Resource utilization in job scheduler systems
Methods, systems, and computer-readable storage media for receiving a first set of historical processing data for a first job, the first set of historical processing data including a first value for a first characteristic type and a second value for a second characteristic type, determining a first consumption type for the first job based on the first value and the second value, assigning the first job and a second job to a job tuple in response to determining that the first consumption type of the first job is combinable with a second consumption type of the second job, fetching, by a first job worker, the job tuple from a job queue, and concurrently executing, by the first job worker, the first job and the second job of the job tuple.
1 . A computer-implemented method for distributing jobs for execution in cloud-based environments, the method being executed by one or more processors and comprising:
receiving a first set of historical processing data for a first job, the first set of historical processing data comprising a first value for a first characteristic type and a second value for a second characteristic type;
determining a first consumption type for the first job based on the first value and the second value;
assigning the first job and a second job to a job tuple in response to determining that the first consumption type of the first job is combinable with a second consumption type of the second job;
fetching, by a first job worker, the job tuple from a job queue; and
concurrently executing, by the first job worker, the first job and the second job of the job tuple.
2 . The method of claim 1 , wherein determining a first consumption type for the first job based on the first value and the second value comprises determining that the first value is equal to or above a first threshold value and the second value is less than a second threshold value, and in response, assigning the first consumption type to the first job.
3 . The method of claim 1 , wherein determining a first consumption type for the first job based on the first value and the second value comprises determining that the first value is equal to or above a first threshold value and the second value is equal to or above a second threshold value, and in response, assigning the first consumption type to the first job.
4 . The method of claim 1 , further comprising:
assigning a third job to be non-concurrently executed by a job worker in response to determining that a first consumption type of the third job is not combinable with consumption types of other jobs;
fetching, by a second job worker, the third job from the job queue; and
executing, by the second job worker, the third job.
5 . The method of claim 1 , wherein the first characteristic type and the second characteristic type are included in a set of characteristic types comprising processing cost, memory cost, and network cost.
6 . The method of claim 1 , wherein the first consumption type and the second consumption type are included in a set of consumption types comprising, processing-only, processing-memory, processing-network, memory-only, memory-network, network-only, and other.
7 . The method of claim 1 , wherein the first job worker fetches the job tuple from the job queue based on a load balancing algorithm that designates an order of job workers for fetching from the job queue.
8 . A non-transitory computer-readable storage medium coupled to one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations for distributing jobs for execution in cloud-based environments, the operations comprising:
receiving a first set of historical processing data for a first job, the first set of historical processing data comprising a first value for a first characteristic type and a second value for a second characteristic type;
determining a first consumption type for the first job based on the first value and the second value;
assigning the first job and a second job to a job tuple in response to determining that the first consumption type of the first job is combinable with a second consumption type of the second job;
fetching, by a first job worker, the job tuple from a job queue; and
concurrently executing, by the first job worker, the first job and the second job of the job tuple.
9 . The non-transitory computer-readable storage medium of claim 8 , wherein determining a first consumption type for the first job based on the first value and the second value comprises determining that the first value is equal to or above a first threshold value and the second value is less than a second threshold value, and in response, assigning the first consumption type to the first job.
10 . The non-transitory computer-readable storage medium of claim 8 , wherein determining a first consumption type for the first job based on the first value and the second value comprises determining that the first value is equal to or above a first threshold value and the second value is equal to or above a second threshold value, and in response, assigning the first consumption type to the first job.
11 . The non-transitory computer-readable storage medium of claim 8 , wherein operations further comprise:
assigning a third job to be non-concurrently executed by a job worker in response to determining that a first consumption type of the third job is not combinable with consumption types of other jobs;
fetching, by a second job worker, the third job from the job queue; and
executing, by the second job worker, the third job.
12 . The non-transitory computer-readable storage medium of claim 8 , wherein the first characteristic type and the second characteristic type are included in a set of characteristic types comprising processing cost, memory cost, and network cost.
13 . The non-transitory computer-readable storage medium of claim 8 , wherein the first consumption type and the second consumption type are included in a set of consumption types comprising, processing-only, processing-memory, processing-network, memory-only, memory-network, network-only, and other.
14 . The non-transitory computer-readable storage medium of claim 8 , wherein the first job worker fetches the job tuple from the job queue based on a load balancing algorithm that designates an order of job workers for fetching from the job queue.
15 . A system, comprising:
a computing device; and
a computer-readable storage device coupled to the computing device and having instructions stored thereon which, when executed by the computing device, cause the computing device to perform operations for distributing jobs for execution in cloud-based environments, the operations comprising:
receiving a first set of historical processing data for a first job, the first set of historical processing data comprising a first value for a first characteristic type and a second value for a second characteristic type;
determining a first consumption type for the first job based on the first value and the second value;
assigning the first job and a second job to a job tuple in response to determining that the first consumption type of the first job is combinable with a second consumption type of the second job;
fetching, by a first job worker, the job tuple from a job queue; and
concurrently executing, by the first job worker, the first job and the second job of the job tuple.
16 . The system of claim 15 , wherein determining a first consumption type for the first job based on the first value and the second value comprises determining that the first value is equal to or above a first threshold value and the second value is less than a second threshold value, and in response, assigning the first consumption type to the first job.
17 . The system of claim 15 , wherein determining a first consumption type for the first job based on the first value and the second value comprises determining that the first value is equal to or above a first threshold value and the second value is equal to or above a second threshold value, and in response, assigning the first consumption type to the first job.
18 . The system of claim 15 , wherein operations further comprise:
assigning a third job to be non-concurrently executed by a job worker in response to determining that a first consumption type of the third job is not combinable with consumption types of other jobs;
fetching, by a second job worker, the third job from the job queue; and
executing, by the second job worker, the third job.
19 . The system of claim 15 , wherein the first characteristic type and the second characteristic type are included in a set of characteristic types comprising processing cost, memory cost, and network cost.
20 . The system of claim 15 , wherein the first consumption type and the second consumption type are included in a set of consumption types comprising, processing-only, processing-memory, processing-network, memory-only, memory-network, network-only, and other.