Establishing Applicability of SSDs to LHC Tier-2 Hardware Configuration



Similar documents
Intel Solid- State Drive Data Center P3700 Series NVMe Hybrid Storage Performance

SSDs: Practical Ways to Accelerate Virtual Servers

SSDs: Practical Ways to Accelerate Virtual Servers

Accelerating Enterprise Applications and Reducing TCO with SanDisk ZetaScale Software

Cloud Storage. Parallels. Performance Benchmark Results. White Paper.

Evaluation Report: Supporting Microsoft Exchange on the Lenovo S3200 Hybrid Array

The Data Placement Challenge

Analysis of VDI Storage Performance During Bootstorm

SLIDE 1 Previous Next Exit

Increasing Storage Performance

Accelerating Server Storage Performance on Lenovo ThinkServer

F600Q 8Gb FC Storage Performance Report Date: 2012/10/30

DIABLO TECHNOLOGIES MEMORY CHANNEL STORAGE AND VMWARE VIRTUAL SAN : VDI ACCELERATION

Lab Evaluation of NetApp Hybrid Array with Flash Pool Technology

The Economics of Intelligent Hybrid Storage. An Enmotus White Paper Sep 2014

PARALLELS CLOUD STORAGE

Mixed All-Flash Array Delivers Safer High Performance

Scientific Computing Data Management Visions

Integrating SSDs into Virtual Servers

Optimizing SQL Server Storage Performance with the PowerEdge R720

Flash Performance in Storage Systems. Bill Moore Chief Engineer, Storage Systems Sun Microsystems

Parallels Cloud Server 6.0

Hyperscale Use Cases for Scaling Out with Flash. David Olszewski

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

Parallels Cloud Server 6.0

Advances in Virtualization In Support of In-Memory Big Data Applications

Status of Grid Activities in Pakistan. FAWAD SAEED National Centre For Physics, Pakistan

VMware Virtual SAN Backup Using VMware vsphere Data Protection Advanced SEPTEMBER 2014

Evaluation Report: Accelerating SQL Server Database Performance with the Lenovo Storage S3200 SAN Array


SanDisk SSD Boot Storm Testing for Virtual Desktop Infrastructure (VDI)

White paper. QNAP Turbo NAS with SSD Cache

Automated Data-Aware Tiering

Can Flash help you ride the Big Data Wave? Steve Fingerhut Vice President, Marketing Enterprise Storage Solutions Corporation

Analyzing Big Data with Splunk A Cost Effective Storage Architecture and Solution

Running Highly Available, High Performance Databases in a SAN-Free Environment

Low-cost

Scaling from Datacenter to Client

LEVERAGING FLASH MEMORY in ENTERPRISE STORAGE. Matt Kixmoeller, Pure Storage

Intel Solid-State Drives Increase Productivity of Product Design and Simulation

Flash at the price of disk Redefining the Economics of Storage. Kris Van Haverbeke Enterprise Marketing Manager Dell Belux

The IntelliMagic White Paper: Storage Performance Analysis for an IBM Storwize V7000

An Introduction - ZNetLive's Hybrid Dedicated Servers

Virtuozzo 7 Technical Preview - Virtual Machines Getting Started Guide

Architecting High-Speed Data Streaming Systems. Sujit Basu

UNIFIED HYBRID STORAGE. Performance, Availability and Scale for Any SAN and NAS Workload in Your Environment

Converged storage architecture for Oracle RAC based on NVMe SSDs and standard x86 servers

HP 3PAR StoreServ 8000 Storage - what s new

Marvell DragonFly. TPC-C OLTP Database Benchmark: 20x Higher-performance using Marvell DragonFly NVCACHE with SanDisk X110 SSD 256GB

Comparison of Hybrid Flash Storage System Performance

N /150/151/160 RAID Controller. N MegaRAID CacheCade. Feature Overview

Intel RAID SSD Cache Controller RCS25ZB040

MaxDeploy Ready. Hyper- Converged Virtualization Solution. With SanDisk Fusion iomemory products

High Performance. CAEA elearning Series. Jonathan G. Dudley, Ph.D. 06/09/ CAE Associates

How SSDs Fit in Different Data Center Applications

Implementing Enterprise Disk Arrays Using Open Source Software. Marc Smith Mott Community College - Flint, MI Merit Member Conference 2012

Certification Document bluechip STORAGEline R54300s NAS-Server 03/06/2014. bluechip STORAGEline R54300s NAS-Server system

System Architecture. In-Memory Database

præsentation oktober 2011

CMS Tier-3 cluster at NISER. Dr. Tania Moulik

POSIX and Object Distributed Storage Systems

System requirements for A+

firemon Powering Proactive Security Appliance Features: Meet the Family Quick initial setup Hardened O/S

WHITE PAPER. Drobo TM Hybrid Storage TM

Client-aware Cloud Storage

SAP Running on an EMC Virtualized Infrastructure and SAP Deployment of Fully Automated Storage Tiering

HP SN1000E 16 Gb Fibre Channel HBA Evaluation

Evaluation Report: Supporting Multiple Workloads with the Lenovo S3200 Storage Array

Fusion iomemory iodrive PCIe Application Accelerator Performance Testing

USB Flash Drives as an Energy Efficient Storage Alternative

D1.2 Network Load Balancing

SUN HARDWARE FROM ORACLE: PRICING FOR EDUCATION

IOmark- VDI. HP HP ConvergedSystem 242- HC StoreVirtual Test Report: VDI- HC b Test Report Date: 27, April

Removing Performance Bottlenecks in Databases with Red Hat Enterprise Linux and Violin Memory Flash Storage Arrays. Red Hat Performance Engineering

Flash Memory Arrays Enabling the Virtualized Data Center. July 2010

EMC SYMMETRIX VMAX 20K STORAGE SYSTEM

AirWave 7.7. Server Sizing Guide

Using Synology SSD Technology to Enhance System Performance. Based on DSM 5.2

The Hardware Dilemma. Stephanie Best, SGI Director Big Data Marketing Ray Morcos, SGI Big Data Engineering

nexsan NAS just got faster, easier and more affordable.

SECURE Web Gateway Sizing Guide

DSS. High performance storage pools for LHC. Data & Storage Services. Łukasz Janyst. on behalf of the CERN IT-DSS group

HP Z Turbo Drive PCIe SSD

White Paper. Educational. Measuring Storage Performance

Deep Dive on SimpliVity s OmniStack A Technical Whitepaper

Colgate-Palmolive selects SAP HANA to improve the speed of business analytics with IBM and SAP

Monitoring the Grid at local, national, and global levels

VMware Virtual SAN 6.0 Performance

Getting the Most Out of Flash Storage

Software-defined Storage Architecture for Analytics Computing

CERN Cloud Storage Evaluation Geoffray Adde, Dirk Duellmann, Maitane Zotes CERN IT

The next step in Software-Defined Storage with Virtual SAN

How To Speed Up A Flash Flash Storage System With The Hyperq Memory Router

VMware Software-Defined Storage Vision

VMware Virtual SAN and VMware Horizon 6: Cost Leadership Through Storage Savings WHITE PAPER

How To Build A Cloud Computing Datacenter

Using Synology SSD Technology to Enhance System Performance Synology Inc.

Brainlab Node TM Technical Specifications

All-Flash Arrays. A real market segment or analyst hype? Chris M Evans. Amsterdam, 24th September 2015

CloudSpeed SATA SSDs Support Faster Hadoop Performance and TCO Savings

Transcription:

Establishing Applicability of SSDs to LHC Tier-2 Hardware Configuration A CHEP 2010 presentation by: Sam Skipsey and The GridPP Storage Group With particular acknowledgments to: Wahid Bhimji (go see his talk on wider Storage Performance matters) Dan van der Ster (HammerCloud awesomeness)

Itinerary Background Tests: Glasgow hardware HammerClouds, blktrace Results Why not remote i/o? Conclusions

Background Particle Physics analysis is I/O intensive. Particle Physics analysis is single-threaded. Modern servers are very multicore. Modern storage is not (usually) multiheaded. SSDs provide much faster seeks than HDDs, though... Why not use SSDs for worker nodes (or servers)?

Glasgow Setup Conventional Worker nodes: 8 cores (2 4core Intel Xeon E5420, 2.5GHz) 1Gb networking to storage single 7200RPM SATA disk (partitioned) 24 core node (Magny Cours test box)

Test hardware 7200RPM 500GB SATA HDD Standard server-class hard disk. Kingston SSDNow V-series 128GB SSD Value SSD option. Intel X-25 G2 M 160GB SSD Commodity SSD option. Deliberately only affordable solutions!

Blktrace SL5 + only (needs kernel > 2.6.10+) reads raw kernel io events from debugfs Output to a device separate from the one being monitored Process with: blkparse (statistics) seekwatcher (graphs)

HammerClouds ATLAS (CMS, LHCb) automated testing framework. Uses Ganga to automatically load sites with test jobs and maintain statistics on them. http://hammercloud.cern.ch/ HC tests stored forever: 1332, 1334, 1348 most relevant tests

The test Use HammerCloud to send identical jobs to a subcluster at Glasgow. All jobs stage their files to the worker. Replace some of the working storage on workers with SSDs (and other things). Compare efficiencies and collect data.

Results (FileStager) Jobs:Cores Storage Efficiency Throughput Standard Node 8:8 1 Kingston Value SSD 60% 4.5 8:8 1 SATA HDD 75% 5.5 8:8 1 Intel X25 SSD 80% 6 8:8 2 SATA HDD (RAID 1) 83% 6.6 8:8 2 SATA HDD (RAID 0) 90% 7 Magny-Cours Node 24:24 1 Intel X25 SSD 50% 12 24:24 2 SATA HDD (RAID 0) 86% 21 Single Occupancy Efficiency (Measured) 1 SATA HDD 90% 0.9

Blktrace (HDD)

Blktrace (SSD)

Blktrace (RAID 0)

Price/performance Intel X25 G2 M - 340 / 160GB ( 2.13 / GB) 4.25 per %efficiency RAID-0 Hard disks - 130 / 1TB ( 0.13 / GB) 1.44 per %efficiency For a 2000 worker node, the effective difference is on the order of 10 to 15% of the cost. ATLAS require 50GB scratch per core!

But what about remote I/O? Why not access data with direct rfio against disk server, if local io isn t sufficient? We tested this too. HammerCloud against same data. DQ2_LOCAL remote IO jobs sent. Caveat: all nodes limited to 1Gb/s links.

Results (Remote I/O) Jobs:Cores Storage Efficiency Throughput Standard Node 8:8 1 Kingston Value SSD 67% 5.35 8:8 1 Intel X25 SSD 73% 5.86 8:8 2 SATA HDD (RAID 1) 73% 5.88 8:8 1 SATA HDD 78% 6.25 Magny-Cours Node 24:24 2 SATA HDD (RAID 0) 73% 17.4 24:24 3 SATA HDD (RAID 0) 76% 18.2

Real Analysis / pcache Node type Efficiency Test efficiency Intel X25 SSD 78% 80% 2 SATA HDD (RAID 0) 88% 90% Cluster was retrofitted with RAID 0 for all but the Intel nodes. Efficiency for sample of ATLAS analysis pilots from 1 September - 3 September taken. Nodes also now have pcache installed... but we see no statistical improvement here

Metrics and Conclusions Metrics should be taken with respect to cost. There is a minimum effective IOPs per core. Above that limit, bandwidth is more important Write efficiency issues with SSDs show in limited performance gains in some metrics.. RAID0 wins vs current SSDs Back in 2 years for a rematch?

Addendum: Server Class Machines What front-end servers might benefit from SSDs? Database backends (SEs, LBs) CREAM CE sandbox dir creation. Note that all of these are also improved by better caching, buffering etc. Tests in progress at Glasgow for the former cases.