Mixing Hadoop and HPC Workloads on Parallel Filesystems



Similar documents
Performance Analysis of Mixed Distributed Filesystem Workloads

I/O intensive applications: what are the main differences in the design of the HPC filesystems vs the MapReduce ones?

Hadoop Distributed File System. T Seminar On Multimedia Eero Kurkela

Hadoop Architecture. Part 1

Analysis and Optimization of Massive Data Processing on High Performance Computing Architecture

Leveraging BlobSeer to boost up the deployment and execution of Hadoop applications in Nimbus cloud environments on Grid 5000

Accelerating and Simplifying Apache

Welcome to the unit of Hadoop Fundamentals on Hadoop architecture. I will begin with a terminology review and then cover the major components

Performance Comparison of Intel Enterprise Edition for Lustre* software and HDFS for MapReduce Applications

Performance Comparison of SQL based Big Data Analytics with Lustre and HDFS file systems

A Performance Analysis of Distributed Indexing using Terrier

Take An Internal Look at Hadoop. Hairong Kuang Grid Team, Yahoo! Inc

Hadoop IST 734 SS CHUNG

Department of Computer Science University of Cyprus EPL646 Advanced Topics in Databases. Lecture 14

Distributed File System. MCSN N. Tonellotto Complements of Distributed Enabling Platforms

MapReduce and Hadoop. Aaron Birkland Cornell Center for Advanced Computing. January 2012

Outline. High Performance Computing (HPC) Big Data meets HPC. Case Studies: Some facts about Big Data Technologies HPC and Big Data converging

HDFS Space Consolidation

GeoGrid Project and Experiences with Hadoop

BENCHMARKING CLOUD DATABASES CASE STUDY on HBASE, HADOOP and CASSANDRA USING YCSB

A REVIEW PAPER ON THE HADOOP DISTRIBUTED FILE SYSTEM

Lustre * Filesystem for Cloud and Hadoop *

Prepared By : Manoj Kumar Joshi & Vikas Sawhney

CSE 590: Special Topics Course ( Supercomputing ) Lecture 10 ( MapReduce& Hadoop)

Use of Hadoop File System for Nuclear Physics Analyses in STAR

BlobSeer: Towards efficient data storage management on large-scale, distributed systems

Scaling Objectivity Database Performance with Panasas Scale-Out NAS Storage

Distributed Filesystems

Linux Performance Optimizations for Big Data Environments

Can High-Performance Interconnects Benefit Memcached and Hadoop?

Big Data Analytics. Lucas Rego Drumond

Hadoop MapReduce over Lustre* High Performance Data Division Omkar Kulkarni April 16, 2013

Hadoop. Sunday, November 25, 12

Data Analytics. CloudSuite1.0 Benchmark Suite Copyright (c) 2011, Parallel Systems Architecture Lab, EPFL. All rights reserved.

Open source Google-style large scale data analysis with Hadoop

BookKeeper. Flavio Junqueira Yahoo! Research, Barcelona. Hadoop in China 2011

Hadoop s Entry into the Traditional Analytical DBMS Market. Daniel Abadi Yale University August 3 rd, 2010

Map Reduce / Hadoop / HDFS

How To Scale Out Of A Nosql Database

Performance Evaluation for BlobSeer and Hadoop using Machine Learning Algorithms

HPCHadoop: MapReduce on Cray X-series

Benchmarking Hadoop & HBase on Violin

A Study on Workload Imbalance Issues in Data Intensive Distributed Computing

RADOS: A Scalable, Reliable Storage Service for Petabyte- scale Storage Clusters

LS-DYNA Best-Practices: Networking, MPI and Parallel File System Effect on LS-DYNA Performance

HADOOP PERFORMANCE TUNING

A Micro-benchmark Suite for Evaluating Hadoop RPC on High-Performance Networks

CSE-E5430 Scalable Cloud Computing Lecture 2

CS2510 Computer Operating Systems

CS2510 Computer Operating Systems

Chapter 7. Using Hadoop Cluster and MapReduce

Cray XC30 Hadoop Platform Jonathan (Bill) Sparks Howard Pritchard Martha Dumler

Evaluating HDFS I/O Performance on Virtualized Systems

Duke University

Hadoop Distributed File System. Dhruba Borthakur June, 2007

Optimize the execution of local physics analysis workflows using Hadoop

Hadoop MapReduce and Spark. Giorgio Pedrazzi, CINECA-SCAI School of Data Analytics and Visualisation Milan, 10/06/2015

The Comprehensive Performance Rating for Hadoop Clusters on Cloud Computing Platform

Lecture 5: GFS & HDFS! Claudia Hauff (Web Information Systems)! ti2736b-ewi@tudelft.nl

Parallel Databases. Parallel Architectures. Parallelism Terminology 1/4/2015. Increase performance by performing operations in parallel

THE HADOOP DISTRIBUTED FILE SYSTEM

Enabling High performance Big Data platform with RDMA

Hadoop. Apache Hadoop is an open-source software framework for storage and large scale processing of data-sets on clusters of commodity hardware.

InfoScale Storage & Media Server Workloads

HPC and Big Data. EPCC The University of Edinburgh. Adrian Jackson Technical Architect

Research Article Hadoop-Based Distributed Sensor Node Management System

Jeffrey D. Ullman slides. MapReduce for data intensive computing

Large scale processing using Hadoop. Ján Vaňo

Investigation of storage options for scientific computing on Grid and Cloud facilities

EFFICIENT GEAR-SHIFTING FOR A POWER-PROPORTIONAL DISTRIBUTED DATA-PLACEMENT METHOD

BIG DATA TRENDS AND TECHNOLOGIES

THE ATLAS DISTRIBUTED DATA MANAGEMENT SYSTEM & DATABASES

WITH A FUSION POWERED SQL SERVER 2014 IN-MEMORY OLTP DATABASE

Snapshots in Hadoop Distributed File System

OSG Hadoop is packaged into rpms for SL4, SL5 by Caltech BeStMan, gridftp backend

Apache Hadoop new way for the company to store and analyze big data

Apache Hadoop. Alexandru Costan

Michael Thomas, Dorian Kcira California Institute of Technology. CMS Offline & Computing Week

Comprehending the Tradeoffs between Deploying Oracle Database on RAID 5 and RAID 10 Storage Configurations. Database Solutions Engineering

Transcription:

Mixing Hadoop and HPC Workloads on Parallel Filesystems Esteban Molina-Estolano *, Maya Gokhale, Carlos Maltzahn *, John May, John Bent, Scott Brandt * * UC Santa Cruz, ISSDM, PDSI Lawrence Livermore National Laboratory Los Alamos National Laboratory

Motivation Strong interest in running both HPC and large-scale data mining workloads on the same infrastructure Hadoop-tailored filesystems (e.g. CloudStore) and highperformance computing filesystems (e.g. PVFS) are tailored to considerably different workloads Existing investments in HPC systems and Hadoop systems should be usable for both workloads Goal: Examine the performance of both types of workloads running concurrently on the same filesystem Goal: collect I/O traces from concurrent workload runs, for parallel filesystem simulator work

MapReduce-oriented filesystems Large-scale batch data processing and analysis Single cluster of unreliable commodity machines for both storage and computation Data locality is important for performance Examples: Google FS, Hadoop DFS, CloudStore

Hadoop DFS architecture 2"3,,4(567("$'8).%'.9$%!"#$%&'%(!)*%$+,$%(-".),&"/(!"0,$".,$1 "##$%&&"'())$*'$'+",*)-.!

High-Performance Computing filesystems 2)3456%$7,$+"&'%(8,+9:.)&3(7)/%;1;.%+; High-throughput, lowlatency workloads!!"#$%&$'()#$*)&+,-(.% -/&0123,.('4-(/56! 7'2$"&02&)'08,60*/'/&0, 2(9*)&0,/15,6&('/#0, 2-)6&0'6+,$"#$%6*005, :'"5#0,:0&.001,&$09! ;3*"2/-,.('4-(/58, 6"9)-/&"(1,2$024*("1&"1#! <=/9*-068,>?@A+,B)6&0'+, Architecture: separate compute and storage clusters, high-speed bridge between them Typical workload: >/1@A simulation checkpointing.$/01#()2314#(% 56'7840((9):%69'( Examples: PVFS, Lustre, PanFS, Ceph!"#$%&'%(!)*%$+,$%(-".),&"/(!"0,$".,$1 "#$%&'()*%(&)+(#,$%-!

Running each workload on the non-native filesystem Two-sided problem: running HPC workloads on a Hadoop filesystem, and Hadoop workloads on an HPC filesystem Different interfaces: HPC workloads need a POSIX-like interface and shared writes Hadoop is write-once-read-many Different data layout policies

Running HPC workloads on a Hadoop filesystem Chosen filesystem: CloudStore Downside of Hadoop s HDFS: no support for shared writes (needed for HPC N-1 workloads) Cloudstore has HDFS-like architecture, and shared write support

Running Hadoop workloads on an HPC filesystem Chosen HPC filesystem: PVFS PVFS is open-source and easy to configure Tantisiriroj et al. at CMU have created a shim to run Hadoop on PVFS Shim also adds prefetching, buffering, exposes data layout

The two concurrent workloads IOR checkpointing workload writes large amounts of data to disk from many clients N-1 and N-N write patterns Hadoop MapReduce HTTP attack classifier (TFIDF) Using a pre-generated attack model, classify HTTP headers as normal traffic or attack traffic

Experimental Setup System: 19 nodes, 2-core 2.4 GHz Xeon, 120 GB disks IOR baseline: N-1 strided workload, 64 MB chunks IOR baseline: N-N workload, 64 MB chunks TFIDF baseline: classify 7.2 GB of HTTP headers Mixed workloads: IOR N-1 and TFIDF, IOR N-N and TFIDF Checkpoint size adjusted to make IOR and TFIDF take the same amount of time

Performance metrics Throughputs are not comparable between workloads Per-workload throughput: measure how much each job is slowed down by the mixed workload Runtime: compare the runtime of the mixed workload with the runtime of the same jobs run sequentially

Hadoop performance results Classification throughput (MB/s) 20 15 10 5 0 TFIDF classification throughput, standalone and with IOR CloudStore Baseline with IOR N-1 with IOR N-N PVFS

IOR performance results Write throughput (MB/s) 90 80 70 60 50 40 30 20 10 0 IOR checkpointing on CloudStore N-1 N-N IOR checkpointing on PVFS Standalone Mixed N-1 N-N

Runtime (seconds) 2000 1800 1600 1400 1200 1000 800 600 400 200 0 Runtime results Runtime comparison of mixed vs. serial workloads Serial runtime Mixed runtime PVFS N-1 PVFS N-N CloudStore N-1 CloudStore N-N

Tracing infrastructure We gather traces to use for our parallel filesystem simulator Existing tracing mechanisms (e.g. strace, Pianola, Darshan) don t work well with Java or CloudStore Solution: our own tracing mechanisms for IOR and Hadoop

Tracing IOR workloads 2$"')&3(456(#,$7/,"89 Trace shim intercepts I/O calls, sends to stdio!!"#$%&'()*&$#+,-"%'&./0&$#11'2&'%34'&,5&',4)5 #$%&'()*&.$/#' #$%&'()* #$%&'()*&+*,-) #$%&'()*&0.##$ 89,*9&9;=)>?@*<-)88&AB=>?C*),:DE*;9)F> <((8)9>?8;G)>?)A:&9;=) #$%&'()*&1234 #$%&'()*&560.# 89:;< #$%&'()*&73/!"#$%&'%(!)*%$+,$%(-".),&"/(!"0,$".,$1!"

2$"')&3(4"5,,6(7"68%59'% Tracing Hadoop #$%&'$(+0%.%1234.+.$'%/ #$%&'$()*'+,-.'/ 56(+7()*'+,-.'/ :6%& ;$%".%!!"#$$%&'(")*+,&-.*/0&1(")2(3*4256-'2/! 78"/%420&'9-0::%;9-<='>-$+<?0<@@@@:&'$&'(")2&AB35 Tracing shim wraps filesystem interfaces, sends I/O calls! C"-2&9*42-6-'2/-&/$#*9*2#&'$&D("%&E+%>':F>'%>'5'(2"/-& to Hadoop logs! E:F&$%2("'*$+-&4$,,2#&'$&!"#$$%&%2(='"-G&4$,- 56(+70%.%1234.+.$'%/ 9%:;;3<*;=- #$%&'$(+0%.%84.34.+.$'%/ 56(+70%.%84.34.+.$'%/ (;$/%.><?)*'2%/'@<3):@<-.%$.A.)/'@<'2:A.)/'@<;3'$%.);2B3%$%/@<CCCD<E<$'-4*.<F'*%3-':</-G!"#$%&'%(!)*%$+,$%(-".),&"/(!"0,$".,$1!"

Tracing overhead Trace data goes to NFS-mounted share (no disk overhead) Small Hadoop reads caused huge tracing overhead Solution: record traces behind read-ahead buffers Overhead (throughput slowdown): IOR checkpointing: 1% TFIDF Hadoop: 5% Mixed workloads: 10%

Conclusions Each mixed workload component is noticeably slowed, but... If only total runtime matters, the mixed workloads are faster PVFS shows different slowdowns for N-N vs. N-1 workloads Tracing infrastructure: buffering required for small I/O tracing Future work: Run experiments at a larger scale Use experimental results to improve parallel filesystem simulator Investigate scheduling strategies for mixed workloads

Questions? Esteban Molina-Estolano: eestolan@soe.ucsc.edu