SlideShare uma empresa Scribd logo
1 de 22
Baixar para ler offline
PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 1
Ericsson HDS8000
server platform
based on intel’s rsd
zmierzch klasycznych architektur
serwerowych
September 26th, KRAKÓW
PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 2
The Advent of HyperScale Computing:
Google. Amazon. Facebook.
designed to provide a single, massively
scalable compute architecture
start small, infrastructure will expand
as demand grows
PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 3
Challenges and opportunities
Infrastructure silos with low utilization
DC as a differentiator
- Web scale flexibility,
performance and
economics
Workloads and
data growth is sky
rocketing
Low function velocity – slow Time To Market
Weeks / months
PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 4
Hyperscale
Datacenter
OperationalEfficiency
Asset Efficiency
Operator
Operator
Google
Amazon
Facebook
Operators
Operator
The Advent of HyperScale Computing
PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 5
Cloud giants has taken the
next quantum leap
60%
30%
15%
Data center operators
have led an efficiency
revolution through the
use of virtualization
solutions
Cloud giants have
jumped to a new level
of efficiency with
hyper-scale data
center operations
reaching utilization as
high as 65%
Traditional Server
Hyperscale Strategic Data Center
Virtualized Data Center
Enterprisedatacenterutilization
PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 6
Hyperscale datacenter metrics
PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 7
The Problem:
HyperSCale Vendors (google, amazon,
Facebook) are Not Selling Their Secrets
The answer:
Industrialized hyperscale datacenter:
Intel® rack scale design
Ericsson HDS8000
PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 8
HOW DO WE DO THIS?
Ericsson HDS8000
PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 9
› HW infrastructure: HW and management
› Software-defined HW for all workloads
› NFV/Telco, IT and OSS/BSS workloads
› Using Intel RSD technology
Hyperscale Datacenter
System 8000
PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 10
Intel and Ericsson - realizing the software defined
infrastructure vision based on Intel RSD
Ericsson Make hyperscale available for every industry
with Cloud Giants economics
Ericsson and Intel CEOs at
MWC 2013
Intel Confidential 11
Data Center Challenges
Infrastructure has not kept up with increasing business demands
Business Needs
• Reduce operational and capital expenses.
• Deliver new services in minutes, not months.
• Optimize data center based on real-time analytics.
• Address application workload needs with agility.
• Scale capacity without interruption.
Less than 50%
server utilization2
Inefficiency
Data growth doubles
every 18 months1
Growth
Agility
New services can
take a week or more
to provision1
1 Worldwide and Regional Public IT Cloud Services 2013–2017 Forecast. IDC (August 2013) idc.com/getdoc.jsp?containerId=242464
2 IDC’s Digital Universe Study, sponsored by EMC, December 2012
Intel Confidential 12
Today’s Architecture
• Proprietary and preconfigured
• Upgrade as a system
• Limited flexibility
Intel Confidential 13
Intel ® Rack Scale Design: The Framework
1. Pooled systems 2. Pod management 3. Network fabric 4. Pod-wide storage
Modular scalable management architecture
Pod-wide Management
Scalability
Pod wide storage Network fabric
Intel Confidential 14
Intel® Rack Scale Design
INCREASED
PERFORMANCE/$
HYPERSCALE
AGILITY
• Black Box to Glass box
• Avoid outages, over subscription and under performance through
HW specific insights and telemetry
• Eliminates stranded resources
• Software configurable capacity coupled with high performance
interconnects to increase utilization and reduce TCO
• Self Allocating Storage provides IT with improved performance/$
IMPROVES DATA
CENTER
OPERATIONS
• Software Defined Infrastructure: Shape shift capacity and capability
with modular, open architecture to meet the application
• Tailor performance to meet application SLAs by selecting from
pooled compute, storage & network resources
• Faster Time to Market
Industry standards based hyperscale solution for CSPs and the Telecommunications industry
PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 15
15
HW disaggregation
Current server
›CPU, Disc, Ram and NIC (>80% of server
cost) on same card in same chassis
›Server has a fixed configuration – need to
fit all workloads
›Whole server need to be changed at the
same time even though different
components have different lifecycles
Future server
›CPU, Disc, RAM and NIC on different
sleds
›CPU, Disc, RAM, and NIC can be
changed according to individual lifecycles
›HW can be configured dynamically for
better utilization and performance
CPU
RAM
Disc
NIC
CPU
RAM Disc
NIC
PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 16
High resource utilization
Today’s servers
CPU Mem Disks NIC Acc CPU Mem Disks NIC Acc
Disaggregated Datacenter
~80% of HW CAPEX & power consumption
Workload usage
Un-used hardware
CPUs
Disks
Memory
NICs
Accelerators
x86 x86x86
x86
PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 17
Memory
Pool
Storage
Pool
Networking
Pool
Accelerator
Pool
CPU
Pool
RESOURCE POOLING
Private CloudTelecom Cloud Commercial Cloud
HDS Command Center & RSD
Network
functions
OSS/BSS, Media & IT
functions
Commercial XaaS
offerings
Workload optimized, dynamically provisioned datacenter hardware
Optical Backplane
PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 18
Software defined infrastructure
(SDI)
Disaggregate and pool (RSD) Software defined composition
Command center
Optical interconnect
CPUs
NICs
RAMs
Disks
PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 19
SDI resource management
HDS Command Center
HDS 8000 Command Center
Independent of virtualization
environment
vPOD 1
vPOD 2
Seamless management and
integration of Ericsson and 3PP
infrastructure
Manage vPODs across 3PP and
Ericsson HW
vPOD vPOD vPOD
VIM VIM VIM
Complete analytical platform,
monitoring and recording every
aspect of the infrastructure
Real-time analytics and off-line
data mining
VM VM VM
PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 20
Software defined infrastructure
lean and agile data center
PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 21
Bare metal as a service
Customer A
Customer C
Customer B
› Next phase of cloud computing
› Leverage RSD and hardware
orchestration to fully customize
servers.
› Move both legacy &
performance critical workloads
to the cloud.
› Cloud economics for bare-metal
infrastructure
› Consolidate internal legacy silos
PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 22

Mais conteúdo relacionado

Mais procurados

SDN_and_NFV_technologies_in_IoT_Networks
SDN_and_NFV_technologies_in_IoT_NetworksSDN_and_NFV_technologies_in_IoT_Networks
SDN_and_NFV_technologies_in_IoT_Networks
Srinivasa Addepalli
 
Living objects network performance_management_v2
Living objects network performance_management_v2Living objects network performance_management_v2
Living objects network performance_management_v2
Yoan SMADJA
 

Mais procurados (20)

Accelerating Edge Computing Adoption
Accelerating Edge Computing Adoption Accelerating Edge Computing Adoption
Accelerating Edge Computing Adoption
 
How to use SDN to Innovate, Expand and Deliver for your business
How to use SDN to Innovate, Expand and Deliver for your businessHow to use SDN to Innovate, Expand and Deliver for your business
How to use SDN to Innovate, Expand and Deliver for your business
 
Artificial Intelligence in the Network
Artificial Intelligence in the Network Artificial Intelligence in the Network
Artificial Intelligence in the Network
 
SEBA: SDN Enabled Broadband Access - Transporting SDN principles to PON Networks
SEBA: SDN Enabled Broadband Access - Transporting SDN principles to PON NetworksSEBA: SDN Enabled Broadband Access - Transporting SDN principles to PON Networks
SEBA: SDN Enabled Broadband Access - Transporting SDN principles to PON Networks
 
Using Microservices Architecture and Patterns to Address Applications Require...
Using Microservices Architecture and Patterns to Address Applications Require...Using Microservices Architecture and Patterns to Address Applications Require...
Using Microservices Architecture and Patterns to Address Applications Require...
 
Innovation Summit 2015 - 6 - Project mangOH
Innovation Summit 2015 - 6 - Project mangOHInnovation Summit 2015 - 6 - Project mangOH
Innovation Summit 2015 - 6 - Project mangOH
 
SDN/NFV architecture vision and reality
SDN/NFV architecture vision and reality SDN/NFV architecture vision and reality
SDN/NFV architecture vision and reality
 
Evolving the WAN for the Cloud, using SD-WAN & NFV
Evolving the WAN for the Cloud, using SD-WAN & NFV Evolving the WAN for the Cloud, using SD-WAN & NFV
Evolving the WAN for the Cloud, using SD-WAN & NFV
 
DPDK & Cloud Native
DPDK & Cloud NativeDPDK & Cloud Native
DPDK & Cloud Native
 
Moving Beyond the Router to a Thin-branch or Application-driven SD-WAN
Moving Beyond the Router to a Thin-branch or Application-driven SD-WANMoving Beyond the Router to a Thin-branch or Application-driven SD-WAN
Moving Beyond the Router to a Thin-branch or Application-driven SD-WAN
 
Edge and 5G: What is in it for the developers?
Edge and 5G: What is in it for the developers?Edge and 5G: What is in it for the developers?
Edge and 5G: What is in it for the developers?
 
Transforming optical networking with AI
Transforming optical networking with AITransforming optical networking with AI
Transforming optical networking with AI
 
De-fogging Edge Computing: Ecosystem, Use-cases, and Opportunities
De-fogging Edge Computing: Ecosystem, Use-cases, and OpportunitiesDe-fogging Edge Computing: Ecosystem, Use-cases, and Opportunities
De-fogging Edge Computing: Ecosystem, Use-cases, and Opportunities
 
SDN_and_NFV_technologies_in_IoT_Networks
SDN_and_NFV_technologies_in_IoT_NetworksSDN_and_NFV_technologies_in_IoT_Networks
SDN_and_NFV_technologies_in_IoT_Networks
 
OSS in the era of SDN and NFV: Evolution vs Revolution - What we can learn f...
OSS in the era of SDN and NFV:  Evolution vs Revolution - What we can learn f...OSS in the era of SDN and NFV:  Evolution vs Revolution - What we can learn f...
OSS in the era of SDN and NFV: Evolution vs Revolution - What we can learn f...
 
Fog computing
Fog computingFog computing
Fog computing
 
Hyper efficient data centres – key ingredient intelligence networkshop44
Hyper efficient data centres – key ingredient intelligence   networkshop44Hyper efficient data centres – key ingredient intelligence   networkshop44
Hyper efficient data centres – key ingredient intelligence networkshop44
 
Living objects network performance_management_v2
Living objects network performance_management_v2Living objects network performance_management_v2
Living objects network performance_management_v2
 
Johan Hjalmarsson - NetAdmin Systems
Johan Hjalmarsson - NetAdmin SystemsJohan Hjalmarsson - NetAdmin Systems
Johan Hjalmarsson - NetAdmin Systems
 
TFI2014 Session I - State of SDN - Recep Ozdag
TFI2014 Session I - State of SDN - Recep OzdagTFI2014 Session I - State of SDN - Recep Ozdag
TFI2014 Session I - State of SDN - Recep Ozdag
 

Destaque

PLNOG 17 - Marek Czardybon - Grupa 3S dla Światowych Dni Młodzieży 2016
PLNOG 17 - Marek Czardybon - Grupa 3S dla Światowych Dni Młodzieży 2016PLNOG 17 - Marek Czardybon - Grupa 3S dla Światowych Dni Młodzieży 2016
PLNOG 17 - Marek Czardybon - Grupa 3S dla Światowych Dni Młodzieży 2016
PROIDEA
 
PLNOG 17 - Shabbir Ahmad - Dell EMC’s SDN strategy based on Open Networking
PLNOG 17 - Shabbir Ahmad - Dell EMC’s SDN strategy based on Open NetworkingPLNOG 17 - Shabbir Ahmad - Dell EMC’s SDN strategy based on Open Networking
PLNOG 17 - Shabbir Ahmad - Dell EMC’s SDN strategy based on Open Networking
PROIDEA
 

Destaque (20)

PLNOG 17 - Marek Czardybon - Grupa 3S dla Światowych Dni Młodzieży 2016
PLNOG 17 - Marek Czardybon - Grupa 3S dla Światowych Dni Młodzieży 2016PLNOG 17 - Marek Czardybon - Grupa 3S dla Światowych Dni Młodzieży 2016
PLNOG 17 - Marek Czardybon - Grupa 3S dla Światowych Dni Młodzieży 2016
 
PLNOG 17 - Krzysztof Wilczyński - EVPN – zwycięzca w wyścigu standardów budow...
PLNOG 17 - Krzysztof Wilczyński - EVPN – zwycięzca w wyścigu standardów budow...PLNOG 17 - Krzysztof Wilczyński - EVPN – zwycięzca w wyścigu standardów budow...
PLNOG 17 - Krzysztof Wilczyński - EVPN – zwycięzca w wyścigu standardów budow...
 
PLNOG 17 - Konrad Kulikowski - Cisco WAE - Wan Automation Engine - Co SDN moż...
PLNOG 17 - Konrad Kulikowski - Cisco WAE - Wan Automation Engine - Co SDN moż...PLNOG 17 - Konrad Kulikowski - Cisco WAE - Wan Automation Engine - Co SDN moż...
PLNOG 17 - Konrad Kulikowski - Cisco WAE - Wan Automation Engine - Co SDN moż...
 
PLNOG 17 - Piotr Jabłoński - Sieci nakładkowe w Data Center - uproszczenie, c...
PLNOG 17 - Piotr Jabłoński - Sieci nakładkowe w Data Center - uproszczenie, c...PLNOG 17 - Piotr Jabłoński - Sieci nakładkowe w Data Center - uproszczenie, c...
PLNOG 17 - Piotr Jabłoński - Sieci nakładkowe w Data Center - uproszczenie, c...
 
PLNOG 17 - Robert Rosiak - Zcentralizowane i dystrybuowane CPE - różnice i po...
PLNOG 17 - Robert Rosiak - Zcentralizowane i dystrybuowane CPE - różnice i po...PLNOG 17 - Robert Rosiak - Zcentralizowane i dystrybuowane CPE - różnice i po...
PLNOG 17 - Robert Rosiak - Zcentralizowane i dystrybuowane CPE - różnice i po...
 
PLNOG 17 - Piotr Pieprzycki - Praktycznie: Ścieżka Continuous Integration w k...
PLNOG 17 - Piotr Pieprzycki - Praktycznie: Ścieżka Continuous Integration w k...PLNOG 17 - Piotr Pieprzycki - Praktycznie: Ścieżka Continuous Integration w k...
PLNOG 17 - Piotr Pieprzycki - Praktycznie: Ścieżka Continuous Integration w k...
 
PLNOG 17 - Nicolai van der Smagt - Building and connecting the eBay Classifie...
PLNOG 17 - Nicolai van der Smagt - Building and connecting the eBay Classifie...PLNOG 17 - Nicolai van der Smagt - Building and connecting the eBay Classifie...
PLNOG 17 - Nicolai van der Smagt - Building and connecting the eBay Classifie...
 
PLNOG 17 - Tomasz Brol - loT w chmurach
PLNOG 17 - Tomasz Brol - loT w chmurachPLNOG 17 - Tomasz Brol - loT w chmurach
PLNOG 17 - Tomasz Brol - loT w chmurach
 
PLNOG 17 - Andrzej Jeruzal - Dell Networking OS10: sieciowy system operacyjny...
PLNOG 17 - Andrzej Jeruzal - Dell Networking OS10: sieciowy system operacyjny...PLNOG 17 - Andrzej Jeruzal - Dell Networking OS10: sieciowy system operacyjny...
PLNOG 17 - Andrzej Jeruzal - Dell Networking OS10: sieciowy system operacyjny...
 
PLNOG 17 - Marcin Aronowski - Technologie dostępowe dla IoT. Jak się w tym ws...
PLNOG 17 - Marcin Aronowski - Technologie dostępowe dla IoT. Jak się w tym ws...PLNOG 17 - Marcin Aronowski - Technologie dostępowe dla IoT. Jak się w tym ws...
PLNOG 17 - Marcin Aronowski - Technologie dostępowe dla IoT. Jak się w tym ws...
 
PLNOG 17 - Piotr Strzyżewski - Regulacje RIPE które przekładają sie na realia...
PLNOG 17 - Piotr Strzyżewski - Regulacje RIPE które przekładają sie na realia...PLNOG 17 - Piotr Strzyżewski - Regulacje RIPE które przekładają sie na realia...
PLNOG 17 - Piotr Strzyżewski - Regulacje RIPE które przekładają sie na realia...
 
PLNOG 17 - Piotr Wojciechowski - 802.1s MST, czyli STP u operatora i w DC nie...
PLNOG 17 - Piotr Wojciechowski - 802.1s MST, czyli STP u operatora i w DC nie...PLNOG 17 - Piotr Wojciechowski - 802.1s MST, czyli STP u operatora i w DC nie...
PLNOG 17 - Piotr Wojciechowski - 802.1s MST, czyli STP u operatora i w DC nie...
 
PLNOG 17 - Alexis Dacquay - 100 G, Skalowalność i Widoczność
PLNOG 17 - Alexis Dacquay - 100 G, Skalowalność i WidocznośćPLNOG 17 - Alexis Dacquay - 100 G, Skalowalność i Widoczność
PLNOG 17 - Alexis Dacquay - 100 G, Skalowalność i Widoczność
 
PLNOG 17 - Stefan Meinders - Slow is the new Down
PLNOG 17 - Stefan Meinders - Slow is the new DownPLNOG 17 - Stefan Meinders - Slow is the new Down
PLNOG 17 - Stefan Meinders - Slow is the new Down
 
PLNOG 17 - Paweł Wachelka - Zastosowanie 802.1x w sieciach kampusowych - nowe...
PLNOG 17 - Paweł Wachelka - Zastosowanie 802.1x w sieciach kampusowych - nowe...PLNOG 17 - Paweł Wachelka - Zastosowanie 802.1x w sieciach kampusowych - nowe...
PLNOG 17 - Paweł Wachelka - Zastosowanie 802.1x w sieciach kampusowych - nowe...
 
PLNOG 17 - Maciej Flak - Cisco Cloud Networking - czyli kompletna infrastrukt...
PLNOG 17 - Maciej Flak - Cisco Cloud Networking - czyli kompletna infrastrukt...PLNOG 17 - Maciej Flak - Cisco Cloud Networking - czyli kompletna infrastrukt...
PLNOG 17 - Maciej Flak - Cisco Cloud Networking - czyli kompletna infrastrukt...
 
PLNOG 17 - Shabbir Ahmad - Dell EMC’s SDN strategy based on Open Networking
PLNOG 17 - Shabbir Ahmad - Dell EMC’s SDN strategy based on Open NetworkingPLNOG 17 - Shabbir Ahmad - Dell EMC’s SDN strategy based on Open Networking
PLNOG 17 - Shabbir Ahmad - Dell EMC’s SDN strategy based on Open Networking
 
PLNOG 17 - Leonir Hoxha - Next Generation Network Architecture - Segment Routing
PLNOG 17 - Leonir Hoxha - Next Generation Network Architecture - Segment RoutingPLNOG 17 - Leonir Hoxha - Next Generation Network Architecture - Segment Routing
PLNOG 17 - Leonir Hoxha - Next Generation Network Architecture - Segment Routing
 
PLNOG 17 - Shabbir Ahmad - Dell Open Networking i Big Monitoring Fabric: unik...
PLNOG 17 - Shabbir Ahmad - Dell Open Networking i Big Monitoring Fabric: unik...PLNOG 17 - Shabbir Ahmad - Dell Open Networking i Big Monitoring Fabric: unik...
PLNOG 17 - Shabbir Ahmad - Dell Open Networking i Big Monitoring Fabric: unik...
 
PLNOG 17 - Dominik Bocheński, Łukasz Walicki - Zapomnij o VPS - nadeszła era ...
PLNOG 17 - Dominik Bocheński, Łukasz Walicki - Zapomnij o VPS - nadeszła era ...PLNOG 17 - Dominik Bocheński, Łukasz Walicki - Zapomnij o VPS - nadeszła era ...
PLNOG 17 - Dominik Bocheński, Łukasz Walicki - Zapomnij o VPS - nadeszła era ...
 

Semelhante a PLNOG 17 - Piotr Jasiniewski, Przemek Papużyński - Ericsson HDS 8000 Server platform based on Intel’s RSD – zmierzch klasycznych architektur serwerowych

28701-FGB1010554_EN_A_PDFV1R1
28701-FGB1010554_EN_A_PDFV1R128701-FGB1010554_EN_A_PDFV1R1
28701-FGB1010554_EN_A_PDFV1R1
Jason Hoffman
 
MIG 5th Data Centre Summit 2016 PTS Presentation v1
MIG 5th Data Centre Summit 2016 PTS Presentation v1MIG 5th Data Centre Summit 2016 PTS Presentation v1
MIG 5th Data Centre Summit 2016 PTS Presentation v1
blewington
 
K5.Fujitsu World Tour 2016-Winning with NetApp in Digital Transformation Age,...
K5.Fujitsu World Tour 2016-Winning with NetApp in Digital Transformation Age,...K5.Fujitsu World Tour 2016-Winning with NetApp in Digital Transformation Age,...
K5.Fujitsu World Tour 2016-Winning with NetApp in Digital Transformation Age,...
Fujitsu India
 

Semelhante a PLNOG 17 - Piotr Jasiniewski, Przemek Papużyński - Ericsson HDS 8000 Server platform based on Intel’s RSD – zmierzch klasycznych architektur serwerowych (20)

28701-FGB1010554_EN_A_PDFV1R1
28701-FGB1010554_EN_A_PDFV1R128701-FGB1010554_EN_A_PDFV1R1
28701-FGB1010554_EN_A_PDFV1R1
 
Ericsson introduces a hyperscale cloud solution
Ericsson introduces a hyperscale cloud solutionEricsson introduces a hyperscale cloud solution
Ericsson introduces a hyperscale cloud solution
 
Cisco Connect Vancouver 2017 - Compute infrastructure for a hybrid cloud
Cisco Connect Vancouver 2017 - Compute infrastructure for a hybrid cloudCisco Connect Vancouver 2017 - Compute infrastructure for a hybrid cloud
Cisco Connect Vancouver 2017 - Compute infrastructure for a hybrid cloud
 
White Paper: Hyperscale cloud – reimagining data centers from hardware to app...
White Paper: Hyperscale cloud – reimagining data centers from hardware to app...White Paper: Hyperscale cloud – reimagining data centers from hardware to app...
White Paper: Hyperscale cloud – reimagining data centers from hardware to app...
 
Krones AG case study
Krones AG case studyKrones AG case study
Krones AG case study
 
UCS Update: Efficiently Managing your server environment for traditional ente...
UCS Update: Efficiently Managing your server environment for traditional ente...UCS Update: Efficiently Managing your server environment for traditional ente...
UCS Update: Efficiently Managing your server environment for traditional ente...
 
Converged Everything, Converged Infrastructure delivering business value and ...
Converged Everything, Converged Infrastructure delivering business value and ...Converged Everything, Converged Infrastructure delivering business value and ...
Converged Everything, Converged Infrastructure delivering business value and ...
 
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
 
transform your busines with superior cloud economics
transform your busines with superior cloud economicstransform your busines with superior cloud economics
transform your busines with superior cloud economics
 
Cisco storage networking protect scale-simplify_dec_2016
Cisco storage networking   protect scale-simplify_dec_2016Cisco storage networking   protect scale-simplify_dec_2016
Cisco storage networking protect scale-simplify_dec_2016
 
Cisco UCS Servers Presentation
Cisco UCS Servers PresentationCisco UCS Servers Presentation
Cisco UCS Servers Presentation
 
Compute Infrastructure for Hybrid Cloud
Compute Infrastructure for Hybrid CloudCompute Infrastructure for Hybrid Cloud
Compute Infrastructure for Hybrid Cloud
 
Compute Infrastructure for a Hybrid Cloud
Compute Infrastructure for a Hybrid CloudCompute Infrastructure for a Hybrid Cloud
Compute Infrastructure for a Hybrid Cloud
 
Cisco Connect Toronto 2017 - UCS and Hyperflex update
Cisco Connect Toronto 2017 - UCS and Hyperflex updateCisco Connect Toronto 2017 - UCS and Hyperflex update
Cisco Connect Toronto 2017 - UCS and Hyperflex update
 
Cisco connect winnipeg 2018 compute infrastructure for a hybrid cloud
Cisco connect winnipeg 2018   compute infrastructure for a hybrid cloudCisco connect winnipeg 2018   compute infrastructure for a hybrid cloud
Cisco connect winnipeg 2018 compute infrastructure for a hybrid cloud
 
MIG 5th Data Centre Summit 2016 PTS Presentation v1
MIG 5th Data Centre Summit 2016 PTS Presentation v1MIG 5th Data Centre Summit 2016 PTS Presentation v1
MIG 5th Data Centre Summit 2016 PTS Presentation v1
 
K5.Fujitsu World Tour 2016-Winning with NetApp in Digital Transformation Age,...
K5.Fujitsu World Tour 2016-Winning with NetApp in Digital Transformation Age,...K5.Fujitsu World Tour 2016-Winning with NetApp in Digital Transformation Age,...
K5.Fujitsu World Tour 2016-Winning with NetApp in Digital Transformation Age,...
 
Converged Everything, Converged Infrastructure Delivering Business Value and ...
Converged Everything, Converged Infrastructure Delivering Business Value and ...Converged Everything, Converged Infrastructure Delivering Business Value and ...
Converged Everything, Converged Infrastructure Delivering Business Value and ...
 
20230614 LinuxONE Distinguished_Recognition ISSIP_Award_Talk.pptx
20230614 LinuxONE Distinguished_Recognition ISSIP_Award_Talk.pptx20230614 LinuxONE Distinguished_Recognition ISSIP_Award_Talk.pptx
20230614 LinuxONE Distinguished_Recognition ISSIP_Award_Talk.pptx
 
End User Computing with NetApp
End User Computing with NetAppEnd User Computing with NetApp
End User Computing with NetApp
 

Último

Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Safe Software
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
Joaquim Jorge
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
panagenda
 

Último (20)

Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
HTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation StrategiesHTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation Strategies
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
 

PLNOG 17 - Piotr Jasiniewski, Przemek Papużyński - Ericsson HDS 8000 Server platform based on Intel’s RSD – zmierzch klasycznych architektur serwerowych

  • 1. PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 1 Ericsson HDS8000 server platform based on intel’s rsd zmierzch klasycznych architektur serwerowych September 26th, KRAKÓW
  • 2. PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 2 The Advent of HyperScale Computing: Google. Amazon. Facebook. designed to provide a single, massively scalable compute architecture start small, infrastructure will expand as demand grows
  • 3. PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 3 Challenges and opportunities Infrastructure silos with low utilization DC as a differentiator - Web scale flexibility, performance and economics Workloads and data growth is sky rocketing Low function velocity – slow Time To Market Weeks / months
  • 4. PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 4 Hyperscale Datacenter OperationalEfficiency Asset Efficiency Operator Operator Google Amazon Facebook Operators Operator The Advent of HyperScale Computing
  • 5. PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 5 Cloud giants has taken the next quantum leap 60% 30% 15% Data center operators have led an efficiency revolution through the use of virtualization solutions Cloud giants have jumped to a new level of efficiency with hyper-scale data center operations reaching utilization as high as 65% Traditional Server Hyperscale Strategic Data Center Virtualized Data Center Enterprisedatacenterutilization
  • 6. PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 6 Hyperscale datacenter metrics
  • 7. PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 7 The Problem: HyperSCale Vendors (google, amazon, Facebook) are Not Selling Their Secrets The answer: Industrialized hyperscale datacenter: Intel® rack scale design Ericsson HDS8000
  • 8. PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 8 HOW DO WE DO THIS? Ericsson HDS8000
  • 9. PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 9 › HW infrastructure: HW and management › Software-defined HW for all workloads › NFV/Telco, IT and OSS/BSS workloads › Using Intel RSD technology Hyperscale Datacenter System 8000
  • 10. PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 10 Intel and Ericsson - realizing the software defined infrastructure vision based on Intel RSD Ericsson Make hyperscale available for every industry with Cloud Giants economics Ericsson and Intel CEOs at MWC 2013
  • 11. Intel Confidential 11 Data Center Challenges Infrastructure has not kept up with increasing business demands Business Needs • Reduce operational and capital expenses. • Deliver new services in minutes, not months. • Optimize data center based on real-time analytics. • Address application workload needs with agility. • Scale capacity without interruption. Less than 50% server utilization2 Inefficiency Data growth doubles every 18 months1 Growth Agility New services can take a week or more to provision1 1 Worldwide and Regional Public IT Cloud Services 2013–2017 Forecast. IDC (August 2013) idc.com/getdoc.jsp?containerId=242464 2 IDC’s Digital Universe Study, sponsored by EMC, December 2012
  • 12. Intel Confidential 12 Today’s Architecture • Proprietary and preconfigured • Upgrade as a system • Limited flexibility
  • 13. Intel Confidential 13 Intel ® Rack Scale Design: The Framework 1. Pooled systems 2. Pod management 3. Network fabric 4. Pod-wide storage Modular scalable management architecture Pod-wide Management Scalability Pod wide storage Network fabric
  • 14. Intel Confidential 14 Intel® Rack Scale Design INCREASED PERFORMANCE/$ HYPERSCALE AGILITY • Black Box to Glass box • Avoid outages, over subscription and under performance through HW specific insights and telemetry • Eliminates stranded resources • Software configurable capacity coupled with high performance interconnects to increase utilization and reduce TCO • Self Allocating Storage provides IT with improved performance/$ IMPROVES DATA CENTER OPERATIONS • Software Defined Infrastructure: Shape shift capacity and capability with modular, open architecture to meet the application • Tailor performance to meet application SLAs by selecting from pooled compute, storage & network resources • Faster Time to Market Industry standards based hyperscale solution for CSPs and the Telecommunications industry
  • 15. PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 15 15 HW disaggregation Current server ›CPU, Disc, Ram and NIC (>80% of server cost) on same card in same chassis ›Server has a fixed configuration – need to fit all workloads ›Whole server need to be changed at the same time even though different components have different lifecycles Future server ›CPU, Disc, RAM and NIC on different sleds ›CPU, Disc, RAM, and NIC can be changed according to individual lifecycles ›HW can be configured dynamically for better utilization and performance CPU RAM Disc NIC CPU RAM Disc NIC
  • 16. PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 16 High resource utilization Today’s servers CPU Mem Disks NIC Acc CPU Mem Disks NIC Acc Disaggregated Datacenter ~80% of HW CAPEX & power consumption Workload usage Un-used hardware CPUs Disks Memory NICs Accelerators x86 x86x86 x86
  • 17. PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 17 Memory Pool Storage Pool Networking Pool Accelerator Pool CPU Pool RESOURCE POOLING Private CloudTelecom Cloud Commercial Cloud HDS Command Center & RSD Network functions OSS/BSS, Media & IT functions Commercial XaaS offerings Workload optimized, dynamically provisioned datacenter hardware Optical Backplane
  • 18. PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 18 Software defined infrastructure (SDI) Disaggregate and pool (RSD) Software defined composition Command center Optical interconnect CPUs NICs RAMs Disks
  • 19. PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 19 SDI resource management HDS Command Center HDS 8000 Command Center Independent of virtualization environment vPOD 1 vPOD 2 Seamless management and integration of Ericsson and 3PP infrastructure Manage vPODs across 3PP and Ericsson HW vPOD vPOD vPOD VIM VIM VIM Complete analytical platform, monitoring and recording every aspect of the infrastructure Real-time analytics and off-line data mining VM VM VM
  • 20. PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 20 Software defined infrastructure lean and agile data center
  • 21. PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 21 Bare metal as a service Customer A Customer C Customer B › Next phase of cloud computing › Leverage RSD and hardware orchestration to fully customize servers. › Move both legacy & performance critical workloads to the cloud. › Cloud economics for bare-metal infrastructure › Consolidate internal legacy silos
  • 22. PLNOG 2016 INTEL and ERICSSON | © Ericsson AB 2016 | 2016-09-26 | Page 22