Comprehensive Elastic Resource Management to Ensure Predictable - - PowerPoint PPT Presentation

▶
comprehensive elastic resource management to ensure
SMART_READER_LITE
LIVE PREVIEW

Comprehensive Elastic Resource Management to Ensure Predictable - - PowerPoint PPT Presentation

Feb 28, 2023 484 likes •684 views

Comprehensive Elastic Resource Management to Ensure Predictable Performance for Scientific Applications on Public IaaS Clouds. In Kee Kim , Jacob Steele, Yanjun Qi, Marty Humphrey CS@University of Virginia Motivation Goals Meet Job

slide-1
SLIDE 1

Comprehensive Elastic Resource Management to Ensure Predictable Performance for Scientific Applications

  • n Public IaaS Clouds.

In Kee Kim, Jacob Steele, Yanjun Qi, Marty Humphrey

CS@University of Virginia

slide-2
SLIDE 2

Motivation

  • Goals

– Meet Job Deadline – Low Cost

slide-3
SLIDE 3

[1] Schedule-based Scaling Static approach [2] Rule-based Scaling

  • Dynamic but Delays

– Reactive

  • Auto-Scaling
  • Scale Up – Job Deadline Satisfaction (High Demand)
  • Scale Down – Cost Efficiency (Low Demand)

Schedule-based Scaling T1 T2 T3 T1 Rule-based Scaling

Over Provisioning Under Provisioning Scale Up Delay Scale Down Delay

Current Approach

slide-4
SLIDE 4

Research Goal and Approach

4

  • In order to meet 1) user-defined job deadline and 2)

minimize execution cost for scientific applications that have highly variable job execution time, we design a Comprehensive Resource Management System by utilizing

  • Local Linear Regression-based Job Execution Time Prediction
  • Cost/Performance-Ratio based Resource Evaluation
  • Availability-Aware Job Scheduling and VM Scaling
slide-5
SLIDE 5

Outline

5

  • Motivation
  • Three approaches of LCA
  • Experiment
  • Conclusion
slide-6
SLIDE 6

LLR: Job Execution Time Prediction

  • Initial Intuition

– Job execution time has a linear relationship with IaaS/Application parameters

  • Data Collection (26 samples on 4 types of VMs) and Correlation Analysis
  • Local Linear Regression

Size of Data Type of VM Non-Data Intensive Operation 0.0973 (negligible) 0.7089 (strong) Data Intensive Operation 0.6129 (moderate) 0.3223 (weak)

Simple Linear Model → Cannot Produce Reliable Prediction

error

(a) Global Linear regression on m1.large (using all samples) (b) Local Linear Regression on m1.large (Using three samples)

Job Execution Time (sec.) Job Execution Time (sec.)

slide-7
SLIDE 7

Cost-Perf. Ratio-based Resource Evaluation

slide-8
SLIDE 8

Availability-Aware Job Scheduling

  • AAJS first assigns as many jobs as possible to current running VMs

based on CP evaluation results.

– Maximize machine utilization of current running VM instances. – Minimizing overhead from staring new VMs

  • Job Assignment Criteria

1) VM which has higher order (rank) in Cost/Performance ratio. 2) VM which offers earliest job completion time if multiple options available.

Queue Wait Time + New Job Exec Time

slide-9
SLIDE 9

Experiment Setup

  • Baselines

– SCS – MH [SC 2011] – SCS + LLR [NEW]

  • Implementation & Deploy

– LCA and 2 baselines on AWS

  • VM Types for Experiments
  • Workload Generation

# of Jobs 100 Watershed Delineation Jobs Job Deadline Mean Deadline STD DEV 30 min. 9.7 min. Job Duration Mean Duration STD DEV 15 min. 12.5 min.

(a) Steady (b) Bursty (c) Incremental (d) Random

Instance Type CPU/Mem Hourly Price m1.small 1/1.7G $0.091/Hr. m1.medium 1/3.7G $0.182/Hr. m1.large 2/7. 5G $0.364/Hr. m1.xlarge 4/15G $0.728/Hr.

slide-10
SLIDE 10

Job Exec. Time Predictor Performance

LLR LR kNN Mean

  • Avg. Predict. Acc.

78.77%

67.62% 65.38% 60.99% MAPE

0.2773

0.3901 0.5012 0.8254

LLR: Local Linear Regression, LR: Linear Regression, MAPE: Mean Absolute Percentage Error

slide-11
SLIDE 11

Job Deadline Satisfaction Rate

LCA: Average 83.25% of Job Deadline Satisfaction Rate

  • 9% better than SCS+LLR
  • 33% better than SCS
slide-12
SLIDE 12

Overall Running Cost

LCA: Average $8.9 of Overall Running Cost

  • $2.5 of cheaper than SCS+LLR
  • $5.2 of more expensive than SCS
  • (but performance is not comparable)
slide-13
SLIDE 13

Conclusion

  • LCA is a novel elastic resource management system for scientific

applications on public IaaS cloud based on three approaches:

[1] Local Linear Regression-based Job Execution Time Prediction [2] Cost-Performance Ratio-based Resource Evaluation [3] Availability-Aware Job Scheduling and VM Scaling

  • LCA has better performance than baselines (SCS, SCS with LLR) in Four

different workload patterns (Steady, Bursty, Incremental, Random).

– Predictor Performance: 11%-18% better accuracy – Job Deadline Satisfaction Rate: 9%-33% better rate – Overall Running Cost: $2.45 (22%) better cost efficiency

slide-14
SLIDE 14

Thank you & Questions?

slide-15
SLIDE 15

Back-up Slides

slide-16
SLIDE 16

LCA System Design

6

Job Scheduling & VM Scaling Prediction Module

LLR Predictor Job History Repository

Resource Evaluation

Cost-Performance Optimized Evaluation Request Samples Availability-Aware Job Scheduling and VM Scaling VM Manager Prediction Results VM Ranking & Selection VM Req, Job Assign Job + Deadline +/- VMs, Job Assignment Update Exe Info Results VMs on IaaS User

slide-17
SLIDE 17

VM Utilization

Startup Idle Job Running

LCA: Average 69.17% of VM Utilization

  • 25% higher than SCS + LLR
  • 11% higher than SCS
slide-18
SLIDE 18

VM Instance Types

  • TABLE. SPECIFICATION OF GENERAL PURPOSE MICROSOFT WINDOWS INSTANCES ON AMAZON EC2 IN

US EAST REGION (THE PRICE IS BASED ON MARCH 2014)

Instance Type ECU[1] CPU Cores Memory Hourly Price m1.small 1 1 1.7GB $0.091/Hr. m1.medium 2 1 3.7GB $0.182/Hr. m1.large 4 2 7.5GB $0.364/Hr. m1.xlarge 8 4 15GB $0.728/Hr.

1Single ECU (EC2 Compute Unit) provides the equivalent CPUI capacity of a 1.0-1.2 GHz

2007 Opteron or 2007 Xeon Processor

← Back to Slide – Experiment Setup