SlideShare a Scribd company logo
Our first 5 years with Ceph
Lars Marowsky-Brée
lmb@suse.com
Distinguished Engineer, Architect Software-Defined-Storage
2
Welcome!
33
Enterprise Data Storage Challenges
4
Common Limitations of Traditional
Enterprise Storage
Unable to scale and
manage data
growth
Expensive Won’t extend to
the software-defined
data center
$
PRESENT
FUTURE
£
€
$
5
Data Continues to Grow Very Fast
Medical Data
EmailsVideos
Mobile Data IoT Data
Transactional Data
6
Data Protection Problem is Getting
Compounded
• Inability to keep enough data online
• Not being able to recover lost data fast enough
• Migrations to larger disk or dedupe appliances every year
Increasing volumes of data compound the data protection problem
*SUSE Software Defined Storage Study 2016
Cost of storage
Performance / availability
Challenges with back up, disaster recovery and archiving
Increasing volumes of data
Security and data governance
45%
46%
46%
54%
56%
Customer Facing Numerous Backup Challenges:
Top 5 Data Management Challenges*
7
Open Source is the only sustainable option
88
About SUSE Enterprise Storage
9
SUSE’s history with Ceph
August 2012 SUSE Cloud 1 Argonaut
February 2015 SUSE Enterprise Storage 1 Firefly
October 2015 SUSE Enterprise Storage 2 Hammer
June 2016 SUSE Enterprise Storage 3 Jewel
October 2016 openATTIC team joins SUSE!
November 2016 SUSE Enterprise Storage 4 Jewel
October 2017 SUSE Enterprise Storage 5 Luminous
Later 2018 SUSE Enterprise Storage 6 Mimic
10
●
Curate open source solutions – projects and features
●
Track, test, and manage software dependencies
●
Incorporate and provide patches and backports
●
Advise customers on recommended practices and hardware
●
Represent customers and partners in the community
●
Bridge the worlds of community and IHVs/ISVs
●
Provide high quality support
Vendor value add
11
●
Strong contributor to Ceph community & Ceph Advisory Board
●
True Open Source - “Upstream first”
●
iSCSI with Multipathing/VMware support
●
First supported Ceph distribution for ARM64
●
First to support CephFS for production deployments
●
Salt-based orchestration for upgrade and FileStore/BlueStore migration
●
Lead on openATTIC, Prometheus & Grafana, now merged into core
Ceph management functionality
Major SUSE contributions
12
Monitoring with openATTIC
13
Management with openATTIC
14
openATTIC merging into the Ceph dashboard
1515
Strong industry partnerships
16
Use Case Focused Solutions
Backup to Disk Solution Compliant
Archives
SAP HANA
Storage Solution
Appliance
HPC Archives
Certified RAs
Cloud
SOC SES
IoT
Configuration CSPs +
SES
Mode1
Customers
Mode2
Customers
Example SUSE Enterprise Storage Partners
17
Growth of our Ceph deployments
1818
Industry validation
PUBLIC
Marc Koderer, SAP
March 2018
Case Study: Ceph at SAP
How to Build a Cattle Cloud
20PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ
Integraton
Environment
SAP Cloud Platform, private edition – High Level
Security Platorm
Services
SAP Cloud Platorm Private Cloud
Data & Storage
Foundaton
XS Advanced Development
IaaSSAP HANA
Database
Hardware / Bare Metal
Applicaton / IoT
ERP
21PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ
Traditional applications vs cloud native applications (pets vs cattle)
DB
Standby
DB
Active
App App
Centralized
Storage
Characteristics:
• Runs on bare metal and/or VM’s
• HW failure is exceptional
• Centralized instead of distributed
monolithic payloads
Characteristics:
• Runs on VMs or in Containers
• HW failure can happen all the time
• Highly distributed
Distributed Storage / SDS
DB2DB1
Service Service Service…
DBn…
Distributed/scale-out payloads
22PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ
AZ1 AZ2 AZ3
Private cloud architecture
23PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ
AZ1 AZ2 AZ3
OpenStack Control Plane
C
N
C
N
C
N
C
N
C
N
C
N
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
Private cloud architecture
24PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ
AZ1 AZ2 AZ3
Ceph
S
T
S
T
S
T
S
T
S
T
S
T
S
T
S
T
S
T
OpenStack Control Plane
C
N
C
N
C
N
C
N
C
N
C
N
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
H
V
Private cloud architecture
25PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ
Ceph in detail
S
T
S
T
S
T
S
T
S
T
S
T
S
T
S
T
S
T
spine01 spine02 spine03 spine04
leaf02a leaf02b leaf03a leaf03bleaf01a leaf01b
26PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ
Ceph in detail
S
T
S
T
S
T
S
T
S
T
S
T
S
T
S
T
S
T
spine01 spine02 spine03 spine04
leaf02a leaf02b leaf03a leaf03bleaf01a leaf01b
• Hardware characteristics
• 108 storage nodes
• 24 disk per osd node; 2 NVMEs
• 4x 25 Gbit (2x 25 Gbit bond frontend; 2x 25 Gbit bond backend)
• Spine/leaf network architecture across all AZs
• RBD and Radosgw usage
• The Ceph cluster is designed to compensate the outage of one Availability Zone
• Max performance ~60 GB/sec (writes; 4MB)
27PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ
Ceph in detail: RGW
Loadbalancer
VM VM VM VM VM
mon1 mon2 mon3
osd1 osd2 osd3 osdn…
mon4 mon5
rgw1 rgw2 rgw3 rgw30…
28PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ
RGW stress test
# of RGW
(6 vcpus)
Max
concurrent
connection
Method Throughput
1 512 put 250 MB/sec
1 512 get 300 MB/sec
3 1536 put 700 MB/sec
3 1536 get 900 MB/sec
9 4608 put 1950 MB/sec
9 4608 get 2100 MB/sec
2929
The next 5 years
30
SUSE Enterprise Storage 6 – based on Mimic
•Incorporates Ceph Mimic
•Based on SUSE Linux Enterprise 15
•Improve interoperability
•Internationalization and localization
•Improved scale-out user experience
•Eventing and alerting
•Metric reporting and telemetry
31
Hyper-converged infrastructure
32
SUSE Container as a Service Platform
33
openATTIC <3 Ceph’s Dashboard
Provide a better user experience
Make complex tasks easier
Assist users along the way of sizing,
deploying, and managing a Ceph cluster
34
Machine Learning and AI
35
Ceph? Not if. When.
Open source cloud operating systems and software-defined storage
platforms are based on the Linux operating system.
SUSE is a Linux OS pioneer and successful software vendor with
thousands of installations. Customers should expect to receive
nothing less than expert support for their software-based storage.
Learn more at suse.com/storage/
Ceph's journey at SUSE

More Related Content

What's hot

Ceph optimized Storage / Global HW solutions for SDS, David Alvarez
Ceph optimized Storage / Global HW solutions for SDS, David AlvarezCeph optimized Storage / Global HW solutions for SDS, David Alvarez
Ceph optimized Storage / Global HW solutions for SDS, David Alvarez
Ceph Community
 
Red Hat Storage Day Seattle: Why Software-Defined Storage Matters
Red Hat Storage Day Seattle: Why Software-Defined Storage MattersRed Hat Storage Day Seattle: Why Software-Defined Storage Matters
Red Hat Storage Day Seattle: Why Software-Defined Storage Matters
Red_Hat_Storage
 
Ceph: Low Fail Go Scale
Ceph: Low Fail Go Scale Ceph: Low Fail Go Scale
Ceph: Low Fail Go Scale
Ceph Community
 
Red Hat Storage Day Seattle: Stabilizing Petabyte Ceph Cluster in OpenStack C...
Red Hat Storage Day Seattle: Stabilizing Petabyte Ceph Cluster in OpenStack C...Red Hat Storage Day Seattle: Stabilizing Petabyte Ceph Cluster in OpenStack C...
Red Hat Storage Day Seattle: Stabilizing Petabyte Ceph Cluster in OpenStack C...
Red_Hat_Storage
 
Red Hat Storage Day Boston - Red Hat Gluster Storage vs. Traditional Storage ...
Red Hat Storage Day Boston - Red Hat Gluster Storage vs. Traditional Storage ...Red Hat Storage Day Boston - Red Hat Gluster Storage vs. Traditional Storage ...
Red Hat Storage Day Boston - Red Hat Gluster Storage vs. Traditional Storage ...
Red_Hat_Storage
 
ThunderX ARMV8 Servers: Disruption and Innovation in the Server Market
ThunderX ARMV8 Servers: Disruption and Innovation in the Server MarketThunderX ARMV8 Servers: Disruption and Innovation in the Server Market
ThunderX ARMV8 Servers: Disruption and Innovation in the Server Market
Red_Hat_Storage
 
Red hat Storage Day LA - Designing Ceph Clusters Using Intel-Based Hardware
Red hat Storage Day LA - Designing Ceph Clusters Using Intel-Based HardwareRed hat Storage Day LA - Designing Ceph Clusters Using Intel-Based Hardware
Red hat Storage Day LA - Designing Ceph Clusters Using Intel-Based Hardware
Red_Hat_Storage
 
Intel - optimizing ceph performance by leveraging intel® optane™ and 3 d nand...
Intel - optimizing ceph performance by leveraging intel® optane™ and 3 d nand...Intel - optimizing ceph performance by leveraging intel® optane™ and 3 d nand...
Intel - optimizing ceph performance by leveraging intel® optane™ and 3 d nand...
inwin stack
 
Red Hat Ceph Storage Acceleration Utilizing Flash Technology
Red Hat Ceph Storage Acceleration Utilizing Flash Technology Red Hat Ceph Storage Acceleration Utilizing Flash Technology
Red Hat Ceph Storage Acceleration Utilizing Flash Technology
Red_Hat_Storage
 
Ceph Day San Jose - All-Flahs Ceph on NUMA-Balanced Server
Ceph Day San Jose - All-Flahs Ceph on NUMA-Balanced Server Ceph Day San Jose - All-Flahs Ceph on NUMA-Balanced Server
Ceph Day San Jose - All-Flahs Ceph on NUMA-Balanced Server
Ceph Community
 
Disk health prediction for Ceph
Disk health prediction for CephDisk health prediction for Ceph
Disk health prediction for Ceph
Ceph Community
 
Red Hat Storage Day Boston - Supermicro Super Storage
Red Hat Storage Day Boston - Supermicro Super StorageRed Hat Storage Day Boston - Supermicro Super Storage
Red Hat Storage Day Boston - Supermicro Super Storage
Red_Hat_Storage
 
CEPH DAY BERLIN - DISK HEALTH PREDICTION AND RESOURCE ALLOCATION FOR CEPH BY ...
CEPH DAY BERLIN - DISK HEALTH PREDICTION AND RESOURCE ALLOCATION FOR CEPH BY ...CEPH DAY BERLIN - DISK HEALTH PREDICTION AND RESOURCE ALLOCATION FOR CEPH BY ...
CEPH DAY BERLIN - DISK HEALTH PREDICTION AND RESOURCE ALLOCATION FOR CEPH BY ...
Ceph Community
 
MySQL Head to Head Performance
MySQL Head to Head PerformanceMySQL Head to Head Performance
MySQL Head to Head Performance
Kyle Bader
 
Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...
Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...
Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...
Red_Hat_Storage
 
Ceph Deployment at Target: Customer Spotlight
Ceph Deployment at Target: Customer SpotlightCeph Deployment at Target: Customer Spotlight
Ceph Deployment at Target: Customer Spotlight
Colleen Corrice
 
Implementation of Dense Storage Utilizing HDDs with SSDs and PCIe Flash Acc...
Implementation of Dense Storage Utilizing  HDDs with SSDs and PCIe Flash  Acc...Implementation of Dense Storage Utilizing  HDDs with SSDs and PCIe Flash  Acc...
Implementation of Dense Storage Utilizing HDDs with SSDs and PCIe Flash Acc...
Red_Hat_Storage
 
Red Hat Storage for Mere Mortals
Red Hat Storage for Mere MortalsRed Hat Storage for Mere Mortals
Red Hat Storage for Mere Mortals
Red_Hat_Storage
 
Ceph Day San Jose - Object Storage for Big Data
Ceph Day San Jose - Object Storage for Big Data Ceph Day San Jose - Object Storage for Big Data
Ceph Day San Jose - Object Storage for Big Data
Ceph Community
 
2016-JAN-28 -- High Performance Production Databases on Ceph
2016-JAN-28 -- High Performance Production Databases on Ceph2016-JAN-28 -- High Performance Production Databases on Ceph
2016-JAN-28 -- High Performance Production Databases on Ceph
Ceph Community
 

What's hot (20)

Ceph optimized Storage / Global HW solutions for SDS, David Alvarez
Ceph optimized Storage / Global HW solutions for SDS, David AlvarezCeph optimized Storage / Global HW solutions for SDS, David Alvarez
Ceph optimized Storage / Global HW solutions for SDS, David Alvarez
 
Red Hat Storage Day Seattle: Why Software-Defined Storage Matters
Red Hat Storage Day Seattle: Why Software-Defined Storage MattersRed Hat Storage Day Seattle: Why Software-Defined Storage Matters
Red Hat Storage Day Seattle: Why Software-Defined Storage Matters
 
Ceph: Low Fail Go Scale
Ceph: Low Fail Go Scale Ceph: Low Fail Go Scale
Ceph: Low Fail Go Scale
 
Red Hat Storage Day Seattle: Stabilizing Petabyte Ceph Cluster in OpenStack C...
Red Hat Storage Day Seattle: Stabilizing Petabyte Ceph Cluster in OpenStack C...Red Hat Storage Day Seattle: Stabilizing Petabyte Ceph Cluster in OpenStack C...
Red Hat Storage Day Seattle: Stabilizing Petabyte Ceph Cluster in OpenStack C...
 
Red Hat Storage Day Boston - Red Hat Gluster Storage vs. Traditional Storage ...
Red Hat Storage Day Boston - Red Hat Gluster Storage vs. Traditional Storage ...Red Hat Storage Day Boston - Red Hat Gluster Storage vs. Traditional Storage ...
Red Hat Storage Day Boston - Red Hat Gluster Storage vs. Traditional Storage ...
 
ThunderX ARMV8 Servers: Disruption and Innovation in the Server Market
ThunderX ARMV8 Servers: Disruption and Innovation in the Server MarketThunderX ARMV8 Servers: Disruption and Innovation in the Server Market
ThunderX ARMV8 Servers: Disruption and Innovation in the Server Market
 
Red hat Storage Day LA - Designing Ceph Clusters Using Intel-Based Hardware
Red hat Storage Day LA - Designing Ceph Clusters Using Intel-Based HardwareRed hat Storage Day LA - Designing Ceph Clusters Using Intel-Based Hardware
Red hat Storage Day LA - Designing Ceph Clusters Using Intel-Based Hardware
 
Intel - optimizing ceph performance by leveraging intel® optane™ and 3 d nand...
Intel - optimizing ceph performance by leveraging intel® optane™ and 3 d nand...Intel - optimizing ceph performance by leveraging intel® optane™ and 3 d nand...
Intel - optimizing ceph performance by leveraging intel® optane™ and 3 d nand...
 
Red Hat Ceph Storage Acceleration Utilizing Flash Technology
Red Hat Ceph Storage Acceleration Utilizing Flash Technology Red Hat Ceph Storage Acceleration Utilizing Flash Technology
Red Hat Ceph Storage Acceleration Utilizing Flash Technology
 
Ceph Day San Jose - All-Flahs Ceph on NUMA-Balanced Server
Ceph Day San Jose - All-Flahs Ceph on NUMA-Balanced Server Ceph Day San Jose - All-Flahs Ceph on NUMA-Balanced Server
Ceph Day San Jose - All-Flahs Ceph on NUMA-Balanced Server
 
Disk health prediction for Ceph
Disk health prediction for CephDisk health prediction for Ceph
Disk health prediction for Ceph
 
Red Hat Storage Day Boston - Supermicro Super Storage
Red Hat Storage Day Boston - Supermicro Super StorageRed Hat Storage Day Boston - Supermicro Super Storage
Red Hat Storage Day Boston - Supermicro Super Storage
 
CEPH DAY BERLIN - DISK HEALTH PREDICTION AND RESOURCE ALLOCATION FOR CEPH BY ...
CEPH DAY BERLIN - DISK HEALTH PREDICTION AND RESOURCE ALLOCATION FOR CEPH BY ...CEPH DAY BERLIN - DISK HEALTH PREDICTION AND RESOURCE ALLOCATION FOR CEPH BY ...
CEPH DAY BERLIN - DISK HEALTH PREDICTION AND RESOURCE ALLOCATION FOR CEPH BY ...
 
MySQL Head to Head Performance
MySQL Head to Head PerformanceMySQL Head to Head Performance
MySQL Head to Head Performance
 
Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...
Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...
Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...
 
Ceph Deployment at Target: Customer Spotlight
Ceph Deployment at Target: Customer SpotlightCeph Deployment at Target: Customer Spotlight
Ceph Deployment at Target: Customer Spotlight
 
Implementation of Dense Storage Utilizing HDDs with SSDs and PCIe Flash Acc...
Implementation of Dense Storage Utilizing  HDDs with SSDs and PCIe Flash  Acc...Implementation of Dense Storage Utilizing  HDDs with SSDs and PCIe Flash  Acc...
Implementation of Dense Storage Utilizing HDDs with SSDs and PCIe Flash Acc...
 
Red Hat Storage for Mere Mortals
Red Hat Storage for Mere MortalsRed Hat Storage for Mere Mortals
Red Hat Storage for Mere Mortals
 
Ceph Day San Jose - Object Storage for Big Data
Ceph Day San Jose - Object Storage for Big Data Ceph Day San Jose - Object Storage for Big Data
Ceph Day San Jose - Object Storage for Big Data
 
2016-JAN-28 -- High Performance Production Databases on Ceph
2016-JAN-28 -- High Performance Production Databases on Ceph2016-JAN-28 -- High Performance Production Databases on Ceph
2016-JAN-28 -- High Performance Production Databases on Ceph
 

Similar to Ceph's journey at SUSE

Webinar: All-Flash For Databases: 5 Reasons Why Current Systems Are Off Target
Webinar: All-Flash For Databases: 5 Reasons Why Current Systems Are Off TargetWebinar: All-Flash For Databases: 5 Reasons Why Current Systems Are Off Target
Webinar: All-Flash For Databases: 5 Reasons Why Current Systems Are Off Target
Storage Switzerland
 
NetApp All Flash storage
NetApp All Flash storageNetApp All Flash storage
NetApp All Flash storage
MarketingArrowECS_CZ
 
HPC DAY 2017 | HPE Storage and Data Management for Big Data
HPC DAY 2017 | HPE Storage and Data Management for Big DataHPC DAY 2017 | HPE Storage and Data Management for Big Data
HPC DAY 2017 | HPE Storage and Data Management for Big Data
HPC DAY
 
Lessons learned processing 70 billion data points a day using the hybrid cloud
Lessons learned processing 70 billion data points a day using the hybrid cloudLessons learned processing 70 billion data points a day using the hybrid cloud
Lessons learned processing 70 billion data points a day using the hybrid cloud
DataWorks Summit
 
EMEA TechTalk – The NetApp Flash Optimized Portfolio
EMEA TechTalk – The NetApp Flash Optimized PortfolioEMEA TechTalk – The NetApp Flash Optimized Portfolio
EMEA TechTalk – The NetApp Flash Optimized Portfolio
NetApp
 
Streaming solutions for real time problems
Streaming solutions for real time problems Streaming solutions for real time problems
Streaming solutions for real time problems
Aparna Gaonkar
 
OpenStack and NetApp - Chen Reuven - OpenStack Day Israel 2017
OpenStack and NetApp - Chen Reuven - OpenStack Day Israel 2017OpenStack and NetApp - Chen Reuven - OpenStack Day Israel 2017
OpenStack and NetApp - Chen Reuven - OpenStack Day Israel 2017
Cloud Native Day Tel Aviv
 
Are your ready for in memory applications?
Are your ready for in memory applications?Are your ready for in memory applications?
Are your ready for in memory applications?
G2MCommunications
 
Flash changes everything?! Flash changes nothing...
Flash changes everything?! Flash changes nothing...Flash changes everything?! Flash changes nothing...
Flash changes everything?! Flash changes nothing...
Proact Netherlands B.V.
 
HPE Solutions for Challenges in AI and Big Data
HPE Solutions for Challenges in AI and Big DataHPE Solutions for Challenges in AI and Big Data
HPE Solutions for Challenges in AI and Big Data
Lviv Startup Club
 
Saviak lviv ai-2019-e-mail (1)
Saviak lviv ai-2019-e-mail (1)Saviak lviv ai-2019-e-mail (1)
Saviak lviv ai-2019-e-mail (1)
Lviv Startup Club
 
IBM Power Systems - enabling cloud solutions
IBM Power Systems - enabling cloud solutionsIBM Power Systems - enabling cloud solutions
IBM Power Systems - enabling cloud solutions
David Spurway
 
The Consequences of Infinite Storage Bandwidth: Allen Samuels, SanDisk
The Consequences of Infinite Storage Bandwidth: Allen Samuels, SanDiskThe Consequences of Infinite Storage Bandwidth: Allen Samuels, SanDisk
The Consequences of Infinite Storage Bandwidth: Allen Samuels, SanDisk
OpenStack
 
SAP ASE 16 SP02 Performance Features
SAP ASE 16 SP02 Performance FeaturesSAP ASE 16 SP02 Performance Features
SAP ASE 16 SP02 Performance Features
SAP Technology
 
Webinar: The Bifurcation of the Flash Market
Webinar: The Bifurcation of the Flash MarketWebinar: The Bifurcation of the Flash Market
Webinar: The Bifurcation of the Flash Market
Storage Switzerland
 
Comparing the TCO of HP NonStop with Oracle RAC
Comparing the TCO of HP NonStop with Oracle RACComparing the TCO of HP NonStop with Oracle RAC
Comparing the TCO of HP NonStop with Oracle RAC
Thomas Burg
 
Hp Converged Systems and Hortonworks - Webinar Slides
Hp Converged Systems and Hortonworks - Webinar SlidesHp Converged Systems and Hortonworks - Webinar Slides
Hp Converged Systems and Hortonworks - Webinar Slides
Hortonworks
 
Denver Big Data Analytics Day
Denver Big Data Analytics DayDenver Big Data Analytics Day
Denver Big Data Analytics Day
Zivaro Inc
 
Optimizing Flash Storage for SQL Databases
Optimizing Flash Storage for SQL DatabasesOptimizing Flash Storage for SQL Databases
Optimizing Flash Storage for SQL Databases
Storage Switzerland
 
OWF14 - Plenary Session : Thibaud Besson, IBM POWER Systems Specialist
OWF14 - Plenary Session : Thibaud Besson, IBM POWER Systems SpecialistOWF14 - Plenary Session : Thibaud Besson, IBM POWER Systems Specialist
OWF14 - Plenary Session : Thibaud Besson, IBM POWER Systems Specialist
Paris Open Source Summit
 

Similar to Ceph's journey at SUSE (20)

Webinar: All-Flash For Databases: 5 Reasons Why Current Systems Are Off Target
Webinar: All-Flash For Databases: 5 Reasons Why Current Systems Are Off TargetWebinar: All-Flash For Databases: 5 Reasons Why Current Systems Are Off Target
Webinar: All-Flash For Databases: 5 Reasons Why Current Systems Are Off Target
 
NetApp All Flash storage
NetApp All Flash storageNetApp All Flash storage
NetApp All Flash storage
 
HPC DAY 2017 | HPE Storage and Data Management for Big Data
HPC DAY 2017 | HPE Storage and Data Management for Big DataHPC DAY 2017 | HPE Storage and Data Management for Big Data
HPC DAY 2017 | HPE Storage and Data Management for Big Data
 
Lessons learned processing 70 billion data points a day using the hybrid cloud
Lessons learned processing 70 billion data points a day using the hybrid cloudLessons learned processing 70 billion data points a day using the hybrid cloud
Lessons learned processing 70 billion data points a day using the hybrid cloud
 
EMEA TechTalk – The NetApp Flash Optimized Portfolio
EMEA TechTalk – The NetApp Flash Optimized PortfolioEMEA TechTalk – The NetApp Flash Optimized Portfolio
EMEA TechTalk – The NetApp Flash Optimized Portfolio
 
Streaming solutions for real time problems
Streaming solutions for real time problems Streaming solutions for real time problems
Streaming solutions for real time problems
 
OpenStack and NetApp - Chen Reuven - OpenStack Day Israel 2017
OpenStack and NetApp - Chen Reuven - OpenStack Day Israel 2017OpenStack and NetApp - Chen Reuven - OpenStack Day Israel 2017
OpenStack and NetApp - Chen Reuven - OpenStack Day Israel 2017
 
Are your ready for in memory applications?
Are your ready for in memory applications?Are your ready for in memory applications?
Are your ready for in memory applications?
 
Flash changes everything?! Flash changes nothing...
Flash changes everything?! Flash changes nothing...Flash changes everything?! Flash changes nothing...
Flash changes everything?! Flash changes nothing...
 
HPE Solutions for Challenges in AI and Big Data
HPE Solutions for Challenges in AI and Big DataHPE Solutions for Challenges in AI and Big Data
HPE Solutions for Challenges in AI and Big Data
 
Saviak lviv ai-2019-e-mail (1)
Saviak lviv ai-2019-e-mail (1)Saviak lviv ai-2019-e-mail (1)
Saviak lviv ai-2019-e-mail (1)
 
IBM Power Systems - enabling cloud solutions
IBM Power Systems - enabling cloud solutionsIBM Power Systems - enabling cloud solutions
IBM Power Systems - enabling cloud solutions
 
The Consequences of Infinite Storage Bandwidth: Allen Samuels, SanDisk
The Consequences of Infinite Storage Bandwidth: Allen Samuels, SanDiskThe Consequences of Infinite Storage Bandwidth: Allen Samuels, SanDisk
The Consequences of Infinite Storage Bandwidth: Allen Samuels, SanDisk
 
SAP ASE 16 SP02 Performance Features
SAP ASE 16 SP02 Performance FeaturesSAP ASE 16 SP02 Performance Features
SAP ASE 16 SP02 Performance Features
 
Webinar: The Bifurcation of the Flash Market
Webinar: The Bifurcation of the Flash MarketWebinar: The Bifurcation of the Flash Market
Webinar: The Bifurcation of the Flash Market
 
Comparing the TCO of HP NonStop with Oracle RAC
Comparing the TCO of HP NonStop with Oracle RACComparing the TCO of HP NonStop with Oracle RAC
Comparing the TCO of HP NonStop with Oracle RAC
 
Hp Converged Systems and Hortonworks - Webinar Slides
Hp Converged Systems and Hortonworks - Webinar SlidesHp Converged Systems and Hortonworks - Webinar Slides
Hp Converged Systems and Hortonworks - Webinar Slides
 
Denver Big Data Analytics Day
Denver Big Data Analytics DayDenver Big Data Analytics Day
Denver Big Data Analytics Day
 
Optimizing Flash Storage for SQL Databases
Optimizing Flash Storage for SQL DatabasesOptimizing Flash Storage for SQL Databases
Optimizing Flash Storage for SQL Databases
 
OWF14 - Plenary Session : Thibaud Besson, IBM POWER Systems Specialist
OWF14 - Plenary Session : Thibaud Besson, IBM POWER Systems SpecialistOWF14 - Plenary Session : Thibaud Besson, IBM POWER Systems Specialist
OWF14 - Plenary Session : Thibaud Besson, IBM POWER Systems Specialist
 

Recently uploaded

A Deep Dive into ScyllaDB's Architecture
A Deep Dive into ScyllaDB's ArchitectureA Deep Dive into ScyllaDB's Architecture
A Deep Dive into ScyllaDB's Architecture
ScyllaDB
 
What is an RPA CoE? Session 2 – CoE Roles
What is an RPA CoE?  Session 2 – CoE RolesWhat is an RPA CoE?  Session 2 – CoE Roles
What is an RPA CoE? Session 2 – CoE Roles
DianaGray10
 
GlobalLogic Java Community Webinar #18 “How to Improve Web Application Perfor...
GlobalLogic Java Community Webinar #18 “How to Improve Web Application Perfor...GlobalLogic Java Community Webinar #18 “How to Improve Web Application Perfor...
GlobalLogic Java Community Webinar #18 “How to Improve Web Application Perfor...
GlobalLogic Ukraine
 
GNSS spoofing via SDR (Criptored Talks 2024)
GNSS spoofing via SDR (Criptored Talks 2024)GNSS spoofing via SDR (Criptored Talks 2024)
GNSS spoofing via SDR (Criptored Talks 2024)
Javier Junquera
 
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectorsConnector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
DianaGray10
 
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge GraphGraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
Neo4j
 
ScyllaDB Tablets: Rethinking Replication
ScyllaDB Tablets: Rethinking ReplicationScyllaDB Tablets: Rethinking Replication
ScyllaDB Tablets: Rethinking Replication
ScyllaDB
 
Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving | Nameplate Manufacturing Process - 2024Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving
 
Dandelion Hashtable: beyond billion requests per second on a commodity server
Dandelion Hashtable: beyond billion requests per second on a commodity serverDandelion Hashtable: beyond billion requests per second on a commodity server
Dandelion Hashtable: beyond billion requests per second on a commodity server
Antonios Katsarakis
 
inQuba Webinar Mastering Customer Journey Management with Dr Graham Hill
inQuba Webinar Mastering Customer Journey Management with Dr Graham HillinQuba Webinar Mastering Customer Journey Management with Dr Graham Hill
inQuba Webinar Mastering Customer Journey Management with Dr Graham Hill
LizaNolte
 
"What does it really mean for your system to be available, or how to define w...
"What does it really mean for your system to be available, or how to define w..."What does it really mean for your system to be available, or how to define w...
"What does it really mean for your system to be available, or how to define w...
Fwdays
 
MySQL InnoDB Storage Engine: Deep Dive - Mydbops
MySQL InnoDB Storage Engine: Deep Dive - MydbopsMySQL InnoDB Storage Engine: Deep Dive - Mydbops
MySQL InnoDB Storage Engine: Deep Dive - Mydbops
Mydbops
 
"Choosing proper type of scaling", Olena Syrota
"Choosing proper type of scaling", Olena Syrota"Choosing proper type of scaling", Olena Syrota
"Choosing proper type of scaling", Olena Syrota
Fwdays
 
Call Girls Chandigarh🔥7023059433🔥Agency Profile Escorts in Chandigarh Availab...
Call Girls Chandigarh🔥7023059433🔥Agency Profile Escorts in Chandigarh Availab...Call Girls Chandigarh🔥7023059433🔥Agency Profile Escorts in Chandigarh Availab...
Call Girls Chandigarh🔥7023059433🔥Agency Profile Escorts in Chandigarh Availab...
manji sharman06
 
AppSec PNW: Android and iOS Application Security with MobSF
AppSec PNW: Android and iOS Application Security with MobSFAppSec PNW: Android and iOS Application Security with MobSF
AppSec PNW: Android and iOS Application Security with MobSF
Ajin Abraham
 
Day 2 - Intro to UiPath Studio Fundamentals
Day 2 - Intro to UiPath Studio FundamentalsDay 2 - Intro to UiPath Studio Fundamentals
Day 2 - Intro to UiPath Studio Fundamentals
UiPathCommunity
 
Lee Barnes - Path to Becoming an Effective Test Automation Engineer.pdf
Lee Barnes - Path to Becoming an Effective Test Automation Engineer.pdfLee Barnes - Path to Becoming an Effective Test Automation Engineer.pdf
Lee Barnes - Path to Becoming an Effective Test Automation Engineer.pdf
leebarnesutopia
 
Mutation Testing for Task-Oriented Chatbots
Mutation Testing for Task-Oriented ChatbotsMutation Testing for Task-Oriented Chatbots
Mutation Testing for Task-Oriented Chatbots
Pablo Gómez Abajo
 
From Natural Language to Structured Solr Queries using LLMs
From Natural Language to Structured Solr Queries using LLMsFrom Natural Language to Structured Solr Queries using LLMs
From Natural Language to Structured Solr Queries using LLMs
Sease
 
"Scaling RAG Applications to serve millions of users", Kevin Goedecke
"Scaling RAG Applications to serve millions of users",  Kevin Goedecke"Scaling RAG Applications to serve millions of users",  Kevin Goedecke
"Scaling RAG Applications to serve millions of users", Kevin Goedecke
Fwdays
 

Recently uploaded (20)

A Deep Dive into ScyllaDB's Architecture
A Deep Dive into ScyllaDB's ArchitectureA Deep Dive into ScyllaDB's Architecture
A Deep Dive into ScyllaDB's Architecture
 
What is an RPA CoE? Session 2 – CoE Roles
What is an RPA CoE?  Session 2 – CoE RolesWhat is an RPA CoE?  Session 2 – CoE Roles
What is an RPA CoE? Session 2 – CoE Roles
 
GlobalLogic Java Community Webinar #18 “How to Improve Web Application Perfor...
GlobalLogic Java Community Webinar #18 “How to Improve Web Application Perfor...GlobalLogic Java Community Webinar #18 “How to Improve Web Application Perfor...
GlobalLogic Java Community Webinar #18 “How to Improve Web Application Perfor...
 
GNSS spoofing via SDR (Criptored Talks 2024)
GNSS spoofing via SDR (Criptored Talks 2024)GNSS spoofing via SDR (Criptored Talks 2024)
GNSS spoofing via SDR (Criptored Talks 2024)
 
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectorsConnector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
 
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge GraphGraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
 
ScyllaDB Tablets: Rethinking Replication
ScyllaDB Tablets: Rethinking ReplicationScyllaDB Tablets: Rethinking Replication
ScyllaDB Tablets: Rethinking Replication
 
Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving | Nameplate Manufacturing Process - 2024Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving | Nameplate Manufacturing Process - 2024
 
Dandelion Hashtable: beyond billion requests per second on a commodity server
Dandelion Hashtable: beyond billion requests per second on a commodity serverDandelion Hashtable: beyond billion requests per second on a commodity server
Dandelion Hashtable: beyond billion requests per second on a commodity server
 
inQuba Webinar Mastering Customer Journey Management with Dr Graham Hill
inQuba Webinar Mastering Customer Journey Management with Dr Graham HillinQuba Webinar Mastering Customer Journey Management with Dr Graham Hill
inQuba Webinar Mastering Customer Journey Management with Dr Graham Hill
 
"What does it really mean for your system to be available, or how to define w...
"What does it really mean for your system to be available, or how to define w..."What does it really mean for your system to be available, or how to define w...
"What does it really mean for your system to be available, or how to define w...
 
MySQL InnoDB Storage Engine: Deep Dive - Mydbops
MySQL InnoDB Storage Engine: Deep Dive - MydbopsMySQL InnoDB Storage Engine: Deep Dive - Mydbops
MySQL InnoDB Storage Engine: Deep Dive - Mydbops
 
"Choosing proper type of scaling", Olena Syrota
"Choosing proper type of scaling", Olena Syrota"Choosing proper type of scaling", Olena Syrota
"Choosing proper type of scaling", Olena Syrota
 
Call Girls Chandigarh🔥7023059433🔥Agency Profile Escorts in Chandigarh Availab...
Call Girls Chandigarh🔥7023059433🔥Agency Profile Escorts in Chandigarh Availab...Call Girls Chandigarh🔥7023059433🔥Agency Profile Escorts in Chandigarh Availab...
Call Girls Chandigarh🔥7023059433🔥Agency Profile Escorts in Chandigarh Availab...
 
AppSec PNW: Android and iOS Application Security with MobSF
AppSec PNW: Android and iOS Application Security with MobSFAppSec PNW: Android and iOS Application Security with MobSF
AppSec PNW: Android and iOS Application Security with MobSF
 
Day 2 - Intro to UiPath Studio Fundamentals
Day 2 - Intro to UiPath Studio FundamentalsDay 2 - Intro to UiPath Studio Fundamentals
Day 2 - Intro to UiPath Studio Fundamentals
 
Lee Barnes - Path to Becoming an Effective Test Automation Engineer.pdf
Lee Barnes - Path to Becoming an Effective Test Automation Engineer.pdfLee Barnes - Path to Becoming an Effective Test Automation Engineer.pdf
Lee Barnes - Path to Becoming an Effective Test Automation Engineer.pdf
 
Mutation Testing for Task-Oriented Chatbots
Mutation Testing for Task-Oriented ChatbotsMutation Testing for Task-Oriented Chatbots
Mutation Testing for Task-Oriented Chatbots
 
From Natural Language to Structured Solr Queries using LLMs
From Natural Language to Structured Solr Queries using LLMsFrom Natural Language to Structured Solr Queries using LLMs
From Natural Language to Structured Solr Queries using LLMs
 
"Scaling RAG Applications to serve millions of users", Kevin Goedecke
"Scaling RAG Applications to serve millions of users",  Kevin Goedecke"Scaling RAG Applications to serve millions of users",  Kevin Goedecke
"Scaling RAG Applications to serve millions of users", Kevin Goedecke
 

Ceph's journey at SUSE

  • 1. Our first 5 years with Ceph Lars Marowsky-Brée lmb@suse.com Distinguished Engineer, Architect Software-Defined-Storage
  • 4. 4 Common Limitations of Traditional Enterprise Storage Unable to scale and manage data growth Expensive Won’t extend to the software-defined data center $ PRESENT FUTURE £ € $
  • 5. 5 Data Continues to Grow Very Fast Medical Data EmailsVideos Mobile Data IoT Data Transactional Data
  • 6. 6 Data Protection Problem is Getting Compounded • Inability to keep enough data online • Not being able to recover lost data fast enough • Migrations to larger disk or dedupe appliances every year Increasing volumes of data compound the data protection problem *SUSE Software Defined Storage Study 2016 Cost of storage Performance / availability Challenges with back up, disaster recovery and archiving Increasing volumes of data Security and data governance 45% 46% 46% 54% 56% Customer Facing Numerous Backup Challenges: Top 5 Data Management Challenges*
  • 7. 7 Open Source is the only sustainable option
  • 9. 9 SUSE’s history with Ceph August 2012 SUSE Cloud 1 Argonaut February 2015 SUSE Enterprise Storage 1 Firefly October 2015 SUSE Enterprise Storage 2 Hammer June 2016 SUSE Enterprise Storage 3 Jewel October 2016 openATTIC team joins SUSE! November 2016 SUSE Enterprise Storage 4 Jewel October 2017 SUSE Enterprise Storage 5 Luminous Later 2018 SUSE Enterprise Storage 6 Mimic
  • 10. 10 ● Curate open source solutions – projects and features ● Track, test, and manage software dependencies ● Incorporate and provide patches and backports ● Advise customers on recommended practices and hardware ● Represent customers and partners in the community ● Bridge the worlds of community and IHVs/ISVs ● Provide high quality support Vendor value add
  • 11. 11 ● Strong contributor to Ceph community & Ceph Advisory Board ● True Open Source - “Upstream first” ● iSCSI with Multipathing/VMware support ● First supported Ceph distribution for ARM64 ● First to support CephFS for production deployments ● Salt-based orchestration for upgrade and FileStore/BlueStore migration ● Lead on openATTIC, Prometheus & Grafana, now merged into core Ceph management functionality Major SUSE contributions
  • 14. 14 openATTIC merging into the Ceph dashboard
  • 16. 16 Use Case Focused Solutions Backup to Disk Solution Compliant Archives SAP HANA Storage Solution Appliance HPC Archives Certified RAs Cloud SOC SES IoT Configuration CSPs + SES Mode1 Customers Mode2 Customers Example SUSE Enterprise Storage Partners
  • 17. 17 Growth of our Ceph deployments
  • 19. PUBLIC Marc Koderer, SAP March 2018 Case Study: Ceph at SAP How to Build a Cattle Cloud
  • 20. 20PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ Integraton Environment SAP Cloud Platform, private edition – High Level Security Platorm Services SAP Cloud Platorm Private Cloud Data & Storage Foundaton XS Advanced Development IaaSSAP HANA Database Hardware / Bare Metal Applicaton / IoT ERP
  • 21. 21PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ Traditional applications vs cloud native applications (pets vs cattle) DB Standby DB Active App App Centralized Storage Characteristics: • Runs on bare metal and/or VM’s • HW failure is exceptional • Centralized instead of distributed monolithic payloads Characteristics: • Runs on VMs or in Containers • HW failure can happen all the time • Highly distributed Distributed Storage / SDS DB2DB1 Service Service Service… DBn… Distributed/scale-out payloads
  • 22. 22PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ AZ1 AZ2 AZ3 Private cloud architecture
  • 23. 23PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ AZ1 AZ2 AZ3 OpenStack Control Plane C N C N C N C N C N C N H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V Private cloud architecture
  • 24. 24PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ AZ1 AZ2 AZ3 Ceph S T S T S T S T S T S T S T S T S T OpenStack Control Plane C N C N C N C N C N C N H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V H V Private cloud architecture
  • 25. 25PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ Ceph in detail S T S T S T S T S T S T S T S T S T spine01 spine02 spine03 spine04 leaf02a leaf02b leaf03a leaf03bleaf01a leaf01b
  • 26. 26PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ Ceph in detail S T S T S T S T S T S T S T S T S T spine01 spine02 spine03 spine04 leaf02a leaf02b leaf03a leaf03bleaf01a leaf01b • Hardware characteristics • 108 storage nodes • 24 disk per osd node; 2 NVMEs • 4x 25 Gbit (2x 25 Gbit bond frontend; 2x 25 Gbit bond backend) • Spine/leaf network architecture across all AZs • RBD and Radosgw usage • The Ceph cluster is designed to compensate the outage of one Availability Zone • Max performance ~60 GB/sec (writes; 4MB)
  • 27. 27PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ Ceph in detail: RGW Loadbalancer VM VM VM VM VM mon1 mon2 mon3 osd1 osd2 osd3 osdn… mon4 mon5 rgw1 rgw2 rgw3 rgw30…
  • 28. 28PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ RGW stress test # of RGW (6 vcpus) Max concurrent connection Method Throughput 1 512 put 250 MB/sec 1 512 get 300 MB/sec 3 1536 put 700 MB/sec 3 1536 get 900 MB/sec 9 4608 put 1950 MB/sec 9 4608 get 2100 MB/sec
  • 30. 30 SUSE Enterprise Storage 6 – based on Mimic •Incorporates Ceph Mimic •Based on SUSE Linux Enterprise 15 •Improve interoperability •Internationalization and localization •Improved scale-out user experience •Eventing and alerting •Metric reporting and telemetry
  • 32. 32 SUSE Container as a Service Platform
  • 33. 33 openATTIC <3 Ceph’s Dashboard Provide a better user experience Make complex tasks easier Assist users along the way of sizing, deploying, and managing a Ceph cluster
  • 35. 35 Ceph? Not if. When. Open source cloud operating systems and software-defined storage platforms are based on the Linux operating system. SUSE is a Linux OS pioneer and successful software vendor with thousands of installations. Customers should expect to receive nothing less than expert support for their software-based storage. Learn more at suse.com/storage/