9
Cloud Resource Scheduling for Online and Batch Applications Kick-off meeting

Cloud Resource Scheduling for Online and Batch Applications Kick-off meeting

Embed Size (px)

Citation preview

Page 1: Cloud Resource Scheduling for Online and Batch Applications Kick-off meeting

Cloud Resource Scheduling for Online and Batch ApplicationsKick-off meeting

Page 2: Cloud Resource Scheduling for Online and Batch Applications Kick-off meeting

Project GoalDevelop a resource management

system that◦Deploy different types of jobs to

servers.◦Dynamically adjust the resource

allocation according to job workloads.

◦Meet the Service Level Agreement(SLA) of latency-sensitive jobs.

◦Minimize the cost. Penalty of violating SLA

Page 3: Cloud Resource Scheduling for Online and Batch Applications Kick-off meeting

Type of JobInteractive job

◦Latency-sensitive◦State-less◦Strict SLA

Batch job◦Consists of many (independent)

tasks.◦Soft deadline.

Page 4: Cloud Resource Scheduling for Online and Batch Applications Kick-off meeting

ExampleYouTube

◦Interactive: video streaming◦Batch: flow analysis

Phone billing system◦Interactive: rate querying/changing◦Batch: calculating the phone bill per

user.

Page 5: Cloud Resource Scheduling for Online and Batch Applications Kick-off meeting

Cost“Penalty”

◦The price we have to pay for violating the SLA.

Each job has different penalty rate.◦P( Ja ) = penalty rate( Ja ) * max(0, v),

Ja ∈ I v: percentage of SLA violation within a

time window

◦P( Jb ) = penalty rate ( Jb ) * max(0, d), Jb ∈ B d: difference between job completion

time and deadline.

Page 6: Cloud Resource Scheduling for Online and Batch Applications Kick-off meeting

Problem DefinitionGiven a set of batch job B, a set

of interactive job I, the number of processors m, and a penalty C. Is there a schedule to run all jobs with the total penalty no more than C?◦NP-complete◦Design heuristics to obtain schedule

with reasonable quality.

Page 7: Cloud Resource Scheduling for Online and Batch Applications Kick-off meeting

Processor AllocationEstimate the penalty of

interactive jobs on different number of processors.

Estimate the penalty of batch jobs on different number of processors.

Determine the number of processors for each job.◦With limit number of processors, find

the assignment that minimize the total penalty.

Page 8: Cloud Resource Scheduling for Online and Batch Applications Kick-off meeting

System Architecture

Page 9: Cloud Resource Scheduling for Online and Batch Applications Kick-off meeting

Implement the scheduling algorithm and evaluate the result.

Build the system on Docker / implement the scheduler in Kubernetes.

Consider other resources.◦Memory, network…etc.

To Do