Recent developments in Big Data frameworks are moving towards reservation based approaches as a mean to manage the increasingly complex mix of computations, whereas preemption techniques are employed to meet strict jobs deadlines. Within this work we propose and evaluate a new planning algorithm in the context of reservation based scheduling. Our approach is able to achieve high cluster utilization while minimizing the need for preemption that causes system overheads and planning mispredictions.
Preemption-aware planning on Big-Data systems
RABOZZI, MARCO;MAZZUCCHELLI, MATTEO;CORDONE, ROBERTO;FUMAROLA, GIOVANNI MATTEO;SANTAMBROGIO, MARCO DOMENICO
2016-01-01
Abstract
Recent developments in Big Data frameworks are moving towards reservation based approaches as a mean to manage the increasingly complex mix of computations, whereas preemption techniques are employed to meet strict jobs deadlines. Within this work we propose and evaluate a new planning algorithm in the context of reservation based scheduling. Our approach is able to achieve high cluster utilization while minimizing the need for preemption that causes system overheads and planning mispredictions.File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
a48-rabozzi-2.pdf
Accesso riservato
:
Publisher’s version
Dimensione
193.22 kB
Formato
Adobe PDF
|
193.22 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
