| | |
Summary: Towards High-Level SLAs with Heterogeneous
Workloads: Job Resource Requirements
Prediction for Deadline Schedulers
Gemma Reig1
, Javier Alonso2
and Jordi Guitart 3
Abstract--When executing their tasks, Grid and
Cloud users want to express their requirements in
terms of high-level metrics (e.g. in terms of execu-
tion time, not in terms of CPU MHz). Moreover, at
the submission time they would like to know if the
resource provider will fulfil with their requirements
in order to decide if they would rather prefer another
provider. On the other hand, the resource provider
have to translate these high-level metrics into hard-
ware related metrics, to know if he have enough re-
sources to execute the user's requests. In this con-
text, we present our prediction system to foresee the
amount of CPU required for a job to finish before
its deadline. This prediction system uses machine
|
