Ceph vs Swift Performance Evaluation on a Small Cluster. edupert monthly call Jul 24, 2014

Similar documents
클라우드스토리지구축을 위한 ceph 설치및설정

Enterprise Ceph: Everyway, your way! Amit Dell Kyle Red Hat Red Hat Summit June 2016

OpenIO SDS on ARM A practical and cost-effective object storage infrastructure based on SoYouStart dedicated ARM servers.

Is Open Source good enough? A deep study of Swift and Ceph performance. 11/2013

Operating an OpenStack Cloud

A fields' Introduction to SUSE Enterprise Storage TUT91098

A Gentle Introduction to Ceph

All-NVMe Performance Deep Dive Into Ceph + Sneak Preview of QLC + NVMe Ceph

Ceph Intro & Architectural Overview. Abbas Bangash Intercloud Systems

THE CEPH POWER SHOW. Episode 2 : The Jewel Story. Daniel Messer Technical Marketing Red Hat Storage. Karan Singh Sr. Storage Architect Red Hat Storage

Building Service Platforms using OpenStack and CEPH: A University Cloud at Humboldt University

November 7, DAN WILSON Global Operations Architecture, Concur. OpenStack Summit Hong Kong JOE ARNOLD

Big Data in OpenStack Storage

W H I T E P A P E R. Comparison of Storage Protocol Performance in VMware vsphere 4

Ceph Software Defined Storage Appliance

virtual machine block storage with the ceph distributed storage system sage weil xensummit august 28, 2012

ROCK INK PAPER COMPUTER

Cloudian Sizing and Architecture Guidelines

Hyper-converged infrastructure with Proxmox VE virtualization platform and integrated Ceph Storage.

MySQL and Ceph. A tale of two friends

Summary optimized CRUSH algorithm more than 10% read performance improvement Design and Implementation: 1. Problem Identification 2.

Performance Testing Ceph with CBT

Red Hat Ceph Storage and Samsung NVMe SSDs for intensive workloads

Kinetic drive. Bingzhe Li

A New Key-value Data Store For Heterogeneous Storage Architecture Intel APAC R&D Ltd.

Re-Architecting Cloud Storage with Intel 3D XPoint Technology and Intel 3D NAND SSDs

Ceph Intro & Architectural Overview. Federico Lucifredi Product Management Director, Ceph Storage Vancouver & Guadalajara, May 18th, 2015

Current Status of the Ceph Based Storage Systems at the RACF

OpenStack Swift Workshop

Extremely Fast Distributed Storage for Cloud Service Providers

Block Storage Service: Status and Performance

SolidFire and Ceph Architectural Comparison

SUSE OpenStack Cloud Production Deployment Architecture. Guide. Solution Guide Cloud Computing.

Deploy a High-Performance Database Solution: Cisco UCS B420 M4 Blade Server with Fusion iomemory PX600 Using Oracle Database 12c

-Presented By : Rajeshwari Chatterjee Professor-Andrey Shevel Course: Computing Clusters Grid and Clouds ITMO University, St.

Certification Document Supermicro SSG-6027R-E1R12T 04/30/2014. Supermicro SSG-6027R-E1R12T system

Distributed Systems. 31. The Cloud: Infrastructure as a Service Paul Krzyzanowski. Rutgers University. Fall 2013

What's new in Jewel for RADOS? SAMUEL JUST 2015 VAULT

A FLEXIBLE ARM-BASED CEPH SOLUTION

Scaling Internet TV Content Delivery ALEX GUTARIN DIRECTOR OF ENGINEERING, NETFLIX

Cloud Open Source Innovation on Software Defined Storage

UH-Sky informasjonsmøte

The Lion of storage systems

Windows NAS Delivering Seamless Integration with All Windows Computers and Servers. Windows Storage Server

The Comparison of Ceph and Commercial Server SAN. Yuting Wu AWcloud

How to backup Ceph at scale. FOSDEM, Brussels,

Next-Generation Cloud Platform

Low overhead virtual machines tracing in a cloud infrastructure

Using Cloud Services behind SGI DMF

Understanding Write Behaviors of Storage Backends in Ceph Object Store

Benchmark of a Cubieboard cluster

Deploying Software Defined Storage for the Enterprise with Ceph. PRESENTATION TITLE GOES HERE Paul von Stamwitz Fujitsu

Cluster Setup and Distributed File System

Installation and Cluster Deployment Guide

Highly accurate simulations of big-data clusters for system planning and optimization

PSA: Performance and Space-Aware Data Layout for Hybrid Parallel File Systems

Performance Comparisons of Dell PowerEdge Servers with SQL Server 2000 Service Pack 4 Enterprise Product Group (EPG)

Evaluation and Integration of OCP Servers from Software Perspective. Internet Initiative Japan Inc. Takashi Sogabe

vsan Stretched Cluster Bandwidth Sizing First Published On: Last Updated On:

MySQL and Ceph. MySQL in the Cloud Head-to-Head Performance Lab. 1:20pm 2:10pm Room :20pm 3:10pm Room 203

Cloud Programming. Programming Environment Oct 29, 2015 Osamu Tatebe

COP Cloud Computing. Presented by: Sanketh Beerabbi University of Central Florida

Ceph at DTU Risø Frank Schilder

Introducing SUSE Enterprise Storage 5

Vess A2000 Series. NVR Storage Appliance. SeeTec Surveillance Solution. Version PROMISE Technology, Inc. All Rights Reserved.

Implementing SQL Server 2016 with Microsoft Storage Spaces Direct on Dell EMC PowerEdge R730xd

Cisco UCS S3260 Storage Server and Red Hat Ceph Storage Performance

Monitoring Testbed Experiments with MonEx

OpenStack and Ceph The winning pair OPENSTACK SUMMIT ATLANTA MAY 2014

Supermicro All-Flash NVMe Solution for Ceph Storage Cluster

StorPool Distributed Storage Software Technical Overview

Milestone Solution Partner IT Infrastructure Components Certification Report

CSE 124: Networked Services Lecture-17

Ceph in a Flash. Micron s Adventures in All-Flash Ceph Storage. Ryan Meredith & Brad Spiers, Micron Principal Solutions Engineer and Architect

Parallels Remote Application Server. Scalability Testing with Login VSI

Andrzej Jakowski, Armoun Forghan. Apr 2017 Santa Clara, CA

Next Generation Computing Architectures for Cloud Scale Applications

Microsoft Exchange Server 2010 workload optimization on the new IBM PureFlex System

The Oracle Database Appliance I/O and Performance Architecture

Microsoft SQL Server 2012 Fast Track Reference Configuration Using PowerEdge R720 and EqualLogic PS6110XV Arrays

VMware vsphere Beginner s Guide

Contrail Cloud Platform Architecture

Lenovo - Excelero NVMesh Reference Architecture

SCHOOL OF PHYSICAL, CHEMICAL AND APPLIED SCIENCES

Microsoft SQL Server in a VMware Environment on Dell PowerEdge R810 Servers and Dell EqualLogic Storage

Understanding System Characteristics of Online Erasure Coding on Scalable, Distributed and Large-Scale SSD Array Systems

Certification Document macle GmbH IBM System xx3650 M4 03/06/2014. macle GmbH IBM System x3650 M4

Contrail Cloud Platform Architecture

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

Getting to Know Apache CloudStack

Vess A2000 Series NVR Storage Appliance

Exam : S Title : Snia Storage Network Management/Administration. Version : Demo

Microsoft SharePoint Server 2010

Version 1.26 Installation Guide for On-Premise Uila Deployment

A product by CloudFounders. Wim Provoost Open vstorage

Reference Architecture - Microsoft SharePoint Server 2013 on Dell PowerEdge R630

CloudOpen Europe 2013 SYNNEFO: A COMPLETE CLOUD STACK OVER TECHNICAL LEAD, SYNNEFO

Distributed File Storage in Multi-Tenant Clouds using CephFS

High Availability for Enterprise Clouds: Oracle Solaris Cluster and OpenStack

Samba and Ceph. Release the Kraken! David Disseldorp

Transcription:

Ceph vs Swift Performance Evaluation on a Small Cluster edupert monthly call July, 24th 2014

About me Vincenzo Pii Researcher @ Leading research initiative on Cloud Storage Under the theme IaaS More on ICCLab: www.cloudcomp.ch

About this work Performance evaluation study on cloud storage Small installations Hardware resources hosted at the ZHAW ICCLab data center in Winterthur Two OpenStack clouds (stable and experimental) One cluster dedicated to storage research

INTRODUCTION

Cloud storage Cloud storage Based on distributed, parallel, fault-tolerant file systems Distributed resources exposed through a single homogeneous interface Typical requirements Highly scalable Replication management Redundancy (no single point of failure) Data distribution Object storage A way to manage/access data in a storage system Typical alternatives Block storage File storage

Ceph and Swift Ceph (ceph.com) Supported by Inktank Recently purchased by RedHat (owners of GlusterFS) Mostly developed in C++ Started as PhD thesis project in 2006 Block, file and object storage Swift (launchpad.net/swift) OpenStack object storage Completely written in Python RESTful HTTP APIs

Objectives of the study 1. Performance evaluation of Ceph and Swift on a small cluster Private storage Storage backend for own-apps with limited requirements in size Experimental environments 2. Evaluate Ceph maturity and stability Swift already widely deployed and industry-proven 3. Hands-on experience Configuration Tooling

CONFIGURATION AND PERFORMANCE OF SINGLE COMPONENTS

Network configuration Three servers on a dedicated VLAN 1 Gbps NICs 100BaseT cabling Node 1 (.2) Node 2 (.3) Node 3 (.4) 10.0.5.x/24

Servers configuration Hardware Lynx CALLEO Application Server 1240 2x Intel Xeon E5620 (4 core) 8x 8 GB DDR3 SDRAM, 1333 MHz, registered, ECC 4x 1 TB Enterprise SATA-3 Hard Disk, 7200 RPM, 6 Gb/s (Seagate ST1000NM0011) 2x Gigabit Ethernet network interfaces Operating system Ubuntu 14.04 Server Edition with Kernel 3.13.0-24- generic

Disks performance READ: $ sudo hdparm -t --direct /dev/sdb1 /dev/sdb1: Timing O_DIRECT disk reads: 430 MB in 3.00 seconds = 143.17 MB/sec WRITE: $ dd if=/dev/zero of=anof bs=1g count=1 oflag=direct 1+0 records in 1+0 records out 1073741824 bytes (1.1 GB) copied, 8.75321 s, 123 MB/s

Network performance $ iperf -c ceph-osd0 ------------------------------------------------------------ Client connecting to ceph-osd0, TCP port 5001 TCP window size: 85.0 KByte (default) ------------------------------------------------------------ [ 3] local 10.0.5.2 port 41012 connected with 10.0.5.3 port 5001 [ ID] Interval Transfer Bandwidth [ 3] 0.0-10.0 sec 1.10 GBytes 942 Mbits/sec 942 Mbits/s 117.5 MB/s

CLOUD STORAGE CONFIGURATION

Ceph OSDs cluster-admin@ceph-mon0:~$ ceph status cluster ff0baf2c-922c-4afc-8867-dee72b9325bb health HEALTH_OK monmap e1: 1 mons at {ceph-mon0=10.0.5.2:6789/0}, election epoch 1, quorum 0 ceph-mon0 osdmap e139: 4 osds: 4 up, 4 in pgmap v17348: 632 pgs, 13 pools, 1834 bytes data, 52 objects 199 MB used, 3724 GB / 3724 GB avail 632 active+clean cluster-admin@ceph-mon0:~$ ceph osd tree # id weight type name up/down reweight -1 3.64 root default -2 1.82 host ceph-osd0 0 0.91 osd.0 up 1 1 0.91 osd.1 up 1-3 1.82 host ceph-osd1 2 0.91 osd.2 up 1 3 0.91 osd.3 up 1 Monitor (mon0) HDD1 (OS) Not used Not used Not used St. node 0 HDD1 (OS) osd0 XFS osd1 XFS Journal St. node 1 HDD1 (OS) osd2 XFS osd3 XFS Journal

Swift devices Building rings on storage devices (No separation of Accounts, Containers and Objects) export ZONE= # set the zone number for that storage device export STORAGE_LOCAL_NET_IP= # and the IP address export WEIGHT=100 # relative weight (higher for bigger/faster disks) export DEVICE= swift-ring-builder account.builder add z$zone-$storage_local_net_ip:6002/$device $WEIGHT swift-ring-builder container.builder add z$zone-$storage_local_net_ip:6001/$device $WEIGHT swift-ring-builder object.builder add z$zone-$storage_local_net_ip:6000/$device $WEIGHT Swift Proxy HDD1 (OS) Not used Not used Not used St. node 0 HDD1 (OS) dev1 XFS dev2 XFS Not used St. node 1 HDD1 (OS) dev3 XFS dev4 XFS Not used

Highlighting a difference LibRados used to access Ceph Plain installation of a Ceph storage cluster Non ReST-ful interface This is the fundamental access layer in Ceph RadosGW (Swift/S3 APIs) is an additional component on top of LibRados (as block and file storage clients) ReST-ful APIs over HTTP used to access Swift Extra overhead in the communication Out-of-the box access method for Swift This is part of the differences to be benchmarked, even if... HTTP APIs for object-storage are interesting for many use cases This use case: Unconstrained self-managed storage infrastructure for, e.g., own apps Control over infrastructure and applications

WORKLOADS

Tools COSBench (v. 0.4.0.b2) - https://github.com/intel-cloud/cosbench Developed by Intel Benchmarking for Cloud Object Storage Supports both Swift and Ceph Cool web interface to submit workloads and monitor current status Workloads defined as XML files Very good level of abstractions applying to object storage Supported metrics Op-Count (number of operations) Byte-Count (number of bytes) Response-Time (average response time for each successful request) Processing-Time (average processing time for each successful request) Throughput (operations per seconds) Bandwidth (bytes per seconds) Success-Ratio (ratio of successful operations) Outputs CSV data Graphs generated with cosbench-plot - https://github.com/icclab/cosbench-plot Describe inter-workload charts in Python

Workloads gist

COSBench web interface

Workload matrix Containers Objects size R/W/D Distr. (%) Workers 1 4 kb 80/15/5 1 20 128 kb 100/0/0 16 512 kb 0/100/0 64 1024 kb 128 5 MB 256 10 MB 512

Workloads 216 workstages (all the combinations of the values of the workload matrix) 12 minutes per workstage 2 minutes warmup 10 minutes running time 1000 objects per container (pools in Ceph) Uniformly distributed operations over the available objects (1000 or 20000)

Performance Results READING

Read tpt Workstage AVGs

Read tpt 1 cont 4 KB

Read tpt 1 cont 128 KB

Read ResponseTime 1 cont 128 KB

Read bdw Workstage AVGs

Read tpt 20 cont 1024 KB

Response time 20 cont 1024 KB

Performance Results WRITING

Write tpt Workstage AVGs

Write tpt 1cont 128 KB

Ceph write tpt 1 cont 128 KB replicas

Ceph write RT 1 cont 128 KB replicas

Write bdw Workstage AVGs

Write Response Time 20 cont 512 KB

Performance Results READ/WRITE/DELETE

R/W/D tpt Workstage AVGs

Read R/W/D Response Time

General considerations and future works CONCLUSIONS

Performance Analysis Recap Ceph performs better when reading, Swift when writing Ceph librados Swift ReST APIs over HTTP More remarkable difference with small objects Less overhead for Ceph Librados CRUSH algorithm Comparable performance with bigger objects Network bottleneck at 120 MB/s for read operations Response time Swift: greedy behavior Ceph: fairness

General considerations: challenges Equivalency Comparing two similar systems that are not exactly overlapping Creating fair setups (e.g., Journals on additional disks for Ceph) Transposing corresponding concepts Configuration Choosing the right/best settings for the context (e.g., number of Swift workers) Identifying bottlenecks To be done in advance to create meaningful workloads Workloads Run many tests to identify saturating conditions Huge decision space Keep up the pace Lot of developments going on (new versions, new features)

General considerations: lessons learnt Publication medium (blog post) Excellent feedback (e.g., Rackspace developer) Immediate right of reply and real comments Most important principles Openness Share every bit of information Clear intents, clear justifications Neutrality When analyzing the results When drawing conclusions Very good suggestions coming from you could, you should, you didn t comments

Future works Performance evaluation necessary for cloud storage More object storage evaluations Interesting because it s very close to the application level Block storage evaluations Very appropriate for IaaS Provide storage resources to VMs Seagate Kinetic Possible opportunity to work on a Kinetic setup

Vincenzo Pii: piiv@zhaw.ch THANKS! QUESTIONS?