Long-term SLOs for reclaimed cloud computing resources Carvalho et - - PowerPoint PPT Presentation

long term slos for reclaimed cloud computing resources
SMART_READER_LITE
LIVE PREVIEW

Long-term SLOs for reclaimed cloud computing resources Carvalho et - - PowerPoint PPT Presentation

Long-term SLOs for reclaimed cloud computing resources Carvalho et al. (2014) Christopher Little Motivation Available Capacity CPU Cores Reservation Allocation g Usage Memory Motivation Available Capacity Reservation Allocation CPU


slide-1
SLIDE 1

Long-term SLOs for reclaimed cloud computing resources

Christopher Little Carvalho et al. (2014)

slide-2
SLIDE 2

Motivation

CPU Cores Memory g Available Capacity Usage Allocation Reservation

slide-3
SLIDE 3

Motivation

CPU Memory g Available Capacity Usage Allocation Reservation

slide-4
SLIDE 4

Current Approaches

0% Obtainability 0% Availability Reserved On-Demand Opportunistic 100% Obtainability 99% Availability 99% Obtainability 99% Availability

Service Level Objectives (SLO)

slide-5
SLIDE 5

Current Approaches

0% Obtainability 0% Availability Reserved On-Demand Opportunistic 100% Obtainability 99.9% Availability 99% Obtainability 99.9% Availability

Service Level Objectives (SLO)

Economy @ 6-17% 99% Obtainability 98.9% Availability Economy @ 28-40% 99% Obtainability 88.7% Availability

slide-6
SLIDE 6
slide-7
SLIDE 7
slide-8
SLIDE 8

Making Predictions

Methods:

  • Mean Slack
  • Minimum Slack
  • ARIMA
  • ETS
slide-9
SLIDE 9

Making Predictions

Methods:

  • Mean Slack
  • Minimum Slack
  • ARIMA
  • ETS
slide-10
SLIDE 10

Results

slide-11
SLIDE 11

Results

slide-12
SLIDE 12

Profitability

slide-13
SLIDE 13

Conclusion There is potential to increase profit by using weak promises.

slide-14
SLIDE 14

Evaluation

  • Not particularly novel contribution
  • Data analysis and graphs mostly well reported
  • Though many assumptions in profitability analysis
  • Some ideas are introduced and then never revisited…
  • Why 6 months?
slide-15
SLIDE 15

Long-term SLOs for reclaimed cloud computing resources

Christopher Little Carvalho et al. (2014)