Capacity Planning Primer Dennis Shasha. Capacity Planning Arrival Rate –A1 is given as an assumption –A2 = (0.4 A1) + (0.5 A2) –A3 = 0.1 A2 Service Time.

Slides:



Advertisements
Similar presentations
Block LU Factorization Lecture 24 MA471 Fall 2003.
Advertisements

Scheduling. Main Points Scheduling policy: what to do next, when there are multiple threads ready to run – Or multiple packets to send, or web requests.
Silberschatz, Galvin and Gagne  2002 Modified for CSCI 399, Royden, Operating System Concepts Operating Systems Lecture 19 Scheduling IV.
Advanced Topics in Algorithms and Data Structures Lecture pg 1 Recursion.
Computer Organization and Architecture 18 th March, 2008.
12a.1 Introduction to Parallel Computing UNC-Wilmington, C. Ferner, 2008 Nov 4, 2008.
Crossbar Switches Crossbar switches are an important general architecture for fast switches. 2 x 2 Crossbar Switches A general N x N crossbar switch.
Multiple server queues In particular, we look at M/M/k Need to find steady state probabilities.
Waiting Lines Students should be able to:
Example 14.4 Queuing | 14.2 | 14.3 | 14.5 | 14.6 | 14.7 |14.8 | Background Information n Which system has the.
Data Communication and Networks Lecture 13 Performance December 9, 2004 Joseph Conron Computer Science Department New York University
Complexity 19-1 Parallel Computation Complexity Andrei Bulatov.
Chapter 18 Management of Waiting Lines
Processor 1 Processor 2 Disk 1 Disk 2 tasks Demo 1: Computer System with 2 Processors Sharing 2 Disks in Parallel.
1 Ardavan Asef-Vaziri Sep-09Operations Management: Waiting Lines3  Terminology: The characteristics of a queuing system is captured by five parameters:
Optimizing Cloud Resources for Delivering IPTV Services Through Virtualization.
Introduction to Management Science
McGraw-Hill/Irwin © 2003 The McGraw-Hill Companies, Inc., All Rights Reserved. Waiting Line Models.
1 Chapter 5 Flow Lines Types Issues in Design and Operation Models of Asynchronous Lines –Infinite or Finite Buffers Models of Synchronous (Indexing) Lines.
Supplement D Waiting Line Models Operations Management by R. Dan Reid & Nada R. Sanders 3rd Edition © Wiley 2005 PowerPoint Presentation by Roger B. Grinde,
 Birth Death Processes  M/M/1 Queue  M/M/m Queue  M/M/m/B Queue with Finite Buffers  Results for other Queueing systems 2.
Lecture 10: Queueing Theory. Queueing Analysis Jobs serviced by the system resources Jobs wait in a queue to use a busy server queueserver.
NETE4631:Capacity Planning (2)- Lecture 10 Suronapee Phoomvuthisarn, Ph.D. /
Multiplication Facts. 1 x3 3 Think Fast… 2 x4 8.
 Find the slope-intercept form, given a linear equation  Graph the line described the slope-intercept form  What is the relationship between the slopes.
Queueing Theory What is a queue? Examples of queues: Grocery store checkout Fast food (McDonalds – vs- Wendy’s) Hospital Emergency rooms Machines waiting.
Spreadsheet Models for Managers: Session 12 12/1 Copyright © Richard Brenner Spreadsheet Models for Managers Session 12 Service Systems Single-Server.
Supplement D Waiting Line Models
Time-Series Forecasting Overview Moving Averages Exponential Smoothing Seasonality.
5.2 – Solving Inequalities by Multiplication & Division.
P.5P.5 Solving Inequalities Algebraically and Graphically.
CSCI1600: Embedded and Real Time Software Lecture 19: Queuing Theory Steven Reiss, Fall 2015.
Technical Supplement 2 Waiting Line Models McGraw-Hill/Irwin Copyright © 2011 by the McGraw-Hill Companies, Inc. All rights reserved.
1 Ardavan Asef-Vaziri Sep-09Operations Management: Waiting Lines3 Example: The arrival rate to a GAP store is 6 customers per hour and has Poisson distribution.
Little’s Law & Operational Laws. Little’s Law Proportionality relation between the average number of jobs (E[N]) in a system and the average system time.
Delays  Deterministic Assumes “error free” type case Delay only when demand (known) exceeds capacity (known)  Stochastic Delay may occur any time Random.
Sandtids systemer 2.modul el. Henriks 1. forsøg m. Power Point.
Cs431-cotter1 Processes and Threads Tanenbaum 2.1, 2.2 Crowley Chapters 3, 5 Stallings Chapter 3, 4 Silberschaz & Galvin 3, 4.
Bushy Binary Search Tree from Ordered List. Behavior of the Algorithm Binary Search Tree Recall that tree_search is based closely on binary search. If.
Working in the clouds Making cloud computing work Brian Breslin CEO Infinimedia June 5, 2009.
Queueing Theory/Waiting Line: Models and Analysis Navneet Vidyarthi
Module D Waiting Line Models.
Server Machines By Brett Gunder COSC 101.
Software Architecture in Practice
CPE 619 Mean-Value Analysis
Queueing Theory What is a queue? Examples of queues:
Queuing Theory Non-Markov Systems
Course Description Algorithms are: Recipes for solving problems.
B.Ramamurthy Appendix A
Lecture on Markov Chain
Chapter 5 Designing Services.
Delays Deterministic Stochastic Assumes “error free” type case
System Performance: Queuing
Warm Up #3 1. Evaluate 5x + 2y for x = 2 and y = –4. 2 ANSWER
Supplement D Waiting Line Models
Multiplication Facts.
Amdahl's law.
By Brandon, Ben, and Lee Parallel Computing.
Lecture 13 – Queuing Systems
Delays Deterministic Stochastic Assumes “error free” type case
Planning and Scheduling
Queuing Analysis.
On average, there are 3(4.42) =13.26 claims waiting be processed.
PERFORMANCE MEASURES. COMPUTATIONAL MODELS Equal Duration Model:  It is assumed that a given task can be divided into n equal subtasks, each of which.
Congestion Control (from Chapter 05)
Waiting Line Models Waiting takes place in virtually every productive process or service. Since the time spent by people and things waiting in line is.
Course Description Algorithms are: Recipes for solving problems.
Congestion Control (from Chapter 05)
Chapter 2 Limits and the Derivative
Queueing Problem The performance of network systems rely on different delays. Propagation/processing/transmission/queueing delays Which delay is affected.
Presentation transcript:

Capacity Planning Primer Dennis Shasha

Capacity Planning Arrival Rate –A1 is given as an assumption –A2 = (0.4 A1) + (0.5 A2) –A3 = 0.1 A2 Service Time (S) –S1, S2, S3 are measured Utilization –U = A x S Response Time –R = U/(A(1-U)) = S/(1-U) (assuming Poisson arrivals) Entry (S1) 0.4 Search (S2) Checkout (S3) Getting the demand assumptions right is what makes capacity planning hard

Computing Arrival Rates Given the state transition graph and an assumed arrival rate in S1, we can determine arrival rates for the other states: A2 = (0.4 * A1) + (0.5 * A2) A3 = (0.1 * A2) So, solving this we get A2 = 0.8 A1 and A3 = 0.08 A1

How to Handle Multiple Servers Suppose one has n servers for some task that requires S time for a single server to perform. The perfect parallelism model is that it is as if one has a single server that is n times as fast. However, this overstates the advantage of parallelism, because even if there were no waiting, single tasks require S time.

Rough Estimate for Multiple Servers There are two components to response time: waiting time + service time. In the parallel setting, the service time is still S. The waiting time however can be well estimated by a server that is n times as fast.

Approximating waiting time for n parallel servers. Recall: R = U/(A(1-U)) = S/(1-U) On an n-times faster server, service time is divided by n, so the single processor utilization U is also divided by n. So we would get: Rideal = (S/n)/(1 – (U/n)). That Rideal = serviceideal + waitideal. So waitideal = Rideal – S/n Our assumption: wait for n processors is close to this waitideal.

Approximating response time for n parallel servers Waiting time for n parallel processors ~ (S/n)/(1 – (U/n)) – S/n = (S/n) ( 1/(1-(U/n)) – 1) = (S/(n(1 – U/n)))(U/n) = (S/(n – U))(U/n) So, response time for n parallel processors is above waiting time + S.

Example A = 8 per second. S = 0.1 second. U = 0.8. Single server response time = S/(1-U) = 0.1/0.2 = 0.5 seconds. If we have 2 servers, then we estimate waiting time to be (S/(n – U))(U/n) = (0.1/(2-0.8))(0.4) = 0.04/1.2 = So the response time is For a 2-times faster server, S = 0.05, U = 0.4, so response time is 0.05/0.6 =