Outline What level of resource borrowing leads to user discom as long as t as long as significant fraction of users Outline Measure existing contention 1

Outline What level of resource borrowing leads to user discom as long as t as long as significant fraction of users  Outline Measure existing contention 1 www.phwiki.com

Outline What level of resource borrowing leads to user discom as long as t as long as significant fraction of users Outline Measure existing contention 1

Myers, Steven, Managing Editor has reference to this Academic Journal, PHwiki organized this Journal Ashish Gupta Bin Lin Peter Dinda Department of Computer Science Northwestern University Overview Our Goal Introduce resource borrowing in addition to its motivation Current model in addition to further possibilities What we want to study Methodology Actually try it out ! Design of a system which emulates resource borrowing in addition to captures feedback Design of our application What it does Extensive System Monitoring Resource Exercisers we have For technical details refer to paper in addition to tech report System Design – the client server system, creating in addition to analyzing testcases The controlled study What the user was asked to do, user details etc., set of testcases ( ramp in addition to step) Results Aggregated Context Person Frog in the pot Hardware Internet Wide Study Conclusions in addition to Results Outline Motivation behind Resource Borrowing Measuring user com as long as t System Design as long as Measuring User Com as long as t Controlled User Study Its Results Conclusions

Colorado Christian University US www.phwiki.com

This Particular University is Related to this Particular Journal

New Models of Distributed Computing Observation in addition to ideas Idea: Why not borrow the unused resources Effect of per as long as mance slowdown

Effect of per as long as mance slowdown The question we want to answer Depends on Other Factors as well What level of resource borrowing leads to user discom as long as t as long as significant fraction of users CPU RAM Disk

Context Person Hardware Others Power Users Typical Users Beginners

Outline Motivation behind Resource Borrowing Measuring user com as long as t System Design as long as Measuring User Com as long as t Controlled Study Its Results Conclusions How can we find this out Actually test it with user feedback A system as long as emulating resource borrowing in addition to measuring user discom as long as t using direct feedback http://com as long as t.cs.northwestern.edu How can we find this out Measure existing contention 1

How can we find this out Emulate Resource Borrowing Real Contention Borrowed Contention Final Contention 2 % CPU Usage vs. Time How can we find this out Allow User Feedback 3 F11 How can we find this out Find MAX Level of tolerable contention Borrowed Contention Final Contention 4 % CPU Usage vs. Time

How is it useful To find a quantitative relationship between resource borrowing in addition to user com as long as t Com as long as t = f (Contention) How is it useful Enhances the degree of workstation sharing Interactivity Aware Scheduling More intelligent scheduling of interactive tasks possible via user feedback in addition to our results

Outline Motivation behind Resource Borrowing Measuring user com as long as t System Design as long as Measuring User Com as long as t Controlled Study Its Results Conclusions Testcase Transfer Results Transfer Server Client Resource borrowing using testcase profile Can do large scale user studies in addition to maintain testcase control over wide-area The client design

Myers, Steven Natural Products Insider Managing Editor www.phwiki.com

Testcases Each testcase stores details of resource borrowing Testcase consists of exercise functions as long as each resource Exercise function is a vector of contention values Example: CPU contention: [0,0.5,1.0,1.5,2.0] at 1 Hz Exercise Functions Time Contention Exercise Function 1 Exercise Function 2 Exercise Function 3 Exercise Function 4 Has all sort of strange exercise functions Power-law, exp, pareto Plot our real testcases Flowchart of Testcase Execution No Testcase running

Resource Exercisers CPU Exerciser Contention describes the expected extra number of threads in ready queue Fractional resource borrowing using stochastic scheduling methods Validated to contention level of 10 Disk Exerciser R in addition to om seek in addition to read/write in a large file (twice the memory) Validated to contention level of 7 Memory Exerciser Borrows a fraction of physical memory: from 0 to 1 Outline Motivation behind Resource Borrowing Measuring user com as long as t System Design as long as Measuring User Com as long as t Controlled Study Its Results Conclusions The control study description 33 undergrad in addition to grad students 1.5 hrs each Each user was assigned 4 popular tasks to do MS Word MS Powerpoint MS Explorer searching in addition to saving in as long as mation Quake III

Underst in addition to ing Testcases CPU ramp 1 ramp 2 ramp 3 step 1 step 2 MEM ramp 1 ramp 2 ramp 3 step 1 step 2 Ramp Step Combination of Resources CPU Usage Memory Usage Hard Disk activity Network Traffic Com as long as t Zone surface

Myers, Steven Managing Editor

Myers, Steven is from United States and they belong to Natural Products Insider and they are from  Phoenix, United States got related to this Particular Journal. and Myers, Steven deal with the subjects like Organic and Natural Foods

Journal Ratings by Colorado Christian University

This Particular Journal got reviewed and rated by Colorado Christian University and short form of this particular Institution is US and gave this Journal an Excellent Rating.