future time period.
10 . A system comprising:
one or more processors; and
at least one memory, the one or more processors and the at least one memory configured to:
receive information regarding resources of one or more host machines running one or more virtual machines;
determine, based on the information, to change a quantity of the one or more virtual machines running on the one or more host machines;
determine an amount to change the quantity of the one or more virtual machines running on the one or more host machines based on utilization of one or more resource types of the one or more host machines, the utilization indicated by the information; and
cause a change in the quantity of the one or more virtual machines running on the one or more host machines by the determined amount.
11 . The system of claim 10 , wherein the one or more processors and the at least one memory are further configured to, based on the change in the quantity of the one or more virtual machines run on the one or more host machines, causing a change to a quantity of containers running or permitted to run in the one or more virtual machines.
12 . The system of claim 11 , wherein the one or more processors and the at least one memory are further configured to, based on the change to the quantity of containers running or permitted to run in the one or more virtual machines, change a capacity configuration of a distributed computational framework executing on at least one container running in the one or more virtual machines.
13 . The system of claim 10 , wherein determining to change the quantity of the one or more virtual machines running on the one or more host machines is based on one or more of:
a change in a number of the one or more host machines,
a change in utilization of the one or more resource types of the one or more host machines,
a change in a policy governing an amount of the one or more resource types assignable to the one or more virtual machines, or
a change in date or time triggering a schedule based policy determining maximum utilization of the one or more resource types assignable to the one or more virtual machines.
14 . The system of claim 10 , wherein the one or more virtual machines are assigned to a first priority pool that has a lower priority than one or more other virtual machines running on the one or more host machines.
15 . The system of claim 10 , wherein determining the amount to change the quantity of the one or more virtual machines is further based on a configuration of the one or more virtual machines, the configuration indicating an amount of resources allocated to each of the one or more virtual machines.
16 . The system of claim 10 , wherein determining the amount to change the quantity of the one or more virtual machines is further based on an oversubscription amount of resources of the one or more virtual machines to the one or more resources types of the one or more host machines.
17 . The system of claim 10 , wherein determining the amount to change the quantity of the one or more virtual machines is further based on which of the one or more resource types is a limiting resource type for running of the one or more virtual machines on the one or more hosts.
18 . The system of claim 10 , wherein the utilization comprises a predicted utilization for a future time period.
19 . One or more non-transitory computer-readable media comprising instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations for scaling workloads, the operations comprising:
receiving information regarding resources of one or more host machines running one or more virtual machines;
determining, based on the information, to change a quantity of the one or more virtual machines running on the one or more host machines;
determining an amount to change the quantity of the one or more virtual machines running on the one or more host machines based on utilization of one or more resource types of the one or more host machines, the utilization indicated by the information; and
causing a change in the quantity of the one or more virtual machines running on the one or more host machines by the determined amount.
20 . The one or more non-transitory computer-readable media of claim 19 , wherein the operations further comprise, based on the change in the quantity of the one or more virtual machines running on the one or more host machines, causing a change to a quantity of containers running or permitted to run in the one or more virtual machines.