2015 CWIC Developers Meeting February 19 th 2015 Calin Duma Doug Newman Service Level Agreements High-Availability,

Slides:



Advertisements
Similar presentations
Web Performance Tuning Lin Wang, Ph.D. US Department of Education Copyright [Lin Wang] [2004]. This work is the intellectual property of the author. Permission.
Advertisements

SERVICE LEVEL AGREEMENTS The Technical Contract Within the Master Agreement.
CWIC Start OpenSearch prototype January 28 th 2014 Calin Duma CWIC and GCMD OpenSearch Implementations.
Trace Analysis Chunxu Tang. The Mystery Machine: End-to-end performance analysis of large-scale Internet services.
CLOUD COMPUTING AN OVERVIEW & QUALITY OF SERVICE Hamzeh Khazaei University of Manitoba Department of Computer Science Jan 28, 2010.
WORKSHOP SLA SPECIFICATION BY ETIENNE WERY Lawyer at the Paris & Brussels Bar, Partner ULYS IT OUTSOURCING SUMMIT 27/11/2003.
Capacity Planning and Predicting Growth for Vista Amy Edwards, Ezra Freeloe and George Hernandez University System of Georgia 2007.
Task Scheduling and Distribution System Saeed Mahameed, Hani Ayoub Electrical Engineering Department, Technion – Israel Institute of Technology
Measuring Performance Chapter 12 CSE807. Performance Measurement To assist in guaranteeing Service Level Agreements For capacity planning For troubleshooting.
MCITP Guide to Microsoft Windows Server 2008 Server Administration (Exam #70-646) Chapter 14 Server and Network Monitoring.
Knowledge is Power Marketing Information System (MIS) determines what information managers need and then gathers, sorts, analyzes, stores, and distributes.
What Can You do With BTM? Business Transaction Management touches the following disciplines:  Performance Management  Application Management  Capacity.
RISK MANAGEMENT IN SOFTWARE ENGINEERING RISK MANAGEMENT IN SOFTWARE ENGINEERING Prepared by Prepared by Sneha Mudumba Sneha Mudumba.
Module 8: Monitoring SQL Server for Performance. Overview Why to Monitor SQL Server Performance Monitoring and Tuning Tools for Monitoring SQL Server.
Computer Systems Performance Evaluation CSCI 8710 Kraemer Fall 2008.
WGISS CNES SIT-30 Agenda Item 10 CEOS Action / Work Plan Reference 30 th CEOS SIT Meeting CNES Headquarters, Paris, France 31 st March – 1 st April 2015.
Types of Operating System
Intro Informatica Productivity Pack Save Time and Money while Increasing the Quality of Your PowerCenter Deployment Louis Hausle.
WGISS-37 Meeting Tuesday April 15 th 2014, 1:00PM CWIC-Smart A generic OpenSearch client Calin Duma Doug Newman
Slide: 1 CWIC Status Report Yonsook Enloe WGISS-39, Tsukuba May 13, 2015.
Chapter 4: What is an operating system?. What is an operating system? A program or collection of programs that coordinate computer usage among users and.
WGISS-37 Meeting Tuesday April 15 th 2014, 1:00PM CWIC-Smart and CWIC-Start Testing Calin Duma Doug Newman
CWIC Developers Meeting January 29 th 2014 Calin Duma Service Level Agreements High-Availability, Reliability and Performance.
Cluster Reliability Project ISIS Vanderbilt University.
Page 1 CSISS Center for Spatial Information Science and Systems Design and Implementation of CWIC Metrics Weiguo Han, Liping Di, Yuanzheng Shao, Lingjun.
Computing and the Web Operating Systems. Overview n What is an Operating System n Booting the Computer n User Interfaces n Files and File Management n.
Powered by 3PILLAR LABS HAILSTORM 4.0 TM PERFORMANCE REPORT.
Service Transition & Planning Service Validation & Testing
1 COMPSCI 110 Operating Systems Who - Introductions How - Policies and Administrative Details Why - Objectives and Expectations What - Our Topic: Operating.
Semantic Interoperability Berlin, 25 March 2008 Semantically Enhanced Resource Allocator Marc de Palol Jorge Ejarque, Iñigo Goiri, Ferran Julià, Jordi.
Data Tagging Architecture for System Monitoring in Dynamic Environments Bharat Krishnamurthy, Anindya Neogi, Bikram Sengupta, Raghavendra Singh (IBM Research.
Software Project Management Lecture # 3. Outline Chapter 22- “Metrics for Process & Projects”  Measurement  Measures  Metrics  Software Metrics Process.
CE Operating Systems Lecture 3 Overview of OS functions and structure.
Page 1 CSISS Center for Spatial Information Science and Systems CWIC Metrics: Current and Future Weiguo Han, Liping Di, Yuanzheng Shao, Lingjun Kang Center.
Ó 1998 Menascé & Almeida. All Rights Reserved.1 Part V Workload Characterization for the Web.
CWIC Developers Meeting January 28 th 2014 Calin Duma CSW and OpenSearch from the CWIC Start client perspective.
Slide: 1 CWIC Status Report Yonsook Enloe WGISS-40, Harwell UK Oct 1, 2015.
CMDBs: Above and Beyond…
Performance Testing Test Complete. Performance testing and its sub categories Performance testing is performed, to determine how fast some aspect of a.
CERN IT Department CH-1211 Genève 23 Switzerland t CERN IT Monitoring and Data Analytics Pedro Andrade (IT-GT) Openlab Workshop on Data Analytics.
TARGETED INTERNET ADVERTISING VIIANEN JONNE KAVÉN EETU.
Computer Science 5204 Operating Systems Fall, 2012 Dr. Dennis Kafura Course Overview 1.
1 Presented by: Val Pennell, Test Tool Manager Date: March 9, 2004 Software Testing Tools – Load Testing.
Spark on Entropy : A Reliable & Efficient Scheduler for Low-latency Parallel Jobs in Heterogeneous Cloud Huankai Chen PhD Student at University of Kent.
Enabling Grids for E-sciencE Agreement-based Workload and Resource Management Tiziana Ferrari, Elisabetta Ronchieri Mar 30-31, 2006.
Fundamental of Databases
What is Google Analytics?
OPERATING SYSTEMS CS 3502 Fall 2017
Operating Systems : Overview
Software Architecture in Practice
CWIC Status Report Yonsook Enloe yonsook. k.
Unified Modeling Language
WGISS Connected Data Assets Sept 26, 2017 Yonsook Enloe
Storage Virtualization
Software Project Planning &
Contents A GENERIC IT BALANCED SCORECARD
WGISS Connected Data Assets April 5, 2017 Yonsook Enloe
WGISS Connected Data Assets April 9, 2018 Yonsook Enloe
Operating Systems : Overview
CEOS WGISS INTEGRATED CATALOG (CWIC)
Operating Systems : Overview
Operating Systems : Overview
WGISS Connected Data Assets Oct 24, 2018 Yonsook Enloe
Software metrics.
Working With Cloud - 3.
ESIP Winter Meeting 2016 January 2016
Lecture Topics: 11/1 Hand back midterms
What’s Happening with my App, Application Insights?
WGISS Connected Data Assets Session Today
WGISS WGISS Connected Data Assets Status Report October, 2019 CWIC Team Eugene Yu (GMU), Archie Warnock (A/WWW), Li Lin (GMU)
Presentation transcript:

2015 CWIC Developers Meeting February 19 th 2015 Calin Duma Doug Newman Service Level Agreements High-Availability, Reliability and Performance

Agenda Why are we talking about SLAs again? What are SLAs Why use SLAs Joint SLOs / SLAs dependencies How to establish joint SLOs / SLAs CWIC data providers SLOs challenges Initial Sample Approach CWIC Smart Performance Metrics Approach CWIC Smart PROD metrics options Joint metrics to consider 2

Why are we talking about SLAs again? Revisit topic discussed last year: – CWIC, GCMD and CWIC-Smart made a lot of progress in terms of spearheading OpenSearch and facet specification compliance – We are individually collecting metrics and have some idea about the service levels that we are currently offering – We need to try to quantify them via individual and common metrics Ongoing CWIC-Smart performance tests: – Ongoing task to quantify CWIC-Smart performance (performance and throughput) under load – Translates into performance under load for CWIC and GCMD – Load is placed from ECHO workload environment to GCMD TEST (gcmddemo) and CWIC TEST (cwictest) – Need ability to infer production metrics based on workload metrics based on: TEST / WORKLOAD environment CPU, RAM and disk and network IO and PROD environments for all components (CWIC-Smart, GCMD and CWIC) Performance expectations for both GCMD and CWIC in each environment 3

What are SLAs Service Level Agreements: – Specify service level requirements between a service provider and a service consumer – Often in terms of a legal contract with penalties for non-compliance – Concrete and measurable Service Level Objectives (SLOs) are used to test that SLAs are being met In general there is a recognized gap between the expected service levels and the delivered ones: – Availability : downtime per year (ex 5 minutes translates to an SLO of % uptime) – Reliability : advertised components failure rates, can be mitigated by fault tolerant software and system design – Performance : response time (completion - submission) and throughput (concurrent requests) oriented SLOs Response times increase as throughput increases 4

Why use SLAs CWIC is gaining popularity and is providing world-wide exposure of data islands (India, China, Brazil etc.) We should provide outstanding end-user service: – Service consumers know what to expected when using GCMD, CWIC and CWIC Smart (and other clients) We should establish SLOs for our applications: – Involves hardware resources, infrastructure platforms (OS, Web Application stack) and custom code – Teams are motivated to work toward agreed upon targets – Can dictate and provide empirical data for future hardware and software needs 5

Joint SLOs / SLAs dependencies CWIC Smart depends on GCMD OpenSearch and CWIC OpenSearch CWIC depends on GCMD and 5 providers: –NASA, INPE, GHRSST, NOOA-NODC, USGSLSI, EUMETSAT and CCMEO In order to have availability, reliability and performance SLOs we would have to coordinate among 10 components: 1.CWIC Start 2.GCMD 3.CWIC 4.NASA / ECHO 5.INPE 6.GHRSST 7.NOOA-NODS 8.USGSLSI 9.EUMETSAT 10.CCMEO If any of the above components are down or slow the end-user will be subject to a sub-optimal experience Complexity will increase when more providers are added 6

How to establish joint SLOs / SLAs While usage of our services is free it doesn’t mean that we can’t provide a reasonable user experience and set realistic user expectations True joint SLOs / SLAs would be the SLO / SLA of the weakest component and therefore not desirable CWIC, GCMD, CWIC Smart and ECHO can work together on joint SLOs / SLAs CWIC can obtain existing provider SLAs where available, create basic ones from request/responses or help providers think about SLAs 7

CWIC data providers SLOs challenges Similar to ECHO’s challenges of dealing with its data partners ECHO model is something we can learn from: –Provide individual availability notices on the CWIC WGISS home page –If providers do not communicate down times or availability, collect statistics with monitoring technologies / APIs –Collect CWIC Smart and CWIC metrics that can capture current SLOs for all external dependencies* 8

Initial Sample Approach 9

CWIC Smart Performance Metrics Approach CWIC Smart objective: –Determine maximum throughput (concurrent requests) that does not decrease the average response time below x milliseconds Challenges: –Headless tests vs. browser tests –Environments where we can map concurrency to CPU / CPU cores otherwise we execute sequential requests –Framework (ror) concurrency: Global Interpreter Lock vs. jRuby JVM scheduled threads (green threads) –Result aggregation and analytics 10

CWIC Smart PROD metrics options Real User Monitoring Metrics (RUM): –Google Analytics (~26 subjects with hundreds of dimensions / specific descriptive attributes) –W3C Navigation Timing to complement GA –New Relic: excellent back end code instrumentation targeting SLAs and detailed performance metrics We added semantic logging and detailed durations on many events to make it easy to trace requests on a cluster Splunk reports can currently be used for analytics 11

Joint metrics to consider CWIC ExtJS application is an excellent start Questions to answer: –Who is using CWIC and GCMD OpenSearch (clientId) –Who is using CWIC OpenSearch without GCMD interaction –It is worth tracking browse and granule metadata and data downloads from CWIC Smart? –Percentage of direct downloads vs. provider welcome page redirects (based on provider) –Average response times 12

Joint metrics to consider cont. Questions to answer: –Number of errors due to provider internal errors –Number of errors due to CWIC internal errors –Number of errors due to provider unavailable –CWIC specific performance metrics per provider –GCMD specific performance metrics –Others? 13