Energy Efficient Web Server Cluster Andrew Krioukov, Sara Alspaugh, Laura Keys, David Culler, Randy Katz.

Slides:



Advertisements
Similar presentations
Sabyasachi Ghosh Mark Redekopp Murali Annavaram Ming-Hsieh Department of EE USC KnightShift: Enhancing Energy Efficiency by.
Advertisements

Sweet Storage SLOs with Frosting Andrew Wang, Shivaram Venkataraman, Sara Alspaugh, Ion Stoica, Randy Katz.
Performance Testing - Kanwalpreet Singh.
Energy in Cloud Computing and Renewable Energy
Daniel Schall, Volker Höfner, Prof. Dr. Theo Härder TU Kaiserslautern.
Walter Binder University of Lugano, Switzerland Niranjan Suri IHMC, Florida, USA Green Computing: Energy Consumption Optimized Service Hosting.
Energy-efficient Virtual Machine Provision Algorithms for Cloud System Ching-Chi Lin Institute of Information Science, Academia Sinica Department of Computer.
Enabling High-level SLOs on Shared Storage Andrew Wang, Shivaram Venkataraman, Sara Alspaugh, Randy Katz, Ion Stoica Cake 1.
Energy Conservation in Datacenters through Cluster Memory Management and Barely-Alive Memory Servers Vlasia Anagnostopoulou Susmit.
Green Cloud Computing Hadi Salimi Distributed Systems Lab, School of Computer Engineering, Iran University of Science and Technology,
KnightShift: Scaling the Energy Proportionality Wall Through Server-Level Heterogeneity Daniel WongMurali Annavaram University of Southern California MICRO-2012.
Shimin Chen Big Data Reading Group Presented and modified by Randall Parabicoli.
Datacenter Power State-of-the-Art Randy H. Katz University of California, Berkeley LoCal 0 th Retreat “Energy permits things to exist; information, to.
Exploring The Green Blade Ken Lutz University of California, Berkeley LoCal Retreat, June 8, 2009.
Design and Analysis of an Energy Agile Cluster Computing System Andrew Krioukov, Prashanth Mohan, Stephen Dawson- Haggerty, Sara Alspaugh, David Culler,
Adaptive Content Delivery for Scalable Web Servers Authors: Rahul Pradhan and Mark Claypool Presented by: David Finkel Computer Science Department Worcester.
DESIGN CONSIDERATIONS OF A GEOGRAPHICALLY DISTRIBUTED IAAS CLOUD ARCHITECTURE CS 595 LECTURE 10 3/20/2015.
Dynamic Process Allocation in Apache Server Yu Cai.
CS : Creating the Grid OS—A Computer Science Approach to Energy Problems David E. Culler, Randy H. Katz University of California, Berkeley August.
By- Jaideep Moses, Ravi Iyer , Ramesh Illikkal and
Energy Model for Multiprocess Applications Texas Tech University.
Energy Aware Network Operations Authors: Priya Mahadevan, Puneet Sharma, Sujata Banerjee, Parthasarathy Ranganathan HP Labs IEEE Global Internet Symposium.
Jiazhang Liu;Yiren Ding Team 8 [10/22/13]. Traditional Database Servers Database Admin DBMS 1.
CS 423 – Operating Systems Design Lecture 22 – Power Management Klara Nahrstedt and Raoul Rivas Spring 2013 CS Spring 2013.
Authors: Mateusz Jarus, Ewa Kowalczuk, Michał Madziar, Ariel Oleksiak, Andrzej Pałejko, Michał Witkowski Poznań Supercomputing and Networking Center GICOMP.
Load Balancing Dan Priece. What is Load Balancing? Distributed computing with multiple resources Need some way to distribute workload Discreet from the.
Green IT and Data Centers Darshan R. Kapadia Gregor von Laszewski 1.
Adaptive Control of Virtualized Resources in Utility Computing Environments HP Labs: Xiaoyun Zhu, Mustafa Uysal, Zhikui Wang, Sharad Singhal University.
Dynamic and Decentralized Approaches for Optimal Allocation of Multiple Resources in Virtualized Data Centers Wei Chen, Samuel Hargrove, Heh Miao, Liang.
XI HE Computing and Information Science Rochester Institute of Technology Rochester, NY USA Rochester Institute of Technology Service.
A Novel Adaptive Distributed Load Balancing Strategy for Cluster CHENG Bin and JIN Hai Cluster.
OPTIMAL SERVER PROVISIONING AND FREQUENCY ADJUSTMENT IN SERVER CLUSTERS Presented by: Xinying Zheng 09/13/ XINYING ZHENG, YU CAI MICHIGAN TECHNOLOGICAL.
Best Western Green Bay CHEMS 2013 SYSTEM ARCHITECTURE.
Cloud Computing Energy efficient cloud computing Keke Chen.
AUTHORS: STIJN POLFLIET ET. AL. BY: ALI NIKRAVESH Studying Hardware and Software Trade-Offs for a Real-Life Web 2.0 Workload.
EXPOSE GOOGLE APP ENGINE AS TASKTRACKER NODES AND DATA NODES.
Eneryg Efficiency for MapReduce Workloads: An Indepth Study Boliang Feng Renmin University of China Dec 19.
Architecture for Caching Responses with Multiple Dynamic Dependencies in Multi-Tier Data- Centers over InfiniBand S. Narravula, P. Balaji, K. Vaidyanathan,
Power-Aware Scheduling of Virtual Machines in DVFS-enabled Clusters
Energy Management in Virtualized Environments Gaurav Dhiman, Giacomo Marchetti, Raid Ayoub, Tajana Simunic Rosing (CSE-UCSD) Inside Xen Hypervisor Online.
How AWS Pricing Works Jinesh Varia Technology Evangelist.
Copyright © 2011, Performance Evaluation of a Green Scheduling Algorithm for Energy Savings in Cloud Computing Truong Vinh Truong Duy; Sato,
Dana Butnariu Princeton University EDGE Lab June – September 2011 OPTIMAL SLEEPING IN DATACENTERS Joint work with Professor Mung Chiang, Ioannis Kamitsos,
Data Replication and Power Consumption in Data Grids Susan V. Vrbsky, Ming Lei, Karl Smith and Jeff Byrd Department of Computer Science The University.
VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009.
Green Computing Metrics: Power, Temperature, CO2, … Computing system: Many-cores, Clusters, Grids and Clouds Algorithm and model: task scheduling, CFD.
Performance and Energy Efficiency Evaluation of Big Data Systems Presented by Yingjie Shi Institute of Computing Technology, CAS
XI HE Computing and Information Science Rochester Institute of Technology Rochester, NY USA Rochester Institute of Technology Service.
Accounting for Load Variation in Energy-Efficient Data Centers
Understanding Parallel Computers Parallel Processing EE 613.
Ensieea Rizwani An energy-efficient management mechanism for large-scale server clusters By: Zhenghua Xue, Dong, Ma, Fan, Mei 1.
Chapter 1 — Computer Abstractions and Technology — 1 Uniprocessor Performance Constrained by power, instruction-level parallelism, memory latency.
Jennifer Rexford Fall 2010 (TTh 1:30-2:50 in COS 302) COS 561: Advanced Computer Networks Energy.
CS203 – Advanced Computer Architecture Warehouse Scale Computing.
Cloud-based movie search web application with transaction service Group 14 Yuanfan Zhang Ji Zhang Zhuomeng Li.
Multi-mode Energy Management for Multi-tier Server Clusters Tibor Horvath Kevin Skadron University of Virginia PACT 2008.
Matthew Garrett Going green with Linux Matthew Garrett
Warehouse Scaled Computers
Measuring Performance II and Logic Design
Energy Aware Network Operations
Understanding and Improving Server Performance
Organizations Are Embracing New Opportunities
Green cloud computing 2 Cs 595 Lecture 15.
Chapter 6 Warehouse-Scale Computers to Exploit Request-Level and Data-Level Parallelism Topic 13 Using Energy Efficiently Inside the Server Prof. Zhang.
Be Fast, Cheap and in Control
Zhen Xiao, Qi Chen, and Haipeng Luo May 2013
Internet and Web Simple client-server model
Performance-Robust Parallel I/O
Presentation transcript:

Energy Efficient Web Server Cluster Andrew Krioukov, Sara Alspaugh, Laura Keys, David Culler, Randy Katz

Doubling in 5 years (EPA Report on Server and Data Center Energy Efficiency, 2007) $7.2 billion Energy consumption in data centers

Web Applications Database / SAN Web App Web Server Frontend /Load Balancer Web Server Web App Clients

Core i7 50% Idle Power

Atom 80% Idle Power

Server energy consumption Idle Sleep / Off Active

Server energy efficiency Percent Efficiency Energy Efficiency = Work / Energy

Power Proportional Server

Problem Servers are energy efficient at high utilization Typical server utilization is low – Google: average server utilization 30%

Google CPU Utilization The Case for Energy-Proportional Computing Luiz Barroso, Urs Holzle ,000 servers at Google during a six- month period

Solutions Make servers power proportional – Requires fixing hardware & software Make power proportional cluster – Run nodes at high utilization or “off” – Consolidate workload

Web Servers Stateless Short requests Requests can be served by multiple machines Large variation in load

Web Server Load ISP web server trace from Internet Traffic Archive

Cluster Architecture

Atom Nodes Intel Atom 330 with 945CG chipset 1.6 GHz, 2 cores CPU spec sheet TDP: 8W Chipset spec sheet TDP: 22.2W

Atom Nodes Power states: – Active – Idle: CPU enters C-states – Sleep: Suspend to RAM – Off Power (Watts)Time to Resume (seconds) Active22 – 24 W - Idle22.08 W0 s Sleep1.6 W2.5 s Off0 W61 s

Node Performance Max request rate

Scheduler Algorithm Keep awake desired_servers Put servers to sleep after a timeout

Evaluation Httperf workload generator Synthetic workload – Request files in Zipf distribution – Ramp request rate up and down Working on using real web server traces

Throughput

Energy Savings Simple Load BalancerPower Aware Cluster Manager

Load per Server

Future Work Heterogeneous hardware – Small nodes for low utilization Adjust to changes in request types – Dynamic vs. static requests – Adjust max requests per server

Questions

Adjust to request types

Power vs. server cost In the data center, power and cooling costs more than the IT equipment it supports Christian L. Belady, HP 2007

Saving Energy Turn off unused resources – Use lower states Improve power in states Active Idle Sleep Power Off