Lessons from an Internet-Scale Notification System. Atul Adya
|
|
|
- Elisabeth Shaw
- 10 years ago
- Views:
Transcription
1 Lessons from an Internet-Scale Notification System Atul Adya
2 History End-client notification system Thialfi Presented at SOSP 2011 Since then: Scaled by several orders of magnitude Used by many more products and in different ways Several unexpected lessons
3 Case for Notifications Ensuring cached data is fresh across users and devices "Colin is online" Bob's browser Alice s Notebook Phil's phones
4 Common Pattern #1: Polling Did it change yet? Did it change yet? Did it change yet? Did it change yet? Did it change yet? Did it change yet? Did it change yet?... No! No! No! No! No! Yes! No! Cost and speed issues at scale: 100M clients polling at 10 minute intervals => 166K QPS
5 Common Pattern #2: App pushes updates over point-to-point channels Complicated for every app to build "Colin is online" Plumbing Fan out to endpoints Manage channels Ensure reliable delivery Bookkeeping object ids endpoints registrations cursors ACLs Pending HTTP GCM XMPP
6 Our Solution: Thialfi Scalable: handles hundreds of millions of clients and objects Fast: notifies clients in less than a second Reliable: even when entire data centers fail Easy to use and deploy: Chrome Sync (Desktop/Android), Google Plus, Contacts, Music, GDrive
7 Thialfi Programming Overview Register X Notify X Client C1 Client C2 Thialfi client library Client library Client Data center Notify X Register X Register X Update X Thialfi Service X: C1, C2 Update X Application backend
8 Thialfi Architecture Client Bigtable Registrations, notifications, acknowledgments Registrar HTTP/XMPP/GCM Client library Client Data center Notifications Object Bigtable Matcher Translation Bridge Application Backend Matcher: Object registered clients, version Registrar: Client ID registered object, unacked messages
9 Thialfi Abstraction Objects have unique IDs and version numbers, monotonically increasing on every update Delivery guarantee Registered clients learn latest version number Reliable signal only: cached object ID X at version Y (Think Cache Invalidation )
10 Thialfi Characteristics Built around soft-state Recover registration state from clients Lost notification signal: InvalidateUnknownVersion Registration-Sync: Exchange hash of registrations between client & server Helps in edge cases, async storage, cluster switch Multi-Platform: Libraries: C++, Java, JavaScript, Objective-C OS: Windows/Mac/Linux, browsers, Android, ios Channels: HTTP, XMPP, GCM, Internal-RPC
11 Some Lesions Ouch! I mean, Lessons
12 Lesson 1: Is this thing on? Launch your system and no one is using it How do I know it is working? People start using it Is it working now? Magically know works for % of the time Which %? How to distinguish among ephemeral, disconnected, and buggy clients You can never know
13 Lesson 1: Is this thing on? What s the best you can do? Continuous testing in production But may not be able to get client monitoring Look at server graphs End-to-end, e.g., latency More detailed, e.g., reg-sync per client type
14 Lesson 1: Is this thing on? But graphs are not sufficient Even when it looks right, averages can be deceptive How know if missing some traffic Have other ways of getting more reports: customer monitoring, real customers, Twitter,...
15 Lesson 2: And you thought you could debug? Monitoring indicates that there is a problem Server text logs: but hard to correlate Structured logging: may have to log selectively E.g., cannot log incoming stream multiple times Client logs: typically not available Monitoring graphs: but can be too many signals Specific user has problem (needle-in-a-haystack) Structured logging - if available Custom production code!
16 Customer unable to receive notifications Whole team spent hours looking Early on - debugging support was poor Text logs - had rolled over Structured logs - not there yet Persistent state - had no history Eventually got lucky War Story: VIP Customer Version numbers were timestamps Saw last notification version was very old Deflected the bug
17 Opportunity: Monitoring & Debugging Tools Automated tools to detect anomalies Machine-learning based? Tools for root-cause analysis Which signals to examine when problem occurs Finding needles in a haystack Dynamically switch on debugging for a needle E.g., trace a client s registration and notifications
18 Lesson 3: Clients considered harmful Started out: Offloading work to clients is good But, client code is painful: Maintenance burden of multiple platforms Upgrades: days, weeks, months, years never Hurts evolution and agility
19 War Story: Worldwide crash of Chrome on Android (alpha) Switched a flag to change message delivery via a different client code path Tested this path extensively with tests Unfortunately, our Android code did network access from the main thread on this path Newer versions of the OS than in our tests crashed the application when this happened
20 War Story: Strange Reg-Sync Loops Discovered unnecessary registrations for a (small) customer Some JavaScript clients in Reg-Sync loop Theories: Races, Bug - app, library, Closure,... Theory: HTTP clients switching too much Nope!
21 War Story: Buggy Platform Logged platform of every Reg-sync looping client Found 6.0 and that meant Safari Wrote test but failed to find bug Engineer searched for safari javascript runtime bug" Ran test in a loop SHA-1 hash not the same in all runs of loop! Safari JavaScript mis-jit i++ to ++i sometimes
22 Future direction: Thin client Move complexity to where it can be maintained Removing most code from client Trying to make library be a thin wrapper around API Planning to use Spanner (synchronous store) But still keeping soft-state aspects of Thialfi
23 Lesson 4: Getting your foot (code) in the door Developers will use a system iff it obviously makes things better than doing it on their own Clean semantics and reliability not the selling point you think they are Clients care about features not properties
24 Lesson 4: Getting your foot (code) in the door May need unclean features to get customers Best-effort data along with versions Support special object ids for users Added new server (Bridge) for translating messages Customers may not be able to meet your strong requirements Version numbers not feasible for many systems Allow time instead of version numbers
25 Lesson 4: Getting your foot (code) in the door Understand their architecture and review their code for integrating with your system Error path broken: invalidateunknownversion Naming matters: Changing to mustresync Know where your customer s code is - so that you can migrate them to newer infrastructure Debugging tools also needed for bug deflection
26 War Story: Thialfi is unreliable A team used Thialfi for reliable backup path to augment their unreliable fast path Experienced an outage when their fast path became really unreliable Informed us Thialfi was dropping notifications! Investigation revealed Under stress, backend dropped messages on their path and gave up publishing into Thialfi after few retries
27 Lesson 5: You are building your castle on sand You will do a reasonable job thinking through your own design, protocols, failures, etc Your outage is likely to come from a violation of one of your assumptions or another system several levels of dependencies away
28 War Story: Delayed replication in Chrome Sync Chrome backend dependency stopped sending notifications to Thialfi When it unwedged, traffic went up by more than 3X. We only had capacity for 2X Incoming feed QPS
29 War Story: Delayed replication in Chrome Sync Good news: Internal latency remained low and system did not fall over Bad news: End-to-end latency spiked to minutes for all customers Isolation not strong enough - not only Chrome Sync but all customers saw elevated latency
30 Opportunity: Resource Isolation Need the ability to isolate various customers from each other General problem for shared infrastructure services
31 War Story: Load balancer config change Thialfi needs clients to be stable w.r.t clusters Not globally reshuffle during a single-cluster outage Change to inter-cluster load balancer config to remove ad hoc cluster stickiness Previously discussed with owning team Config change caused large-scale loss of cluster stickiness for clients
32 War Story: Load balancer config change No. of active clients Client flapping between clusters caused an explosion in the number of active clients Same client was using resources many times over
33 Fix: Consistent hash routing Reverted load balancer config change Use consistent hashing for cluster selection Routed client based on client id Not geographically optimal
34 Opportunity: Geo-aware stable routing Stable : Client goes to same cluster for long periods of time Geographically-aware How to ensure clients are somewhat uniformlydistributed? How to add new clusters or shut down clusters (e.g., for maintenance)
35 Lesson 6: The customer is always right Customers will ask for anything and everything Tension between keeping system pure/ wellstructured and responding to customers needs C.f. Getting your foot in the door
36 Initial model: Lack of payload support (Model we had in SOSP 2011) Developers want reliable, in-order data delivery But, adds complexity to Thialfi and application Hard state, arbitrary buffering Offline applications flooded with data on wakeup For most applications, reliable signal is enough Invoke polling path on signal: simplifies integration
37 War Story: No payloads hurts Chrome Sync Logistics: Requires a cache to handle backend fetches Backend writers wanted one team to build a cache Technical: Lost updates with multi-master async stores No monotonically-increasing version Modify object in cluster A and B Need to get both updates to do conflict resolution But only get last update from one of them
38 Fix: Add payload support Expose a Pubsub-like API All updates sent to client No version numbers What about data problems mentioned earlier? System can throw away when too much data and send MustResync signal Clients required to fetch only with MustResync Still believe that reliable signal is the most important aspect of a notification system Data is just the icing on the cake
39 Lesson 6: Except when they are not Latency and SLAs If you ask, customers will tell you they need <100ms, % availability 5 minute response times when paged Lesson: Don t ask your customers Thialfi averages sec: seems to be fine
40 War Story: Unused big feature Important customer wanted large number of objects per client We wanted to scale in various dimensions Optimized architecture to never read all registrations together, never keep them in memory, etc. For Reg-Sync, added Merkle tree support But never shipped it... Most apps use few (one!) objects per client Why? Migrated from polling! Same customer ended up with few objects per client!
41 Lesson 7: You cannot anticipate the hard parts The initial Thialfi design spent enormous energy on making the notification path efficient Once we got into production, we added 100s of ms of batching for efficiency No one cared...
42 Lesson 7: You cannot anticipate the hard parts Hard parts of Thialfi actually are: Registrations: Getting client and data center to agree on registration state with asynchronous storage is tough Reg-Sync solved a number of edge cases Wide-area routing: Earliest Thialfi design ignored this issue completely Had to hack it in on the fly Took significant engineer effort to redo it properly
43 Lesson 7: You cannot anticipate the hard parts Client library and its protocol Did not pay attention initially: grew organically Had to redesign and rebuild this part completely Handling overload Admission control to protect a server Push back to previous server in pipeline Sometimes better to drop data and issue MustResync
44 Lesson summary 1. Is this thing is on? 2. And you thought you could debug 3. Clients considered harmful 4. Getting your foot (code) in the door 5. You are building your castle on sand 6. The customer is sometimes right 7. You cannot anticipate the hard parts
45 More Information Thialfi: A Client Notification Service for Internet-Scale Applications Atul Adya, Gregory Cooper, Daniel Myers, Michael Piatek SOSP 2011
46 Acknowledgements Engineers Interns Alumni Phil Bogle James Chacon Greg Cooper Matthew Harris Vishesh Khemani Nick Kline Colin Meek Daniel Myers Connor Brem Xi Ge Larry Kai Michael Piatek Naveen Sharma Shao Liu Kyle Marvin Joy Zhang
Thialfi: A Client Notification Service for Internet-Scale Applications
Thialfi: A Client Notification Service for Internet-Scale Applications Atul Adya Gregory Cooper Daniel Myers Michael Piatek {adya, ghc, dsmyers, piatek}@google.com Google, Inc. ABSTRACT Ensuring the freshness
Power Tools for Pivotal Tracker
Power Tools for Pivotal Tracker Pivotal Labs Dezmon Fernandez Victoria Kay Eric Dattore June 16th, 2015 Power Tools for Pivotal Tracker 1 Client Description Pivotal Labs is an agile software development
Scaling Web Applications in a Cloud Environment. Emil Ong Caucho Technology 8621
Scaling Web Applications in a Cloud Environment Emil Ong Caucho Technology 8621 2 AGENDA > This talk targets Java web developers and administrators interested in using cloud and enterprise virtualized
DevOps Best Practices for Mobile Apps. Sanjeev Sharma IBM Software Group
DevOps Best Practices for Mobile Apps Sanjeev Sharma IBM Software Group Me 18 year in the software industry 15+ years he has been a solution architect with IBM Areas of work: o DevOps o Enterprise Architecture
Smartphone Enterprise Application Integration
WHITE PAPER MARCH 2011 Smartphone Enterprise Application Integration Rhomobile - Mobilize Your Enterprise Overview For more information on optimal smartphone development please see the Rhomobile White
Web Application Deployment in the Cloud Using Amazon Web Services From Infancy to Maturity
P3 InfoTech Solutions Pvt. Ltd http://www.p3infotech.in July 2013 Created by P3 InfoTech Solutions Pvt. Ltd., http://p3infotech.in 1 Web Application Deployment in the Cloud Using Amazon Web Services From
Google Developer Group Perugia http://gdg-perugia.org. 16.11.2013 DevFest Central Italy @ Rome
Google Developer Group Perugia http://gdg-perugia.org 16.11.2013 DevFest Central Italy @ Rome Who am I? +EmanuelePalazzetti Manager Google Developer Group Perugia @palazzem github.com/emanuele-palazzetti
Enterprise Application Monitoring with
Enterprise Application Monitoring with 11/10/2007 Presented by James Peel [email protected] / www.altinity.com 1 Who am I? James Peel - [email protected] Job: Managing Director of Altinity
Designing Apps for Amazon Web Services
Designing Apps for Amazon Web Services Mathias Meyer, GOTO Aarhus 2011 Montag, 10. Oktober 11 Montag, 10. Oktober 11 Me infrastructure code databases @roidrage www.paperplanes.de Montag, 10. Oktober 11
What I Advise Every Customer To Do On Their Oracle SOA Projects
What I Advise Every Customer To Do On Their Oracle SOA Projects Save yourself future redesign by considering a few key elements when embarking on your new SOA project. By Javier Mendez & Ahmed Aboulnaga,
Update logo and logo link on A Master. Update Date and Product on B Master
Cover Be sure to: Update META data Update logo and logo link on A Master Update Date and Product on B Master Web Performance Metrics 101 Contents Preface...3 Response Time...4 DNS Resolution Time... 4
Kony Mobile Application Management (MAM)
Kony Mobile Application Management (MAM) Kony s Secure Mobile Application Management Feature Brief Contents What is Mobile Application Management? 3 Kony Mobile Application Management Solution Overview
Integrating Mobile apps with your Enterprise
Integrating Mobile apps with your Enterprise Jonathan Marshall [email protected] @jmarshall1 Agenda Mobile apps and the enterprise Integrating mobile apps with Enterprise Applications Mobile apps and
Lecture 3: Scaling by Load Balancing 1. Comments on reviews i. 2. Topic 1: Scalability a. QUESTION: What are problems? i. These papers look at
Lecture 3: Scaling by Load Balancing 1. Comments on reviews i. 2. Topic 1: Scalability a. QUESTION: What are problems? i. These papers look at distributing load b. QUESTION: What is the context? i. How
Microsoft SQL Server Always On Technologies
Microsoft SQL Server Always On Technologies Hitachi Data Systems Contributes Always On Storage Solutions A Partner Solutions White Paper By Rick Andersen and Simon Pengelly December 2006 Executive Summary
CA Application Performance Management Cloud Monitor
PRODUCT SHEET: CA APM Cloud Monitor CA Application Performance Management Cloud Monitor agility made possible CA Application Performance Management Cloud Monitor (CA APM Cloud Monitor) provides end-to-end
YouTube Vitess. Cloud-Native MySQL. Oracle OpenWorld Conference October 26, 2015. Anthony Yeh, Software Engineer, YouTube. http://vitess.
YouTube Vitess Cloud-Native MySQL Oracle OpenWorld Conference October 26, 2015 Anthony Yeh, Software Engineer, YouTube http://vitess.io/ Spoiler Alert Spoilers 1. History of Vitess 2. What is Cloud-Native
ZooKeeper. Table of contents
by Table of contents 1 ZooKeeper: A Distributed Coordination Service for Distributed Applications... 2 1.1 Design Goals...2 1.2 Data model and the hierarchical namespace...3 1.3 Nodes and ephemeral nodes...
ROCANA WHITEPAPER How to Investigate an Infrastructure Performance Problem
ROCANA WHITEPAPER How to Investigate an Infrastructure Performance Problem INTRODUCTION As IT infrastructure has grown more complex, IT administrators and operators have struggled to retain control. Gone
Exam : Oracle 1Z0-108. : Oracle WebLogic Server 10gSystem Administration. Version : DEMO
Exam : Oracle 1Z0-108 Title : Oracle WebLogic Server 10gSystem Administration Version : DEMO 1. Scenario : A single tier WebLogic cluster is configured with six Managed Servers. An Enterprise application
Apache Tomcat Clustering
Apache Tomcat Clustering Mark Thomas, Staff Engineer 2012 SpringSource, by VMware. All rights reserved Agenda Introductions Terminology When to cluster Components Configuration choices Debugging Questions
Session Storage in Zend Server Cluster Manager
Session Storage in Zend Server Cluster Manager Shahar Evron Technical Product Manager, Zend Technologies Welcome! All Phones are muted type your questions into the Webex Q&A box A recording of this session
New Relic & JMeter - Perfect Performance Testing
TUTORIAL New Relic & JMeter - Perfect Performance Testing by David Sale Contents Introduction 3 Demo Application 4 Hooking Into New Relic 4 What Is JMeter? 6 Installation and Usage 6 Analysis In New Relic
emontage: An Architecture for Rapid Integration of Situational Awareness Data at the Edge
emontage: An Architecture for Rapid Integration of Situational Awareness Data at the Edge Soumya Simanta Gene Cahill Ed Morris Motivation Situational Awareness First responders and others operating in
Eloquence Training What s new in Eloquence B.08.00
Eloquence Training What s new in Eloquence B.08.00 2010 Marxmeier Software AG Rev:100727 Overview Released December 2008 Supported until November 2013 Supports 32-bit and 64-bit platforms HP-UX Itanium
Informix Dynamic Server May 2007. Availability Solutions with Informix Dynamic Server 11
Informix Dynamic Server May 2007 Availability Solutions with Informix Dynamic Server 11 1 Availability Solutions with IBM Informix Dynamic Server 11.10 Madison Pruet Ajay Gupta The addition of Multi-node
PostgreSQL Backup Strategies
PostgreSQL Backup Strategies Austin PGDay 2012 Austin, TX Magnus Hagander [email protected] PRODUCTS CONSULTING APPLICATION MANAGEMENT IT OPERATIONS SUPPORT TRAINING Replication! But I have replication!
Top 10 Reasons why MySQL Experts Switch to SchoonerSQL - Solving the common problems users face with MySQL
SCHOONER WHITE PAPER Top 10 Reasons why MySQL Experts Switch to SchoonerSQL - Solving the common problems users face with MySQL About Schooner Information Technology Schooner Information Technology provides
Build Your Mobile Strategy Not Just Your Mobile Apps
Mobile Cloud Service Build Your Mobile Strategy Not Just Your Mobile Apps Copyright 2015 Oracle Corporation. All Rights Reserved. What is is it? Oracle Mobile Cloud Service provides everything you need
Designing a Cloud Storage System
Designing a Cloud Storage System End to End Cloud Storage When designing a cloud storage system, there is value in decoupling the system s archival capacity (its ability to persistently store large volumes
3. Broken Account and Session Management. 4. Cross-Site Scripting (XSS) Flaws. Web browsers execute code sent from websites. Account Management
What is an? s Ten Most Critical Web Application Security Vulnerabilities Anthony LAI, CISSP, CISA Chapter Leader (Hong Kong) [email protected] Open Web Application Security Project http://www.owasp.org
Test Driven Development Part III: Continuous Integration Venkat Subramaniam [email protected] http://www.agiledeveloper.com/download.
Test Driven Development Part III: Continuous Integration Venkat Subramaniam [email protected] http://www.agiledeveloper.com/download.aspx Abstract In this final part of the three part series on
ThreatSpike Dome: A New Approach To Security Monitoring
ThreatSpike Dome: A New Approach To Security Monitoring 2015 ThreatSpike Labs Limited The problem with SIEM Hacking, insider and advanced persistent threats can be difficult to detect with existing product
Best Practices for Web Application Load Testing
Best Practices for Web Application Load Testing This paper presents load testing best practices based on 20 years of work with customers and partners. They will help you make a quick start on the road
Sharp.Xmpp, a multiplatform.net XMPP client library, and Android
, a multiplatform.net XMPP client library, and Android Panagiotis (Takis) Stathopoulos https://twitter.com/panstath http://pgstath.me Presentation supported by the Greek Free/Open Source Software Society
Cisco TelePresence Management Suite Extension for Microsoft Exchange Version 4.0.3
Cisco TelePresence Management Suite Extension for Microsoft Exchange Version 4.0.3 Software Release Notes Revised September 2014 Contents Introduction 1 Changes to interoperability 1 Product documentation
Fast Data in the Era of Big Data: Tiwtter s Real-Time Related Query Suggestion Architecture
Fast Data in the Era of Big Data: Tiwtter s Real-Time Related Query Suggestion Architecture Gilad Mishne, Jeff Dalton, Zhenghua Li, Aneesh Sharma, Jimmy Lin Adeniyi Abdul 2522715 Agenda Abstract Introduction
co Characterizing and Tracing Packet Floods Using Cisco R
co Characterizing and Tracing Packet Floods Using Cisco R Table of Contents Characterizing and Tracing Packet Floods Using Cisco Routers...1 Introduction...1 Before You Begin...1 Conventions...1 Prerequisites...1
High Availability with Postgres Plus Advanced Server. An EnterpriseDB White Paper
High Availability with Postgres Plus Advanced Server An EnterpriseDB White Paper For DBAs, Database Architects & IT Directors December 2013 Table of Contents Introduction 3 Active/Passive Clustering 4
A Near Real-Time Personalization for ecommerce Platform Amit Rustagi [email protected]
A Near Real-Time Personalization for ecommerce Platform Amit Rustagi [email protected] Abstract. In today's competitive environment, you only have a few seconds to help site visitors understand that you
Highly Available Service Environments Introduction
Highly Available Service Environments Introduction This paper gives a very brief overview of the common issues that occur at the network, hardware, and application layers, as well as possible solutions,
Testing & Assuring Mobile End User Experience Before Production. Neotys
Testing & Assuring Mobile End User Experience Before Production Neotys Agenda Introduction The challenges Best practices NeoLoad mobile capabilities Mobile devices are used more and more At Home In 2014,
Complex Event Processing (CEP) Why and How. Richard Hallgren BUGS 2013-05-30
Complex Event Processing (CEP) Why and How Richard Hallgren BUGS 2013-05-30 Objectives Understand why and how CEP is important for modern business processes Concepts within a CEP solution Overview of StreamInsight
Appscend Mobile Platform Presentation Enterprise Solutions Whitepaper
Appscend Mobile Platform Presentation Enterprise Solutions Whitepaper The VAP License Appscend s Value Added Partner license is the best solution for large organizations in need of a unified mobile platform
PLA 7 WAYS TO USE LOG DATA FOR PROACTIVE PERFORMANCE MONITORING. [ WhitePaper ]
[ WhitePaper ] PLA 7 WAYS TO USE LOG DATA FOR PROACTIVE PERFORMANCE MONITORING. Over the past decade, the value of log data for monitoring and diagnosing complex networks has become increasingly obvious.
ios SDK possibilities & limitations
ios SDK possibilities & limitations Licensing Licensing Registered as an Apple Developer (free) Access to XCode3 and ios SDK ios, Mac and Safari Dev Center Resources No possibility of distribution of developed
Maximum Availability Architecture
Oracle Data Guard: Disaster Recovery for Sun Oracle Database Machine Oracle Maximum Availability Architecture White Paper April 2010 Maximum Availability Architecture Oracle Best Practices For High Availability
THE MOBlLE APP. REVOLUTlON. 8 STEPS TO BUlLDING MOBlLE APPS FAST ln THE CLOUD
THE MOBlLE APP REVOLUTlON 8 STEPS TO BUlLDING MOBlLE APPS FAST ln THE CLOUD People use hand-held devices for everything from communicating and playing games to shopping and surfing the Internet. In fact,
http://ubiqmobile.com
Mobile Development Made Easy! http://ubiqmobile.com Ubiq Mobile Serves Businesses, Developers and Wireless Service Providers Businesses Be among the first to enter the mobile market! - Low development
10 Best Practices for Application Performance Testing
Business white paper 10 Best Practices for Application Performance Testing Leveraging Agile Performance Testing for Web and Mobile Applications 10 Best Practices for Application Performance Testing Table
The Evolution of Load Testing. Why Gomez 360 o Web Load Testing Is a
Technical White Paper: WEb Load Testing To perform as intended, today s mission-critical applications rely on highly available, stable and trusted software services. Load testing ensures that those criteria
FioranoMQ 9. High Availability Guide
FioranoMQ 9 High Availability Guide Copyright (c) 1999-2008, Fiorano Software Technologies Pvt. Ltd., Copyright (c) 2008-2009, Fiorano Software Pty. Ltd. All rights reserved. This software is the confidential
High Availability Solutions for the MariaDB and MySQL Database
High Availability Solutions for the MariaDB and MySQL Database 1 Introduction This paper introduces recommendations and some of the solutions used to create an availability or high availability environment
Hadoop. History and Introduction. Explained By Vaibhav Agarwal
Hadoop History and Introduction Explained By Vaibhav Agarwal Agenda Architecture HDFS Data Flow Map Reduce Data Flow Hadoop Versions History Hadoop version 2 Hadoop Architecture HADOOP (HDFS) Data Flow
Scaling Graphite Installations
Scaling Graphite Installations Graphite basics Graphite is a web based Graphing program for time series data series plots. Written in Python Consists of multiple separate daemons Has it's own storage backend
Social Networks and the Richness of Data
Social Networks and the Richness of Data Getting distributed Webservices Done with NoSQL Fabrizio Schmidt, Lars George VZnet Netzwerke Ltd. Content Unique Challenges System Evolution Architecture Activity
Database FAQs - SQL Server
Database FAQs - SQL Server Kony Platform Release 5.0 Copyright 2013 by Kony, Inc. All rights reserved. August, 2013 This document contains information proprietary to Kony, Inc., is bound by the Kony license
Resource Utilization of Middleware Components in Embedded Systems
Resource Utilization of Middleware Components in Embedded Systems 3 Introduction System memory, CPU, and network resources are critical to the operation and performance of any software system. These system
Apache Tomcat. Load-balancing and Clustering. Mark Thomas, 20 November 2014. 2014 Pivotal Software, Inc. All rights reserved.
2 Apache Tomcat Load-balancing and Clustering Mark Thomas, 20 November 2014 Introduction Apache Tomcat committer since December 2003 [email protected] Tomcat 8 release manager Member of the Servlet, WebSocket
In depth study - Dev teams tooling
In depth study - Dev teams tooling Max Åberg mat09mab@ Jacob Burenstam Linder ada09jbu@ Desired feedback Structure of paper Problem description Inconsistencies git story explanation 1 Introduction Hypotheses
A Modern Approach to Monitoring Performance in Production
An AppDynamics Business White Paper WHEN LOGGING ISN T ENOUGH A Modern Approach to Monitoring Performance in Production Ten years ago, the standard way to troubleshoot an application issue was to look
Building Success on Acquia Cloud:
Building Success on Acquia Cloud: 10 Layers of PaaS TECHNICAL Guide Table of Contents Executive Summary.... 3 Introducing the 10 Layers of PaaS... 4 The Foundation: Five Layers of PaaS Infrastructure...
Monitoring Remedy with BMC Solutions
Monitoring Remedy with BMC Solutions Overview How does BMC Software monitor Remedy with our own solutions? The challenge is many fold with a solution like Remedy and this does not only apply to Remedy,
Cisco TelePresence Management Suite Extension for Microsoft Exchange Version 4.0
Cisco TelePresence Management Suite Extension for Microsoft Exchange Version 4.0 Software Release Notes May 2014 Contents Introduction 1 Changes to interoperability 1 Product documentation 1 New features
HIGH-SPEED BRIDGE TO CLOUD STORAGE
HIGH-SPEED BRIDGE TO CLOUD STORAGE Addressing throughput bottlenecks with Signiant s SkyDrop 2 The heart of the Internet is a pulsing movement of data circulating among billions of devices worldwide between
Globule: a Platform for Self-Replicating Web Documents
Globule: a Platform for Self-Replicating Web Documents Guillaume Pierre Maarten van Steen Vrije Universiteit, Amsterdam Internal report IR-483 January 2001 Abstract Replicating Web documents at a worldwide
CORD Monitoring Service
CORD Design Notes CORD Monitoring Service Srikanth Vavilapalli, Ericsson Larry Peterson, Open Networking Lab November 17, 2015 Introduction The XOS Monitoring service provides a generic platform to support
Using the Push Notifications Extension Part 1: Certificates and Setup
// tutorial Using the Push Notifications Extension Part 1: Certificates and Setup Version 1.0 This tutorial is the second part of our tutorials covering setting up and running the Push Notifications Native
SCALABILITY IN THE CLOUD
SCALABILITY IN THE CLOUD A TWILIO PERSPECTIVE twilio.com OUR SOFTWARE Twilio has built a 100 percent software-based infrastructure using many of the same distributed systems engineering and design principles
This talk is mostly about Data Center Replication, but along the way we'll have to talk about why you'd want transactionality arnd the Low-Level API.
This talk is mostly about Data Center Replication, but along the way we'll have to talk about why you'd want transactionality arnd the Low-Level API. Roughly speaking, the yellow boxes here represenet
Relational Databases in the Cloud
Contact Information: February 2011 zimory scale White Paper Relational Databases in the Cloud Target audience CIO/CTOs/Architects with medium to large IT installations looking to reduce IT costs by creating
Monitoring Best Practices for COMMERCE
Monitoring Best Practices for COMMERCE OVERVIEW Providing the right level and depth of monitoring is key to ensuring the effective operation of IT systems. This is especially true for ecommerce systems
Zero-Touch Drupal Deployment
Zero-Touch Drupal Deployment Whitepaper Date 25th October 2011 Document Number MIG5-WP-D-004 Revision 01 1 Table of Contents Preamble The concept Version control Consistency breeds abstraction Automation
AppConnect FAQ for MobileIron Technology Partners! AppConnect Overview
AppConnect FAQ for MobileIron Technology Partners! AppConnect Overview What is AppConnect? AppConnect is a MobileIron product that secures and protects enterprise mobile apps. It manages the complete lifecycle
Actualtests.C2010-508.40 questions
Actualtests.C2010-508.40 questions Number: C2010-508 Passing Score: 800 Time Limit: 120 min File Version: 5.6 http://www.gratisexam.com/ C2010-508 IBM Endpoint Manager V9.0 Fundamentals Finally, I got
Mini Project - Phase 3 Connexus Mobile App (Android)
Mini Project - Phase 3 Connexus Mobile App (Android) Click here to get Connexus apk. It is inside the shared folder Here is my github repository: https://github.com/azizclass/nimadini The 3 rd phase is
DISASTER RECOVERY WITH AWS
DISASTER RECOVERY WITH AWS Every company is vulnerable to a range of outages and disasters. From a common computer virus or network outage to a fire or flood these interruptions can wreak havoc on your
Unwired Revolution Gains Full Visibility into Enterprise Environments with Server Side and Mobile App Monitoring from New Relic.
At a Glance INDUSTRY Professional services LOCATION Phoenix, Arizona USE CASE Monitor performance of mobile apps designed for enterprise clients WHY NEW RELIC No firewall exceptions or additional servers
Apache Traffic Server Extensible Host Resolution
Apache Traffic Server Extensible Host Resolution at ApacheCon NA 2014 Speaker Alan M. Carroll, Apache Member, PMC Started working on Traffic Server in summer 2010. Implemented Transparency, IPv6, range
From Traditional Functional Testing to Enabling Continuous Quality in Mobile App Development
From Traditional Functional Testing to Enabling Continuous Quality in Mobile App Development Introduction Today s developers are under constant pressure to launch killer apps and release enhancements as
Cloud to Device Messaging with Voice Notification Using GCM
, October 21-23, 2015, San Francisco, USA Cloud to Device Messaging with Voice Notification Using GCM C. Tamilselvi, B. Vijaya Kumar Abstract: Push Messaging for Android devices are going to be implemented
This presentation covers virtual application shared services supplied with IBM Workload Deployer version 3.1.
This presentation covers virtual application shared services supplied with IBM Workload Deployer version 3.1. WD31_VirtualApplicationSharedServices.ppt Page 1 of 29 This presentation covers the shared
API Management Introduction and Principles
API Management Introduction and Principles by Vijay Alagarasan, Principal Architect, Enterprise Architecture and Strategy of Asurion Abstract: This article is focused on providing solutions for common
MOBILIZING ORACLE APPLICATIONS ERP. An Approach for Building Scalable Mobility Solutions. A RapidValue Solutions Whitepaper
MOBILIZING ORACLE APPLICATIONS ERP An Approach for Building Scalable Mobility Solutions A RapidValue Solutions Whitepaper TABLE OF CONTENTS Executive Overview Typical Architecture for Mobilizing Oracle
Responsive, resilient, elastic and message driven system
Responsive, resilient, elastic and message driven system solving scalability problems of course registrations Janina Mincer-Daszkiewicz, University of Warsaw [email protected] Dundee, 2015-06-14 Agenda
What Is Specific in Load Testing?
What Is Specific in Load Testing? Testing of multi-user applications under realistic and stress loads is really the only way to ensure appropriate performance and reliability in production. Load testing
