Presentation is loading. Please wait.

Presentation is loading. Please wait.

Experiments in Utility Computing: Hadoop and Condor Sameer Paranjpye Y! Web Search.

Similar presentations


Presentation on theme: "Experiments in Utility Computing: Hadoop and Condor Sameer Paranjpye Y! Web Search."— Presentation transcript:

1 Experiments in Utility Computing: Hadoop and Condor Sameer Paranjpye Y! Web Search

2 Condor Week 2006 Outline Introduction –Application environment, motivation, development principles Hadoop and Condor –Description, Hadoop-Condor interaction

3 Introduction

4 Condor Week 2006 Web Search Application Environment Data intensive distributed applications –Crawling, Document Analysis and Indexing, Web Graphs, Log Processing, … –Highly parallel workloads –Bandwidth to data is a significant design driver Very large production deployments –Several clusters of 100s-1000s of nodes –Lots of data (billions of records, input/output of 10s of TB in a single run)

5 Condor Week 2006 Why Condor and Hadoop? To date, our Utility Computing efforts have been conducted using a command-and-control model –Closed, “cathedral” style development –Custom built, proprietary solutions Hadoop and Condor –Experimental effort to leverage open source for infrastructure components –Current deployment: Cluster for supporting research computations Multiple users, running ad-hoc, experimental programs

6 Condor Week 2006 Vision - Layered Platform, Open APIs Batch Scheduling (Condor, SGE, SLURM, …) Distributed Store (HDFS, Lustre, Ibrix, …) Programming Models (MPI, DAG, MW, MR…) Applications (Crawl, Index, …)

7 Condor Week 2006 Development philosophy Adopt, Collaborate, Extend Open source commodity software Open APIs for interoperability Identify and use existing robust platform components Engage community and participate in developing nascent and emerging solutions

8 Hadoop and Condor

9 Condor Week 2006 Hadoop Open source project developing –Distributed store –Implementation of Map/Reduce programming model –Led by Doug Cutting –Implemented in Java –Alpha (0.1) release available for download Apache distribution Genesis –Lucene and Nutch (Open source search) –Hadoop (factors out distributed compute/storage infrastructure) http://lucene.apache.org/hadoop

10 Condor Week 2006 Hadoop DFS Distributed storage system –Files are divided into uniform sized blocks and distributed across cluster nodes –Block replication for failover –Checksums for corruption detection and recovery –DFS exposes details of block placement so that computes can be migrated to data Notable differences from mainstream DFS work –Single ‘storage + compute’ cluster vs. Separate clusters –Simple I/O centric API vs. Attempts at POSIX compliance

11 Condor Week 2006 Hadoop DFS Architecture Master Slave architecture DFS Master “Namenode” –Manages all filesystem metadata –Controls read/write access to files –Manages block replication DFS Slaves “Datanodes” –Serve read/write requests from clients –Perform replication tasks upon instruction by namenode

12 Condor Week 2006 Hadoop DFS Architecture Client I/O Namenode Metadata (Name, replicas, …): /home/sameerp/foo, 3, … /home/sameerp/docs, 4, … Client Datanodes Rack 1Rack 2 Metadata ops

13 Condor Week 2006 Benchmarks

14 Condor Week 2006 Deployment Research cluster of 600 nodes –Billion+ web pages –Several months worth of logs –10s of TB of data –Multiple-users running ad-hoc research computations Crawl experiments, various kinds of log analysis, … –Commodity Platform: Intel/AMD, Linux, locally attached SATA drives Testbed for open source approach Still early days, deployment exposed many bugs Future releases to –First stabilize at current size –Then scale to 1000+ nodes

15 Condor Week 2006 Hadoop-Condor interactions DFS makes data locations available to applications Applications generate job descriptions (class- ads) to schedule jobs close to data Extensions to enable Hadoop programming models to run in scheduler universe –Master/Worker, MPI universe like meta-scheduling Condor enables sharing among applications –Priority, accounting, quota mechanisms to manage resource allocation among users and apps

16 Condor Week 2006 Hadoop-Condor interactions Condor HDFS 4 a 3 b 2 c 1 d 1 2 3 4 Scheduler universe apps Data locations (d,e) Classads (Schedule on d,e) 1 e Resource allocation

17 Condor Week 2006 The end THE END


Download ppt "Experiments in Utility Computing: Hadoop and Condor Sameer Paranjpye Y! Web Search."

Similar presentations


Ads by Google