System for adaptive determination of computing resources and method therefor
View Patent ↗A system and method for adaptive determination of computing resources is presented. Sometimes, computing jobs are to be allocated among a set of computers. Historical information regarding input data size and output data size is retrieved. Capacity information about each machine is retrieved. A weighted function is used to calculate a desired allocation of computing resources based on historical input data size and output data size. Computing resources are allocated based on the calculated allocation. The computing job can be performed on the allocated computing resources. Other embodiments also are disclosed.
1. A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform acts of:
receiving first data regarding historical data of input size for a particular computing task;
receiving second data regarding historical data of output size for the particular computing task;
receiving capacity data indicating a capacity of each computing machine of a set of computing machines;
determining a desired number of computing machines of the set of computing machines to assign to a computing job in view of the first data, the second data, and the capacity data; and
allocating the desired number of computing machines of the set of computing machines to the computing job;
wherein:
determining the desired number of computing machines of the set of computing machines to assign to the computing job comprises:
using a function to determine the desired number of computing machines of the set of computing machines based on the historical data of input size and the historical data of output size;
the function is further based on the capacity of each computing machine of the set of computing machines; and
the function has a form:
n
vm
=
N
o
N
i
R
t
×
N
,
where N o is data regarding the historical data of input size for the particular computing task, N i is data regarding the historical data of output size for the particular computing task, R t is a capacity of a single computing machine of the set of computing machines, and N is a size of current input data of the computing job.
2. The system of claim 1 , wherein:
a weighting is applied to the function to give greater weight to at least a portion of at least one of (1) the historical data of input size for the particular computing task or (2) the historical data of output size for the particular computing task, whichever is more recent in time.
3. The system of claim 2 , wherein:
the weighting is an exponential factor.
4. The system of claim 1 , wherein:
each computing machine of the set of computing machines is a virtual machine.
5. The system of claim 1 , wherein:
a weighting is applied to the function to give greater weight to at least a portion of at least one of (1) the historical data of input size for the particular computing task or (2) the historical data of output size for the particular computing task, whichever is more recent in time;
the weighting is an exponential factor; and
each computing machine of the set of computing machines is a virtual machine.
6. A method comprising:
receiving first data regarding historical data of input size for a particular computing task;
receiving second data regarding historical data of output size for the particular computing task;
receiving capacity data indicating a capacity of each computing machine of a set of computing machines;
determining a desired number of computing machines of the set of computing machines to assign to a computing job in view of the first data, the second data, and the capacity data; and
allocating the desired number of computing machines of the set of computing machines to the computing job;
wherein:
determining the desired number of computing machines of the set of computing machines to assign to the computing job comprises:
using a function to determine the desired number of computing machines of the set of computing machines based on the historical data of input size and the historical data of output size;
the function is further based on the capacity of each computing machine of the set of computing machines; and
the function has a form:
n
vm
=
N
o
N
i
R
t
×
N
,
where N o is data regarding the historical data of input size for the particular computing task, N i is data regarding the historical data of output size for the particular computing task, R t is a capacity of a single computing machine of the set of computing machines, and N is a size of current input data of the computing job.
7. The method of claim 6 , wherein:
a weighting is applied to the function to give greater weight to at least a portion of at least one of (1) the historical data of input size for the particular computing task or (2) the historical data of output size for the particular computing task, whichever is more recent in time.
8. The method of claim 7 , wherein:
the weighting is an exponential factor.
9. The method of claim 6 , wherein:
each computing machine of the set of computing machines is a virtual machine.
10. The method of claim 6 , wherein:
a weighting is applied to the function to give greater weight to at least a portion of at least one of (1) the historical data of input size for the particular computing task or (2) the historical data of output size for the particular computing task, whichever is more recent in time;
the weighting is an exponential factor; and
each computing machine of the set of computing machines is a virtual machine.
11. A non-transitory computer-readable storage medium having data stored therein representing software executable by a computer, the non-transitory computer-readable storage medium comprising:
instructions for receiving first data regarding historical data of input size for a particular computing task;
instructions for receiving second data regarding historical data of output size for the particular computing task;
instructions for receiving capacity data indicating a capacity of each computing machine of a set of computing machines;
instructions for determining a desired number of computing machines of the set of computing machines to assign to a computing job in view of the first data, the second data, and the capacity data; and
instructions for allocating the desired number of computing machines of the set of computing machines to the computing job;
wherein:
determining the desired number of computing machines of the set of computing machines to assign to the computing job comprises:
using a function to determine the desired number of computing machines of the set of computing machines based on the historical data of input size and the historical data of output size;
the function is further based on the capacity of each computing machine of the set of computing machines; and
the function has a form:
n
vm
=
N
o
N
i
R
t
×
N
,
where N o is data regarding the historical data of input size for the particular computing task, N i is data regarding the historical data of output size for the particular computing task, R t is a capacity of a single computing machine of the set of computing machines, and N is a size of current input data of the computing job.
12. The non-transitory computer-readable storage medium of claim 11 , wherein:
a weighting is applied to the function to give greater weight to at least a portion of at least one of (1) the historical data of input size for the particular computing task or (2) the historical data of output size for the particular computing task, whichever is more recent in time;
the weighting is an exponential factor; and
each computing machine of the set of computing machines is a virtual machine.
13. The non-transitory computer-readable storage medium of claim 11 , wherein a weighting is applied to the function to give greater weight to at least a portion of at least one of (1) the historical data of input size for the particular computing task or (2) the historical data of output size for the particular computing task, whichever is more recent in time.
14. The non-transitory computer-readable storage medium of claim 13 , wherein the weighting is an exponential factor.
15. The non-transitory computer-readable storage medium of claim 11 , wherein each computing machine of the set of computing machines is a virtual machine.