A Study on the Performance Measurement of Memory Hyun-Ju Song 1, Young-Hun Lee 2* 1 Dept. of Electronic Eng., Hannam University, Ojeong -dong, Daedeok-gu,

Slides:



Advertisements
Similar presentations
Database Software File Management Systems Database Management Systems.
Advertisements

Introduction to Systems Architecture Kieran Mathieson.
SESSION 7 MANAGING DATA DATARESOURCES. File Organization Terms and Concepts Field: Group of words or a complete number Record: Group of related fields.
Chapter 9 Overview  Reasons to monitor SQL Server  Performance Monitoring and Tuning  Tools for Monitoring SQL Server  Common Monitoring and Tuning.
Module 8: Monitoring SQL Server for Performance. Overview Why to Monitor SQL Server Performance Monitoring and Tuning Tools for Monitoring SQL Server.
Measuring zSeries System Performance Dr. Chu J. Jong School of Information Technology Illinois State University 06/11/2012 Sponsored in part by Deer &
Shilpa Seth.  Centralized System Centralized System  Client Server System Client Server System  Parallel System Parallel System.
Database Architecture Introduction to Databases. The Nature of Data Un-structured Semi-structured Structured.
Logging in Flash-based Database Systems Lu Zeping
Information Systems: Databases Define the role of general information systems Describe the elements of a database management system (DBMS) Describe the.
M1G Introduction to Database Development 6. Building Applications.
Copyright © 2010, Scryer Analytics, LLC. All rights reserved. Optimizing SAS System Performance − A Platform Perspective Patrick McDonald Scryer Analytics,
« Performance of Compressed Inverted List Caching in Search Engines » Proceedings of the International World Wide Web Conference Commitee, Beijing 2008)
Database Design and Management CPTG /23/2015Chapter 12 of 38 Functions of a Database Store data Store data School: student records, class schedules,
Frontiers in Massive Data Analysis Chapter 3.  Difficult to include data from multiple sources  Each organization develops a unique way of representing.
The Client/Server Database Environment Ployphan Sornsuwit KPRU Ref.
Intro – Part 2 Introduction to Database Management: Ch 1 & 2.
MANAGING SOFTWARE ASSETS ~ pertemuan 6 ~ Oleh: Ir. Abdul Hayat, MTI 1[Abdul Hayat, SIM, Semester Genap 2007/2008]
MANAGING DATA RESOURCES ~ pertemuan 7 ~ Oleh: Ir. Abdul Hayat, MTI.
Development of a Software Renderer for utilizing 3D Contents on a 2D-based Mobile System Sungkwan Kang 1, Joonseub Cha 2, Jimin Lee 1 and Jongan Park 1,
A Study of Secure Communications in WiFi Networks Bumjo Park 1 and Namgi Kim 11 1 Dept. Of Computer Science, Kyonggi Univ. San 94-1, Iui, Yeongtong, Suwon,
Effect Analysis of Electric Vehicle Charging to Smart Grid with Anti-Islanding Method Bum-Sik Shin, Kyung-Jung Lee, Sunny Ro, Young-Hun Ki and Hyun-Sik.
Applicability Analysis of Software Testing for Actual Operating Railway Software Jong-Gyu Hwang 1, Hyun-Jeong Jo 1, Baek-Hyun Kim 1, Jong-Hyun Baek 1 1.
Advanced Science and Technology Letters Vol.46 (Mobile and Wireless 2014), pp University Dedicated Next.
G046 Lecture 04 Task C Briefing Notes Mr C Johnston ICT Teacher
PRESENTATION TITLE GOES HERE Emerald NAS Extensions Chuck Paridon Performance Architect H-P Enterprise Data Contributed by Nick Principe – EMC, Demartek.
BLFS: Supporting Fast Editing/Writing for Large- Sized Multimedia Files Seung Wan Jung 1, Seok Young Ko 2, Young Jin Nam 3, Dae-Wha Seo 1, 1 Kyungpook.
Advanced Science and Technology Letters Vol.29 (ASEA 2013), pp Effectiveness of Memory according to.
The Design of Smart RFID Tag System for Food Poisoning Index Monitoring Chang Won Lee 1.1, Nghia Truong Van 1, Kyung Kwon Jung 2, Joo Woong Kim 1, Woo.
The Design of Smart Management System for Unmanned Clothing Stores Lin Sen ',', Chang Won Lee 2, Kyung Kwon Jung 3, Won Gap Choi 2 and Ki-Hwan Eom 2 '
Managing Data Resources File Organization and databases for business information systems.
Food Distribution Management System with the Smart RFID-PH Sensor Tag Chang Won Lee 1,1, So Young Park 1, Joo woongKim 1 and Ki-Hwan Eom 1 1 Department.
Chapter 1 Introduction.
Lecture 2: Performance Evaluation
Computer Science 2 What’s this course all about?
Advantages of ICT over Manual Methods of Processing Data
HPE Persistent Memory Microsoft Ignite 2017
The Client/Server Database Environment
Created by Kamila zhakupova
The Client/Server Database Environment
Development and Test of Simultaneous Power Analysis System for Three-Phase and Four-Wire Power System Hun Oh1, In Ho Ryu2 and Jeong-Chay Jeon3* 1Department.
Jong-Gyu Hwang1, Hyun-Jeong Jo1 , Baek-Hyun Kim1, Jong-Hyun Baek1
Efficient Load Balancing Algorithm for Cloud
ICT Database Lesson 1 What is a Database?.
PHP / MySQL Introduction
Query in Streaming Environment
YangSun Lee*, YunSik Son**
Study of Optical Interface for CCTV Camera
Storage Virtualization
Yunsik Son1, Seman Oh1, Yangsun Lee2
File Processing : Storage Media
Chapter 1: Introduction
Lecture 11: DMBS Internals
Tutorial 8 Objectives Continue presenting methods to import data into Access, export data from Access, link applications with data stored in Access, and.
Copyright © 2011 Pearson Education, Inc. Publishing as Pearson Addison-Wesley Chapter 2 Database System Concepts and Architecture.
Oracle Storage Performance Studies
Agenda Database Development – Best Practices Why Performance Matters ?
MANAGING DATA RESOURCES
File Processing : Storage Media
Building a Database on S3
Cloud computing mechanisms
Chap. 12 Memory Organization
Memory Organization.
Performance And Scalability In Oracle9i And SQL Server 2000
Performance And Scalability In Oracle9i And SQL Server 2000
Database System Architectures
UFCEUS-20-2 Web Programming
Request Units & Billing
Performance Measurement and Analysis
Efficient Migration of Large-memory VMs Using Private Virtual Memory
Presentation transcript:

A Study on the Performance Measurement of Memory Hyun-Ju Song 1, Young-Hun Lee 2* 1 Dept. of Electronic Eng., Hannam University, Ojeong -dong, Daedeok-gu, Daejon , Korea. Phone : * Dept. of Electronic Eng., Hannam University, Ojeong -dong, Daedeok-gu, Daejon , Korea Phone: , Author Abstract. In this paper, Performance comparative-analyzed used Tool accordingly that make up a total of two kinds of environments and created three kinds of conditions, and comparative-analyzed CO2 generated amount each of storage when experiment. Through this study result, when processing of low data I/O, use the product that using a HDD was judged beneficial. Used DRAM-SSD when stored and administered large amount data that is judged to be more effective which reduction in the time. Keywords: SAN, TPC-H, SSD, HDD, CO2 1 Introduction Recently, as the amount of data is bulky, study is increasing about storage device and technology that stored and quickly process data of large amount. Difference has occurred in the weak development speed of the HDD and processing speed of CPU, therefore, serious data input/output bottleneck has occurred. that was created to solve a problem is SSD. From the research of by applying HDD and SSD with storage, the difference of data I/O processing performance was progressed by comparing performance of storage device of each.[1-3] 2 Related Technology 2.1 MYSQL MYSQL is the relative database management system of open source that uses SQL which is standard database quality language, which is very fast, flexible, and easy to use. MYSQL offers client/server environment, and a server installed MYSQL has MYSQL daemon called mysqld, so client program connects via network by this daemon so that it can control data. [4] SoftTech 2013, ASTL Vol. 19, pp , © SERSC

Proceedings, The 2nd International Conference on Software Technology 2.2 TPC-H TPC-H is benchmarking tool that to measure how quickly can handle complex SQL. It defines 22 SQL statements and DB schema, and set of data about 1GB. TPC-H benchmark is public performance test that is used SQL that Business-oriented ad-hoc Query and concurrent data modifications made by the combination about large data. Fig. 1. Performance Structure of MYSQL 3 Experimental environment and conditions 3.1 Experimental conditions Postmark benchmark condition As shown in Table 1, performance analysis of HDD storage and DRAM-SSD storage were measured simultaneously power consumption as the target three kinds of standard measurement criteria (Low, Medium, High) of postmark. Measuring the Block Size = 4KB, File Size = 327KB measured at a fixed total of 10 times, the average was calculated. Table 1. Performance testing condition that using postmark Benchmark Postmark Test Level Test condition Subdirectory numberFile numberTransaction number Low1010,00050,000 Medium1030,00050,000 High10070,000100, TPC-H condition Using the TPC-H tool to analyze the performance of three-step procedure has changed compared with values from the final analysis. Load Test is the first step, which make up database and step data store to generate. But, performance analysis did not include results. Next, when Single active user in the Power Test is run the 228

A Study on the Performance Measurement of Memory Query that was analyzed by measuring the ability. Finally, when Multi active user in the Throughput Test is run Query at same time that was analyzed by measuring the ability. Power TEST and Throughput Test results have combined to analyze the performance of each storage device. Table 2 is conditions for the through test, figure 7 shows the results of the TPC-H applies will get the block diagram. Table 2. Conditions for Throughput Test Database capacityUser number 1GB2 5GB2 10GB3 4 Experiment 4.1 results and analysis using postmark Table 3 is result measuring total performance time during load occurs from each of level. Table 3. Postmark performance measurement results Postmark Test Level Test results(performance time : Sec) HDDDRAM-SSD Rate Low Medium High results and analysis using TPC-H Local environment Fig. 2. value in the Local environment 2 2 9

Proceedings, The 2nd International Conference on Software Technology As can be seen as a result of figure 2, value that can handle ad-hoc queries, find out the difference between less to handle ad-hoc query capabilities of HDD Storage and DRAM-SSD Storage in a small database capacity, but With increasing amount of data to the DRAM-SSD Storage HDD Storage for more than an hour to handle ad-hoc query capabilities that can be seen that much higher SAN environment Performance test results also at SAN environment, performance of storage were few difference in low load database capacity, but DRAM-SSD storage can be seen that much higher which per hour to handle ad-hoc query capabilities more than HDD storage when amounts of data is increasing. Per hour ad-hoc query capabilities known good HDD storage and DRAM-SSD storage regardless of the database capacity in a SAN environment than the Local environment.. Fig 3. value in the SAN environment 4.3 CO2 emission comparison Fig 4. CO2 ratio of HDD and DRAM-SSD CO2 emissions analysis result during analysis of performance of each storage using Postmark and TPC-H, as shown in Figure 4 5 Conclusion In this paper, we show the performance analysis results by looking for experiment in many ways DRAM-SSD and HDD. As a result of a postmark benchmark and TPC-H 230

A Study on the Performance Measurement of Memory analyzed about the HDD storage and DRAM-SSD storage for performance analysis, the performance difference of HDD and DRAM-SSD was little in low data I/O. But, the DRAM-SSD had a better performance than the HDD in large amounts of data I/O. References 1.Kyung-Hee Park, Jin-kyu Choe, Young-Hun Lee, Seung-Kook Cheong, Young-Sun Kim.: “Performance Analysis for DRAM-based SSD system”. Korean information technical academic society dissertation Vol. 7 Unit 4, pp. 41 – 47( ) 2.Yun-Hee Kang, Jin-Ho Yoo, Seung-Kook Cheong. “Performance Evaluation of the SSD based on DRAM Storage System IOPS”. Korean information technical academic society dissertation Vol. 7 Unit 1, pp. 265 – 272(2009) 3.Seung-Kook Cheong, Yong-Wan Jeong, Yong-Jin Jeong, Jae-jin Jeong. : “Input-Output Performance Analysis of HDD and DDR-SSD Storage under the Streaming Workload”. Korean information technical academic society dissertation. pp. 322 – 325( ) 4.Josb Judd and CbrisBeaucbamp, "Building SANs Witch Brocade," syngess, pp. 9-16, Nov