SlideShare a Scribd company logo
SUSE® Storage 
Sizing and Performance for Ceph 
Lars Marowsky-Brée 
Distinguished Engineer 
lmb@suse.com
What is Ceph?
3 
From 10,000 Meters 
• Open Source Distributed Storage solution 
• Most popular choice of distributed storage for 
[1] 
OpenStack 
• Lots of goodies 
‒ Distributed Object Storage 
‒ Redundancy 
‒ Efficient Scale-Out 
‒ Can be built on commodity hardware 
‒ Lower operational cost 
[1] http://www.openstack.org/blog/2013/11/openstack-user-survey-statistics-november-2013/
4 
From 1,000 Meters 
• Three interfaces rolled into one 
‒ Object Access (like Amazon S3) 
‒ Block Access 
‒ (Distributed File System) 
• Sitting on top of a Storage Cluster 
‒ Self Healing 
‒ Self Managed 
‒ No Bottlenecks
5 
From 1,000 Meters 
Unified Data Handling for 3 Purposes 
Object Storage 
(Like Amazon S3) Block Device File System 
●RESTful Interface 
●S3 and SWIFT APIs 
●Block devices 
●Up to 16 EiB 
●Thin Provisioning 
●Snapshots 
●POSIX Compliant 
●Separate Data and 
Metadata 
●For use e.g. with 
Hadoop 
Autonomous, Redundant Storage Cluster
6 
Component Names 
radosgw 
Object Storage 
RBD 
Block Device 
Ceph FS 
File System 
RADOS 
librados 
Direct 
Application 
Access to 
RADOS
7 
SUSE Storage architectural benefits 
● Integration with SUSE Cloud and SUSE Linux Enterprise Server 
●Exabyte scalability 
● No bottlenecks or single points of failure 
● Industry-leading functionality 
● Remote replication, erasure coding 
● Cache tiering 
● Unified block, file and object interface 
● Thin provisioning, copy on write 
●100% software based; can use commodity hardware 
●Automated management 
● Self-managing, self-healing
How Does Ceph Work?
9 
For a Moment, Zooming to Atom Level 
OSD Object Storage Daemon 
FS 
Disk 
File System (btrfs, xfs) 
Physical Disk 
● OSDs serve storage objects to clients 
● Peer to perform replication and recovery
10 
Put Several of These in One Node 
OSD 
FS 
Disk 
OSD 
FS 
Disk 
OSD 
FS 
Disk 
OSD 
FS 
Disk 
OSD 
FS 
Disk 
OSD 
FS 
Disk
11 
Mix In a Few Monitor Nodes 
M • Monitors are the brain cells of the cluster 
‒ Cluster Membership 
‒ Consensus for Distributed Decision Making 
• Do not serve stored objects to clients
12 
Voilà, a Small RADOS Cluster 
M M 
M
13 
Different Access Modes 
• radosgw: 
‒ An additional gateway in 
front of your RADOS cluster 
‒ Little impact on throughput, 
but it does affect latency 
• User-space RADOS 
access: 
‒ More feature rich than in-kernel 
rbd.ko module 
‒ Typically provides higher 
performance
14 
Several Ingredients 
• Basic Idea 
‒ Coarse grained partitioning of storage supports policy based 
mapping (don't put all copies of my data in one rack) 
‒ Topology map and Rules allow clients to “compute” the exact 
location of any storage object 
• Three conceptual components 
‒ Pools 
‒ Placement groups 
‒ CRUSH: deterministic decentralized placement algorithm
15 
Pools 
• A pool is a logical container for storage objects 
• A pool has a set of parameters 
‒ a name 
‒ a numerical ID (internal to RADOS) 
‒ number of replicas OR erasure encoding settings 
‒ number of placement groups 
‒ placement rule set 
‒ owner 
• Pools support certain operations 
‒ create/remove/read/write entire objects 
‒ snapshot of the entire pool
16 
Placement Groups 
• Placement groups help balance data across OSDs 
• Consider a pool named “swimmingpool” 
‒ with a pool ID of 38 and 8192 placement groups (PGs) 
• Consider object “rubberduck” in “swimmingpool” 
‒ hash(“rubberduck”) % 8192 = 0xb0b 
‒ The resulting PG is 38.b0b 
• One PG typically exists on several OSDs 
‒ for replication 
• One OSD typically serves many PGs
17 
CRUSH 
• CRUSH uses a map of all OSDs in your 
cluster 
‒ includes physical topology, like row, rack, host 
‒ includes rules describing which OSDs to 
consider for what type of pool/PG 
• This map is maintained by the monitor 
nodes 
‒ Monitor nodes use standard cluster algorithms 
for consensus building, etc
18 
swimmingpool/rubberduck
19 
CRUSH in Action: Reading 
swimmingpool/rubberduck 
M 
M 
M 
38.b0b 
Reads could be 
serviced by any 
of the replicas 
(parallel reads 
improve thruput)
20 
CRUSH in Action: Writing 
swimmingpool/rubberduck 
M 
M 
M 
38.b0b 
Writes go to one 
OSD, which then 
propagates the 
changes to other 
replicas
Software Defined Storage
22 
Legacy Storage Arrays 
• Limits: 
‒ Tightly controlled 
environment 
‒ Limited scalability 
‒ Few options 
‒ Only certain approved drives 
‒ Constrained number of disk 
slots 
‒ Few memory variations 
‒ Only very few networking 
choices 
‒ Typically fixed controller and 
CPU 
• Benefits: 
‒ Reasonably easy to 
understand 
‒ Long-term experience and 
“gut instincts” 
‒ Somewhat deterministic 
behavior and pricing
23 
Software Defined Storage (SDS) 
• Limits: 
‒ ? 
• Benefits: 
‒ Infinite scalability 
‒ Infinite adaptability 
‒ Infinite choices 
‒ Infinite flexibility 
‒ ... right.
24 
Properties of a SDS System 
• Throughput 
• Latency 
• IOPS 
• Availability 
• Reliability 
• Capacity • Cost 
• Density
25 
Architecting a SDS system 
• These goals often conflict: 
‒ Availability versus Density 
‒ IOPS versus Density 
‒ Everything versus Cost 
• Many hardware options 
• Software topology offers many configuration choices 
• There is no one size fits all
Setup Choices
27 
Network 
• Choose the fastest network you can afford 
• Switches should be low latency with fully meshed 
backplane 
• Separate public and cluster network 
• Cluster network should typically be twice the public 
bandwidth 
‒ Incoming writes are replicated over the cluster network 
‒ Re-balancing and re-mirroring utilize the cluster network
28 
Networking (Public and Internal) 
• Ethernet (1, 10, 40 GbE) 
‒ Reasonably inexpensive (except for 40 GbE) 
‒ Can easily be bonded for availability 
‒ Use jumbo frames 
• Infiniband 
‒ High bandwidth 
‒ Low latency 
‒ Typically more expensive 
‒ No support for RDMA yet in Ceph, need to use IPoIB
29 
Storage Node 
• CPU 
‒ Number and speed of cores 
• Memory 
• Storage controller 
‒ Bandwidth, performance, cache size 
• SSDs for OSD journal 
‒ SSD to HDD ratio 
• HDDs 
‒ Count, capacity, performance
30 
Adding More Nodes 
• Capacity increases 
• Total throughput 
increases 
• IOPS increase 
• Redundancy increases 
• Latency unchanged 
• Eventually: network 
topology limitations 
• Temporary impact during 
re-balancing
31 
Adding More Disks to a Node 
• Capacity increases 
• Redundancy increases 
• Throughput might 
increase 
• IOPS might increase 
• Internal node bandwidth 
is consumed 
• Higher CPU and memory 
load 
• Cache contention 
• Latency unchanged
32 
OSD File System 
• btrfs 
‒ Typically better write 
throughput performance 
‒ Higher CPU utilization 
‒ Feature rich 
‒ Compression, checksums, copy 
on write 
‒ The choice for the future! 
• XFS 
‒ Good all around choice 
‒ Very mature for data 
partitions 
‒ Typically lower CPU 
utilization 
‒ The choice for today!
33 
Impact of Caches 
• Cache on the client side 
‒ Typically, biggest impact on performance 
‒ Does not help with write performance 
• Server OS cache 
‒ Low impact: reads have already been cached on the client 
‒ Still, helps with readahead 
• Caching controller, battery backed: 
‒ Significant impact for writes
34 
Impact of SSD Journals 
• SSD journals accelerate bursts and random write IO 
• For sustained writes that overflow the journal, 
performance degrades to HDD levels 
• SSDs help very little with read performance 
• SSDs are very costly 
‒ ... and consume storage slots -> lower density 
• A large battery-backed cache on the storage controller 
is highly recommended if not using SSD journals
35 
Hard Disk Parameters 
• Capacity matters 
‒ Often, highest density is not 
most cost effective 
‒ On-disk cache matters less 
• Reliability advantage of 
Enterprise drives typically 
marginal compared to 
cost 
‒ Buy more drives instead 
‒ Consider validation matrices 
for small/medium NAS 
servers as a guide 
• RPM: 
‒ Increase IOPS & throughput 
‒ Increases power 
consumption 
‒ 15k drives quite expensive 
still
36 
Impact of Redundancy Choices 
• Replication: 
‒ n number of exact, full-size 
copies 
‒ Potentially increased read 
performance due to striping 
‒ More copies lower 
throughput, increase latency 
‒ Increased cluster network 
utilization for writes 
‒ Rebuilds can leverage 
multiple sources 
‒ Significant capacity impact 
• Erasure coding: 
‒ Data split into k parts plus m 
redundancy codes 
‒ Better space efficiency 
‒ Higher CPU overhead 
‒ Significant CPU and cluster 
network impact, especially 
during rebuild 
‒ Cannot directly be used with 
block devices (see next 
slide)
37 
Cache Tiering 
• Multi-tier storage architecture: 
‒ Pool acts as a transparent write-back overlay for another 
‒ e.g., SSD 3-way replication over HDDs with erasure coding 
‒ Can flush either on relative or absolute dirty levels, or age 
‒ Additional configuration complexity and requires workload-specific 
tuning 
‒ Also available: read-only mode (no write acceleration) 
‒ Some downsides (no snapshots), memory consumption for 
HitSet 
• A good way to combine the advantages of replication 
and erasure coding
38 
Number of placement groups 
●Number of hash buckets 
per pool 
● Data is chunked & 
distributed across nodes 
● Typically approx. 100 per 
OSD/TB 
• Too many: 
‒ More peering 
‒ More resources used 
• Too few: 
‒ Large amounts of data per 
group 
‒ More hotspots, less striping 
‒ Slower recovery from failure 
‒ Slower re-balancing
39 
Measuring Ceph performance 
• rados bench 
‒ Measures backend performance of the RADOS store 
‒ Simple options 
• rados load-gen 
‒ Generate configurable load on the cluster 
• fio rbd backend 
‒ Swiss army knife of IO benchmarking on Linux 
‒ Can also compare in-kernel rbd with user-space librados 
• rest-bench 
‒ Measures S3/radosgw performance
Conclusion
41 
How to size a Ceph cluster? 
• Understand your workload 
• Make a best guess, based on the desirable properties 
and factors 
• Build a 10% pilot / proof of concept 
‒ Preferably using loaner hardware from a vendor to avoid early 
commitment 
‒ The outlook of selling a few PB of storage and compute nodes 
makes vendors very cooperative 
• Refine this until desired performance is achieved 
• Scale up 
‒ Ceph retains most characteristics at scale or even improves
Thank you. 
42 
Questions and Answers?
Corporate Headquarters 
Maxfeldstrasse 5 
90409 Nuremberg 
Germany 
+49 911 740 53 0 (Worldwide) 
www.suse.com 
Join us on: 
www.opensuse.org 
43
Unpublished Work of SUSE LLC. All Rights Reserved. 
This work is an unpublished work and contains confidential, proprietary and trade secret information of SUSE LLC. 
Access to this work is restricted to SUSE employees who have a need to know to perform tasks within the scope of 
their assignments. No part of this work may be practiced, performed, copied, distributed, revised, modified, translated, 
abridged, condensed, expanded, collected, or adapted without the prior written consent of SUSE. 
Any use or exploitation of this work without authorization could subject the perpetrator to criminal and civil liability. 
General Disclaimer 
This document is not to be construed as a promise by any participating company to develop, deliver, or market a 
product. It is not a commitment to deliver any material, code, or functionality, and should not be relied upon in making 
purchasing decisions. SUSE makes no representations or warranties with respect to the contents of this document, 
and specifically disclaims any express or implied warranties of merchantability or fitness for any particular purpose. The 
development, release, and timing of features or functionality described for SUSE products remains at the sole 
discretion of SUSE. Further, SUSE reserves the right to revise this document and to make changes to its content, at 
any time, without obligation to notify any person or entity of such revisions or changes. All SUSE marks referenced in 
this presentation are trademarks or registered trademarks of Novell, Inc. in the United States and other countries. All 
third-party trademarks are the property of their respective owners.

More Related Content

What's hot

librados
libradoslibrados
librados
Patrick McGarry
 
Your 1st Ceph cluster
Your 1st Ceph clusterYour 1st Ceph cluster
Your 1st Ceph cluster
Mirantis
 
ceph-barcelona-v-1.2
ceph-barcelona-v-1.2ceph-barcelona-v-1.2
ceph-barcelona-v-1.2
Ranga Swami Reddy Muthumula
 
Ceph - High Performance Without High Costs
Ceph - High Performance Without High CostsCeph - High Performance Without High Costs
Ceph - High Performance Without High Costs
Jonathan Long
 
Ceph - A distributed storage system
Ceph - A distributed storage systemCeph - A distributed storage system
Ceph - A distributed storage system
Italo Santos
 
Ceph Day Beijing - Ceph All-Flash Array Design Based on NUMA Architecture
Ceph Day Beijing - Ceph All-Flash Array Design Based on NUMA ArchitectureCeph Day Beijing - Ceph All-Flash Array Design Based on NUMA Architecture
Ceph Day Beijing - Ceph All-Flash Array Design Based on NUMA Architecture
Danielle Womboldt
 
Journey to Stability: Petabyte Ceph Cluster in OpenStack Cloud
Journey to Stability: Petabyte Ceph Cluster in OpenStack CloudJourney to Stability: Petabyte Ceph Cluster in OpenStack Cloud
Journey to Stability: Petabyte Ceph Cluster in OpenStack Cloud
Patrick McGarry
 
BlueStore: a new, faster storage backend for Ceph
BlueStore: a new, faster storage backend for CephBlueStore: a new, faster storage backend for Ceph
BlueStore: a new, faster storage backend for Ceph
Sage Weil
 
HKG15-401: Ceph and Software Defined Storage on ARM servers
HKG15-401: Ceph and Software Defined Storage on ARM serversHKG15-401: Ceph and Software Defined Storage on ARM servers
HKG15-401: Ceph and Software Defined Storage on ARM servers
Linaro
 
Ceph Day Taipei - Bring Ceph to Enterprise
Ceph Day Taipei - Bring Ceph to EnterpriseCeph Day Taipei - Bring Ceph to Enterprise
Ceph Day Taipei - Bring Ceph to Enterprise
Ceph Community
 
Ceph Object Storage Performance Secrets and Ceph Data Lake Solution
Ceph Object Storage Performance Secrets and Ceph Data Lake SolutionCeph Object Storage Performance Secrets and Ceph Data Lake Solution
Ceph Object Storage Performance Secrets and Ceph Data Lake Solution
Karan Singh
 
Ceph Intro and Architectural Overview by Ross Turk
Ceph Intro and Architectural Overview by Ross TurkCeph Intro and Architectural Overview by Ross Turk
Ceph Intro and Architectural Overview by Ross Turk
buildacloud
 
Ceph on Intel: Intel Storage Components, Benchmarks, and Contributions
Ceph on Intel: Intel Storage Components, Benchmarks, and ContributionsCeph on Intel: Intel Storage Components, Benchmarks, and Contributions
Ceph on Intel: Intel Storage Components, Benchmarks, and Contributions
Colleen Corrice
 
Ceph: Open Source Storage Software Optimizations on Intel® Architecture for C...
Ceph: Open Source Storage Software Optimizations on Intel® Architecture for C...Ceph: Open Source Storage Software Optimizations on Intel® Architecture for C...
Ceph: Open Source Storage Software Optimizations on Intel® Architecture for C...
Odinot Stanislas
 
Block Storage For VMs With Ceph
Block Storage For VMs With CephBlock Storage For VMs With Ceph
Block Storage For VMs With Ceph
The Linux Foundation
 
Quick-and-Easy Deployment of a Ceph Storage Cluster with SLES
Quick-and-Easy Deployment of a Ceph Storage Cluster with SLESQuick-and-Easy Deployment of a Ceph Storage Cluster with SLES
Quick-and-Easy Deployment of a Ceph Storage Cluster with SLES
Jan Kalcic
 
Bluestore
BluestoreBluestore
Bluestore
Patrick McGarry
 
Ceph Day Bring Ceph To Enterprise
Ceph Day Bring Ceph To EnterpriseCeph Day Bring Ceph To Enterprise
Ceph Day Bring Ceph To Enterprise
Alex Lau
 
Ceph on 64-bit ARM with X-Gene
Ceph on 64-bit ARM with X-GeneCeph on 64-bit ARM with X-Gene
Ceph on 64-bit ARM with X-Gene
Ceph Community
 
QCT Ceph Solution - Design Consideration and Reference Architecture
QCT Ceph Solution - Design Consideration and Reference ArchitectureQCT Ceph Solution - Design Consideration and Reference Architecture
QCT Ceph Solution - Design Consideration and Reference Architecture
Patrick McGarry
 

What's hot (20)

librados
libradoslibrados
librados
 
Your 1st Ceph cluster
Your 1st Ceph clusterYour 1st Ceph cluster
Your 1st Ceph cluster
 
ceph-barcelona-v-1.2
ceph-barcelona-v-1.2ceph-barcelona-v-1.2
ceph-barcelona-v-1.2
 
Ceph - High Performance Without High Costs
Ceph - High Performance Without High CostsCeph - High Performance Without High Costs
Ceph - High Performance Without High Costs
 
Ceph - A distributed storage system
Ceph - A distributed storage systemCeph - A distributed storage system
Ceph - A distributed storage system
 
Ceph Day Beijing - Ceph All-Flash Array Design Based on NUMA Architecture
Ceph Day Beijing - Ceph All-Flash Array Design Based on NUMA ArchitectureCeph Day Beijing - Ceph All-Flash Array Design Based on NUMA Architecture
Ceph Day Beijing - Ceph All-Flash Array Design Based on NUMA Architecture
 
Journey to Stability: Petabyte Ceph Cluster in OpenStack Cloud
Journey to Stability: Petabyte Ceph Cluster in OpenStack CloudJourney to Stability: Petabyte Ceph Cluster in OpenStack Cloud
Journey to Stability: Petabyte Ceph Cluster in OpenStack Cloud
 
BlueStore: a new, faster storage backend for Ceph
BlueStore: a new, faster storage backend for CephBlueStore: a new, faster storage backend for Ceph
BlueStore: a new, faster storage backend for Ceph
 
HKG15-401: Ceph and Software Defined Storage on ARM servers
HKG15-401: Ceph and Software Defined Storage on ARM serversHKG15-401: Ceph and Software Defined Storage on ARM servers
HKG15-401: Ceph and Software Defined Storage on ARM servers
 
Ceph Day Taipei - Bring Ceph to Enterprise
Ceph Day Taipei - Bring Ceph to EnterpriseCeph Day Taipei - Bring Ceph to Enterprise
Ceph Day Taipei - Bring Ceph to Enterprise
 
Ceph Object Storage Performance Secrets and Ceph Data Lake Solution
Ceph Object Storage Performance Secrets and Ceph Data Lake SolutionCeph Object Storage Performance Secrets and Ceph Data Lake Solution
Ceph Object Storage Performance Secrets and Ceph Data Lake Solution
 
Ceph Intro and Architectural Overview by Ross Turk
Ceph Intro and Architectural Overview by Ross TurkCeph Intro and Architectural Overview by Ross Turk
Ceph Intro and Architectural Overview by Ross Turk
 
Ceph on Intel: Intel Storage Components, Benchmarks, and Contributions
Ceph on Intel: Intel Storage Components, Benchmarks, and ContributionsCeph on Intel: Intel Storage Components, Benchmarks, and Contributions
Ceph on Intel: Intel Storage Components, Benchmarks, and Contributions
 
Ceph: Open Source Storage Software Optimizations on Intel® Architecture for C...
Ceph: Open Source Storage Software Optimizations on Intel® Architecture for C...Ceph: Open Source Storage Software Optimizations on Intel® Architecture for C...
Ceph: Open Source Storage Software Optimizations on Intel® Architecture for C...
 
Block Storage For VMs With Ceph
Block Storage For VMs With CephBlock Storage For VMs With Ceph
Block Storage For VMs With Ceph
 
Quick-and-Easy Deployment of a Ceph Storage Cluster with SLES
Quick-and-Easy Deployment of a Ceph Storage Cluster with SLESQuick-and-Easy Deployment of a Ceph Storage Cluster with SLES
Quick-and-Easy Deployment of a Ceph Storage Cluster with SLES
 
Bluestore
BluestoreBluestore
Bluestore
 
Ceph Day Bring Ceph To Enterprise
Ceph Day Bring Ceph To EnterpriseCeph Day Bring Ceph To Enterprise
Ceph Day Bring Ceph To Enterprise
 
Ceph on 64-bit ARM with X-Gene
Ceph on 64-bit ARM with X-GeneCeph on 64-bit ARM with X-Gene
Ceph on 64-bit ARM with X-Gene
 
QCT Ceph Solution - Design Consideration and Reference Architecture
QCT Ceph Solution - Design Consideration and Reference ArchitectureQCT Ceph Solution - Design Consideration and Reference Architecture
QCT Ceph Solution - Design Consideration and Reference Architecture
 

Viewers also liked

TUT18972: Unleash the power of Ceph across the Data Center
TUT18972: Unleash the power of Ceph across the Data CenterTUT18972: Unleash the power of Ceph across the Data Center
TUT18972: Unleash the power of Ceph across the Data Center
Ettore Simone
 
SUSE Enterprise Storage - a Gentle Introduction
SUSE Enterprise Storage - a Gentle IntroductionSUSE Enterprise Storage - a Gentle Introduction
SUSE Enterprise Storage - a Gentle Introduction
Gábor Nyers
 
Ceph Introduction 2017
Ceph Introduction 2017  Ceph Introduction 2017
Ceph Introduction 2017
Karan Singh
 
SUSE OpenStack Cloud
SUSE OpenStack CloudSUSE OpenStack Cloud
SUSE OpenStack Cloud
Finceptum Oy
 
8/ SUSE @ OPEN'16
8/ SUSE @ OPEN'168/ SUSE @ OPEN'16
8/ SUSE @ OPEN'16
Kangaroot
 
SUSE KVM Ecosystem
SUSE KVM EcosystemSUSE KVM Ecosystem
SUSE KVM Ecosystem
Patrick Quairoli
 
SUSE Linux Enterprise Server for IBM Power
SUSE Linux Enterprise Server for IBM Power SUSE Linux Enterprise Server for IBM Power
SUSE Linux Enterprise Server for IBM Power
Patrick Quairoli
 
Cephfs - Red Hat Openstack and Ceph meetup, Pune 28th november 2015
Cephfs - Red Hat Openstack and Ceph meetup, Pune 28th november 2015Cephfs - Red Hat Openstack and Ceph meetup, Pune 28th november 2015
Cephfs - Red Hat Openstack and Ceph meetup, Pune 28th november 2015
bipin kunal
 
Ceph, storage cluster to go exabyte and beyond
Ceph, storage cluster to go exabyte  and beyondCeph, storage cluster to go exabyte  and beyond
Ceph, storage cluster to go exabyte and beyond
Alvaro Soto
 
Ceph
CephCeph
adp.ceph.openstack.talk
adp.ceph.openstack.talkadp.ceph.openstack.talk
adp.ceph.openstack.talk
Udo Seidel
 
Ceph and Storage Management with openATTIC - FOSDEM 2017-02-05
Ceph and Storage Management with openATTIC - FOSDEM 2017-02-05Ceph and Storage Management with openATTIC - FOSDEM 2017-02-05
Ceph and Storage Management with openATTIC - FOSDEM 2017-02-05
Lenz Grimmer
 
Ceph, Xen, and CloudStack: Semper Melior-XPUS13 McGarry
Ceph, Xen, and CloudStack: Semper Melior-XPUS13 McGarryCeph, Xen, and CloudStack: Semper Melior-XPUS13 McGarry
Ceph, Xen, and CloudStack: Semper Melior-XPUS13 McGarry
The Linux Foundation
 
Gluster.community.day.2013
Gluster.community.day.2013Gluster.community.day.2013
Gluster.community.day.2013
Udo Seidel
 
Ceph Loves OpenStack: Why and How
Ceph Loves OpenStack: Why and HowCeph Loves OpenStack: Why and How
Ceph Loves OpenStack: Why and How
Emma Haruka Iwao
 
Gluster Data Tiering
Gluster Data TieringGluster Data Tiering
Gluster Data Tiering
Joseph Elwin Fernandes
 
Private Cloud mit Ceph und OpenStack
Private Cloud mit Ceph und OpenStackPrivate Cloud mit Ceph und OpenStack
Private Cloud mit Ceph und OpenStack
Daniel Schneller
 
State of Gluster Performance
State of Gluster PerformanceState of Gluster Performance
State of Gluster Performance
Gluster.org
 
Guts & OpenStack migration
Guts & OpenStack migrationGuts & OpenStack migration
Guts & OpenStack migration
openstackindia
 
OpenStack Storage Buddy Ceph
OpenStack Storage Buddy CephOpenStack Storage Buddy Ceph
OpenStack Storage Buddy Ceph
openstackindia
 

Viewers also liked (20)

TUT18972: Unleash the power of Ceph across the Data Center
TUT18972: Unleash the power of Ceph across the Data CenterTUT18972: Unleash the power of Ceph across the Data Center
TUT18972: Unleash the power of Ceph across the Data Center
 
SUSE Enterprise Storage - a Gentle Introduction
SUSE Enterprise Storage - a Gentle IntroductionSUSE Enterprise Storage - a Gentle Introduction
SUSE Enterprise Storage - a Gentle Introduction
 
Ceph Introduction 2017
Ceph Introduction 2017  Ceph Introduction 2017
Ceph Introduction 2017
 
SUSE OpenStack Cloud
SUSE OpenStack CloudSUSE OpenStack Cloud
SUSE OpenStack Cloud
 
8/ SUSE @ OPEN'16
8/ SUSE @ OPEN'168/ SUSE @ OPEN'16
8/ SUSE @ OPEN'16
 
SUSE KVM Ecosystem
SUSE KVM EcosystemSUSE KVM Ecosystem
SUSE KVM Ecosystem
 
SUSE Linux Enterprise Server for IBM Power
SUSE Linux Enterprise Server for IBM Power SUSE Linux Enterprise Server for IBM Power
SUSE Linux Enterprise Server for IBM Power
 
Cephfs - Red Hat Openstack and Ceph meetup, Pune 28th november 2015
Cephfs - Red Hat Openstack and Ceph meetup, Pune 28th november 2015Cephfs - Red Hat Openstack and Ceph meetup, Pune 28th november 2015
Cephfs - Red Hat Openstack and Ceph meetup, Pune 28th november 2015
 
Ceph, storage cluster to go exabyte and beyond
Ceph, storage cluster to go exabyte  and beyondCeph, storage cluster to go exabyte  and beyond
Ceph, storage cluster to go exabyte and beyond
 
Ceph
CephCeph
Ceph
 
adp.ceph.openstack.talk
adp.ceph.openstack.talkadp.ceph.openstack.talk
adp.ceph.openstack.talk
 
Ceph and Storage Management with openATTIC - FOSDEM 2017-02-05
Ceph and Storage Management with openATTIC - FOSDEM 2017-02-05Ceph and Storage Management with openATTIC - FOSDEM 2017-02-05
Ceph and Storage Management with openATTIC - FOSDEM 2017-02-05
 
Ceph, Xen, and CloudStack: Semper Melior-XPUS13 McGarry
Ceph, Xen, and CloudStack: Semper Melior-XPUS13 McGarryCeph, Xen, and CloudStack: Semper Melior-XPUS13 McGarry
Ceph, Xen, and CloudStack: Semper Melior-XPUS13 McGarry
 
Gluster.community.day.2013
Gluster.community.day.2013Gluster.community.day.2013
Gluster.community.day.2013
 
Ceph Loves OpenStack: Why and How
Ceph Loves OpenStack: Why and HowCeph Loves OpenStack: Why and How
Ceph Loves OpenStack: Why and How
 
Gluster Data Tiering
Gluster Data TieringGluster Data Tiering
Gluster Data Tiering
 
Private Cloud mit Ceph und OpenStack
Private Cloud mit Ceph und OpenStackPrivate Cloud mit Ceph und OpenStack
Private Cloud mit Ceph und OpenStack
 
State of Gluster Performance
State of Gluster PerformanceState of Gluster Performance
State of Gluster Performance
 
Guts & OpenStack migration
Guts & OpenStack migrationGuts & OpenStack migration
Guts & OpenStack migration
 
OpenStack Storage Buddy Ceph
OpenStack Storage Buddy CephOpenStack Storage Buddy Ceph
OpenStack Storage Buddy Ceph
 

Similar to SUSE Storage: Sizing and Performance (Ceph)

Ceph Day Amsterdam 2015: Measuring and predicting performance of Ceph clusters
Ceph Day Amsterdam 2015: Measuring and predicting performance of Ceph clusters Ceph Day Amsterdam 2015: Measuring and predicting performance of Ceph clusters
Ceph Day Amsterdam 2015: Measuring and predicting performance of Ceph clusters
Ceph Community
 
Ceph Day Berlin: Measuring and predicting performance of Ceph clusters
Ceph Day Berlin: Measuring and predicting performance of Ceph clustersCeph Day Berlin: Measuring and predicting performance of Ceph clusters
Ceph Day Berlin: Measuring and predicting performance of Ceph clusters
Ceph Community
 
MongoDB Capacity Planning
MongoDB Capacity PlanningMongoDB Capacity Planning
MongoDB Capacity Planning
Norberto Leite
 
Taking Splunk to the Next Level - Architecture Breakout Session
Taking Splunk to the Next Level - Architecture Breakout SessionTaking Splunk to the Next Level - Architecture Breakout Session
Taking Splunk to the Next Level - Architecture Breakout Session
Splunk
 
Ambedded - how to build a true no single point of failure ceph cluster
Ambedded - how to build a true no single point of failure ceph cluster Ambedded - how to build a true no single point of failure ceph cluster
Ambedded - how to build a true no single point of failure ceph cluster
inwin stack
 
Capacity Planning
Capacity PlanningCapacity Planning
Capacity Planning
MongoDB
 
Reference Architecture: Architecting Ceph Storage Solutions
Reference Architecture: Architecting Ceph Storage Solutions Reference Architecture: Architecting Ceph Storage Solutions
Reference Architecture: Architecting Ceph Storage Solutions
Ceph Community
 
Building Data Pipelines with SMACK: Designing Storage Strategies for Scale an...
Building Data Pipelines with SMACK: Designing Storage Strategies for Scale an...Building Data Pipelines with SMACK: Designing Storage Strategies for Scale an...
Building Data Pipelines with SMACK: Designing Storage Strategies for Scale an...
DataStax
 
Gluster for Geeks: Performance Tuning Tips & Tricks
Gluster for Geeks: Performance Tuning Tips & TricksGluster for Geeks: Performance Tuning Tips & Tricks
Gluster for Geeks: Performance Tuning Tips & Tricks
GlusterFS
 
Managing Security At 1M Events a Second using Elasticsearch
Managing Security At 1M Events a Second using ElasticsearchManaging Security At 1M Events a Second using Elasticsearch
Managing Security At 1M Events a Second using Elasticsearch
Joe Alex
 
In-memory Data Management Trends & Techniques
In-memory Data Management Trends & TechniquesIn-memory Data Management Trends & Techniques
In-memory Data Management Trends & Techniques
Hazelcast
 
HBase Sizing Guide
HBase Sizing GuideHBase Sizing Guide
HBase Sizing Guide
larsgeorge
 
Backup management with Ceph Storage - Camilo Echevarne, Félix Barbeira
Backup management with Ceph Storage - Camilo Echevarne, Félix BarbeiraBackup management with Ceph Storage - Camilo Echevarne, Félix Barbeira
Backup management with Ceph Storage - Camilo Echevarne, Félix Barbeira
Ceph Community
 
09. storage-part-1
09. storage-part-109. storage-part-1
09. storage-part-1
Muhammad Ahad
 
Tuning Linux Windows and Firebird for Heavy Workload
Tuning Linux Windows and Firebird for Heavy WorkloadTuning Linux Windows and Firebird for Heavy Workload
Tuning Linux Windows and Firebird for Heavy Workload
Marius Adrian Popa
 
Ceph Day London 2014 - Best Practices for Ceph-powered Implementations of Sto...
Ceph Day London 2014 - Best Practices for Ceph-powered Implementations of Sto...Ceph Day London 2014 - Best Practices for Ceph-powered Implementations of Sto...
Ceph Day London 2014 - Best Practices for Ceph-powered Implementations of Sto...
Ceph Community
 
Os7
Os7Os7
Oracle real application_cluster
Oracle real application_clusterOracle real application_cluster
Oracle real application_cluster
Prabhat gangwar
 
Mike Pittaro - High Performance Hardware for Data Analysis
Mike Pittaro - High Performance Hardware for Data Analysis Mike Pittaro - High Performance Hardware for Data Analysis
Mike Pittaro - High Performance Hardware for Data Analysis
PyData
 
High Performance Hardware for Data Analysis
High Performance Hardware for Data AnalysisHigh Performance Hardware for Data Analysis
High Performance Hardware for Data Analysis
Mike Pittaro
 

Similar to SUSE Storage: Sizing and Performance (Ceph) (20)

Ceph Day Amsterdam 2015: Measuring and predicting performance of Ceph clusters
Ceph Day Amsterdam 2015: Measuring and predicting performance of Ceph clusters Ceph Day Amsterdam 2015: Measuring and predicting performance of Ceph clusters
Ceph Day Amsterdam 2015: Measuring and predicting performance of Ceph clusters
 
Ceph Day Berlin: Measuring and predicting performance of Ceph clusters
Ceph Day Berlin: Measuring and predicting performance of Ceph clustersCeph Day Berlin: Measuring and predicting performance of Ceph clusters
Ceph Day Berlin: Measuring and predicting performance of Ceph clusters
 
MongoDB Capacity Planning
MongoDB Capacity PlanningMongoDB Capacity Planning
MongoDB Capacity Planning
 
Taking Splunk to the Next Level - Architecture Breakout Session
Taking Splunk to the Next Level - Architecture Breakout SessionTaking Splunk to the Next Level - Architecture Breakout Session
Taking Splunk to the Next Level - Architecture Breakout Session
 
Ambedded - how to build a true no single point of failure ceph cluster
Ambedded - how to build a true no single point of failure ceph cluster Ambedded - how to build a true no single point of failure ceph cluster
Ambedded - how to build a true no single point of failure ceph cluster
 
Capacity Planning
Capacity PlanningCapacity Planning
Capacity Planning
 
Reference Architecture: Architecting Ceph Storage Solutions
Reference Architecture: Architecting Ceph Storage Solutions Reference Architecture: Architecting Ceph Storage Solutions
Reference Architecture: Architecting Ceph Storage Solutions
 
Building Data Pipelines with SMACK: Designing Storage Strategies for Scale an...
Building Data Pipelines with SMACK: Designing Storage Strategies for Scale an...Building Data Pipelines with SMACK: Designing Storage Strategies for Scale an...
Building Data Pipelines with SMACK: Designing Storage Strategies for Scale an...
 
Gluster for Geeks: Performance Tuning Tips & Tricks
Gluster for Geeks: Performance Tuning Tips & TricksGluster for Geeks: Performance Tuning Tips & Tricks
Gluster for Geeks: Performance Tuning Tips & Tricks
 
Managing Security At 1M Events a Second using Elasticsearch
Managing Security At 1M Events a Second using ElasticsearchManaging Security At 1M Events a Second using Elasticsearch
Managing Security At 1M Events a Second using Elasticsearch
 
In-memory Data Management Trends & Techniques
In-memory Data Management Trends & TechniquesIn-memory Data Management Trends & Techniques
In-memory Data Management Trends & Techniques
 
HBase Sizing Guide
HBase Sizing GuideHBase Sizing Guide
HBase Sizing Guide
 
Backup management with Ceph Storage - Camilo Echevarne, Félix Barbeira
Backup management with Ceph Storage - Camilo Echevarne, Félix BarbeiraBackup management with Ceph Storage - Camilo Echevarne, Félix Barbeira
Backup management with Ceph Storage - Camilo Echevarne, Félix Barbeira
 
09. storage-part-1
09. storage-part-109. storage-part-1
09. storage-part-1
 
Tuning Linux Windows and Firebird for Heavy Workload
Tuning Linux Windows and Firebird for Heavy WorkloadTuning Linux Windows and Firebird for Heavy Workload
Tuning Linux Windows and Firebird for Heavy Workload
 
Ceph Day London 2014 - Best Practices for Ceph-powered Implementations of Sto...
Ceph Day London 2014 - Best Practices for Ceph-powered Implementations of Sto...Ceph Day London 2014 - Best Practices for Ceph-powered Implementations of Sto...
Ceph Day London 2014 - Best Practices for Ceph-powered Implementations of Sto...
 
Os7
Os7Os7
Os7
 
Oracle real application_cluster
Oracle real application_clusterOracle real application_cluster
Oracle real application_cluster
 
Mike Pittaro - High Performance Hardware for Data Analysis
Mike Pittaro - High Performance Hardware for Data Analysis Mike Pittaro - High Performance Hardware for Data Analysis
Mike Pittaro - High Performance Hardware for Data Analysis
 
High Performance Hardware for Data Analysis
High Performance Hardware for Data AnalysisHigh Performance Hardware for Data Analysis
High Performance Hardware for Data Analysis
 

Recently uploaded

Webinar On-Demand: Using Flutter for Embedded
Webinar On-Demand: Using Flutter for EmbeddedWebinar On-Demand: Using Flutter for Embedded
Webinar On-Demand: Using Flutter for Embedded
ICS
 
Transform Your Communication with Cloud-Based IVR Solutions
Transform Your Communication with Cloud-Based IVR SolutionsTransform Your Communication with Cloud-Based IVR Solutions
Transform Your Communication with Cloud-Based IVR Solutions
TheSMSPoint
 
Hand Rolled Applicative User Validation Code Kata
Hand Rolled Applicative User ValidationCode KataHand Rolled Applicative User ValidationCode Kata
Hand Rolled Applicative User Validation Code Kata
Philip Schwarz
 
GOING AOT WITH GRAALVM FOR SPRING BOOT (SPRING IO)
GOING AOT WITH GRAALVM FOR  SPRING BOOT (SPRING IO)GOING AOT WITH GRAALVM FOR  SPRING BOOT (SPRING IO)
GOING AOT WITH GRAALVM FOR SPRING BOOT (SPRING IO)
Alina Yurenko
 
SWEBOK and Education at FUSE Okinawa 2024
SWEBOK and Education at FUSE Okinawa 2024SWEBOK and Education at FUSE Okinawa 2024
SWEBOK and Education at FUSE Okinawa 2024
Hironori Washizaki
 
AI Fusion Buddy Review: Brand New, Groundbreaking Gemini-Powered AI App
AI Fusion Buddy Review: Brand New, Groundbreaking Gemini-Powered AI AppAI Fusion Buddy Review: Brand New, Groundbreaking Gemini-Powered AI App
AI Fusion Buddy Review: Brand New, Groundbreaking Gemini-Powered AI App
Google
 
May Marketo Masterclass, London MUG May 22 2024.pdf
May Marketo Masterclass, London MUG May 22 2024.pdfMay Marketo Masterclass, London MUG May 22 2024.pdf
May Marketo Masterclass, London MUG May 22 2024.pdf
Adele Miller
 
What is Augmented Reality Image Tracking
What is Augmented Reality Image TrackingWhat is Augmented Reality Image Tracking
What is Augmented Reality Image Tracking
pavan998932
 
Revolutionizing Visual Effects Mastering AI Face Swaps.pdf
Revolutionizing Visual Effects Mastering AI Face Swaps.pdfRevolutionizing Visual Effects Mastering AI Face Swaps.pdf
Revolutionizing Visual Effects Mastering AI Face Swaps.pdf
Undress Baby
 
E-commerce Application Development Company.pdf
E-commerce Application Development Company.pdfE-commerce Application Development Company.pdf
E-commerce Application Development Company.pdf
Hornet Dynamics
 
Neo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
Neo4j - Product Vision and Knowledge Graphs - GraphSummit ParisNeo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
Neo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
Neo4j
 
DDS-Security 1.2 - What's New? Stronger security for long-running systems
DDS-Security 1.2 - What's New? Stronger security for long-running systemsDDS-Security 1.2 - What's New? Stronger security for long-running systems
DDS-Security 1.2 - What's New? Stronger security for long-running systems
Gerardo Pardo-Castellote
 
Why Choose Odoo 17 Community & How it differs from Odoo 17 Enterprise Edition
Why Choose Odoo 17 Community & How it differs from Odoo 17 Enterprise EditionWhy Choose Odoo 17 Community & How it differs from Odoo 17 Enterprise Edition
Why Choose Odoo 17 Community & How it differs from Odoo 17 Enterprise Edition
Envertis Software Solutions
 
OpenMetadata Community Meeting - 5th June 2024
OpenMetadata Community Meeting - 5th June 2024OpenMetadata Community Meeting - 5th June 2024
OpenMetadata Community Meeting - 5th June 2024
OpenMetadata
 
Need for Speed: Removing speed bumps from your Symfony projects ⚡️
Need for Speed: Removing speed bumps from your Symfony projects ⚡️Need for Speed: Removing speed bumps from your Symfony projects ⚡️
Need for Speed: Removing speed bumps from your Symfony projects ⚡️
Łukasz Chruściel
 
LORRAINE ANDREI_LEQUIGAN_HOW TO USE ZOOM
LORRAINE ANDREI_LEQUIGAN_HOW TO USE ZOOMLORRAINE ANDREI_LEQUIGAN_HOW TO USE ZOOM
LORRAINE ANDREI_LEQUIGAN_HOW TO USE ZOOM
lorraineandreiamcidl
 
Empowering Growth with Best Software Development Company in Noida - Deuglo
Empowering Growth with Best Software  Development Company in Noida - DeugloEmpowering Growth with Best Software  Development Company in Noida - Deuglo
Empowering Growth with Best Software Development Company in Noida - Deuglo
Deuglo Infosystem Pvt Ltd
 
KuberTENes Birthday Bash Guadalajara - Introducción a Argo CD
KuberTENes Birthday Bash Guadalajara - Introducción a Argo CDKuberTENes Birthday Bash Guadalajara - Introducción a Argo CD
KuberTENes Birthday Bash Guadalajara - Introducción a Argo CD
rodomar2
 
GreenCode-A-VSCode-Plugin--Dario-Jurisic
GreenCode-A-VSCode-Plugin--Dario-JurisicGreenCode-A-VSCode-Plugin--Dario-Jurisic
GreenCode-A-VSCode-Plugin--Dario-Jurisic
Green Software Development
 
A Study of Variable-Role-based Feature Enrichment in Neural Models of Code
A Study of Variable-Role-based Feature Enrichment in Neural Models of CodeA Study of Variable-Role-based Feature Enrichment in Neural Models of Code
A Study of Variable-Role-based Feature Enrichment in Neural Models of Code
Aftab Hussain
 

Recently uploaded (20)

Webinar On-Demand: Using Flutter for Embedded
Webinar On-Demand: Using Flutter for EmbeddedWebinar On-Demand: Using Flutter for Embedded
Webinar On-Demand: Using Flutter for Embedded
 
Transform Your Communication with Cloud-Based IVR Solutions
Transform Your Communication with Cloud-Based IVR SolutionsTransform Your Communication with Cloud-Based IVR Solutions
Transform Your Communication with Cloud-Based IVR Solutions
 
Hand Rolled Applicative User Validation Code Kata
Hand Rolled Applicative User ValidationCode KataHand Rolled Applicative User ValidationCode Kata
Hand Rolled Applicative User Validation Code Kata
 
GOING AOT WITH GRAALVM FOR SPRING BOOT (SPRING IO)
GOING AOT WITH GRAALVM FOR  SPRING BOOT (SPRING IO)GOING AOT WITH GRAALVM FOR  SPRING BOOT (SPRING IO)
GOING AOT WITH GRAALVM FOR SPRING BOOT (SPRING IO)
 
SWEBOK and Education at FUSE Okinawa 2024
SWEBOK and Education at FUSE Okinawa 2024SWEBOK and Education at FUSE Okinawa 2024
SWEBOK and Education at FUSE Okinawa 2024
 
AI Fusion Buddy Review: Brand New, Groundbreaking Gemini-Powered AI App
AI Fusion Buddy Review: Brand New, Groundbreaking Gemini-Powered AI AppAI Fusion Buddy Review: Brand New, Groundbreaking Gemini-Powered AI App
AI Fusion Buddy Review: Brand New, Groundbreaking Gemini-Powered AI App
 
May Marketo Masterclass, London MUG May 22 2024.pdf
May Marketo Masterclass, London MUG May 22 2024.pdfMay Marketo Masterclass, London MUG May 22 2024.pdf
May Marketo Masterclass, London MUG May 22 2024.pdf
 
What is Augmented Reality Image Tracking
What is Augmented Reality Image TrackingWhat is Augmented Reality Image Tracking
What is Augmented Reality Image Tracking
 
Revolutionizing Visual Effects Mastering AI Face Swaps.pdf
Revolutionizing Visual Effects Mastering AI Face Swaps.pdfRevolutionizing Visual Effects Mastering AI Face Swaps.pdf
Revolutionizing Visual Effects Mastering AI Face Swaps.pdf
 
E-commerce Application Development Company.pdf
E-commerce Application Development Company.pdfE-commerce Application Development Company.pdf
E-commerce Application Development Company.pdf
 
Neo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
Neo4j - Product Vision and Knowledge Graphs - GraphSummit ParisNeo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
Neo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
 
DDS-Security 1.2 - What's New? Stronger security for long-running systems
DDS-Security 1.2 - What's New? Stronger security for long-running systemsDDS-Security 1.2 - What's New? Stronger security for long-running systems
DDS-Security 1.2 - What's New? Stronger security for long-running systems
 
Why Choose Odoo 17 Community & How it differs from Odoo 17 Enterprise Edition
Why Choose Odoo 17 Community & How it differs from Odoo 17 Enterprise EditionWhy Choose Odoo 17 Community & How it differs from Odoo 17 Enterprise Edition
Why Choose Odoo 17 Community & How it differs from Odoo 17 Enterprise Edition
 
OpenMetadata Community Meeting - 5th June 2024
OpenMetadata Community Meeting - 5th June 2024OpenMetadata Community Meeting - 5th June 2024
OpenMetadata Community Meeting - 5th June 2024
 
Need for Speed: Removing speed bumps from your Symfony projects ⚡️
Need for Speed: Removing speed bumps from your Symfony projects ⚡️Need for Speed: Removing speed bumps from your Symfony projects ⚡️
Need for Speed: Removing speed bumps from your Symfony projects ⚡️
 
LORRAINE ANDREI_LEQUIGAN_HOW TO USE ZOOM
LORRAINE ANDREI_LEQUIGAN_HOW TO USE ZOOMLORRAINE ANDREI_LEQUIGAN_HOW TO USE ZOOM
LORRAINE ANDREI_LEQUIGAN_HOW TO USE ZOOM
 
Empowering Growth with Best Software Development Company in Noida - Deuglo
Empowering Growth with Best Software  Development Company in Noida - DeugloEmpowering Growth with Best Software  Development Company in Noida - Deuglo
Empowering Growth with Best Software Development Company in Noida - Deuglo
 
KuberTENes Birthday Bash Guadalajara - Introducción a Argo CD
KuberTENes Birthday Bash Guadalajara - Introducción a Argo CDKuberTENes Birthday Bash Guadalajara - Introducción a Argo CD
KuberTENes Birthday Bash Guadalajara - Introducción a Argo CD
 
GreenCode-A-VSCode-Plugin--Dario-Jurisic
GreenCode-A-VSCode-Plugin--Dario-JurisicGreenCode-A-VSCode-Plugin--Dario-Jurisic
GreenCode-A-VSCode-Plugin--Dario-Jurisic
 
A Study of Variable-Role-based Feature Enrichment in Neural Models of Code
A Study of Variable-Role-based Feature Enrichment in Neural Models of CodeA Study of Variable-Role-based Feature Enrichment in Neural Models of Code
A Study of Variable-Role-based Feature Enrichment in Neural Models of Code
 

SUSE Storage: Sizing and Performance (Ceph)

  • 1. SUSE® Storage Sizing and Performance for Ceph Lars Marowsky-Brée Distinguished Engineer lmb@suse.com
  • 3. 3 From 10,000 Meters • Open Source Distributed Storage solution • Most popular choice of distributed storage for [1] OpenStack • Lots of goodies ‒ Distributed Object Storage ‒ Redundancy ‒ Efficient Scale-Out ‒ Can be built on commodity hardware ‒ Lower operational cost [1] http://www.openstack.org/blog/2013/11/openstack-user-survey-statistics-november-2013/
  • 4. 4 From 1,000 Meters • Three interfaces rolled into one ‒ Object Access (like Amazon S3) ‒ Block Access ‒ (Distributed File System) • Sitting on top of a Storage Cluster ‒ Self Healing ‒ Self Managed ‒ No Bottlenecks
  • 5. 5 From 1,000 Meters Unified Data Handling for 3 Purposes Object Storage (Like Amazon S3) Block Device File System ●RESTful Interface ●S3 and SWIFT APIs ●Block devices ●Up to 16 EiB ●Thin Provisioning ●Snapshots ●POSIX Compliant ●Separate Data and Metadata ●For use e.g. with Hadoop Autonomous, Redundant Storage Cluster
  • 6. 6 Component Names radosgw Object Storage RBD Block Device Ceph FS File System RADOS librados Direct Application Access to RADOS
  • 7. 7 SUSE Storage architectural benefits ● Integration with SUSE Cloud and SUSE Linux Enterprise Server ●Exabyte scalability ● No bottlenecks or single points of failure ● Industry-leading functionality ● Remote replication, erasure coding ● Cache tiering ● Unified block, file and object interface ● Thin provisioning, copy on write ●100% software based; can use commodity hardware ●Automated management ● Self-managing, self-healing
  • 9. 9 For a Moment, Zooming to Atom Level OSD Object Storage Daemon FS Disk File System (btrfs, xfs) Physical Disk ● OSDs serve storage objects to clients ● Peer to perform replication and recovery
  • 10. 10 Put Several of These in One Node OSD FS Disk OSD FS Disk OSD FS Disk OSD FS Disk OSD FS Disk OSD FS Disk
  • 11. 11 Mix In a Few Monitor Nodes M • Monitors are the brain cells of the cluster ‒ Cluster Membership ‒ Consensus for Distributed Decision Making • Do not serve stored objects to clients
  • 12. 12 Voilà, a Small RADOS Cluster M M M
  • 13. 13 Different Access Modes • radosgw: ‒ An additional gateway in front of your RADOS cluster ‒ Little impact on throughput, but it does affect latency • User-space RADOS access: ‒ More feature rich than in-kernel rbd.ko module ‒ Typically provides higher performance
  • 14. 14 Several Ingredients • Basic Idea ‒ Coarse grained partitioning of storage supports policy based mapping (don't put all copies of my data in one rack) ‒ Topology map and Rules allow clients to “compute” the exact location of any storage object • Three conceptual components ‒ Pools ‒ Placement groups ‒ CRUSH: deterministic decentralized placement algorithm
  • 15. 15 Pools • A pool is a logical container for storage objects • A pool has a set of parameters ‒ a name ‒ a numerical ID (internal to RADOS) ‒ number of replicas OR erasure encoding settings ‒ number of placement groups ‒ placement rule set ‒ owner • Pools support certain operations ‒ create/remove/read/write entire objects ‒ snapshot of the entire pool
  • 16. 16 Placement Groups • Placement groups help balance data across OSDs • Consider a pool named “swimmingpool” ‒ with a pool ID of 38 and 8192 placement groups (PGs) • Consider object “rubberduck” in “swimmingpool” ‒ hash(“rubberduck”) % 8192 = 0xb0b ‒ The resulting PG is 38.b0b • One PG typically exists on several OSDs ‒ for replication • One OSD typically serves many PGs
  • 17. 17 CRUSH • CRUSH uses a map of all OSDs in your cluster ‒ includes physical topology, like row, rack, host ‒ includes rules describing which OSDs to consider for what type of pool/PG • This map is maintained by the monitor nodes ‒ Monitor nodes use standard cluster algorithms for consensus building, etc
  • 19. 19 CRUSH in Action: Reading swimmingpool/rubberduck M M M 38.b0b Reads could be serviced by any of the replicas (parallel reads improve thruput)
  • 20. 20 CRUSH in Action: Writing swimmingpool/rubberduck M M M 38.b0b Writes go to one OSD, which then propagates the changes to other replicas
  • 22. 22 Legacy Storage Arrays • Limits: ‒ Tightly controlled environment ‒ Limited scalability ‒ Few options ‒ Only certain approved drives ‒ Constrained number of disk slots ‒ Few memory variations ‒ Only very few networking choices ‒ Typically fixed controller and CPU • Benefits: ‒ Reasonably easy to understand ‒ Long-term experience and “gut instincts” ‒ Somewhat deterministic behavior and pricing
  • 23. 23 Software Defined Storage (SDS) • Limits: ‒ ? • Benefits: ‒ Infinite scalability ‒ Infinite adaptability ‒ Infinite choices ‒ Infinite flexibility ‒ ... right.
  • 24. 24 Properties of a SDS System • Throughput • Latency • IOPS • Availability • Reliability • Capacity • Cost • Density
  • 25. 25 Architecting a SDS system • These goals often conflict: ‒ Availability versus Density ‒ IOPS versus Density ‒ Everything versus Cost • Many hardware options • Software topology offers many configuration choices • There is no one size fits all
  • 27. 27 Network • Choose the fastest network you can afford • Switches should be low latency with fully meshed backplane • Separate public and cluster network • Cluster network should typically be twice the public bandwidth ‒ Incoming writes are replicated over the cluster network ‒ Re-balancing and re-mirroring utilize the cluster network
  • 28. 28 Networking (Public and Internal) • Ethernet (1, 10, 40 GbE) ‒ Reasonably inexpensive (except for 40 GbE) ‒ Can easily be bonded for availability ‒ Use jumbo frames • Infiniband ‒ High bandwidth ‒ Low latency ‒ Typically more expensive ‒ No support for RDMA yet in Ceph, need to use IPoIB
  • 29. 29 Storage Node • CPU ‒ Number and speed of cores • Memory • Storage controller ‒ Bandwidth, performance, cache size • SSDs for OSD journal ‒ SSD to HDD ratio • HDDs ‒ Count, capacity, performance
  • 30. 30 Adding More Nodes • Capacity increases • Total throughput increases • IOPS increase • Redundancy increases • Latency unchanged • Eventually: network topology limitations • Temporary impact during re-balancing
  • 31. 31 Adding More Disks to a Node • Capacity increases • Redundancy increases • Throughput might increase • IOPS might increase • Internal node bandwidth is consumed • Higher CPU and memory load • Cache contention • Latency unchanged
  • 32. 32 OSD File System • btrfs ‒ Typically better write throughput performance ‒ Higher CPU utilization ‒ Feature rich ‒ Compression, checksums, copy on write ‒ The choice for the future! • XFS ‒ Good all around choice ‒ Very mature for data partitions ‒ Typically lower CPU utilization ‒ The choice for today!
  • 33. 33 Impact of Caches • Cache on the client side ‒ Typically, biggest impact on performance ‒ Does not help with write performance • Server OS cache ‒ Low impact: reads have already been cached on the client ‒ Still, helps with readahead • Caching controller, battery backed: ‒ Significant impact for writes
  • 34. 34 Impact of SSD Journals • SSD journals accelerate bursts and random write IO • For sustained writes that overflow the journal, performance degrades to HDD levels • SSDs help very little with read performance • SSDs are very costly ‒ ... and consume storage slots -> lower density • A large battery-backed cache on the storage controller is highly recommended if not using SSD journals
  • 35. 35 Hard Disk Parameters • Capacity matters ‒ Often, highest density is not most cost effective ‒ On-disk cache matters less • Reliability advantage of Enterprise drives typically marginal compared to cost ‒ Buy more drives instead ‒ Consider validation matrices for small/medium NAS servers as a guide • RPM: ‒ Increase IOPS & throughput ‒ Increases power consumption ‒ 15k drives quite expensive still
  • 36. 36 Impact of Redundancy Choices • Replication: ‒ n number of exact, full-size copies ‒ Potentially increased read performance due to striping ‒ More copies lower throughput, increase latency ‒ Increased cluster network utilization for writes ‒ Rebuilds can leverage multiple sources ‒ Significant capacity impact • Erasure coding: ‒ Data split into k parts plus m redundancy codes ‒ Better space efficiency ‒ Higher CPU overhead ‒ Significant CPU and cluster network impact, especially during rebuild ‒ Cannot directly be used with block devices (see next slide)
  • 37. 37 Cache Tiering • Multi-tier storage architecture: ‒ Pool acts as a transparent write-back overlay for another ‒ e.g., SSD 3-way replication over HDDs with erasure coding ‒ Can flush either on relative or absolute dirty levels, or age ‒ Additional configuration complexity and requires workload-specific tuning ‒ Also available: read-only mode (no write acceleration) ‒ Some downsides (no snapshots), memory consumption for HitSet • A good way to combine the advantages of replication and erasure coding
  • 38. 38 Number of placement groups ●Number of hash buckets per pool ● Data is chunked & distributed across nodes ● Typically approx. 100 per OSD/TB • Too many: ‒ More peering ‒ More resources used • Too few: ‒ Large amounts of data per group ‒ More hotspots, less striping ‒ Slower recovery from failure ‒ Slower re-balancing
  • 39. 39 Measuring Ceph performance • rados bench ‒ Measures backend performance of the RADOS store ‒ Simple options • rados load-gen ‒ Generate configurable load on the cluster • fio rbd backend ‒ Swiss army knife of IO benchmarking on Linux ‒ Can also compare in-kernel rbd with user-space librados • rest-bench ‒ Measures S3/radosgw performance
  • 41. 41 How to size a Ceph cluster? • Understand your workload • Make a best guess, based on the desirable properties and factors • Build a 10% pilot / proof of concept ‒ Preferably using loaner hardware from a vendor to avoid early commitment ‒ The outlook of selling a few PB of storage and compute nodes makes vendors very cooperative • Refine this until desired performance is achieved • Scale up ‒ Ceph retains most characteristics at scale or even improves
  • 42. Thank you. 42 Questions and Answers?
  • 43. Corporate Headquarters Maxfeldstrasse 5 90409 Nuremberg Germany +49 911 740 53 0 (Worldwide) www.suse.com Join us on: www.opensuse.org 43
  • 44. Unpublished Work of SUSE LLC. All Rights Reserved. This work is an unpublished work and contains confidential, proprietary and trade secret information of SUSE LLC. Access to this work is restricted to SUSE employees who have a need to know to perform tasks within the scope of their assignments. No part of this work may be practiced, performed, copied, distributed, revised, modified, translated, abridged, condensed, expanded, collected, or adapted without the prior written consent of SUSE. Any use or exploitation of this work without authorization could subject the perpetrator to criminal and civil liability. General Disclaimer This document is not to be construed as a promise by any participating company to develop, deliver, or market a product. It is not a commitment to deliver any material, code, or functionality, and should not be relied upon in making purchasing decisions. SUSE makes no representations or warranties with respect to the contents of this document, and specifically disclaims any express or implied warranties of merchantability or fitness for any particular purpose. The development, release, and timing of features or functionality described for SUSE products remains at the sole discretion of SUSE. Further, SUSE reserves the right to revise this document and to make changes to its content, at any time, without obligation to notify any person or entity of such revisions or changes. All SUSE marks referenced in this presentation are trademarks or registered trademarks of Novell, Inc. in the United States and other countries. All third-party trademarks are the property of their respective owners.