HPSS Best Practices. Erich Thanhardt Bill Anderson Marc Genty B



Similar documents
NERSC Archival Storage: Best Practices

Archival Storage At LANL Past, Present and Future

Quick Introduction to HPSS at NERSC

OPTIMIZING EXCHANGE SERVER IN A TIERED STORAGE ENVIRONMENT WHITE PAPER NOVEMBER 2006

SwiftStack Filesystem Gateway Architecture

XenData Archive Series Software Technical Overview

Hitachi NAS Platform and Hitachi Content Platform with ESRI Image

The Archival Upheaval Petabyte Pandemonium Developing Your Game Plan Fred Moore President

Forschungszentrum Karlsruhe in der Helmholtz-Gemeinschaft. dcache Introduction

SAM-FS - Advanced Storage Management Solutions for High Performance Computing Environments

Diagram 1: Islands of storage across a digital broadcast workflow

Understanding Disk Storage in Tivoli Storage Manager

WHAT S THE DIFFERENCE? JENNIFER RICKER DIGITAL COLLECTIONS MANAGER STATE LIBRARY OF NORTH CAROLINA

Considerations when Choosing a Backup System for AFS

Solution Brief: Creating Avid Project Archives

Data Deduplication in Tivoli Storage Manager. Andrzej Bugowski Spała

High Performance Storage System. Overview

Media Cloud Building Practicalities

GPFS Cloud ILM. IBM Research - Zurich. Storage Research Technology Outlook

Multi-Terabyte Archives for Medical Imaging Applications

RAID. RAID 0 No redundancy ( AID?) Just stripe data over multiple disks But it does improve performance. Chapter 6 Storage and Other I/O Topics 29

Research Technologies Data Storage for HPC

Data storage services at CC-IN2P3

WOS OBJECT STORAGE PRODUCT BROCHURE DDN.COM Full Spectrum Object Storage

A Survey of Shared File Systems

IBM TotalStorage IBM TotalStorage Virtual Tape Server

IM and Presence Disaster Recovery System

COSC 6374 Parallel Computation. Parallel I/O (I) I/O basics. Concept of a clusters

<Insert Picture Here> Refreshing Your Data Protection Environment with Next-Generation Architectures

Object Storage, Cloud Storage, and High Capacity File Systems

Enterprise Backup and Restore technology and solutions

Four Reasons To Start Working With NFSv4.1 Now

IBM Spectrum Protect in the Cloud

Open Text Archive Server and Microsoft Windows Azure Storage

Hadoop Distributed File System. Dhruba Borthakur June, 2007

IBM Tivoli Storage Manager Version Introduction to Data Protection Solutions IBM

Setup and Configuration Setup Assistant Migration Assistant System Preferences Configuration Profiles System Information

List of Figures and Tables

LDA, the new family of Lortu Data Appliances

Lustre* is designed to achieve the maximum performance and scalability for POSIX applications that need outstanding streamed I/O.

Introduction Disks RAID Tertiary storage. Mass Storage. CMSC 412, University of Maryland. Guest lecturer: David Hovemeyer.

Considerations when Choosing a Backup System for AFS

Tech Application Chapter 3 STUDY GUIDE

Tivoli Storage Manager Explained

Protect Data... in the Cloud

Capacity Planning for Microsoft SharePoint Technologies

WHITE PAPER. Reinventing Large-Scale Digital Libraries With Object Storage Technology

CROSS PLATFORM AUTOMATIC FILE REPLICATION AND SERVER TO SERVER FILE SYNCHRONIZATION

Enterprise Backup Solution Vendor Questions

Virtual Tape Systems for IBM Mainframes A comparative analysis

Salesforce Certified Data Architecture and Management Designer. Study Guide. Summer 16 TRAINING & CERTIFICATION

Backup and Recovery 1

Optimizing Storage for Better TCO in Oracle Environments. Part 1: Management INFOSTOR. Executive Brief

Technical White Paper. Symantec Backup Exec 10d System Sizing. Best Practices For Optimizing Performance of the Continuous Protection Server

Evaluation Guide. Software vs. Appliance Deduplication

ETERNUS CS High End Unified Data Protection

Introduction to Optical Archiving Library Solution for Long-term Data Retention

Flexible Scalable Hardware independent. Solutions for Long Term Archiving

Considerations for Management of Laboratory Data

Introduction to Archival Storage at NERSC

PetaLibrary Storage Service MOU

Cloud Based Application Architectures using Smart Computing

CPS104 Computer Organization and Programming Lecture 18: Input-Output. Robert Wagner

STORAGE CENTER. The Industry s Only SAN with Automated Tiered Storage STORAGE CENTER

Scientific Storage at FNAL. Gerard Bernabeu Altayo Dmitry Litvintsev Gene Oleynik 14/10/2015

GPFS und HPSS am HLRS

Implementing a Digital Video Archive Using XenData Software and a Spectra Logic Archive

NetApp High-Performance Computing Solution for Lustre: Solution Guide

SAP HANA - Main Memory Technology: A Challenge for Development of Business Applications. Jürgen Primsch, SAP AG July 2011

Amazon Cloud Storage Options

LinuxWorld Conference & Expo Server Farms and XML Web Services

Protecting Information in a Smarter Data Center with the Performance of Flash

VMware vcenter 4.0 Database Performance for Microsoft SQL Server 2008

XenData Video Edition. Product Brief:

Symantec Backup Exec 2014 TM Licensing Guide

Automated file management with IBM Active Cloud Engine

IBM Tivoli Storage Manager

BlueArc unified network storage systems 7th TF-Storage Meeting. Scale Bigger, Store Smarter, Accelerate Everything

The legal admissibility of information stored on electronic document management systems

The ROI of Tape Consolidation

White paper 200 Camera Surveillance Video Vault Solution Powered by Fujitsu

Transcription:

HPSS Best Practices Erich Thanhardt Bill Anderson Marc Genty B

Overview Idea is to Look Under the Hood of HPSS to help you better understand Best Practices Expose you to concepts, architecture, and tape tech Cite Best Practice s in context along the way Talk ends with references to further resources Talk is interactive, please ask questions along the way

HPSS - What is it? Acronym Stands for High Performance Storage System HPSS is software that manages petabytes of data on disk and robotic tape libraries. Quoted from:http://www.hpss-collaboration.org

HPSS - What makes it different? Hardware: Use of tape technology is a distinguishing characteristic of HPSS Use case: HPSS is an archive and not a (parallel) file system system is remote, not cross mounted operation set is limited to metadata and file transfers Best Practice: Be aware what makes HPSS very different than GLADE - intended use

Archive HPSS Main Use Cases Data is stored and preserved indefinitely While system components come and go Model data and observational data collections Disaster Recovery Leverage dual sites for geographic separation Additional level of archival preservation

HPSS Software Architecture AUTH Authentication 4x Gateway Servers HPSS End User Control Gateway Linux/Unix Host HSI/HTAR Client Metadata CLint Interface (CLI) DATA HPSS

HPSS Software Architecture Best Practice: Reporting errors via EV ticket include: name, host, datetime, -d4 error tracing authentication problems those pesky parallel file transfer limits your guaranteed on-ramp to the system data bandwidth allocation will be increasing over the next few months

HPSS Software Architecture Best Practice: Validating that a file was written ls -l both locally and on HPSS compare pathname and size not sufficient to see the pathname (ls) Here is what can happen: Creating pathname in HPSS happens first Then data transfer between client and HPSS That transfer can be interrupted

HPSS - One System/Two Sites NWSC Cheyenne ARCHIVE DISASTER RECOVERY MLCF Boulder HPSS Disk Cache Oracle Tape Drives + Media Oracle SL8500 Tape Library

HPSS Libraries - Oracle SL8500

HPSS Tape Libraries Frontal View MLCF ACSLS Server SL8500 Tape Library

HPSS Libraries Top View Tape Library

HPSS Libraries - Photos

ORACLE DRIVE & MEDIA

Small File Problem Cost of a random read: Robot retrieval, mount, seek: 70 secs to avg file Transfer data rate: 240 MB/sec 184 MB file means 99% latency 1% transfer Cost of returning tape Double it - indirect cost to you 368 MB file means 99% latency 1% transfer Compare these with avg filesize of 166 MB

Small File Problem Best Practice: best is to avoid small files, but where needed - aggregate with htar

Deleting files File Deletion Deleting data on tape creates unusable spaces on tape because it s linear and continuous Mischaracterizations and system data migrations Best Practice - delete un-needed files but also avoid temporary files (whether rewriting or create/delete s)

Repeated Reads and Writes Best Practice: avoid both repeated reads from and repeated writes to an archive file - bring the file out and park it somewhere else

File Rescue Adopting orphaned files from others user/proj combo goes invalid after period of time someone needs to take ownership and pay storage costs Best Practice - never use cp to copy data internally in order to move it if you don t have proper permissions - open ticket

Optimizing Reads Best Practice - if you are reading back data at large scales, contact Helpdesk at cislhelp@ucar.edu for ways to order your requests - it can be done! Process is not perfect but usually has a positive effect

Storage Hierarchy Concept CPU Memory Disk Tape

Attributes of Storage Hierarchy Cost & Characteristics Speed & Capacity Persistence & Reliability hardware, RAID/RAIT, dual copy Availability online/nearline/offline Location onsite/offsite

HPSS Storage Pyramid DISK CACHE Disk TAPE LIBS ROBOTICS DRIVES & MEDIA Tape

Hierarchical Storage Manager (HSM) Purge DISK Stage Migrate TAPE

User Interaction with HPSS Purge DISK Stage Migrate TAPE

Basic Stats Jun-Aug 2014 Writes/Reads ratio ~4-5 to 1 User response times ~116 sec/read vs. ~9-10 sec/write ratio read/write response times ~ 13 to 1

Tape Technology Upgrades Purge DISK Stage Migrate Migrate TAPE

Data Services Pyramid - Workflow PFS GLADE GPFS 90 GB/sec Archive DR HPSS 9 GB/sec

Workflow - Optimal Create data on GLADE/GPFS Post process (new data plus deletes) Commit data selectively to HPSS Best Practice!

Workflow - Realistic Create data on GLADE/GPFS Commit to HPSS (back it up) Post process (new data) Commit post-processed data (selectively?) to HPSS

Workflow - To Avoid Create data on GLADE/GPFS Commit to HPSS (back it up) Delete from GLADE/GPFS. time passes Stage from HPSS back to GLADE/GPFS. process staged data

Workflow - To Avoid Create data on GLADE/GPFS Commit to HPSS (back it up) Delete from GLADE/GPFS. time passes Stage from HPSS back to GLADE/GPFS. process staged data BEST PRACTICE - contact cislhelp@ucar.edu

Additional Resources CISL Support & Allocations Helpdesk & CISL Consulting send email to cislhelp@ucar.edu HPSS Documentation http://www2.cisl.ucar.edu/docs/hpss Best Practices doc http://www2.cisl.ucar.edu/docs/best_practices

The End