Enabling High performance Big Data platform with RDMA



Similar documents
State of the Art Cloud Infrastructure

SMB Direct for SQL Server and Private Cloud

High Performance OpenStack Cloud. Eli Karpilovski Cloud Advisory Council Chairman

Solving I/O Bottlenecks to Enable Superior Cloud Efficiency

Comparing SMB Direct 3.0 performance over RoCE, InfiniBand and Ethernet. September 2014

Unstructured Data Accelerator (UDA) Author: Motti Beck, Mellanox Technologies Date: March 27, 2012

Driving IBM BigInsights Performance Over GPFS Using InfiniBand+RDMA

Can High-Performance Interconnects Benefit Memcached and Hadoop?

Maximizing Hadoop Performance and Storage Capacity with AltraHD TM

Achieving Real-Time Business Solutions Using Graph Database Technology and High Performance Networks

Building a Scalable Storage with InfiniBand

Storage, Cloud, Web 2.0, Big Data Driving Growth

Hadoop: Embracing future hardware

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

LS DYNA Performance Benchmarks and Profiling. January 2009

Storage Architectures for Big Data in the Cloud

Accelerating and Simplifying Apache

Mellanox Cloud and Database Acceleration Solution over Windows Server 2012 SMB Direct

Mellanox Accelerated Storage Solutions

ECLIPSE Performance Benchmarks and Profiling. January 2009

Simplifying Big Data Deployments in Cloud Environments with Mellanox Interconnects and QualiSystems Orchestration Solutions

Modernizing Hadoop Architecture for Superior Scalability, Efficiency & Productive Throughput. ddn.com

Introduction to Hadoop HDFS and Ecosystems. Slides credits: Cloudera Academic Partners Program & Prof. De Liu, MSBA 6330 Harvesting Big Data

HADOOP MOCK TEST HADOOP MOCK TEST I

Hyper-V over SMB Remote File Storage support in Windows Server 8 Hyper-V. Jose Barreto Principal Program Manager Microsoft Corporation

Hyper-V over SMB: Remote File Storage Support in Windows Server 2012 Hyper-V. Jose Barreto Principal Program Manager Microsoft Corporation

CSE-E5430 Scalable Cloud Computing Lecture 2

SMB Advanced Networking for Fault Tolerance and Performance. Jose Barreto Principal Program Managers Microsoft Corporation

I/O Considerations in Big Data Analytics

Integrated Grid Solutions. and Greenplum

Big Data Analytics - Accelerated. stream-horizon.com

Connecting the Clouds

IOmark- VDI. Nimbus Data Gemini Test Report: VDI a Test Report Date: 6, September

Accelerating Spark with RDMA for Big Data Processing: Early Experiences

EMC IRODS RESOURCE DRIVERS

Benchmarking Hadoop & HBase on Violin

An Oracle White Paper June High Performance Connectors for Load and Access of Data from Hadoop to Oracle Database

Big Fast Data Hadoop acceleration with Flash. June 2013

HadoopTM Analytics DDN

Installing Hadoop over Ceph, Using High Performance Networking

Big Data: A Storage Systems Perspective Muthukumar Murugan Ph.D. HP Storage Division

InfiniBand Software and Protocols Enable Seamless Off-the-shelf Applications Deployment

Connecting Flash in Cloud Storage

Virtualizing Apache Hadoop. June, 2012

Mellanox Academy Online Training (E-learning)

Oracle s Big Data solutions. Roger Wullschleger. <Insert Picture Here>

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

EMC s Enterprise Hadoop Solution. By Julie Lockner, Senior Analyst, and Terri McClure, Senior Analyst

CDH AND BUSINESS CONTINUITY:

News and trends in Data Warehouse Automation, Big Data and BI. Johan Hendrickx & Dirk Vermeiren

Maximizing Hadoop Performance with Hardware Compression

Hadoop on the Gordon Data Intensive Cluster

Introduction to Cloud Design Four Design Principals For IaaS

Apache HBase. Crazy dances on the elephant back

Case Study : 3 different hadoop cluster deployments

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

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

Building Enterprise-Class Storage Using 40GbE

From Ethernet Ubiquity to Ethernet Convergence: The Emergence of the Converged Network Interface Controller

THE EMC ISILON STORY. Big Data In The Enterprise. Copyright 2012 EMC Corporation. All rights reserved.

Hadoop Ecosystem B Y R A H I M A.

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

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

High Performance Computing OpenStack Options. September 22, 2015

Data-Intensive Programming. Timo Aaltonen Department of Pervasive Computing

Big Data With Hadoop

Open source software framework designed for storage and processing of large scale data on clusters of commodity hardware

HADOOP SOLUTION USING EMC ISILON AND CLOUDERA ENTERPRISE Efficient, Flexible In-Place Hadoop Analytics

A REVIEW PAPER ON THE HADOOP DISTRIBUTED FILE SYSTEM

StarWind Virtual SAN for Microsoft SOFS

Hadoop Architecture. Part 1

The virtualization of SAP environments to accommodate standardization and easier management is gaining momentum in data centers.

How To Scale Out Of A Nosql Database

Introduction to Hadoop. New York Oracle User Group Vikas Sawhney

Enabling the Use of Data

RoCE vs. iwarp Competitive Analysis

Big Data Storage Options for Hadoop Sam Fineberg, HP Storage

Advancing Applications Performance With InfiniBand

Replacing SAN with High Performance Windows Share over a Converged Network

Protecting Big Data Data Protection Solutions for the Business Data Lake

Scaling Objectivity Database Performance with Panasas Scale-Out NAS Storage

Achieving Mainframe-Class Performance on Intel Servers Using InfiniBand Building Blocks. An Oracle White Paper April 2003

Lecture 32 Big Data. 1. Big Data problem 2. Why the excitement about big data 3. What is MapReduce 4. What is Hadoop 5. Get started with Hadoop

ENABLING GLOBAL HADOOP WITH EMC ELASTIC CLOUD STORAGE

An Alternative Storage Solution for MapReduce. Eric Lomascolo Director, Solutions Marketing

Big Data: Are You Ready? Kevin Lancaster

EMC XtremSF: Delivering Next Generation Performance for Oracle Database

What s new in Hyper-V 2012 R2

Cloudera Enterprise Reference Architecture for Google Cloud Platform Deployments

New Storage System Solutions

New Features in PSP2 for SANsymphony -V10 Software-defined Storage Platform and DataCore Virtual SAN

Hadoop Optimizations for BigData Analytics

Oracle Exadata: The World s Fastest Database Machine Exadata Database Machine Architecture

Big data management with IBM General Parallel File System

Fast, Low-Overhead Encryption for Apache Hadoop*

CS2510 Computer Operating Systems

Transcription:

Enabling High performance Big Data platform with RDMA Tong Liu HPC Advisory Council Oct 7 th, 2014

Shortcomings of Hadoop Administration tooling Performance Reliability SQL support Backup and recovery From 451 Research 2013 Hadoop survey 2

Where can we improve Hadoop? Hive Pig Map Reduce SQL (e.g. Impala) HBase HDFS (Hadoop Distributed File System) High demand to improve Real-time operation Fast execution Streaming data Issues Inherent data latency issue with HDFS Cannot support large number of small files Efficiency of Map Reduce, Hbase, Hive, etc. 3

HDFS Operation NameNode HDFS Federation NameNode Client Read Write DataNode DataNode DataNode 1 4 8 Replication 4 8 Replication 4 2 1 HDFS Federation Faster Disks Faster CPU and Memory Bigger network pipe 4

HARDWARE KERNEL USER RDMA (Remote Directory Memory Access) Application 1 Buffer 1 Application Buffer 1 2 OS Buffer 1 Buffer 1 Buffer 1 Buffer 1 OS RDMA over InfiniBand or Ethernet HCA HCA NIC Buffer 1 Buffer 1 NIC TCP/IP RACK 1 RACK 2 5

RDMA: Critical for Efficient Data Movement ZERO Copy Remote Data Transfer USER KERNEL Application Buffer Application Buffer HARDWARE Kernel Bypass Protocol Offload Low Latency, High Performance Data Transfers InfiniBand - 56Gb/s RoCE * RDMA over Converged Ethernet 6

HDFS Operation with RDMA NameNode NameNode Client Read Write DataNode DataNode DataNode 1 4 8 Replication 4 8 Replication 4 2 1 7

HDFS RDMA Acceleration Solution 1 Hadoop HDFS-RDMA acceleration: 100% java code written on top of JXIO Same memory footprint as the vanilla client/server uses First results show double performance for HDFS WRITE operation With 3 replications compared to vanilla 8

Accelio, High-Performance Reliable Messaging and RPC Library Open source https://github.com/accelio/accelio/ && www.accelio.org Faster RDMA integration to application Maximize message and CPU parallelism 9

HDFS RDMA Acceleration Solution 2 Package available at: http://hadooprdma.cse.ohio-state.edu/ Big performance gain with RDMA support 10

Map Reduce Workflow 11

RDMA-Enabled MapReduce Unstructured Data Accelerator - UDA Uses RDMA to do the Shuffle & Merge Plug-in architecture Open-source Supported Hadoop Distributions Apache 3.0, Apache 2.2.x, Apache 1.3 Cloudera Distribution Hadoop 4.4 Inbox 12

Storage Limitations for Hadoop Hadoop using local disk to maintain data locality and reduce latency High-value that resides on external storage systems Copy data onto HDFS, run Analytics, and then copy the results to another system Wasting storage space As data sources increase, managing data is nightmare Option of just accessing the external data without having to deal with copying Need to provide performance 13

Storage: From Scale-Up to Scale-Out Scale-out storage systems using distributed computing architectures Scalable and resilient 14

Sequential Read Performance (singe port) 15

Fastest and Lowest Latency Storage Access with iser K IOPs @ 4K IO Size 2500 2000 1500 1000 500 0 iscsi (TCP/IP) 1 x FC 8 Gb port 4 x FC 8 Gb port iser 1 x 40GbE/IB Port iser 2 x 40GbE/IB Port (+Acceleratio n) KIOPs 130 200 800 1100 2300 16

Lustre as Hadoop Storage Solution RDMA enables highest Lustre performance 17

Hadoop over Cloud?? Performance? Benefits: Lowering the cost of innovation Procuring large scale resources quickly Running closer to the data Simplifying Hadoop operations Concerns: Heavily utilized, rather than being massively provisioned Cloud storage is slower and expensive Data locality makes a big difference for performance 18

Fastest OpenStack Storage Access Compute Servers V V V OS M OS M OS M Storage Servers OpenStack (Cinder) iscsi/iser Target (tgt) Hypervisor (KVM) Open-iSCSI w iser RDMA Cache Adapter Adapter Local Disks Using RDMA to accelerate iscsi storage RDMA Capable Interconnect Using OpenStack Built-in components and management RDMA is already inbox and used by OpenStack RDMA enables faster performance, with much lower CPU% 19

Fast Interconnect with RDMA to Boost Big Data 4X Faster Run Time! Benchmark: TestDFSIO (1TeraByte, 100 files) 2X Higher Performance! Benchmark: 1M Records Workload (4M Operations) 2X faster run time and 2X higher throughput 2X Faster Run Time! Benchmark: MemCacheD Operations 3X Faster Run Time! Benchmark: Redis Operations 20

RDMA Can Accelerate All Layers Compute I/O Nodes Filesystem Storage 21

What s Happening with Big Data Platform Big Data Meets HPC! 22

Questions? All trademarks are property of their respective owners. All information is provided As-Is without any kind of warranty. The HPC Advisory Council makes no representation to the accuracy and completeness of the information contained herein. HPC Advisory Council Mellanox undertakes no duty and assumes no obligation to update or correct any information presented herein 23 23