Minerva User Group 2018
|
|
- Barnard Thornton
- 5 years ago
- Views:
Transcription
1 Minerva User Group 2018 Patricia Kovatch Bhupender Thakur, PhD Francesca Tartaglione, MS Dansha Jiang, PhD Eugene Fluder, PhD Hyung Min Cho, PhD Lili Gai, PhD Jan 18, 2018
2 Outline Welcome and general comments 2017 Accomplishments 2017 Minerva usage 2017 outages and known issues Survey results and discussion Q&A Road map for 2018 Compute and storage upgrade OS upgrade and package rebuild Demeter data science cluster Cloud services such as VM, Spark and containers (Docker/Shifter) Documentation and tutorial sessions Q&A; Floor walk 2
3 Welcome and general comments
4 2017 Accomplishments GPFS upgrade Upgraded Minerva file system from release 3.5 to 4.1 which introduced improvements and bug fixes. IBM ESS storage installation and data migration Installed 6 PB of IBM Elastic Storage Server to provide additional and faster storage to Minerva users and started users data migration to the new pool. TSM upgrade Successfully upgraded TSM software from v6.1 to v8.1, as well as tape library and tape drives firmware of our archive storage system for better performance and reliability. New database server deployment and data migration Installed and configured a new database server (7.3 SSD disk space, Centos 7.3, MariaDB v10.1). Migrated the users and their data from the old system that was reaching EOL. New compute nodes including high-mem node and GPU nodes Installed and configured a new high-mem node ( GHz, 1.7 TB memory). Job tested and now in production. Installed and configured a new GPU node which equipped with 4*P100 Nvidia GPUs. Job tested on this node and will open to users in 01/
5 2017 Accomplishments - continued Minerva OS upgrade Started the preparations for the cluster operating system update from CentOS 6.3 to CentOS 7 (OS image setup, packages rebuild, testing). Consulting services Provided consulting for users private nodes purchases. User support Continued to support Minerva users through ticketing system (closed more than 2,304 tickets in 2017) and in person meetings. Packages installation Installed more than 100 packages to satisfy users requests and needs (1,299 total packages and growing). Accomplished a new round of allocations Allocated 228 users projects for a total of 2.6 PB on BODE and 3.7 PB on ESS storage. New storage purchase New Flash file system 260 TB for metadata and small files. New ESS file system 3.7 PB to be added to the existing storage. Collaboration accounts for groups 5
6 2017 Minerva Usage
7 2017 Minerva usage summary Accounts Number of new users 422 Number of active users in Number of total users Number of project groups 1,735 (600 external users) 267 Compute Number of jobs run 28,672,579 CPU-hours utilized 61,208,294 hours Storage High-speed storage used Archival storage used 5.1 PB (77% utilization) 6.8 PB (13.7 PB total including offsite copy) System Number of maintenance sessions 3 planned / 4 unplanned (99% uptime) 7
8 Jobs and CPU-hours break down by compute resource: Compute # Jobs CPU-hour Utilization Manda 14,709,127 28,183,931 88% Mothra 8,369,565 11,467,197 93% BODE 8,994,398 7,636,607 79% ,215 2, ,166 28,672,579 61,208,294 Hi-memory node GPU nodes Total: 91% 20% increase in compute cycles used compared to
9 CPU-hours break down by project Avner Schlessinger Gabriel Hoffman Rui Chang Marta Filizola Hardik Shah Gaurav Pandey Eimear Kenny 9
10 Job Mix 10
11 High-speed storage (Orga) What Minerva s storage processes on a daily basis: # of reads and writes Storage FLASH (Small File/Metadata) Total (GSS+DDN+FLASH) Size Reads/Day Writes/Day Reads/day Writes/day 150 TB ~1.05 billion ~0.6 billion PB ~1.8 billion ~1 billion ~500 TB ~175 TB 11
12 Storage usage breakdown by research project Milind Mahajan Production Bioinformatics Group 22,532,449 files Gabriel Hoffman Common Mind Psychiatry 170,553,026 files Alison Goate LOAD 30,060,193 files Bin Zhang Adineto 52,056,583 files Milind Mahajan Genomics Core Facility 208,067,608 files Gabriel Hoffman Psychiatry 19,167,326 files Lisa Edelman Hardik Shah (Robert Sebra) Pacbio SmrtPortal Genetics and Genomic Sciences 26,342,148 files CCSQXT 19,398,482 files Michael Marin MMAAAS 344,530 files Total: 5.1 PB used by 1,452,320,208 files from 267 projects. Bin Zhang AMPADWGS 131,182 files 12
13 Archive storage Current archive storage usage Archived data 6.85 PB (270,461,256 files) Total data with offsite copy PB Number of tapes used 8,673 Statistics of 2017 Archived data in ,834 TB # of archive operations 23,065 # of archive users 106 Retrieved data 7.5 % # of retrieve operations 7,917 # of retrieve users 63 13
14 Archival storage occupancy by users 14
15 2017 Outages and Known issues
16 2017 Minerva Outages Summary Planned / unplanned Date Duration GPFS issue, long waiters and file system not accessible Unplanned 04/26/2017 ~6 h ESS recovery groups lost causing long waiters and file system issues Unplanned 08/02/2017 ~4 h ESS node communication problems causing long waiters and file system issues Unplanned 08/05/2017 ~4 h Two ESS nodes went arbitrating and several servers in unknown state Unplanned 08/08/2017 ~3 h The new version of GPFS ( ) was installed on all Minerva nodes and storage servers Planned 08/22/2017 ~8 h Upgraded GPFS on GSS, worked on GOLD and DB1 Planned 09/19/2017 ~8 h Generated new keys for GPFS, tested ESS system on orga compute nodes, upgraded minerva2, added fixes for LSF Planned 11/07/2017 ~8 h TSM upgrade which includes, Firmware upgrade on tape library, OS upgrade on hpctsm1, tsm upgrade on both server nodes and client nodes. Planned 11/06/2017 ~7 days Total 99% uptime 16
17 LSF Job Scheduler Overload in Dec Caused by certain pipelines submitting several (tens of thousands) short jobs (~minutes) query the LSF too often. "Batch system concurrent query limit exceeded... retrying in 1 second(s)." - Resolved by communicating with users to understand and optimize the script. We also put a limit on a couple of user s jobs. 17
18 2017 Survey Results
19 Survey results and discussion We asked four questions: Q1: Overall, how satisfied are you with queue structure, compute and storage resources? Q2: Please rate current software environment (packages and services such as database, web, container etc): Q3: Please rate your satisfaction with operations (documentation, ticket system, responsiveness of staff,...): Q4: General suggestions for service improvement. We received 42 responses and 52 comments. 19
20 Survey results and discussion Q1: Overall, how satisfied are you with queue structure, compute and storage resources? Comments: Short of compute resources: long waiting time for job to start; queues are crowded. Storage issues: Not enough space in Scratch and longer time before deletion; file-system not stable. Better queue support: the compute resource can be occupied by one group only; different queues for many small jobs and high CPU jobs. Memory usage exceed in login nodes; need more interactive nodes. 20
21 Survey results and discussion Q2: Please rate current software environment (packages and services such as database, web, container etc): Comments: Any omissions in the packages are quickly installed, but need to keep up-to-date. OS upgrade with services such as containers, VM, Hadoop, Spark and HDFS. 21
22 Survey results and discussion Q3: Please rate your satisfaction with operations (documentation, ticket system, responsiveness of staff,...): Comments: Lack of documentation and examples, documentations are outdated. Training for new users. 22
23 Summary Thank you for your feedback! Actions we took and/or are taking: Upgrading storage and compute nodes. Upgrading the OS and rebuilding packages. Deploying the Demeter data science cluster for the community Making cloud services available such as VMs, Spark and containers (Docker/Shifter). Updating the documentation and increasing the number of tutorial sessions. Please continue to provide feedback at any time via our ticketing system or talk to us directly. 23
24 2018 Minerva Roadmap
25 Drivers for our 2018 Roadmap Hardware reaching end of life (no vendor will support anymore) Storage component Flash (Stores all metadata for the file system) 50 TB, EOL in Q1. Ramsan (Stores tiny files which see frequent use) 100 TB, EOL in Q1. GSS (The default location for all data and sees highest use) 2.9 PB, unsupported in Q1. DDN10k (The oldest and the smallest storage tier) 1.2 PB EOL in Q1. Computes Manda compute nodes, EOL in Q4. Outdated OS/Software stack Minerva OS and base packages CentOS 6.4 is out of support. Older base compilers and libraries block newer packages. Newer MPI/OFED stack will require dependent packages to be rebuilt. Feedback from user survey 25
26 Storage and file system upgrade plan Client side: GPFS upgrade from v3.5 to v4.2 Manda Mothra/Bode Login nodes Login nodes Mgmt nodes Mgmt nodes Compute nodes Compute nodes Infiniband (IB) network 1G Ethernet network File system side: Orga ESS Data Pool (6PB) Data Transfer GSS Data Pool (3PB) DDN 12K Data Pool (4PB) DDN 10K Data Pool (1.5PB) Flash Data Pool (160TB)
27 Current file system upgrade status Storage upgrade completed in 2017: After the last town hall we setup a separate GPFS cluster to: Identify with the vendors (IBM and Mellanox) what went wrong during the first integration. Solve the remaining issues (mainly related to the Infiniband network). Extensively test and stress the ESS file system to be sure the new storage is stable. Currently: We gradually integrated the ESS storage into orga. We started the data migration from the DDN10 (~790 TB) and GSS (~2.2 PB) to the ESS pool (currently migrated ~27% of data). In future: Complete the current file-system upgrade (ETA 2018/03). Remove GSS and DDN10k from Orga after data migration completion. Upgrade client cluster and file system cluster to GPFS v
28 New storage purchase and integration In Dec 2017, we purchased: New Flash file system 260 TB for metadata and small files. New ESS file system 3.7 PB to be added to the existing storage. Integration schedule: We will work on a plan with IBM to integrate the new ESS storage and replace the metadata tier. ETA: April-May 2018 (need to coordinate with IBM). Storage tier after the upgrade Size NewFlash (Stores all metadata for the file system) 132 TB NewRamsan (Stores tiny files which see frequent use) 132 TB ESS (IBM storage where the current data is being migrated to) 5.1 PB NewESS 3.7 PB Total storage available after the upgrade: 8.8 PB 28
29 Compute upgrades for 2018 Login nodes New set of public login nodes to replace overloaded minerva2. Compute upgrade Newer racks of high density nodes to replace Manda compute partition. We will tailor the nodes based on usage (more memory? more cores? more GPUs? ) Infrastructure upgrade: New management and infrastructure nodes. New network switches. Dedicated data transfer nodes. Additional VMs for web services. A migration path to EDR+ Infiniband fabric. If you have special requirements for compute resources, please let us know, we are happy to work with you. 29
30 OS upgrade and package rebuild Centos 7 image is being tested on new login nodes: data2. A new set of load-balanced login nodes will be made available to users for CentOS 7 testing. We are currently rebuilding the software packages on a test cluster, which we will open for early user testing in 02/2018. The new pool of compute nodes (due this year) will be installed with Centos 7 and newer packages. We will update the rest of the computes partition, i.e., manda, mothra and bode, after the integration of the new compute nodes. We need your help to test the new OS and packages! 30
31 Demeter data science cluster The Demeter cluster has been run by Hammerbacher Lab and is being transferred to HPC. It is a Hadoop cluster with 80+ nodes, 3 PB storage space as an hdfs file system. the Demeter cluster is not under maintenance from any vendor, so when compute nodes or storage fail, they cannot be replaced. We are in the process of upgrading it to make it available to you to determine the demand for this type of cluster. We plan to open it for early user testing in April If you have an Apache/Spark pipeline which can benefit from this resource, let us know! 31
32 Cloud services - VM, containers, and other services Containers We will provide containers via Shifter or Singularity on Minerva by April This will be part of the new OS stack on the compute nodes. We will be adding additional GPU nodes (with newer GPUs) to support containers. VMs We are considering migrating Minerva user websites to multiple VMs to support multiple package requirements (would like your feedback). We are considering support for user VMs going forward (would like your feedback). Database We will provide support for MongoDB user databases going forward. 32
33 Documentation and training For most recent announcement and updates: Four training sessions will be offered this year. Two sets of training sessions in spring and fall. Topics include Introduction to Minerva and LSF job scheduler. Introduction to Scientific Computing BSR1015 is now a two credit course with an expanded lab. It s being taught this spring by Anthony Costa, PhD. Documentation update on the website ( Join our mail-list: hpcusers@mssm.edu Follow us on Minerva user group meetings will be scheduled as needed. We will refresh the website by March. We will add newer pages/articles as needed over next 3-6 months. We will provide additional training material (including slides) online. We are also considering a new ticket system/knowledge base (please give us feedback). 33
34 HPC Roadmap Finish ESS migration New ESS and Flash storage deployment CentOS 7 upgrade and package rebuild Cloud technology deployment and testing New Compute nodes Demeter data science cluster reinstall and deployment Compute node early testing Documentation and web page updates Spring training Fall training 34
35 Question and comments
36 Thank you!
Experiences using a multi-tiered GPFS file system at Mount Sinai. Bhupender Thakur Patricia Kovatch Francesca Tartagliogne Dansha Jiang
Experiences using a multi-tiered GPFS file system at Mount Sinai Bhupender Thakur Patricia Kovatch Francesca Tartagliogne Dansha Jiang Outline 1. Storage summary 2. Planning and Migration 3. Challenges
More informationTECHNICAL GUIDELINES FOR APPLICANTS TO PRACE 13 th CALL (T ier-0)
TECHNICAL GUIDELINES FOR APPLICANTS TO PRACE 13 th CALL (T ier-0) Contributing sites and the corresponding computer systems for this call are: BSC, Spain IBM System x idataplex CINECA, Italy Lenovo System
More informationGuillimin HPC Users Meeting. Bryan Caron
July 17, 2014 Bryan Caron bryan.caron@mcgill.ca McGill University / Calcul Québec / Compute Canada Montréal, QC Canada Outline Compute Canada News Upcoming Maintenance Downtime in August Storage System
More informationGuillimin HPC Users Meeting February 11, McGill University / Calcul Québec / Compute Canada Montréal, QC Canada
Guillimin HPC Users Meeting February 11, 2016 guillimin@calculquebec.ca McGill University / Calcul Québec / Compute Canada Montréal, QC Canada Compute Canada News Scheduler Updates Software Updates Training
More informationMagellan Project. Jeff Broughton NERSC Systems Department Head October 7, 2009
Magellan Project Jeff Broughton NERSC Systems Department Head October 7, 2009 1 Magellan Background National Energy Research Scientific Computing Center (NERSC) Argonne Leadership Computing Facility (ALCF)
More informationAn ESS implementation in a Tier 1 HPC Centre
An ESS implementation in a Tier 1 HPC Centre Maximising Performance - the NeSI Experience José Higino (NeSI Platforms and NIWA, HPC Systems Engineer) Outline What is NeSI? The National Platforms Framework
More informationHabanero Operating Committee. January
Habanero Operating Committee January 25 2017 Habanero Overview 1. Execute Nodes 2. Head Nodes 3. Storage 4. Network Execute Nodes Type Quantity Standard 176 High Memory 32 GPU* 14 Total 222 Execute Nodes
More informationGuillimin HPC Users Meeting. Bart Oldeman
June 19, 2014 Bart Oldeman bart.oldeman@mcgill.ca McGill University / Calcul Québec / Compute Canada Montréal, QC Canada Outline Compute Canada News Upcoming Maintenance Downtime in August Storage System
More informationGuillimin HPC Users Meeting November 16, 2017
Guillimin HPC Users Meeting November 16, 2017 guillimin@calculquebec.ca McGill University / Calcul Québec / Compute Canada Montréal, QC Canada Please be kind to your fellow user meeting attendees Limit
More informationOrganizational Update: December 2015
Organizational Update: December 2015 David Hudak Doug Johnson Alan Chalker www.osc.edu Slide 1 OSC Organizational Update Leadership changes State of OSC Roadmap Web app demonstration (if time) Slide 2
More informationTECHNICAL GUIDELINES FOR APPLICANTS TO PRACE 6 th CALL (Tier-0)
TECHNICAL GUIDELINES FOR APPLICANTS TO PRACE 6 th CALL (Tier-0) Contributing sites and the corresponding computer systems for this call are: GCS@Jülich, Germany IBM Blue Gene/Q GENCI@CEA, France Bull Bullx
More informationIntroduction to High-Performance Computing (HPC)
Introduction to High-Performance Computing (HPC) Computer components CPU : Central Processing Unit cores : individual processing units within a CPU Storage : Disk drives HDD : Hard Disk Drive SSD : Solid
More informationData storage services at KEK/CRC -- status and plan
Data storage services at KEK/CRC -- status and plan KEK/CRC Hiroyuki Matsunaga Most of the slides are prepared by Koichi Murakami and Go Iwai KEKCC System Overview KEKCC (Central Computing System) The
More informationLeonhard: a new cluster for Big Data at ETH
Leonhard: a new cluster for Big Data at ETH Bernd Rinn, Head of Scientific IT Services Olivier Byrde, Group leader High Performance Computing Bernd Rinn & Olivier Byrde 2017-02-15 1 Agenda Welcome address
More informationAzure SQL Database for Gaming Industry Workloads Technical Whitepaper
Azure SQL Database for Gaming Industry Workloads Technical Whitepaper Author: Pankaj Arora, Senior Software Engineer, Microsoft Contents 1 Introduction... 2 2 Proven Platform... 2 2.1 Azure SQL Database
More informationUsers and utilization of CERIT-SC infrastructure
Users and utilization of CERIT-SC infrastructure Equipment CERIT-SC is an integral part of the national e-infrastructure operated by CESNET, and it leverages many of its services (e.g. management of user
More informationOutline. March 5, 2012 CIRMMT - McGill University 2
Outline CLUMEQ, Calcul Quebec and Compute Canada Research Support Objectives and Focal Points CLUMEQ Site at McGill ETS Key Specifications and Status CLUMEQ HPC Support Staff at McGill Getting Started
More informationExtraordinary HPC file system solutions at KIT
Extraordinary HPC file system solutions at KIT Roland Laifer STEINBUCH CENTRE FOR COMPUTING - SCC KIT University of the State Roland of Baden-Württemberg Laifer Lustre and tools for ldiskfs investigation
More informationParallel File Systems. John White Lawrence Berkeley National Lab
Parallel File Systems John White Lawrence Berkeley National Lab Topics Defining a File System Our Specific Case for File Systems Parallel File Systems A Survey of Current Parallel File Systems Implementation
More informationTHE DEFINITIVE GUIDE FOR AWS CLOUD EC2 FAMILIES
THE DEFINITIVE GUIDE FOR AWS CLOUD EC2 FAMILIES Introduction Amazon Web Services (AWS), which was officially launched in 2006, offers you varying cloud services that are not only cost effective but scalable
More informationJÜLICH SUPERCOMPUTING CENTRE Site Introduction Michael Stephan Forschungszentrum Jülich
JÜLICH SUPERCOMPUTING CENTRE Site Introduction 09.04.2018 Michael Stephan JSC @ Forschungszentrum Jülich FORSCHUNGSZENTRUM JÜLICH Research Centre Jülich One of the 15 Helmholtz Research Centers in Germany
More informationStorage for HPC, HPDA and Machine Learning (ML)
for HPC, HPDA and Machine Learning (ML) Frank Kraemer, IBM Systems Architect mailto:kraemerf@de.ibm.com IBM Data Management for Autonomous Driving (AD) significantly increase development efficiency by
More informationHPC and IT Issues Session Agenda. Deployment of Simulation (Trends and Issues Impacting IT) Mapping HPC to Performance (Scaling, Technology Advances)
HPC and IT Issues Session Agenda Deployment of Simulation (Trends and Issues Impacting IT) Discussion Mapping HPC to Performance (Scaling, Technology Advances) Discussion Optimizing IT for Remote Access
More informationEnde-zu-Ende Datensicherungs-Architektur bei einem Pharmaunternehmen
Software Defined Data Protection mit Ende-zu-Ende Datensicherungs-Architektur bei einem Pharmaunternehmen Flexibler Speicher für Spectrum Protect 08. März 2017 Stefan Schädeli, SME Storage and Backup Andre
More informationOracle Autonomous Database
Oracle Autonomous Database Maria Colgan Master Product Manager Oracle Database Development August 2018 @SQLMaria #thinkautonomous Safe Harbor Statement The following is intended to outline our general
More informationUAntwerpen, 24 June 2016
Tier-1b Info Session UAntwerpen, 24 June 2016 VSC HPC environment Tier - 0 47 PF Tier -1 623 TF Tier -2 510 Tf 16,240 CPU cores 128/256 GB memory/node IB EDR interconnect Tier -3 HOPPER/TURING STEVIN THINKING/CEREBRO
More informationOUR CUSTOMER TERMS CLOUD SERVICES - INFRASTRUCTURE
CONTENTS 1 ABOUT THIS PART... 2 2 GENERAL... 2 3 CLOUD INFRASTRUCTURE (FORMERLY UTILITY HOSTING)... 2 4 TAILORED INFRASTRUCTURE (FORMERLY DEDICATED HOSTING)... 3 5 COMPUTE... 3 6 BACKUP & RECOVERY... 8
More informationStorage Supporting DOE Science
Storage Supporting DOE Science Jason Hick jhick@lbl.gov NERSC LBNL http://www.nersc.gov/nusers/systems/hpss/ http://www.nersc.gov/nusers/systems/ngf/ May 12, 2011 The Production Facility for DOE Office
More informationGraham vs legacy systems
New User Seminar Graham vs legacy systems This webinar only covers topics pertaining to graham. For the introduction to our legacy systems (Orca etc.), please check the following recorded webinar: SHARCNet
More informationGuillimin HPC Users Meeting June 16, 2016
Guillimin HPC Users Meeting June 16, 2016 guillimin@calculquebec.ca McGill University / Calcul Québec / Compute Canada Montréal, QC Canada Compute Canada News System Status Software Updates Training News
More informationDDN s Vision for the Future of Lustre LUG2015 Robert Triendl
DDN s Vision for the Future of Lustre LUG2015 Robert Triendl 3 Topics 1. The Changing Markets for Lustre 2. A Vision for Lustre that isn t Exascale 3. Building Lustre for the Future 4. Peak vs. Operational
More informationHPC learning using Cloud infrastructure
HPC learning using Cloud infrastructure Florin MANAILA IT Architect florin.manaila@ro.ibm.com Cluj-Napoca 16 March, 2010 Agenda 1. Leveraging Cloud model 2. HPC on Cloud 3. Recent projects - FutureGRID
More informationPurchasing Services AOC East Fowler Avenue Tampa, Florida (813) Web Address:
Purchasing Services AOC 200 4202 East Fowler Avenue Tampa, Florida 33620 (813) 974-2481 Web Address: http://usfweb2.usf.edu/purchasing/purch2.htm November 10, 2015 Invitation to Negotiate No. Entitled:
More informationCopyright 2011, Oracle and/or its affiliates. All rights reserved.
The following is intended to outline our general product direction. It is intended for information purposes only, and may not be incorporated into any contract. It is not a commitment to deliver any material,
More informationIBM Spectrum Scale vs EMC Isilon for IBM Spectrum Protect Workloads
89 Fifth Avenue, 7th Floor New York, NY 10003 www.theedison.com @EdisonGroupInc 212.367.7400 IBM Spectrum Scale vs EMC Isilon for IBM Spectrum Protect Workloads A Competitive Test and Evaluation Report
More informationDeploying virtualisation in a production grid
Deploying virtualisation in a production grid Stephen Childs Trinity College Dublin & Grid-Ireland TERENA NRENs and Grids workshop 2 nd September 2008 www.eu-egee.org EGEE and glite are registered trademarks
More informationMission-Critical Lustre at Santos. Adam Fox, Lustre User Group 2016
Mission-Critical Lustre at Santos Adam Fox, Lustre User Group 2016 About Santos One of the leading oil and gas producers in APAC Founded in 1954 South Australia Northern Territory Oil Search Cooper Basin
More informationData center requirements
Prerequisites, page 1 Data center workflow, page 2 Determine data center requirements, page 2 Gather data for initial data center planning, page 2 Determine the data center deployment model, page 3 Determine
More information1 Copyright 2011, Oracle and/or its affiliates. All rights reserved. reserved. Insert Information Protection Policy Classification from Slide 8
The following is intended to outline our general product direction. It is intended for information purposes only, and may not be incorporated into any contract. It is not a commitment to deliver any material,
More informationComet Virtualization Code & Design Sprint
Comet Virtualization Code & Design Sprint SDSC September 23-24 Rick Wagner San Diego Supercomputer Center Meeting Goals Build personal connections between the IU and SDSC members of the Comet team working
More informationTECHNICAL GUIDELINES FOR APPLICANTS TO PRACE 11th CALL (T ier-0)
TECHNICAL GUIDELINES FOR APPLICANTS TO PRACE 11th CALL (T ier-0) Contributing sites and the corresponding computer systems for this call are: BSC, Spain IBM System X idataplex CINECA, Italy The site selection
More informationIBM Spectrum NAS, IBM Spectrum Scale and IBM Cloud Object Storage
IBM Spectrum NAS, IBM Spectrum Scale and IBM Cloud Object Storage Silverton Consulting, Inc. StorInt Briefing 2017 SILVERTON CONSULTING, INC. ALL RIGHTS RESERVED Page 2 Introduction Unstructured data has
More informationIntroduction to BioHPC
Introduction to BioHPC New User Training [web] [email] portal.biohpc.swmed.edu biohpc-help@utsouthwestern.edu 1 Updated for 2015-06-03 Overview Today we re going to cover: What is BioHPC? How do I access
More informationBRC HPC Services/Savio
BRC HPC Services/Savio Krishna Muriki and Gregory Kurtzer LBNL/BRC kmuriki@berkeley.edu, gmk@lbl.gov SAVIO - The Need Has Been Stated Inception and design was based on a specific need articulated by Eliot
More informationOracle Real Application Clusters (RAC) 12c Release 2 What s Next?
Oracle Real Application Clusters (RAC) 12c Release 2 What s Next? Markus Michalewicz Senior Director of Product Management, Oracle RAC Development Markus.Michalewicz@oracle.com @OracleRACpm http://www.linkedin.com/in/markusmichalewicz
More informationGuillimin HPC Users Meeting April 13, 2017
Guillimin HPC Users Meeting April 13, 2017 guillimin@calculquebec.ca McGill University / Calcul Québec / Compute Canada Montréal, QC Canada Please be kind to your fellow user meeting attendees Limit to
More informationNetwork Design Considerations for Grid Computing
Network Design Considerations for Grid Computing Engineering Systems How Bandwidth, Latency, and Packet Size Impact Grid Job Performance by Erik Burrows, Engineering Systems Analyst, Principal, Broadcom
More informationDell EMC ScaleIO Ready Node
Essentials Pre-validated, tested and optimized servers to provide the best performance possible Single vendor for the purchase and support of your SDS software and hardware All-Flash configurations provide
More informationHitachi Adaptable Modular Storage and Hitachi Workgroup Modular Storage
O V E R V I E W Hitachi Adaptable Modular Storage and Hitachi Workgroup Modular Storage Modular Hitachi Storage Delivers Enterprise-level Benefits Hitachi Adaptable Modular Storage and Hitachi Workgroup
More informationGuillimin HPC Users Meeting December 14, 2017
Guillimin HPC Users Meeting December 14, 2017 guillimin@calculquebec.ca McGill University / Calcul Québec / Compute Canada Montréal, QC Canada Please be kind to your fellow user meeting attendees Limit
More informationSun Lustre Storage System Simplifying and Accelerating Lustre Deployments
Sun Lustre Storage System Simplifying and Accelerating Lustre Deployments Torben Kling-Petersen, PhD Presenter s Name Principle Field Title andengineer Division HPC &Cloud LoB SunComputing Microsystems
More informationHOW TO BUILD A MODERN AI
HOW TO BUILD A MODERN AI FOR THE UNKNOWN IN MODERN DATA 1 2016 PURE STORAGE INC. 2 Official Languages Act (1969/1988) 3 Translation Bureau 4 5 DAWN OF 4 TH INDUSTRIAL REVOLUTION BIG DATA, AI DRIVING CHANGE
More informationLecture 9: MIMD Architectures
Lecture 9: MIMD Architectures Introduction and classification Symmetric multiprocessors NUMA architecture Clusters Zebo Peng, IDA, LiTH 1 Introduction A set of general purpose processors is connected together.
More informationA Container On a Virtual Machine On an HPC? Presentation to HPC Advisory Council. Perth, July 31-Aug 01, 2017
A Container On a Virtual Machine On an HPC? Presentation to HPC Advisory Council Perth, July 31-Aug 01, 2017 http://levlafayette.com Necessary and Sufficient Definitions High Performance Computing: High
More informationNotes & Lessons Learned from a Field Engineer. Robert M. Smith, Microsoft
Notes & Lessons Learned from a Field Engineer Robert M. Smith, Microsoft SNIA Legal Notice The material contained in this tutorial is copyrighted by the SNIA. Member companies and individual members may
More informationUniversity at Buffalo Center for Computational Research
University at Buffalo Center for Computational Research The following is a short and long description of CCR Facilities for use in proposals, reports, and presentations. If desired, a letter of support
More informationStorage Strategies for vsphere 5.5 users
Storage Strategies for vsphere 5.5 users Silverton Consulting, Inc. StorInt Briefing 2 Introduction VMware vsphere is the number one hypervisor solution in the world with more than 500,000 customers worldwide.
More informationHPC Cloud at SURFsara
HPC Cloud at SURFsara Offering cloud as a service SURF Research Boot Camp 21st April 2016 Ander Astudillo Markus van Dijk What is cloud computing?
More informationBeeGFS. Parallel Cluster File System. Container Workshop ISC July Marco Merkel VP ww Sales, Consulting
BeeGFS The Parallel Cluster File System Container Workshop ISC 28.7.18 www.beegfs.io July 2018 Marco Merkel VP ww Sales, Consulting HPC & Cognitive Workloads Demand Today Flash Storage HDD Storage Shingled
More informationThe Leading Parallel Cluster File System
The Leading Parallel Cluster File System www.thinkparq.com www.beegfs.io ABOUT BEEGFS What is BeeGFS BeeGFS (formerly FhGFS) is the leading parallel cluster file system, developed with a strong focus on
More informationProviding a first class, enterprise-level, backup and archive service for Oxford University
Providing a first class, enterprise-level, backup and archive service for Oxford University delivering responsive, innovative IT 11th June 2013 11 th June 2013 Contents Service description Service infrastructure
More informationBring Context To Your Machine Data With Hadoop, RDBMS & Splunk
Bring Context To Your Machine Data With Hadoop, RDBMS & Splunk Raanan Dagan and Rohit Pujari September 25, 2017 Washington, DC Forward-Looking Statements During the course of this presentation, we may
More informationChallenges in making Lustre systems reliable
Challenges in making Lustre systems reliable Roland Laifer STEINBUCH CENTRE FOR COMPUTING - SCC KIT University of the State Roland of Baden-Württemberg Laifer Challenges and in making Lustre systems reliable
More informationIBM Emulex 16Gb Fibre Channel HBA Evaluation
IBM Emulex 16Gb Fibre Channel HBA Evaluation Evaluation report prepared under contract with Emulex Executive Summary The computing industry is experiencing an increasing demand for storage performance
More informationChoosing Resources Wisely Plamen Krastev Office: 38 Oxford, Room 117 FAS Research Computing
Choosing Resources Wisely Plamen Krastev Office: 38 Oxford, Room 117 Email:plamenkrastev@fas.harvard.edu Objectives Inform you of available computational resources Help you choose appropriate computational
More informationPreparing GPU-Accelerated Applications for the Summit Supercomputer
Preparing GPU-Accelerated Applications for the Summit Supercomputer Fernanda Foertter HPC User Assistance Group Training Lead foertterfs@ornl.gov This research used resources of the Oak Ridge Leadership
More informationHigh Performance Computing Resources at MSU
MICHIGAN STATE UNIVERSITY High Performance Computing Resources at MSU Last Update: August 15, 2017 Institute for Cyber-Enabled Research Misson icer is MSU s central research computing facility. The unit
More informationPrivate Cloud Database Consolidation Name, Title
Private Cloud Database Consolidation Name, Title Agenda Cloud Introduction Business Drivers Cloud Architectures Enabling Technologies Service Level Expectations Customer Case Studies Conclusions
More informationIsilon: Raising The Bar On Performance & Archive Use Cases. John Har Solutions Product Manager Unstructured Data Storage Team
Isilon: Raising The Bar On Performance & Archive Use Cases John Har Solutions Product Manager Unstructured Data Storage Team What we ll cover in this session Isilon Overview Streaming workflows High ops/s
More informationirods and Objectstorage UGM 2016, Chapel Hill / Othmar Weber, Bayer Business Services / v0.2
irods and Objectstorage UGM 2016, Chapel Hill 2016-06-08 / Othmar Weber, Bayer Business Services / v0.2 Agenda irods at Bayer Situation and call for action Object Storage PoC Pillow talks Page 2 Overview
More informationUsing DC/OS for Continuous Delivery
Using DC/OS for Continuous Delivery DevPulseCon 2017 Elizabeth K. Joseph, @pleia2 Mesosphere 1 Elizabeth K. Joseph, Developer Advocate, Mesosphere 15+ years working in open source communities 10+ years
More informationDeveloping Enterprise Cloud Solutions with Azure
Developing Enterprise Cloud Solutions with Azure Java Focused 5 Day Course AUDIENCE FORMAT Developers and Software Architects Instructor-led with hands-on labs LEVEL 300 COURSE DESCRIPTION This course
More informationUnderstanding Cloud Migration. Ruth Wilson, Data Center Services Executive
Understanding Cloud Migration Ruth Wilson, Data Center Services Executive rhwilson@us.ibm.com Migrating to a Cloud is similar to migrating data and applications between data centers with a few key differences
More informationALICE Grid Activities in US
ALICE Grid Activities in US 1 ALICE-USA Computing Project ALICE-USA Collaboration formed to focus on the ALICE EMCal project Construction, installation, testing and integration participating institutions
More informationHyper-Convergence De-mystified. Francis O Haire Group Technology Director
Hyper-Convergence De-mystified Francis O Haire Group Technology Director The Cloud Era Is Well Underway Rapid Time to Market I deployed my application in five minutes. Fractional IT Consumption I use and
More informationNew Approach to Unstructured Data
Innovations in All-Flash Storage Deliver a New Approach to Unstructured Data Table of Contents Developing a new approach to unstructured data...2 Designing a new storage architecture...2 Understanding
More informationGenius Quick Start Guide
Genius Quick Start Guide Overview of the system Genius consists of a total of 116 nodes with 2 Skylake Xeon Gold 6140 processors. Each with 18 cores, at least 192GB of memory and 800 GB of local SSD disk.
More informationGuillimin HPC Users Meeting March 16, 2017
Guillimin HPC Users Meeting March 16, 2017 guillimin@calculquebec.ca McGill University / Calcul Québec / Compute Canada Montréal, QC Canada Please be kind to your fellow user meeting attendees Limit to
More informationUNIFY DATA AT MEMORY SPEED. Haoyuan (HY) Li, Alluxio Inc. VAULT Conference 2017
UNIFY DATA AT MEMORY SPEED Haoyuan (HY) Li, CEO @ Alluxio Inc. VAULT Conference 2017 March 2017 HISTORY Started at UC Berkeley AMPLab In Summer 2012 Originally named as Tachyon Rebranded to Alluxio in
More informationLeveraging the power of Flash to Enable IT as a Service
Leveraging the power of Flash to Enable IT as a Service Steve Knipple CTO / VP Engineering August 5, 2014 In summary Flash in the datacenter, simply put, solves numerous problems. The challenge is to use
More informationDatabase Level 100. Rohit Rahi November Copyright 2018, Oracle and/or its affiliates. All rights reserved.
Database Level 100 Rohit Rahi November 2018 1 Safe Harbor Statement The following is intended to outline our general product direction. It is intended for information purposes only, and may not be incorporated
More informationWorkload management at KEK/CRC -- status and plan
Workload management at KEK/CRC -- status and plan KEK/CRC Hiroyuki Matsunaga Most of the slides are prepared by Koichi Murakami and Go Iwai CPU in KEKCC Work server & Batch server Xeon 5670 (2.93 GHz /
More informationEmerging Technologies for HPC Storage
Emerging Technologies for HPC Storage Dr. Wolfgang Mertz CTO EMEA Unstructured Data Solutions June 2018 The very definition of HPC is expanding Blazing Fast Speed Accessibility and flexibility 2 Traditional
More informationSPARC 2 Consultations January-February 2016
SPARC 2 Consultations January-February 2016 1 Outline Introduction to Compute Canada SPARC 2 Consultation Context Capital Deployment Plan Services Plan Access and Allocation Policies (RAC, etc.) Discussion
More informationSQL Server 2014 Upgrade
SQL Server 2014 Upgrade Case study featuring In-Memory OLTP and Hybrid-Cloud Scenarios Evgeny Ternovsky, Program Manager II, Data Platform Group Bill Kan, Service Engineer II, Data Platform Group Background
More informationVxRack FLEX Technical Deep Dive: Building Hyper-converged Solutions at Rackscale. Kiewiet Kritzinger DELL EMC CPSD Snr varchitect
VxRack FLEX Technical Deep Dive: Building Hyper-converged Solutions at Rackscale Kiewiet Kritzinger DELL EMC CPSD Snr varchitect Introduction to hyper-converged Focus on innovation, not IT integration
More informationGuillimin HPC Users Meeting January 13, 2017
Guillimin HPC Users Meeting January 13, 2017 guillimin@calculquebec.ca McGill University / Calcul Québec / Compute Canada Montréal, QC Canada Please be kind to your fellow user meeting attendees Limit
More informationData Analytics and Storage System (DASS) Mixing POSIX and Hadoop Architectures. 13 November 2016
National Aeronautics and Space Administration Data Analytics and Storage System (DASS) Mixing POSIX and Hadoop Architectures 13 November 2016 Carrie Spear (carrie.e.spear@nasa.gov) HPC Architect/Contractor
More informationSession 4112 BW NLS Data Archiving: Keeping BW in Tip-Top Shape for SAP HANA. Sandy Speizer, PSEG SAP Principal Architect
Session 4112 BW NLS Data Archiving: Keeping BW in Tip-Top Shape for SAP HANA Sandy Speizer, PSEG SAP Principal Architect Public Service Enterprise Group PSEG SAP ECC (R/3) Core Implementation SAP BW Implementation
More informationSurveillance Dell EMC Storage with Aimetis Symphony
Surveillance Dell EMC Storage with Aimetis Symphony Configuration Guide H13960 REV 3.1 Copyright 2016-2017 Dell Inc. or its subsidiaries. All rights reserved. Published August 2016 Dell believes the information
More informationHitachi Adaptable Modular Storage and Workgroup Modular Storage
O V E R V I E W Hitachi Adaptable Modular Storage and Workgroup Modular Storage Modular Hitachi Storage Delivers Enterprise-level Benefits Hitachi Data Systems Hitachi Adaptable Modular Storage and Workgroup
More informationClustering. Research and Teaching Unit
Clustering Research and Teaching Unit Disclaimer...though it cannot hope to be useful or informative on all matters, it does at least make the reassuring claim, that where it is inaccurate it is at least
More informationBill Boroski LQCD-ext II Contractor Project Manager
Bill Boroski LQCD-ext II Contractor Project Manager boroski@fnal.gov Robert D. Kennedy LQCD-ext II Assoc. Contractor Project Manager kennedy@fnal.gov USQCD All-Hands Meeting Jefferson Lab April 28-29,
More informationLustre usages and experiences
Lustre usages and experiences at German Climate Computing Centre in Hamburg Carsten Beyer High Performance Computing Center Exclusively for the German Climate Research Limited Company, non-profit Staff:
More informationMIGRATING TO THE SHARED COMPUTING CLUSTER (SCC) SCV Staff Boston University Scientific Computing and Visualization
MIGRATING TO THE SHARED COMPUTING CLUSTER (SCC) SCV Staff Boston University Scientific Computing and Visualization 2 Glenn Bresnahan Director, SCV MGHPCC Buy-in Program Kadin Tseng HPC Programmer/Consultant
More informationIBM Case Manager on Cloud
Service Description IBM Case Manager on Cloud This Service Description describes the Cloud Service IBM provides to Client. Client means the company and its authorized users and recipients of the Cloud
More informationVeritas NetBackup Appliance Family OVERVIEW BROCHURE
Veritas NetBackup Appliance Family OVERVIEW BROCHURE Veritas NETBACKUP APPLIANCES Veritas understands the shifting needs of the data center and offers NetBackup Appliances as a way for customers to simplify
More informationIBM Spectrum Scale IO performance
IBM Spectrum Scale 5.0.0 IO performance Silverton Consulting, Inc. StorInt Briefing 2 Introduction High-performance computing (HPC) and scientific computing are in a constant state of transition. Artificial
More informationNext-Generation NVMe-Native Parallel Filesystem for Accelerating HPC Workloads
Next-Generation NVMe-Native Parallel Filesystem for Accelerating HPC Workloads Liran Zvibel CEO, Co-founder WekaIO @liranzvibel 1 WekaIO Matrix: Full-featured and Flexible Public or Private S3 Compatible
More informationOverview of the Texas Advanced Computing Center. Bill Barth TACC September 12, 2011
Overview of the Texas Advanced Computing Center Bill Barth TACC September 12, 2011 TACC Mission & Strategic Approach To enable discoveries that advance science and society through the application of advanced
More information