Erlang and Scalability

Size: px
Start display at page:

Download "Erlang and Scalability"

Transcription

1 Erlang and Scalability Percona Performance 2009 Jan Henry Nystrom Course Introduction Course Course Author 2007

2 Introduction Scalability Killers Design Decisions Language and Yours Thinking Scalable/Parallel Code for the correct case Rules of Thumb Scalability in the small: SMP Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 2

3 Scalability Killers Synchronization Resource contention Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 3

4 Scalability Killers Synchronization Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 3

5 Design Decisions No sharing Processes Encapsulation No implicit synchronization Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 4

6 Design Decisions No implicit synchronization Spawn always succeed Sending always succeed Random access message buffer Fire and forget unless you need the synchronization Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 5

7 Design Decisions Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 6

8 Design Decisions Concurrency oriented programming Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 6

9 Design Decisions Concurrency oriented programming Concurrency support an integral part of the language Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 6

10 Design Decisions Concurrency oriented programming Concurrency support an integral part of the language Distribution support Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 6

11 Design Decisions Concurrency oriented programming Concurrency support an integral part of the language Distribution support Sets the focus firmly on the concurrent tasks Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 6

12 Design Decisions Concurrency oriented programming Concurrency support an integral part of the language Distribution support Sets the focus firmly on the concurrent tasks Code for the correct case Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 6

13 Design Decisions Concurrency oriented programming Concurrency support an integral part of the language Distribution support Sets the focus firmly on the concurrent tasks Code for the correct case Clear Code Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 6

14 Design Decisions Concurrency oriented programming Concurrency support an integral part of the language Distribution support Sets the focus firmly on the concurrent tasks Code for the correct case Clear Code Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 6

15 Design Decisions Concurrency oriented programming Concurrency support an integral part of the language Distribution support Sets the focus firmly on the concurrent tasks Code for the correct case Clear Code Clarity is King! Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 6

16 Design Decisions Concurrency oriented programming Concurrency support an integral part of the language Distribution support Sets the focus firmly on the concurrent tasks Code for the correct case Clear Code Clarity is King! Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 6

17 Design Decisions Concurrency oriented programming Concurrency support an integral part of the language Distribution support Sets the focus firmly on the concurrent tasks Code for the correct case Clear Code Clarity is King! I rather try to get clear code correct than correct code clear Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 6

18 Thinking Scalable/Parallel 0 Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 7

19 Thinking Scalable/Parallel List length: Obviously Linear 4 : But not when you have n processors? Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 7

20 Thinking Scalable/Parallel List length: O(logN) with sufficient processors Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 8

21 Thinking Scalable/Parallel List length: O(logN) with sufficient processors Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 8

22 Thinking Scalable/Parallel In the Erlang setting Do not introduce unneeded synchronization Remember processes are cheap Do not introduce unneeded synchronization A terminated process is all garbage Do not introduce unneeded synchronization Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 9

23 Code for the Correct Case Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 10

24 Code for the Correct Case set timer request set timer request set timer request Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 10

25 Code for the Correct Case set timer request set timer release timer check answer set timer release timer check answer request request answer release timer check Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 10

26 Code for the Correct Case set timer request set timer release timer check answer set timer release timer check answer request request answer release timer check Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 10

27 Code for the Correct Case Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 11

28 Code for the Correct Case set timer request request request Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 11

29 Code for the Correct Case set timer request request request answer Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 11

30 Rules of Thumb Rule 1 - All independent tasks should be processes Rule 2 - Do not invent concurrency that is not there! f() g() h() Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 12

31 Rules of Thumb Rule 1 - All independent tasks should be processes Rule 2 - Do not invent concurrency that is not there! f() g() h() Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 12

32 Rules of Thumb Rule 1 - All independent tasks should be processes Rule 2 - Do not invent concurrency that is not there! f() g() h(g(f())) h() Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 12

33 Rules of Thumb Rule 1 - All independent tasks should be processes Rule 2 - Do not invent concurrency that is not there! f() g() h() h(g(f())) h(g(f())) h(g(f())) h(g(f())) Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 12

34 Scalability in the small: SMP Erlang SMP Credo SMP should be transparent to the programmer in much the same way as Erlang Distribution You shouldn t have to think about it...but sometimes you must Use SMP mainly for stuff that you d make concurrent anyway Erlang uses concurrency as a structuring principle Model for the natural concurrency in your problem Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 13

35 Scalability in the small: SMP Erlang on multicore Big bang benchmark on Sunfire T2000 SMP prototype 97, First OTP release May 06. Mid -06 benchmark mimicking call handling (axdmark) on the (experimental) SMP emulator. Observed speedup/core: 0.95 First Ericsson product (TGC) released on SMP Erlang in Q scheduler Simultaneous processes 16 schedulers Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 14

36 Scalability in the small: SMP Case Study: Telephony Gateway Controller AXE TGC Mediates between legacy telephony and multimedia networks. Hugely complex state machines + massive concurrency. Developed in Erlang. Multicore version shipped to customer Q207. GW GW Porting from 1-core PPC to 2-core Intel took < 1 man-year (including testing). GW Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 15

37 Scalability in the small: SMP Case Study: Telephony Gateway Controller Traffic scenario IS/GCP 1slot/board IS/GEP Dual core One core running 2slots/board IS/GEP Dual core Two cores running 2slots/board AXD CPB5 AXD CPB6 POTS-POTS / AGW X call/sec 2.3X call/sec One core used 4.3X call/sec OTP R11_3 beta +patches 0.4X call/sec 2.1X call/sec ISUP-ISUP /Inter MGW 3.6X call/sec 7.7X call/sec One core used 13X call/sec OTP R11_3 beta +patches 1.55X call/sec 7.6X call/sec ISUP-ISUP /Intra MGW 5.5X call/sec 26X call/sec 3.17X call/sec 14X call/sec Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 16

38 Scalability in the small: SMP Case Study: Telephony Gateway Controller Traffic scenario IS/GCP 1slot/board IS/GEP Dual core One core running 2slots/board IS/GEP Dual core Two cores running 2slots/board AXD CPB5 AXD CPB6 POTS-POTS / AGW X call/sec 2.3X call/sec One core used 4.3X call/sec OTP R11_3 beta +patches 0.4X call/sec 2.1X call/sec ISUP-ISUP /Inter MGW 3.6X call/sec 7.7X call/sec One core used 13X call/sec OTP R11_3 beta +patches 1.55X call/sec 7.6X call/sec ISUP-ISUP /Intra MGW 5.5X call/sec 26X call/sec 3.17X call/sec 14X call/sec Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 16

39 Scalability in the small: SMP 5.00 Speedup on 4 Hyper Threaded Pentium4 Speddup # Schedulers Chatty 1000 processes created Each process randomly sends req/recieves ack from all other processes Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 17

40 Scalability in the small: SMP non-smp VM Erlang VM run queue Scheduler Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 18

41 Scalability in the small: SMP Current SMP VM OTP R11/R12 Erlang VM Scheduler #1 run queue Scheduler #2 Scheduler #N Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 19

42 Scalability in the small: SMP New SMP VM OTP R13 Erlang VM Scheduler #1run queue Released 21th April Scheduler #2 run queue migration logic Scheduler #N run queue Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 20

43 Scalability in the small: SMP Multiple run queues Speedup: Ca 0.43 * 32 cores Memory allocation locks dominate... Single run queue Speedup of Big Bang on a Tilera Tile64 chip (R13A) 1000 processes, all talking to each other Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 21

44 Scalability in the small: SMP Shift in Bottlenecks All scalable Erlang systems were stress tested for CPU usage for network usage With SMP hardware we must stress test for memory usage In the typical SMP system, the bottleneck has shifted from the CPU to the memory Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 22

45 Scalability in the small: SMP Death by a thousand cuts Many requests that generate short spikes in memory usage Limit or serialize those requests More on this in coming paper from CTO Ulf Wiger loop(state) -> receive {request, typea, Data} -> Data1 = allocate_lots_of_memory(data), a_server! {request, typea, self()}, receive {answer, Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 23

46 Questions??? Erlang and Scalability Percona Performance Conference , Erlang Training and Consulting 24

Accelerating Motif Finding in DNA Sequences with Multicore CPUs

Accelerating Motif Finding in DNA Sequences with Multicore CPUs Accelerating Motif Finding in DNA Sequences with Multicore CPUs Pramitha Perera and Roshan Ragel, Member, IEEE Abstract Motif discovery in DNA sequences is a challenging task in molecular biology. In computational

More information

Oracle Communications Billing and Revenue Management Elastic Charging Engine Performance. Oracle VM Server for SPARC

Oracle Communications Billing and Revenue Management Elastic Charging Engine Performance. Oracle VM Server for SPARC Oracle Communications Billing and Revenue Management Elastic Charging Engine Performance Oracle VM Server for SPARC Table of Contents Introduction 1 About Oracle Communications Billing and Revenue Management

More information

Deploying IBM Cognos 8 BI on VMware ESX. Barnaby Cole Practice Lead, Technical Services

Deploying IBM Cognos 8 BI on VMware ESX. Barnaby Cole Practice Lead, Technical Services Deploying IBM Cognos 8 BI on VMware ESX Barnaby Cole Practice Lead, Technical Services Agenda > Overview IBM Cognos 8 BI Architecture VMware ESX > Deployment Options > Our Testing > Optimization of VMware

More information

STAND: New Tool for Performance Estimation of the Block Data Processing Algorithms in High-load Systems

STAND: New Tool for Performance Estimation of the Block Data Processing Algorithms in High-load Systems STAND: New Tool for Performance Estimation of the Block Data Processing Algorithms in High-load Systems Victor Minchenkov, Vladimir Bashun St-Petersburg State University of Aerospace Instrumentation {victor,

More information

Optimizing Fine-grained Communication in a Biomolecular Simulation Application on Cray XK6

Optimizing Fine-grained Communication in a Biomolecular Simulation Application on Cray XK6 Optimizing Fine-grained Communication in a Biomolecular Simulation Application on Cray XK6 Yanhua Sun 1 Gengbin Zheng 1 Chao Mei 1 Eric J. Bohm 1 James C. Phillips 1 Terry Jones 2 Laxmikant(Sanjay) V.

More information

Windows Server Capacity Management 101

Windows Server Capacity Management 101 Windows Server Capacity Management 101 What is Capacity Management? ITIL definition of Capacity Management is: Capacity Management is responsible for ensuring that adequate capacity is available at all

More information

Challenges for Performance Analysis in High-Performance RC

Challenges for Performance Analysis in High-Performance RC Challenges for Performance Analysis in High-Performance RC July 20, 2007 Seth Koehler Ph.D. Student, University of Florida John Curreri Ph.D. Student, University of Florida Dr. Alan D. George Professor

More information

On Cloud Computational Models and the Heterogeneity Challenge

On Cloud Computational Models and the Heterogeneity Challenge On Cloud Computational Models and the Heterogeneity Challenge Raouf Boutaba D. Cheriton School of Computer Science University of Waterloo WCU IT Convergence Engineering Division POSTECH FOME, December

More information

July, 10 th From exotics to vanillas with GPU Murex 2014

July, 10 th From exotics to vanillas with GPU Murex 2014 July, 10 th 2014 From exotics to vanillas with GPU Murex 2014 COMPANY Selected Industry Recognition and Rankings 2013-2014 OVERALL #1 TOP TECHNOLOGY VENDOR #1 Trading Systems #1 Pricing & Risk Analytics

More information

Operating Systems. Scheduling

Operating Systems. Scheduling Operating Systems Fall 2014 Scheduling Myungjin Lee myungjin.lee@ed.ac.uk 1 Scheduling In discussing processes and threads, we talked about context switching an interrupt occurs (device completion, timer

More information

Secure High-Performance SOA Management with Intel SOA Expressway

Secure High-Performance SOA Management with Intel SOA Expressway Secure High-Performance SOA Management with Intel SOA Expressway A Report from SAP Co-Innovation Lab Intel: Blake Dournaee, William Jorns SAP: Canyang Kevin Liu, Joerg Nalik, Siva Gopal Modadugula April,

More information

OPERATING SYSTEMS. Systems and Models. CS 3502 Spring Chapter 03

OPERATING SYSTEMS. Systems and Models. CS 3502 Spring Chapter 03 OPERATING SYSTEMS CS 3502 Spring 2018 Systems and Models Chapter 03 Systems and Models A system is the part of the real world under study. It is composed of a set of entities interacting among themselves

More information

Improving Throughput and Utilization in Parallel Machines Through Concurrent Gang

Improving Throughput and Utilization in Parallel Machines Through Concurrent Gang Improving Throughput and Utilization in Parallel Machines Through Concurrent Fabricio Alves Barbosa da Silva Laboratoire ASIM, LIP6 Universite Pierre et Marie Curie Paris, France fabricio.silva@lip6.fr

More information

Real-Time Systems. Modeling Real-Time Systems

Real-Time Systems. Modeling Real-Time Systems Real-Time Systems Modeling Real-Time Systems Hermann Härtig WS 2013/14 Models purpose of models describe: certain properties derive: knowledge about (same or other) properties (using tools) neglect: details

More information

ORACLE DATABASE PERFORMANCE: VMWARE CLOUD ON AWS PERFORMANCE STUDY JULY 2018

ORACLE DATABASE PERFORMANCE: VMWARE CLOUD ON AWS PERFORMANCE STUDY JULY 2018 ORACLE DATABASE PERFORMANCE: VMWARE CLOUD ON AWS PERFORMANCE STUDY JULY 2018 Table of Contents Executive Summary...3 Introduction...3 Test Environment... 4 Test Workload... 6 Virtual Machine Configuration...

More information

Microsoft Dynamics AX 2012 Day in the life benchmark summary

Microsoft Dynamics AX 2012 Day in the life benchmark summary Microsoft Dynamics AX 2012 Day in the life benchmark summary In August 2011, Microsoft conducted a day in the life benchmark of Microsoft Dynamics AX 2012 to measure the application s performance and scalability

More information

Starfish CM Dashboard

Starfish CM Dashboard Real-time Visibility into Communication Systems Vital Signs Knowledge is power especially in large, global enterprises that have complex and extensive communications systems and contact centers. In these

More information

Erlang Patterns Matching Business Needs. Torben Hoffmann CTO, Erlang

Erlang Patterns Matching Business Needs. Torben Hoffmann CTO, Erlang Erlang Patterns Matching Business Needs Torben Hoffmann CTO, Erlang Solutions torben.hoffmann@erlang-solutions.com @LeHoff & Idioms Erlang Patterns Matching Business Needs Torben Hoffmann CTO, Erlang Solutions

More information

Delivering High Performance for Financial Models and Risk Analytics

Delivering High Performance for Financial Models and Risk Analytics QuantCatalyst Delivering High Performance for Financial Models and Risk Analytics September 2008 Risk Breakfast London Dr D. Egloff daniel.egloff@quantcatalyst.com QuantCatalyst Inc. Technology and software

More information

Oracle PaaS and IaaS Universal Credits Service Descriptions

Oracle PaaS and IaaS Universal Credits Service Descriptions Oracle PaaS and IaaS Universal Credits Service Descriptions December 1, 2017 Oracle PaaS_IaaS_Universal_CreditsV120117 1 Metrics... 3 Oracle PaaS and IaaS Universal Credit... 8 Oracle PaaS and IaaS Universal

More information

1 Copyright 2011, Oracle and/or its affiliates. All rights reserved.

1 Copyright 2011, Oracle and/or its affiliates. All rights reserved. 1 Copyright 2011, Oracle and/or its affiliates. All rights ORACLE PRODUCT LOGO Virtualization and Cloud Deployments of Oracle E-Business Suite Ivo Dujmović, Director, Applications Development 2 Copyright

More information

Sizing SAP Hybris Billing, pricing simulation Consultant Information for Release 1.1 (et seq.) Document Version

Sizing SAP Hybris Billing, pricing simulation Consultant Information for Release 1.1 (et seq.) Document Version Sizing SAP Hybris Billing, pricing simulation Consultant Information for Release 1.1 (et seq.) Document Version 1.2 2016-06-15 www.sap.com TABLE OF CONTENTS 1. INTRODUCTION... 3 1.1 Functions of SAP SAP

More information

White paper A Reference Model for High Performance Data Analytics(HPDA) using an HPC infrastructure

White paper A Reference Model for High Performance Data Analytics(HPDA) using an HPC infrastructure White paper A Reference Model for High Performance Data Analytics(HPDA) using an HPC infrastructure Discover how to reshape an existing HPC infrastructure to run High Performance Data Analytics (HPDA)

More information

CPU Scheduling (Chapters 7-11)

CPU Scheduling (Chapters 7-11) CPU Scheduling (Chapters 7-11) CS 4410 Operating Systems [R. Agarwal, L. Alvisi, A. Bracy, M. George, E. Sirer, R. Van Renesse] The Problem You re the cook at State Street Diner customers continuously

More information

Increased Informix Awareness Discover Informix microsite launched

Increased Informix Awareness Discover Informix microsite launched Information Management Increased Informix Awareness Discover Informix microsite launched www.ibm.com/discoverinformix 2010 IBM Corporation Informix Panther Early Program Want to be on the cutting-edge

More information

Functional Programming In Real Life. Dr. Erik Stenman Director of Engineering Kreditor Europe AB

Functional Programming In Real Life. Dr. Erik Stenman Director of Engineering Kreditor Europe AB Functional Programming In Real Life Dr. Erik Stenman Director of Engineering Kreditor Europe AB 1 Introduction I will talk about KREDITOR, a company that bet it's future on Erlang a functional programming

More information

NVIDIA QUADRO VIRTUAL DATA CENTER WORKSTATION APPLICATION SIZING GUIDE FOR SIEMENS NX APPLICATION GUIDE. Ver 1.0

NVIDIA QUADRO VIRTUAL DATA CENTER WORKSTATION APPLICATION SIZING GUIDE FOR SIEMENS NX APPLICATION GUIDE. Ver 1.0 NVIDIA QUADRO VIRTUAL DATA CENTER WORKSTATION APPLICATION SIZING GUIDE FOR SIEMENS NX APPLICATION GUIDE Ver 1.0 EXECUTIVE SUMMARY This document provides insights into how to deploy NVIDIA Quadro Virtual

More information

The Need for a New Communications Architecture

The Need for a New Communications Architecture ISI Telemanagement Solutions, Inc. The Need for a New Communications Architecture Many of your customers today are using traditional communications architectures a wide variety of individual PBX s and

More information

CS3211 Project 2 OthelloX

CS3211 Project 2 OthelloX CS3211 Project 2 OthelloX Contents SECTION I. TERMINOLOGY 2 SECTION II. EXPERIMENTAL METHODOLOGY 3 SECTION III. DISTRIBUTION METHOD 4 SECTION IV. GRANULARITY 6 SECTION V. JOB POOLING 8 SECTION VI. SPEEDUP

More information

Principal Product Architect. ActiveDocs Opus IT System Administrators ActiveDocs Opus Evaluator

Principal Product Architect. ActiveDocs Opus IT System Administrators ActiveDocs Opus Evaluator ACTIVEDOCS OPUS TOPOLOGY AND PERFORMANCE Prepared by: Audience: Abstract: Chris Rust Principal Product Architect ActiveDocs Opus IT System Administrators ActiveDocs Opus Evaluator This document provides

More information

Platform-Based Design of Heterogeneous Embedded Systems

Platform-Based Design of Heterogeneous Embedded Systems Platform-Based Design of Heterogeneous Embedded Systems Ingo Sander Royal Institute of Technology Stockholm, Sweden ingo@kth.se Docent Lecture August 31, 2009 Ingo Sander (KTH) Platform-Based Design August

More information

TABLE OF CONTENTS CHAPTER NO. TITLE PAGE NO. ABSTRACT LIST OF TABLES LIST OF FIGURES LIST OF SYMBOLS AND ABBREVIATIONS

TABLE OF CONTENTS CHAPTER NO. TITLE PAGE NO. ABSTRACT LIST OF TABLES LIST OF FIGURES LIST OF SYMBOLS AND ABBREVIATIONS viii TABLE OF CONTENTS ABSTRACT LIST OF TABLES LIST OF FIGURES LIST OF SYMBOLS AND ABBREVIATIONS v xviii xix xxii 1. INTRODUCTION 1 1.1 MOTIVATION OF THE RESEARCH 1 1.2 OVERVIEW OF PROPOSED WORK 3 1.3

More information

GTC Using GPUs to Speedup Chip Verification. Tomer Ben-David, VP R&D

GTC Using GPUs to Speedup Chip Verification. Tomer Ben-David, VP R&D GTC-2012 Using GPUs to Speedup Chip Verification Tomer Ben-David, VP R&D The Verification Bottleneck Long verification process 66% of designs, verification takes 50% of the design cycle In ~40% of projects,

More information

Platform-Based Design of Heterogeneous Embedded Systems

Platform-Based Design of Heterogeneous Embedded Systems Platform-Based Design of Heterogeneous Embedded Systems Ingo Sander Royal Institute of Technology Stockholm, Sweden ingo@kth.se Docent Lecture August 31, 2009 Ingo Sander (KTH) Platform-Based Design August

More information

Oracle Financial Services Revenue Management and Billing V2.3 Performance Stress Test on Exalogic X3-2 & Exadata X3-2

Oracle Financial Services Revenue Management and Billing V2.3 Performance Stress Test on Exalogic X3-2 & Exadata X3-2 Oracle Financial Services Revenue Management and Billing V2.3 Performance Stress Test on Exalogic X3-2 & Exadata X3-2 O R A C L E W H I T E P A P E R J A N U A R Y 2 0 1 5 Table of Contents Disclaimer

More information

Triage: Balancing Energy and Quality of Service in a Microserver

Triage: Balancing Energy and Quality of Service in a Microserver Triage: Balancing Energy and Quality of Service in a Microserver Nilanjan Banerjee, Jacob Sorber, Mark Corner, Sami Rollins, Deepak Ganesan University of Massachusetts, Amherst University of San Francisco,

More information

An Oracle White Paper June Maximizing Performance and Scalability of a Policy Automation Solution

An Oracle White Paper June Maximizing Performance and Scalability of a Policy Automation Solution An Oracle White Paper June 2010 Maximizing Performance and Scalability of a Policy Automation Solution Executive Overview Most enterprises are now moving towards a modern IT architecture that is based

More information

Is Parallel Programming Hard, And If So, Why?

Is Parallel Programming Hard, And If So, Why? 2009 linux.conf.au Kernel Miniconf Is Parallel Programming Hard, And If So, Why? Paul E. McKenney IBM Distinguished Engineer & CTO Linux Linux Technology Center January 19, 2009 Copyright 2009 IBM 2002

More information

comp 180 Lecture 04 Outline of Lecture 1. The Role of Computer Performance 2. Measuring Performance

comp 180 Lecture 04 Outline of Lecture 1. The Role of Computer Performance 2. Measuring Performance Outline of Lecture 1. The Role of Computer Performance 2. Measuring Performance Summary The CPU time can be decomposed as follows: CPU time = Instructions --------------------------------- Program Clock

More information

Why more and more SAP customers are migrating to Solaris

Why more and more SAP customers are migrating to Solaris Why more and more SAP customers are migrating to Solaris Your SAP environment is critical to business operations. Migrating your SAP systems to Oracle Solaris delivers the availability, performance, scalability,

More information

Simplifying Hadoop. Sponsored by. July >> Computing View Point

Simplifying Hadoop. Sponsored by. July >> Computing View Point Sponsored by >> Computing View Point Simplifying Hadoop July 2013 The gap between the potential power of Hadoop and the technical difficulties in its implementation are narrowing and about time too Contents

More information

Simulation of Process Scheduling Algorithms

Simulation of Process Scheduling Algorithms International Journal of Engineering Science Invention ISSN (Online): 2319 6734, ISSN (Print): 2319 6726 Volume 6 Issue 11 November 2017 PP. 67-71 Simulation of Process Scheduling Algorithms Akanksha Verma

More information

CS510 Operating System Foundations. Jonathan Walpole

CS510 Operating System Foundations. Jonathan Walpole CS510 Operating System Foundations Jonathan Walpole Project 3 Part 1: The Sleeping Barber problem - Use semaphores and mutex variables for thread synchronization - You decide how to test your code!! We

More information

High Performance Computing(HPC) & Software Stack

High Performance Computing(HPC) & Software Stack IBM HPC Developer Education @ TIFR, Mumbai High Performance Computing(HPC) & Software Stack January 30-31, 2012 Pidad D'Souza (pidsouza@in.ibm.com) IBM, System & Technology Group 2002 IBM Corporation Agenda

More information

Adaptive Scheduling for Systems with Asymmetric Memory Hierarchies. Po-An Tsai, Changping Chen, and Daniel Sanchez

Adaptive Scheduling for Systems with Asymmetric Memory Hierarchies. Po-An Tsai, Changping Chen, and Daniel Sanchez Adaptive Scheduling for Systems with Asymmetric Memory Hierarchies Po-An Tsai, Changping Chen, and Daniel Sanchez Die-stacking has enabled near-data processing Die-stacking has enabled near-data processing

More information

Oracle Licensing in the Cloud. A Version Version 1 All Rights Reserved

Oracle Licensing in the Cloud. A Version Version 1 All Rights Reserved Oracle Licensing in the Cloud A Version 1 Whitepaper @Copyright 2017 Version 1 All Rights Reserved Contents Cloud types Oracle policies revisited Oracle s Cloud policy AWS/Azure Oracle Cloud Non-approved

More information

ANSYS FLUENT Performance Benchmark and Profiling. October 2009

ANSYS FLUENT Performance Benchmark and Profiling. October 2009 ANSYS FLUENT Performance Benchmark and Profiling October 2009 Note The following research was performed under the HPC Advisory Council activities Participating vendors: Intel, ANSYS, Dell, Mellanox Compute

More information

Machina Research White Paper for ABO DATA. Data aware platforms deliver a differentiated service in M2M, IoT and Big Data

Machina Research White Paper for ABO DATA. Data aware platforms deliver a differentiated service in M2M, IoT and Big Data Machina Research White Paper for ABO DATA Data aware platforms deliver a differentiated service in M2M, IoT and Big Data December 2013 Connections (billion) Introduction More and more businesses are making

More information

z Systems The Lowest Cost Platform

z Systems The Lowest Cost Platform z Systems The Lowest Cost Platform Using IT Economics (TCO) to prove that z Systems is in fact the lowest cost platform, with the highest QoS! David F. Anderson PE dfa@us.ibm.com June 24, 2016 Christopher

More information

Interactive presentation. E-commerce methodology

Interactive presentation. E-commerce methodology Interactive presentation E-commerce methodology 01/15/2015 Release with confidence Deliver a performance your customers expect and your team can be proud of. Tap into our 20+ years experience in QA and

More information

Features and benefits The Instant Connect Dispatch Console (Figure 1) is a state-of-the-art, end-to-end radio dispatching solution designed for missio

Features and benefits The Instant Connect Dispatch Console (Figure 1) is a state-of-the-art, end-to-end radio dispatching solution designed for missio Data Sheet Instant Connect Dispatch Console When communication is critical for your business and missions, YOU NEED INSTANT CONNECT. By providing scalable and reliable communications interoperability,

More information

Scalability. Microsoft Dynamics GP Performance Benchmark: 500 Concurrent Users with Microsoft SQL Server White Paper

Scalability. Microsoft Dynamics GP Performance Benchmark: 500 Concurrent Users with Microsoft SQL Server White Paper Scalability Microsoft Dynamics GP 2010 Performance Benchmark: 500 Concurrent Users with Microsoft SQL Server 2008 White Paper September 2010 Contents Executive Overview... 3 Benchmark Performance Overview...

More information

Homework 2: Comparing Scheduling Algorithms

Homework 2: Comparing Scheduling Algorithms Homework 2: Comparing Scheduling Algorithms The purpose of this homework is to build a scheduler to compare performance of a First In First Out (FIFO) versus Round Robin algorithms. The algorithms will

More information

Oracle Platform as a Service and Infrastructure as a Service Public Cloud Service Descriptions-Metered & Non-Metered.

Oracle Platform as a Service and Infrastructure as a Service Public Cloud Service Descriptions-Metered & Non-Metered. Oracle Platform as a Service and Infrastructure as a Service Public Cloud Service Descriptions-Metered & Non-Metered November 20, 2017 Contents GLOSSARY PUBLIC CLOUD SERVICES-NON-METERED... 9 API Call...

More information

Virtualizing Enterprise SAP Software Deployments

Virtualizing Enterprise SAP Software Deployments Virtualizing SAP Software Deployments A Proof of Concept by HP, Intel, SAP, SUSE, and VMware Solution provided by: The Foundation of V Virtualizing SAP Software Deployments A Proof of Concept by HP, Intel,

More information

Optimize the Performance of Your Cloud Infrastructure

Optimize the Performance of Your Cloud Infrastructure Optimize the Performance of Your Cloud Infrastructure AppFormix software leverages cutting-edge Intel Resource Director Technology (RDT) hardware features to improve cloud infrastructure monitoring and

More information

A Computer Controlled Multi-Analysis Titration System

A Computer Controlled Multi-Analysis Titration System A Computer Controlled Multi-Analysis Titration System by Dr Alexander C. Le Dain*, and Mr Tony White *Manager of Programming ICON Technologies Pty Ltd Category: Test and Quality Products Used: LabVIEW

More information

First, I d like to talk a bit about how I see

First, I d like to talk a bit about how I see Perspectives Enabling digital transformation through ALL CLOUD The global trend for digital transformation is driving enterprises to become fully digitized and digitally operated, and Huawei must pinpoint

More information

Bias Scheduling in Heterogeneous Multicore Architectures. David Koufaty Dheeraj Reddy Scott Hahn

Bias Scheduling in Heterogeneous Multicore Architectures. David Koufaty Dheeraj Reddy Scott Hahn Bias Scheduling in Heterogeneous Multicore Architectures David Koufaty Dheeraj Reddy Scott Hahn Motivation Mainstream multicore processors consist of identical cores Complexity dictated by product goals,

More information

Lecture 2: Project Management, Part 1: Requirements, WBS, Scheduling, and Risk Management. Prof. Shervin Shirmohammadi SITE, University of Ottawa

Lecture 2: Project Management, Part 1: Requirements, WBS, Scheduling, and Risk Management. Prof. Shervin Shirmohammadi SITE, University of Ottawa Lecture 2: Project Management, Part 1: Requirements, WBS, Scheduling, and Risk Management Prof. Shervin Shirmohammadi SITE, University of Ottawa Prof. Shervin Shirmohammadi ELG 4912 2-1 Goal of Project

More information

2/12/2008. Management Information Systems LEARNING OBJECTIVES. Computer Software Outline. Information Systems: Computer Software

2/12/2008. Management Information Systems LEARNING OBJECTIVES. Computer Software Outline. Information Systems: Computer Software Management Information Systems Information Systems: Computer Software Dr. Shankar Sundaresan (Adapted from Introduction to IS, Rainer and Turban) Computer Software Outline Significance of Software Systems

More information

Research Report. The Major Difference Between IBM s LinuxONE and x86 Linux Servers

Research Report. The Major Difference Between IBM s LinuxONE and x86 Linux Servers Research Report The Major Difference Between IBM s LinuxONE and x86 Linux Servers Executive Summary The most important point in this Research Report is this: mainframes process certain Linux workloads

More information

Architecture-Aware Cost Modelling for Parallel Performance Portability

Architecture-Aware Cost Modelling for Parallel Performance Portability Architecture-Aware Cost Modelling for Parallel Performance Portability Evgenij Belikov Diploma Thesis Defence August 31, 2011 E. Belikov (HU Berlin) Parallel Performance Portability August 31, 2011 1 /

More information

Introduction to the Transaction Processing Performance Council (TPC)

Introduction to the Transaction Processing Performance Council (TPC) Introduction to the Transaction Processing Performance Council (TPC) Robert M. Lane Performance, Availability & Architecture Engineering Sun Microsystems, Inc. Agenda Purpose of the TPC Membership Organization

More information

SOA Management with Integrated solution from SAP and Sonoa Systems

SOA Management with Integrated solution from SAP and Sonoa Systems SOA Management with Integrated solution from SAP and Sonoa Systems A report from SAP Co-Innovation Lab Sonoa Systems: Ravi Chandra, Co-Founder & VP of Engineering Kishore Sannidhanam, Business Development

More information

SATURN th Annual SEI Architecture Technology User Network Conference

SATURN th Annual SEI Architecture Technology User Network Conference 14 th Annual SEI Architecture Technology User Network Conference MAY 7 10, 2018 PLANO, TEXAS Charles Chow 1 Agenda Why Function As a Service (FaaS) Matters? Serverless Architecture and FaaS Based ERP Implementation

More information

Dive into nova scheduler performance

Dive into nova scheduler performance Dive into nova scheduler performance Where is the bottleneck? Cheng, Yingxin Contents Background Performance, Optimizations (58 simulated runs) Future Background Scheduler architecture Analysis methodology

More information

Optimized Virtual Resource Deployment using CloudSim

Optimized Virtual Resource Deployment using CloudSim Optimized Virtual Resource Deployment using CloudSim Anesul Mandal Software Professional, Aptsource Software Pvt. Ltd., A-5 Rishi Tech Park, New Town, Rajarhat, Kolkata, India. Kamalesh Karmakar Assistant

More information

Application of TTCN-3 for 2.5 and 3G Testing

Application of TTCN-3 for 2.5 and 3G Testing Application of TTCN-3 for 2.5 and 3G Testing dr. György Réthy Ericsson Test Competence Center +36(30) 297-7862 gyorgy.rethy@ericsson.com TTCN-3 3-5 th May 2004 Sophia Antipolis, France 1 3-5 th May 2004,

More information

Best Practices in NAVIS TOS Migration: Exolgan Case Study

Best Practices in NAVIS TOS Migration: Exolgan Case Study Best Practices in NAVIS TOS Migration: Exolgan Case Study Pablo Boulin, Exolgan Container Terminal CONNECT. COLLABORATE. INNOVATE. AGENDA Navis Migration Best Practices Overview Exolgan briefing SPARCS

More information

Design Guidelines and Visualization Support for Developing Parallel Real-Time Applications

Design Guidelines and Visualization Support for Developing Parallel Real-Time Applications Design Guidelines and Visualization Support for Developing Parallel Real-Time Applications Lars Lundberg Department of Computer Science and Business Administration, University College of Karlskrona/Ronneby,

More information

Sizing SAP Central Process Scheduling 8.0 by Redwood

Sizing SAP Central Process Scheduling 8.0 by Redwood Sizing SAP Central Process Scheduling 8.0 by Redwood Released for SAP Customers and Partners January 2012 Copyright 2012 SAP AG. All rights reserved. No part of this publication may be reproduced or transmitted

More information

Single Euro Payments Area

Single Euro Payments Area Single Euro Payments Area Background The Single Euro Payments Area (SEPA) is a payment-integration initiative of the European Union for simplification of bank transfers. As of March 2012, SEPA consists

More information

MySQL Helps Simply Accounting by Sage Increase Revenue, Market Share, and Customer Satisfaction

MySQL Helps Simply Accounting by Sage Increase Revenue, Market Share, and Customer Satisfaction MySQL Helps Simply Accounting by Increase Revenue, Market Share, and Customer Satisfaction Simply Accounting by Overview The Group plc, is one of the world-wide market leaders in accounting and business

More information

Introduction to Operating Systems. Process Scheduling. John Franco. Dept. of Electrical Engineering and Computing Systems University of Cincinnati

Introduction to Operating Systems. Process Scheduling. John Franco. Dept. of Electrical Engineering and Computing Systems University of Cincinnati Introduction to Operating Systems Process Scheduling John Franco Dept. of Electrical Engineering and Computing Systems University of Cincinnati Lifespan of a Process What does a CPU scheduler do? Determines

More information

Srinivasan Sundara Rajan MASTER Architect / Cloud Evangelist / Cloud Computing Journal Author

Srinivasan Sundara Rajan MASTER Architect / Cloud Evangelist / Cloud Computing Journal Author Architecting The Cloud Srinivasan Sundara Rajan MASTER Architect / Cloud Evangelist / Cloud Computing Journal Author Cloud Definition Definition Cloud Computing is a model for enabling convenient, on-demand

More information

Software Performance Estimation in MPSoC Design

Software Performance Estimation in MPSoC Design Software Performance Estimation in MPSoC Design Marcio Seiji Oyamada 1,2, Flávio Rech Wagner 1, Wander Cesario 2, Marius Bonaciu 2, Ahmed Jerraya 2 UFRGS 1 Instituto de Informática Porto Alegre, Brazil

More information

Introduction. Business

Introduction. Business Introduction CTAPPS MyCallSystem (MCS) is an ideal solution for medium to large organizations who wishes to have detailed information and advance billing to manage its telephones calls, lines transactions

More information

Optimizing resource efficiency in Microsoft Azure

Optimizing resource efficiency in Microsoft Azure Microsoft IT Showcase Optimizing resource efficiency in Microsoft Azure By July 2017, Core Services Engineering (CSE, formerly Microsoft IT) plans to have 90 percent of our computing resources hosted in

More information

International Journal of Scientific & Engineering Research, Volume 7, Issue 3, March ISSN

International Journal of Scientific & Engineering Research, Volume 7, Issue 3, March ISSN International Journal of Scientific & Engineering Research, Volume 7, Issue 3, March-2016 1026 LIFI BASED AUTOMATED SMART TROLLEY USING RFID V.Padmapriya 1, R.Sangeetha 2, R.Suganthi 3, E.Thamaraiselvi

More information

Sizing Contact Center Resources

Sizing Contact Center Resources Central to designing a Cisco Unified Contact Center (or any contact center) is the proper sizing of its resources. This chapter discusses the tools and methodologies needed to determine the required number

More information

An operating system executes a variety of programs: Batch system - jobs Time-shared systems - user programs or tasks

An operating system executes a variety of programs: Batch system - jobs Time-shared systems - user programs or tasks Process Concept An operating system executes a variety of programs: Batch system - jobs Time-shared systems - user programs or tasks Process - a program in execution; process execution must progress in

More information

The Manycore Shift. Microsoft Parallel Computing Initiative Ushers Computing into the Next Era

The Manycore Shift. Microsoft Parallel Computing Initiative Ushers Computing into the Next Era The Manycore Shift Microsoft Parallel Computing Initiative Ushers Computing into the Next Era Published: November 2007 Abstract When major qualitative shifts such as the emergence of the graphical user

More information

Prototype-based Software Architecture Evaluation Component Quality Attribute Evaluation

Prototype-based Software Architecture Evaluation Component Quality Attribute Evaluation Prototype-based Software Architecture Evaluation Component Quality Attribute Evaluation Frans Mårtensson, Håkan Grahn, and Michael Mattsson Department of Systems and Software Engineering School of Engineering

More information

Ensure Your Servers Can Support All the Benefits of Virtualization and Private Cloud The State of Server Virtualization... 8

Ensure Your Servers Can Support All the Benefits of Virtualization and Private Cloud The State of Server Virtualization... 8 ... 4 The State of Server Virtualization... 8 Virtualization Comfort Level SQL Server... 12 Case in Point SAP... 14 Virtualization The Server Platform Really Matters... 18 The New Family of Intel-based

More information

Building a Global BusinessObjects Shared Services Environment on VMware

Building a Global BusinessObjects Shared Services Environment on VMware Building a Global BusinessObjects Shared Services Environment on VMware Jay Palevsky, Global Program Manager, BI Architect Rob Isaacson, Global Project Manager, SAP BO Technical Lead Credit Suisse SESSION

More information

Event-Driven Thermal Management in SMP Systems

Event-Driven Thermal Management in SMP Systems Event-Driven Thermal Management in SMP Systems Andreas Merkel l Frank Bellosa l Andreas Weissel System Architecture Group University of Karlsruhe Second Workshop on Temperature-Aware Computer Systems June

More information

Moreno Baricevic Stefano Cozzini. CNR-IOM DEMOCRITOS Trieste, ITALY. Resource Management

Moreno Baricevic Stefano Cozzini. CNR-IOM DEMOCRITOS Trieste, ITALY. Resource Management Moreno Baricevic Stefano Cozzini CNR-IOM DEMOCRITOS Trieste, ITALY Resource Management RESOURCE MANAGEMENT We have a pool of users and a pool of resources, then what? some software that controls available

More information

Knowledge-Based Modeling Approach for Performance Measurement of Parallel Systems

Knowledge-Based Modeling Approach for Performance Measurement of Parallel Systems The International Arab Journal of Information Technology, Vol. 6, No. 1, January 2009 77 Knowledge-Based Modeling Approach for Performance Measurement of Parallel Systems Amit Chhabra and Gurvinder Singh

More information

BENEFITS & ADVANTAGES OF USING THE

BENEFITS & ADVANTAGES OF USING THE BENEFITS & ADVANTAGES OF USING THE INTRODUCTION Carrying a 35 year heritage in software development, Unixfor operates as a complete self service solution provider During the last 15+ years we are developing

More information

Cooperative Software: ETI Data System Library Products Allow Incompatible Systems to Exchange Information

Cooperative Software: ETI Data System Library Products Allow Incompatible Systems to Exchange Information Software Announcement April 4, 2000 Cooperative Software: ETI Data System Library Products Allow Incompatible Systems to Exchange Information Overview The ETI*Extract FX was introduced as part of the Developer

More information

1

1 VE7104/INTRODUCTION TO EMBEDDED CONTROLLERS MULTITASKING AND THE REAL-TIME OPERATING SYSTEM The challenges of multitasking and real-time, Achieving multitasking with sequential programming, RTOS, Scheduling

More information

INOView. Safety at a glance. Sicherheitstechnik GmbH

INOView. Safety at a glance. Sicherheitstechnik GmbH INOView Safety at a glance Sicherheitstechnik GmbH INOTEC Sicherheitstechnik GmbH Innovative emergency lighting technology INOTEC Sicherheitstechnik GmbH is a company with the target to create innovative

More information

SAP relies on Lenovo to help deliver the. next generation of cloud applications

SAP relies on Lenovo to help deliver the. next generation of cloud applications SOFTWARE SAP relies on Lenovo to help deliver the next generation of cloud applications Overview Thousands of enterprises are enjoying the benefits of new cloud-based software from SAP which in turn challenges

More information

Job Scheduling with Lookahead Group Matchmaking for Time/Space Sharing on Multi-core Parallel Machines

Job Scheduling with Lookahead Group Matchmaking for Time/Space Sharing on Multi-core Parallel Machines Job Scheduling with Lookahead Group Matchmaking for Time/Space Sharing on Multi-core Parallel Machines Xijie Zeng and Angela Sodan University of Windsor, Windsor ON N9B 3P4, Canada zengx@uwindsor.ca,acsodan@uwindsor.ca

More information

On the Feasibility of Dynamic Rescheduling on the Intel Distributed Computing Platform

On the Feasibility of Dynamic Rescheduling on the Intel Distributed Computing Platform On the Feasibility of Dynamic Rescheduling on the Intel Distributed Computing Platform Zhuoyao Zhang Linh T.X. Phan Godfrey Tan δ Saumya Jain Harrison Duong Boon Thau Loo Insup Lee University of Pennsylvania

More information

<Insert Picture Here> Coherence as a solution for ecommerce Capacity Absorption

<Insert Picture Here> Coherence as a solution for ecommerce Capacity Absorption Coherence as a solution for ecommerce Capacity Absorption A typical Scenario Commerce website growing at 25-30% annually Capacity growth is typically addressed horizontally w/ more

More information

An Oracle White Paper June Leveraging the Power of Oracle Engineered Systems for Enterprise Policy Automation

An Oracle White Paper June Leveraging the Power of Oracle Engineered Systems for Enterprise Policy Automation An Oracle White Paper June 2012 Leveraging the Power of Oracle Engineered Systems for Enterprise Policy Automation Executive Overview Oracle Engineered Systems deliver compelling return on investment,

More information

NX Nastran performance

NX Nastran performance NX Nastran performance White Paper What Siemens PLM Software is doing to enhance NX Nastran Siemens PLM Software s product development group enhances NX Nastran software in three key areas: by providing

More information

Sizing SAP Systems. Contents. 1 Introduction Sizing Methods Sizing Tools Quick Sizer Sizing Approaches...

Sizing SAP Systems. Contents. 1 Introduction Sizing Methods Sizing Tools Quick Sizer Sizing Approaches... Sizing SAP Systems Susanne Janssen, Ulrich Marquard Contents 1 Introduction... 3 Sizing Definition... 3 The Sizing Principle... 3 Business Management and Technology 4 Goals of This Book... 4 Target Group

More information