Skip to main content
Have a personal or library account? Click to login
Taskfarm: A Client/Server Framework for Supporting Massive Embarrassingly Parallel Workloads Cover

Taskfarm: A Client/Server Framework for Supporting Massive Embarrassingly Parallel Workloads

Open Access
|Jan 2023

Figures & Tables

Table 1

Task farm server REST API URLs.

METHODURLDESCRIPTION
POST/api/runcreate a new run
GET/api/runsget a list of all runs
POST/api/runs/UUID/restartrestart all tasks of a run UUID
GET/api/runs/UUID/tasks/IDget information of task with ID of run UUID
PUT/api/runs/UUID/tasks/IDupdate task with ID of run UUID
POST/api/runs/UUID/taskrequest a task for run UUID
GET/api/runs/UUIDget information about run UUID
DELETE/api/runs/UUIDdelete run UUID
GET/api/tokenget the authentication token
POST/api/workercreate a worker
Figure 1

(a) The average time taken by each worker process to solve a total of 256 tasks when the task farm server uses 1, 2, 4, 8 or 16 worker processes. (b) The average time it takes to update the progress of a task.

DOI: https://doi.org/10.5334/jors.393 | Journal eISSN: 2049-9647
Language: English
Submitted on: Sep 6, 2021
Accepted on: Nov 29, 2022
Published on: Jan 12, 2023
Published by: Ubiquity Press
In partnership with: Paradigm Publishing Services
Publication frequency: 1 issue per year

© 2023 Magnus Hagdorn, Noel Gourmelen, published by Ubiquity Press
This work is licensed under the Creative Commons Attribution 4.0 License.