System and method for low latency node local scheduling in distributed resource management
AssigneeHuawei Technologies Co., Ltd.
InventorsNaganarasimha Ramesh Garla, Varun Saxena, Guilin Sun
Life of this patent
Estimating the term…
Abstract
A system for allocation of resources and processing jobs within a distributed system includes a processor and a memory coupled to the processor. The memory includes at least one process and at least one resource allocator. The process is adapted for processing jobs within a distributed system which receives jobs to be processed. The resource allocator is communicably coupled with at least one process, and is adapted to generate one or more sub-processes within a limit of one or more resources allocated to the process for processing jobs.
Claims20
A device, comprising:
- a memory configured to store instructions;
- and
- one or more processors coupled to the memory and configured to execute the instructions to:
- communicate with a resource master to allocate resources of the device;
- generate, based on the resources, a master container comprising container resources for running the master container and buffer resources for processing job requests in the device;
- receive a first job request;
- generate a sub-container to process the first job request, wherein the sub-container comprises a portion of the buffer resources;
- and
- resize, by a local resource allocator running on the device and based on resource usage of the device after generating the sub-container, a first size of the master container and a second size of the sub-container.
A method, comprising:
- communicating with a resource master to allocate resources of a device;
- generating, based on the resources, a master container comprising container resources for running the master container and buffer resources for processing job requests in the device;
- receiving a first job request;
- generating a sub-container to process the first job request, wherein the sub-container comprises a portion of the buffer resources;
- and
- resizing, by a local resource allocator running on the device and based on resource usage of the device after generating the sub-container, a first size of the master container and a second size of the sub-container.
A computer program product comprising instructions stored on a non-transitory computer-readable medium that, when executed by one or more processors, cause a device to:
- communicate with a resource master to allocate resources of the device;
- generate, based on the resources, a master container comprising container resources for running the master container and buffer resources for processing job requests in the device;
- receive a first job request;
- generate a sub-container to process the first job request, wherein the sub-container comprises a portion of the buffer resources;
- and
- resize, by a local resource allocator running on the device and based on resource usage of the device after generating the sub-container, a first size of the master container and a second size of the sub-container.
Dependencies are inferred from the claim text.