 +284,000,000,000 requests  5 different use cases  Workload characteristics, locality, cache effectiveness 1.

Slides:



Advertisements
Similar presentations
MEMCACHE FOR BIGINNERS
Advertisements

Tag line, tag line Perforce Benchmark with PAM over NFS, FCP & iSCSI Bikash R. Choudhury.
Characterizing and Evaluating a Key-value Store Application on Heterogeneous CPU-GPU Systems Tayler H. Hetherington ɣ Timothy G. Rogers ɣ Lisa Hsu* Mike.
Workloads Experimental environment prototype real sys exec- driven sim trace- driven sim stochastic sim Live workload Benchmark applications Micro- benchmark.
By: Chris Hayes. Facebook Today, Facebook is the most commonly used social networking site for people to connect with one another online. People of all.
1 10 Web Workload Characterization Web Protocols and Practice.
Interactive Analytical Processing in Big Data Systems: A Cross-Industry Study of MapReduce Workloads Jackie.
Thin Servers with Smart Pipes: Designing SoC Accelerators for Memcached Bohua Kou Jing gao.
Diagnostics. Module Objectives By the end of this module participants will be able to: Use diagnostic commands to troubleshoot and monitor performance.
Typical Caching Patterns Web Tier Data Storage SQL Data.
An Adaptable Benchmark for MPFS Performance Testing A Master Thesis Presentation Yubing Wang Advisor: Prof. Mark Claypool.
Web Caching Schemes1 A Survey of Web Caching Schemes for the Internet Jia Wang.
Improving Proxy Cache Performance: Analysis of Three Replacement Policies Dilley, J.; Arlitt, M. A journal paper of IEEE Internet Computing, Volume: 3.
Traffic Characteristics and Communication Patterns in Blogosphere A brilliant and insightful analysis of the access methods of the blogosphere community.
Accurate and Efficient Replaying of File System Traces Nikolai Joukov, TimothyWong, and Erez Zadok Stony Brook University (FAST 2005) USENIX Conference.
Fluxo: Simple Service Compiler Emre Kıcıman, Ben Livshits, Madanlal Musuvathi {emrek, livshits,
Progress Report 11/1/01 Matt Bridges. Overview Data collection and analysis tool for web site traffic Lets website administrators know who is on their.
Differentiated Multimedia Web Services Using Quality Aware Transcoding S. Chandra, C.Schlatter Ellis and A.Vahdat InfoCom 2000, IEEE Journal on Selected.
Module 8: Monitoring SQL Server for Performance. Overview Why to Monitor SQL Server Performance Monitoring and Tuning Tools for Monitoring SQL Server.
Towards Autonomic Hosting of Multi-tier Internet Services Swaminathan Sivasubramanian, Guillaume Pierre and Maarten van Steen Vrije Universiteit, Amsterdam,
Object-based Storage Long Liu Outline Why do we need object based storage? What is object based storage? How to take advantage of it? What's.
NETWORK CENTRIC COMPUTING (With included EMBEDDED SYSTEMS)
What makes Facebook do what it does? By Gavin Mais.
Performance of Web Applications Introduction One of the success-critical quality characteristics of Web applications is system performance. What.
RAMCloud: A Low-Latency Datacenter Storage System Ankita Kejriwal Stanford University (Joint work with Diego Ongaro, Ryan Stutsman, Steve Rumble, Mendel.
Module 10: Monitoring ISA Server Overview Monitoring Overview Configuring Alerts Configuring Session Monitoring Configuring Logging Configuring.
Uncovering the Multicore Processor Bottlenecks Server Design Summit Shay Gal-On Director of Technology, EEMBC.
Building a Parallel File System Simulator E Molina-Estolano, C Maltzahn, etc. UCSC Lab, UC Santa Cruz. Published in Journal of Physics, 2009.
Module 8: Implementing the Placement of Domain Controllers.
The HipHop Compiler from Facebook By Megha Gupta & Nikhil Kapoor.
MIS 424 Professor Sandvig. Overview  Why Analytics?  Two major approaches:  Server logs  Google Analytics.
Performance of HTTP Application in Mobile Ad Hoc Networks Asifuddin Mohammad.
RAMCloud: Low-latency DRAM-based storage Jonathan Ellithorpe, Arjun Gopalan, Ashish Gupta, Ankita Kejriwal, Collin Lee, Behnam Montazeri, Diego Ongaro,
A Measurement Based Memory Performance Evaluation of High Throughput Servers Garba Isa Yau Department of Computer Engineering King Fahd University of Petroleum.
User Log Analyzing Algorithm Simulator 491 May15-11.
Microsoft Research1 Characterizing Alert and Browse Services for Mobile Clients Atul Adya, Victor Bahl, Lili Qiu Microsoft Research USENIX Annual Technical.
Optimizer Deployment Centralized Database module on Optimizer hub server Each monitored server has an instance of optimizer installed.
CS 140 Lecture Notes: Technology and Operating Systems Slide 1 Technology Changes Mid-1980’s2012Change CPU speed15 MHz2.5 GHz167x Memory size8 MB4 GB500x.
© 2005 BEA Systems, Inc. | 1 Portal Server Cache Settings Plumtree (BEA ALUI) March, 2007.
Replicating Memory Behavior for Performance Skeletons Aditya Toomula PC-Doctor Inc. Reno, NV Jaspal Subhlok University of Houston Houston, TX By.
C-Hint: An Effective and Reliable Cache Management for RDMA- Accelerated Key-Value Stores Yandong Wang, Xiaoqiao Meng, Li Zhang, Jian Tan Presented by:
Enabling cache for monitoring application Alexandre Beche.
How to Build High Performance Apps Using Microsoft Azure Redis Cache
Search Engine using Web Mining COMS E Web Enhanced Information Mgmt Prof. Gail Kaiser Presented By: Rupal Shah (UNI: rrs2146)
PHP Performance w/APC + thaicyberpoint.com thaithinkpad.com thaihi5.com.
Dynamo: Amazon’s Highly Available Key-value Store DAAS – Database as a service.
Performance Testing Test Complete. Performance testing and its sub categories Performance testing is performed, to determine how fast some aspect of a.
MemcachedGPU Scaling-up Scale-out Key-value Stores Tayler Hetherington – The University of British Columbia Mike O’Connor – NVIDIA / UT Austin Tor M. Aamodt.
Presented By: Nick Koziol ISC110.  Had 1.19 billion members as of October  Largest social networking site in the world  Mark Zuckerberg  Many databases.
COMP2322 Lab 1 Introduction to Wireshark Weichao Li Jan. 22, 2016.
Scalable Data Scale #2 site on the Internet (time on site) >200 billion monthly page views Over 1 million developers in 180 countries.
Department of Computer Science 6 th Annual Austin CAS Conference – 24 February 2005 Ricardo Portillo, Diana Villa, Patricia J. Teller The University of.
Understanding Online Social Network Usage from a Network Perspective F. Schneider et al (T-Labs, AT&T) Internet Measurement Conference 2009 Networking.
Cloud Computing: Pay-per-Use for On-Demand Scalability Developing Cloud Computing Applications with Open Source Technologies Shlomo Swidler.
Improve query performance with the new SQL Server 2016 query store!! Michelle Gutzait Principal Consultant at
Taeho Kgil, Trevor Mudge Advanced Computer Architecture Laboratory The University of Michigan Ann Arbor, USA CASES’06.
A Practical Performance Analysis of Stream Reuse Techniques in Peer-to-Peer VoD Systems Leonardo B. Pinho and Claudio L. Amorim Parallel Computing Laboratory.
Midterm Review October Closed book one hand written page of notes of your own making October Closed book one hand written page of notes of.
A Comparison of File System Workloads D. Roselli J. Lorch T. Anderson University of California, Berkeley.
Memshare: a Dynamic Multi-tenant Key-value Cache
Measurement-based Design
Technology Vocabulary Words
An Analysis of Facebook photo Caching
Local secondary storage (local disks)
OpenAFS Linux Performance Improvements in 1. 5/1
Load Balancing Memcached Traffic Using SDN
Transport Layer Identification of P2P Traffic
Your computer is the client
What’s Happening with my App, Application Insights?
Presentation transcript:

 +284,000,000,000 requests  5 different use cases  Workload characteristics, locality, cache effectiveness 1

2 Cache Servers Web Servers Database

 Understand workload characteristics  Identify factors affecting performance  Provide a benchmark for future studies 3

 Distributed memory caching system  Key-value store for small objects 4 Hash Function Memcached Servers Key

 Capture traces through a Linux Kernel Module (LKM)  Process traces with Hive 5 Memcached Transport (TCP/UDP) Network Ethernet LKM

6 PoolSizeDescription USRFewUser-account status information APPDozensObject metadata of a popular application SYSFewSystem data on service location VARDozensServer-side browser information ETCHundredsNonspecific, general purpose Contains server related information Anything that doesn’t belong to a specific pool goes to ETC

 Workload Characteristics  Locality, Cache Behavior 7

8 > 99.8% GET GET:UPDATE = 30:1

9 90% of VAR keys are 31B USR keys are 16B or 21B ETC is heterogeneous

10 USR values are only 2B 90% of values are smaller than 500B

11 90% of data is generated by values of 500B or smaller except ETC 90% is 10KB or smaller values for ETC

12 All pools show diurnal pattern except SYS

13 Night time in Western Semiphere North America starts its day

 Workload Characteristics  Locality, Cache Behavior 14

% of keys in 10% of requests in ETC 1% of keys in 55% of requests in ETC Least frequent 50% of keys in 1% of requests in ETC

16

% of SYS keys are reused in 1hr 88.5% of ETC keys are reused in 1hr 96.4% of ETC keys are reused in 6hr

%92.9%81.4% 93.7%98.7% Why?

19 CompulsoryCapacityInvalidation 70%22%8%

 Analyzed 5 different memcached use cases  Different applications of memcached have extreme variations in access patterns  Answered pertinent questions to improve Facebook’s memcached usage 20

 Questions? 21