SPECIFYING THE EXPERIMENTAL SCENARIOS FOR SIMULATED CLOUD STUDIES - - PowerPoint PPT Presentation

specifying the experimental scenarios for simulated cloud
SMART_READER_LITE
LIVE PREVIEW

SPECIFYING THE EXPERIMENTAL SCENARIOS FOR SIMULATED CLOUD STUDIES - - PowerPoint PPT Presentation

SPECIFYING THE EXPERIMENTAL SCENARIOS FOR SIMULATED CLOUD STUDIES Simon Bihel Dept. of Computer Science, ENS Rennnes Internship done at Irisa in the Myriads team Advisors: Martin Quinson and Anne-Ccile Orgerie 1 / 13 BACKGROUND Background


slide-1
SLIDE 1

SPECIFYING THE EXPERIMENTAL SCENARIOS FOR SIMULATED CLOUD STUDIES

Simon Bihel

  • Dept. of Computer Science, ENS Rennnes

Internship done at Irisa in the Myriads team Advisors: Martin Quinson and Anne-Cécile Orgerie

1 / 13

slide-2
SLIDE 2

BACKGROUND

Background Contribution Evaluation Background Cloud Structure Dealing with Fluctuating Workload Typical Experimental Methodologies

2 / 13

slide-3
SLIDE 3

CLOUD STRUCTURE

Background Contribution Evaluation Background Cloud Structure Dealing with Fluctuating Workload Typical Experimental Methodologies

3 / 13

slide-4
SLIDE 4

DEALING WITH FLUCTUATING WORKLOAD

Dynamic management: horizontal scaling, vertical scaling, etc. Typical cloud studies: when to trigger these actions, how to perform them, etc.

Background Contribution Evaluation Background Cloud Structure Dealing with Fluctuating Workload Typical Experimental Methodologies

4 / 13

slide-5
SLIDE 5

TYPICAL EXPERIMENTAL METHODOLOGIES

Traditional experiments steps: what are they evaluating, setup, scenario, the results and their analysis. Simulation has many advantages but real experiments are still more used.

Background Contribution Evaluation Background Cloud Structure Dealing with Fluctuating Workload Typical Experimental Methodologies

5 / 13

slide-6
SLIDE 6

CONTRIBUTION

Defining the needs to represent all possible kinds of workloads.

Background Contribution Evaluation Contribution Scientific Needs Technical Needs

6 / 13

slide-7
SLIDE 7

SCIENTIFIC NEEDS Discrete workloads representation. Elastic Tasks: Repeating identical microtasks (aka tasks, cloudlet) with fixed size. List of hosts to split workload. Hosts overusage detection.

Background Contribution Evaluation Contribution Scientific Needs Technical Needs

7 / 13

slide-8
SLIDE 8

TECHNICAL NEEDS Output function (for tasks workflows). Real traces of requests (e.g. apache). Detailed platform description (core feature of SimGrid).

Background Contribution Evaluation Contribution Scientific Needs Technical Needs

8 / 13

slide-9
SLIDE 9

EVALUATION

Implementation as a SimGrid Plugin. ~400 lines of C++. Hosts overusage detection not fully implemented yet.

Background Contribution Evaluation Evaluation Raw Performances Raw Performances Real Traces

9 / 13

slide-10
SLIDE 10

RAW PERFORMANCES

Background Contribution Evaluation Evaluation Raw Performances Raw Performances Real Traces

10 / 13

slide-11
SLIDE 11

RAW PERFORMANCES

Background Contribution Evaluation Evaluation Raw Performances Raw Performances Real Traces

11 / 13

slide-12
SLIDE 12

REAL TRACES

Tested with the WorldCup 98 data access logs. One day with ~6 million requests is simulated in ~4 minutes. The parsing of the trace may be what takes a long time (file size: 43MB).

Background Contribution Evaluation Evaluation Raw Performances Raw Performances Real Traces

12 / 13

slide-13
SLIDE 13

SPECIFYING THE EXPERIMENTAL SCENARIOS FOR SIMULATED CLOUD STUDIES

Proposed a description of workloads to approach and ease the process of cloud simulations. Implemented the proposition and showed it was usable.

Further work:

Finish implementation of all functionalities. Reproduce papers' experiments. Simulate more complex applications like tasks workflow.

13 / 13