SlideShare una empresa de Scribd logo
1 de 21
Descargar para leer sin conexión
Copyright©2014 NTT corp. All Rights Reserved.
Developing More Efficient Object
Replication on OpenStack Swift
2014/05/16 (OpenStack Juno Design Summit)
Kota Tsuyuzaki
Developer (Swift ATC)
Advanced Information Processing Technology SE Project
NTT Software Innovation Center
Copyright(c)2009-2014 NTT CORPORATION. All Rights Reserved.
2Copyright©2014 NTT corp. All Rights Reserved.
1. Global Distributed Cluster
2. More Efficient Object Replication
3. Benchmark Analysis
Etherpad:
https://etherpad.openstack.org/p/juno_swift
_object_replication
Extra:
ssync issue
Outline
3Copyright©2014 NTT corp. All Rights Reserved.
Demands:
• World Wide Services
• Capacity Optimization
• Disaster Recovery
Solution:
• Global Distributed Cluster
1. Global Distributed Cluster
4Copyright©2014 NTT corp. All Rights Reserved.
Network Issues:
1. Global Distributed Cluster
・High Latency ・Narrow ・Expensive
tens of ~ 100 ms 1~10Gbps $15000/Gbps/mo
5Copyright©2014 NTT corp. All Rights Reserved.
Network Issues:
1. Global Distributed Cluster
・High Latency Excellent
-> Regions
-> Affinity Controls
Region1 Region2
from SwiftStack Blog
https://swiftstack.com/blog/
6Copyright©2014 NTT corp. All Rights Reserved.
Network Issues:
1. Global Distributed Cluster
・Narrow ・Expensive Not So Enough
-> ???
-> ???
• Large Amounts of Transfer
• Replication Delay
7Copyright©2014 NTT corp. All Rights Reserved.
Objective:
Reducing The Amounts of
Replication Network Transfer
between Regions
(focus on Narrow Network)
2. More Efficient Object Replication
8Copyright©2014 NTT corp. All Rights Reserved.
2. More Efficient Object Replication
Current Behavior
9Copyright©2014 NTT corp. All Rights Reserved.
Current:
Model: 2 Regions 3 Replicas with Write Affinity
2. More Efficient Object Replication
Region1
Network between Regions
Region2
User
Internet
PUT object
Primary
Handoff
10Copyright©2014 NTT corp. All Rights Reserved.
Current:
Model: 2 Regions 3 Replicas with Write Affinity
2. More Efficient Object Replication
Region1
Network between Regions
Region2
User
Internet
Primary
Handoff
Unfortunately Copy Twice or More
11Copyright©2014 NTT corp. All Rights Reserved.
2. More Efficient Object Replication
Proposed Approach
12Copyright©2014 NTT corp. All Rights Reserved.
Approach:
• Only push to one remote based on affinity
• Request to sync to others from the remote
• Change only few codes in object-replicator and object-
server
2. More Efficient Object Replication
Region1
Network between Regions
Region2
Only push to one remote
Sync to others
13Copyright©2014 NTT corp. All Rights Reserved.
2. More Efficient Object Replication
*Additional code[Object-Replicator]
find local part suffixes
for each:
find other primary locations
check remote
if not in remote:
if (remote region is local) or (remote region not in synced region):
push data
create remote suffix with request to sync in remote region
add remote region to synced region
[Object-Server (REPLICATE)]
create local suffix
if sync request in header:
push data to requested remotes
14Copyright©2014 NTT corp. All Rights Reserved.
Objective:
• Analyze Replication Performance
• Total transferred data amount
• Average network bandwidth between region
• One pass time
3. Performance Analysis
15Copyright©2014 NTT corp. All Rights Reserved.
Model:
• 2 Regions 3 Replicas
• 1 Gate Way Node(GW) between Regions
Scenario:
• Shaping GW Network as 1Gbps
• Stop object-replicator
• Load objects with Write Affinity
• 1Gbps -> 8MB * 5,000 (40GB total)
• Run object-replicator with once mode (32 concurrency)
Benchmark Patterns:
• Original (ssync)
• Proposed (ssync, rsync)
3. Benchmark Scenario
16Copyright©2014 NTT corp. All Rights Reserved.
3. Benchmark Environment
Storage1 Storage2
Infiniband switch (LAN)
Region 1 Region 2
Proxy
x 36 x 36
Infiniband switch (LAN)
Storage3 Storage4
x 36 x 36
GW
20Gbps 20Gbps
20Gbps
(1G)
20Gbps 20Gbps
Client
Ethernet
Storage:
CPU: 2 * Intel X5650 2.67GHz (6 core * HT)
MEM: 48GB RAM
NIC: 20Gbps Infiniband
Disks: 3TB SATA (7,200 rpm) x 36 disks
GW:
CPU: 2 * Intel X5650 2.67GHz (6 core * HT)
MEM: 64GB RAM
NIC: 2 * 20Gbps Infiniband (Shaping 1G)
20Gbps
(1G)
17Copyright©2014 NTT corp. All Rights Reserved.
3. Result (w/1Gbps shaping)
0
100
200
300
400
500
600
Original Proposed (ssync) Proposed (rsync)
elapsedtime(sec)
One Replication Pass Time (1Gps)
0
10
20
30
40
50
60
70
Original Proposed (ssync) Proposed (rsync)
TransferredDataAmount(GB)
Transferred Data on One Pass (1Gps)
0
0.2
0.4
0.6
0.8
1
Original Proposed (ssync) Proposed (rsync)
AverageNEtworkBandwidth
(Gbps)
Average Network Bandwidth (1Gps)
- Good Reduction in Transferred Data Amount
- Little decreasing appeared in Average
Network Bandwidth
- Good Reduction in One Pass Time
-- ssync is more efficient than rsync.
-- Proposed algorithm has small overhead with waiting node
syncing.
-- Enable to ensure sync all primary nodes with a shorter
time and smaller amount of data transfer.
Very Good!
Very Good!
Little decreasing40GB * 3 replica / 2 = 60GB
1 / 3 has 2 copy in region2
40 GB = theoretical value
18Copyright©2014 NTT corp. All Rights Reserved.
1. Global Distributed Cluster
• Efficient Replication Needs
2. More Efficient Object Replication
• Affinity based approach
• Only push to one remote
3. Benchmark Analysis
• Good reduction of data transfer
• Little overhead in One Pass Time
acknowledgment:
Swiftstack members, Ken Igarachi, Yohei Hayashi, Takashi Shito, Hiromichi Ito, Naoto
Nishizono
Conclusion
19Copyright©2014 NTT corp. All Rights Reserved.
• Is ensuring syncing all nodes needed?
• Request to sync at that time of replicate:
• Pros: Able to ensure to sync all replica
• Cons: Little overhead to wait syncing
• Not to request to sync, update the replica asynchronously:
• Pros: To be simple
• Cons: Unable to ensure to sync all replica
• Good way to sync other nodes in Object-Server
• Naïve (but very simple):
• Use object-replicator instance with unnecessary wasted
information. (e.g. Ring)
• Complex:
• Create syncing function or class for object-server
• Are there more efficient ways?
Discussions
current
current
20Copyright©2014 NTT corp. All Rights Reserved.
Kota Tsuyuzaki
IRC: Kota
tsuyuzaki.kota@lab.ntt.co.jp
21Copyright©2014 NTT corp. All Rights Reserved.
Ssync:
• Replication process improvement based on HTTP
• Replacement of rsync (designed to be slimmer)
• Sender / Receiver Model
Issue:
• Performance of parallel i/o (might be) caused by evenlet
• Disable to access local disk in parallel (maybe, by constraint of
Python VM)
• Slower than rsync in my experiment
• Possible Solution:
• Launch sender as subprocess to allow using another CPU core for
disk read similar with rsync.
• When using os.fork(), performance became better to around same
as rsync.
Extra: Ssync issue

Más contenido relacionado

La actualidad más candente

CERN OpenStack Cloud Control Plane - From VMs to K8s
CERN OpenStack Cloud Control Plane - From VMs to K8sCERN OpenStack Cloud Control Plane - From VMs to K8s
CERN OpenStack Cloud Control Plane - From VMs to K8sBelmiro Moreira
 
Evolution of Openstack Networking at CERN
Evolution of Openstack Networking at CERNEvolution of Openstack Networking at CERN
Evolution of Openstack Networking at CERNBelmiro Moreira
 
The OpenStack Cloud at CERN - OpenStack Nordic
The OpenStack Cloud at CERN - OpenStack NordicThe OpenStack Cloud at CERN - OpenStack Nordic
The OpenStack Cloud at CERN - OpenStack NordicTim Bell
 
20170926 cern cloud v4
20170926 cern cloud v420170926 cern cloud v4
20170926 cern cloud v4Tim Bell
 
IPSN 2009 Contiki / uIP tutorial
IPSN 2009 Contiki / uIP tutorialIPSN 2009 Contiki / uIP tutorial
IPSN 2009 Contiki / uIP tutorialadamdunkels
 
Summit 16: ARM Mini-Summit - OpenFastPath is Open and Fast - Nokia
Summit 16: ARM Mini-Summit - OpenFastPath is Open and Fast - NokiaSummit 16: ARM Mini-Summit - OpenFastPath is Open and Fast - Nokia
Summit 16: ARM Mini-Summit - OpenFastPath is Open and Fast - NokiaOPNFV
 
Introduction of Okinawa Open Laboratory Testbed, OpenStack and SDN Technology...
Introduction of Okinawa Open Laboratory Testbed, OpenStack and SDN Technology...Introduction of Okinawa Open Laboratory Testbed, OpenStack and SDN Technology...
Introduction of Okinawa Open Laboratory Testbed, OpenStack and SDN Technology...Takashi Torii
 
OpenStack at CERN : A 5 year perspective
OpenStack at CERN : A 5 year perspectiveOpenStack at CERN : A 5 year perspective
OpenStack at CERN : A 5 year perspectiveTim Bell
 
OpenStack @ CERN, by Tim Bell
OpenStack @ CERN, by Tim BellOpenStack @ CERN, by Tim Bell
OpenStack @ CERN, by Tim BellAmrita Prasad
 
ONAP integration with opnfv via opera
ONAP integration with opnfv via opera ONAP integration with opnfv via opera
ONAP integration with opnfv via opera OPNFV
 
OpenStack Ottawa Q3 Meetup September 26th 2017
OpenStack Ottawa Q3 Meetup   September 26th 2017OpenStack Ottawa Q3 Meetup   September 26th 2017
OpenStack Ottawa Q3 Meetup September 26th 2017Stacy Véronneau
 
PIT Overload Analysis in Content Centric Networks - Slides ICN '13
PIT Overload Analysis in Content Centric Networks - Slides ICN '13PIT Overload Analysis in Content Centric Networks - Slides ICN '13
PIT Overload Analysis in Content Centric Networks - Slides ICN '13Matteo Virgilio
 
NTTs Journey with Openstack-final
NTTs Journey with Openstack-finalNTTs Journey with Openstack-final
NTTs Journey with Openstack-finalshintaro mizuno
 
Storm: a distributed ,fault tolerant ,real time computation
Storm: a distributed ,fault tolerant ,real time computationStorm: a distributed ,fault tolerant ,real time computation
Storm: a distributed ,fault tolerant ,real time computationNitin Guleria
 
Smallworld Data Check-Out to Microstation
Smallworld Data Check-Out to MicrostationSmallworld Data Check-Out to Microstation
Smallworld Data Check-Out to MicrostationSafe Software
 
How OPNFV Uses OpenStack & How It's Useful
How OPNFV Uses OpenStack & How It's UsefulHow OPNFV Uses OpenStack & How It's Useful
How OPNFV Uses OpenStack & How It's UsefulOPNFV
 

La actualidad más candente (20)

CERN OpenStack Cloud Control Plane - From VMs to K8s
CERN OpenStack Cloud Control Plane - From VMs to K8sCERN OpenStack Cloud Control Plane - From VMs to K8s
CERN OpenStack Cloud Control Plane - From VMs to K8s
 
Evolution of Openstack Networking at CERN
Evolution of Openstack Networking at CERNEvolution of Openstack Networking at CERN
Evolution of Openstack Networking at CERN
 
The OpenStack Cloud at CERN - OpenStack Nordic
The OpenStack Cloud at CERN - OpenStack NordicThe OpenStack Cloud at CERN - OpenStack Nordic
The OpenStack Cloud at CERN - OpenStack Nordic
 
20170926 cern cloud v4
20170926 cern cloud v420170926 cern cloud v4
20170926 cern cloud v4
 
IPSN 2009 Contiki / uIP tutorial
IPSN 2009 Contiki / uIP tutorialIPSN 2009 Contiki / uIP tutorial
IPSN 2009 Contiki / uIP tutorial
 
Summit 16: ARM Mini-Summit - OpenFastPath is Open and Fast - Nokia
Summit 16: ARM Mini-Summit - OpenFastPath is Open and Fast - NokiaSummit 16: ARM Mini-Summit - OpenFastPath is Open and Fast - Nokia
Summit 16: ARM Mini-Summit - OpenFastPath is Open and Fast - Nokia
 
Heatmap
HeatmapHeatmap
Heatmap
 
Introduction of Okinawa Open Laboratory Testbed, OpenStack and SDN Technology...
Introduction of Okinawa Open Laboratory Testbed, OpenStack and SDN Technology...Introduction of Okinawa Open Laboratory Testbed, OpenStack and SDN Technology...
Introduction of Okinawa Open Laboratory Testbed, OpenStack and SDN Technology...
 
OpenStack at CERN : A 5 year perspective
OpenStack at CERN : A 5 year perspectiveOpenStack at CERN : A 5 year perspective
OpenStack at CERN : A 5 year perspective
 
Federated HPC Clouds applied to Radiation Therapy
Federated HPC Clouds applied to Radiation TherapyFederated HPC Clouds applied to Radiation Therapy
Federated HPC Clouds applied to Radiation Therapy
 
OpenStack @ CERN, by Tim Bell
OpenStack @ CERN, by Tim BellOpenStack @ CERN, by Tim Bell
OpenStack @ CERN, by Tim Bell
 
ONAP integration with opnfv via opera
ONAP integration with opnfv via opera ONAP integration with opnfv via opera
ONAP integration with opnfv via opera
 
Collect, summarize and notify of OpenStack's log
Collect, summarize and notify of OpenStack's logCollect, summarize and notify of OpenStack's log
Collect, summarize and notify of OpenStack's log
 
OpenStack Ottawa Q3 Meetup September 26th 2017
OpenStack Ottawa Q3 Meetup   September 26th 2017OpenStack Ottawa Q3 Meetup   September 26th 2017
OpenStack Ottawa Q3 Meetup September 26th 2017
 
PIT Overload Analysis in Content Centric Networks - Slides ICN '13
PIT Overload Analysis in Content Centric Networks - Slides ICN '13PIT Overload Analysis in Content Centric Networks - Slides ICN '13
PIT Overload Analysis in Content Centric Networks - Slides ICN '13
 
NTTs Journey with Openstack-final
NTTs Journey with Openstack-finalNTTs Journey with Openstack-final
NTTs Journey with Openstack-final
 
Storm: a distributed ,fault tolerant ,real time computation
Storm: a distributed ,fault tolerant ,real time computationStorm: a distributed ,fault tolerant ,real time computation
Storm: a distributed ,fault tolerant ,real time computation
 
OpenPOWER ADG key note
OpenPOWER ADG key note OpenPOWER ADG key note
OpenPOWER ADG key note
 
Smallworld Data Check-Out to Microstation
Smallworld Data Check-Out to MicrostationSmallworld Data Check-Out to Microstation
Smallworld Data Check-Out to Microstation
 
How OPNFV Uses OpenStack & How It's Useful
How OPNFV Uses OpenStack & How It's UsefulHow OPNFV Uses OpenStack & How It's Useful
How OPNFV Uses OpenStack & How It's Useful
 

Destacado

日本OpenStackユーザ会 Atlantaサミット報告会 Swift関連報告
日本OpenStackユーザ会 Atlantaサミット報告会 Swift関連報告日本OpenStackユーザ会 Atlantaサミット報告会 Swift関連報告
日本OpenStackユーザ会 Atlantaサミット報告会 Swift関連報告Kota Tsuyuzaki
 
FOSSAsia 2016 - Shared storage management in the virtualization world
FOSSAsia 2016 - Shared storage management in the virtualization worldFOSSAsia 2016 - Shared storage management in the virtualization world
FOSSAsia 2016 - Shared storage management in the virtualization worldLiron Aravot
 
OpenStack Swift production deployments
OpenStack Swift production deploymentsOpenStack Swift production deployments
OpenStack Swift production deploymentsAtul Jha
 
OpenStack Swift In the Enterprise
OpenStack Swift In the EnterpriseOpenStack Swift In the Enterprise
OpenStack Swift In the EnterpriseHostway|HOSTING
 
Fossasia 16 Integrating oVirt, Foreman and Katello to empower your data-center
Fossasia 16 Integrating oVirt, Foreman and Katello to empower your data-centerFossasia 16 Integrating oVirt, Foreman and Katello to empower your data-center
Fossasia 16 Integrating oVirt, Foreman and Katello to empower your data-centerYaniv Bronhaim
 
Open vStorage Meetup - Santa Clara 04/16
Open vStorage Meetup -  Santa Clara 04/16Open vStorage Meetup -  Santa Clara 04/16
Open vStorage Meetup - Santa Clara 04/16wim_provoost
 
Turning object storage into vm storage
Turning object storage into vm storageTurning object storage into vm storage
Turning object storage into vm storagewim_provoost
 
Improving Hadoop Resiliency and Operational Efficiency with EMC Isilon
Improving Hadoop Resiliency and Operational Efficiency with EMC IsilonImproving Hadoop Resiliency and Operational Efficiency with EMC Isilon
Improving Hadoop Resiliency and Operational Efficiency with EMC IsilonDataWorks Summit/Hadoop Summit
 
Deploying and managing gluster using ovirt - fudcon2015
Deploying and managing gluster using ovirt - fudcon2015Deploying and managing gluster using ovirt - fudcon2015
Deploying and managing gluster using ovirt - fudcon2015Ramesh Nachimuthu
 
Turning OpenStack Swift into a VM storage platform
Turning OpenStack Swift into a VM storage platformTurning OpenStack Swift into a VM storage platform
Turning OpenStack Swift into a VM storage platformOpenStack_Online
 
oVirt and OpenStack
oVirt and OpenStackoVirt and OpenStack
oVirt and OpenStackDave Neary
 
Flossuk17 introduction to ovirt
Flossuk17 introduction to ovirtFlossuk17 introduction to ovirt
Flossuk17 introduction to ovirtFreddy Rolland
 

Destacado (17)

日本OpenStackユーザ会 Atlantaサミット報告会 Swift関連報告
日本OpenStackユーザ会 Atlantaサミット報告会 Swift関連報告日本OpenStackユーザ会 Atlantaサミット報告会 Swift関連報告
日本OpenStackユーザ会 Atlantaサミット報告会 Swift関連報告
 
FOSSAsia 2016 - Shared storage management in the virtualization world
FOSSAsia 2016 - Shared storage management in the virtualization worldFOSSAsia 2016 - Shared storage management in the virtualization world
FOSSAsia 2016 - Shared storage management in the virtualization world
 
OpenStack Swift production deployments
OpenStack Swift production deploymentsOpenStack Swift production deployments
OpenStack Swift production deployments
 
OpenStack Swift In the Enterprise
OpenStack Swift In the EnterpriseOpenStack Swift In the Enterprise
OpenStack Swift In the Enterprise
 
Fossasia 16 Integrating oVirt, Foreman and Katello to empower your data-center
Fossasia 16 Integrating oVirt, Foreman and Katello to empower your data-centerFossasia 16 Integrating oVirt, Foreman and Katello to empower your data-center
Fossasia 16 Integrating oVirt, Foreman and Katello to empower your data-center
 
Open vStorage Meetup - Santa Clara 04/16
Open vStorage Meetup -  Santa Clara 04/16Open vStorage Meetup -  Santa Clara 04/16
Open vStorage Meetup - Santa Clara 04/16
 
Turning object storage into vm storage
Turning object storage into vm storageTurning object storage into vm storage
Turning object storage into vm storage
 
Improving Hadoop Resiliency and Operational Efficiency with EMC Isilon
Improving Hadoop Resiliency and Operational Efficiency with EMC IsilonImproving Hadoop Resiliency and Operational Efficiency with EMC Isilon
Improving Hadoop Resiliency and Operational Efficiency with EMC Isilon
 
Deploying and managing gluster using ovirt - fudcon2015
Deploying and managing gluster using ovirt - fudcon2015Deploying and managing gluster using ovirt - fudcon2015
Deploying and managing gluster using ovirt - fudcon2015
 
EMC ScaleIO
EMC ScaleIOEMC ScaleIO
EMC ScaleIO
 
Turning OpenStack Swift into a VM storage platform
Turning OpenStack Swift into a VM storage platformTurning OpenStack Swift into a VM storage platform
Turning OpenStack Swift into a VM storage platform
 
NetApp Product training
NetApp Product trainingNetApp Product training
NetApp Product training
 
Netapp Storage
Netapp StorageNetapp Storage
Netapp Storage
 
oVirt – open your virtual datacenter
oVirt – open your virtual datacenteroVirt – open your virtual datacenter
oVirt – open your virtual datacenter
 
oVirt Introduction
oVirt IntroductionoVirt Introduction
oVirt Introduction
 
oVirt and OpenStack
oVirt and OpenStackoVirt and OpenStack
oVirt and OpenStack
 
Flossuk17 introduction to ovirt
Flossuk17 introduction to ovirtFlossuk17 introduction to ovirt
Flossuk17 introduction to ovirt
 

Similar a More Efficient Object Replication in OpenStack Summit Juno

Netflix Open Source Meetup Season 4 Episode 2
Netflix Open Source Meetup Season 4 Episode 2Netflix Open Source Meetup Season 4 Episode 2
Netflix Open Source Meetup Season 4 Episode 2aspyker
 
[db tech showcase Tokyo 2014] C32: Hadoop最前線 - 開発の現場から by NTT 小沢健史
[db tech showcase Tokyo 2014] C32: Hadoop最前線 - 開発の現場から  by NTT 小沢健史[db tech showcase Tokyo 2014] C32: Hadoop最前線 - 開発の現場から  by NTT 小沢健史
[db tech showcase Tokyo 2014] C32: Hadoop最前線 - 開発の現場から by NTT 小沢健史Insight Technology, Inc.
 
Tackling non-determinism in Hadoop - Testing and debugging distributed system...
Tackling non-determinism in Hadoop - Testing and debugging distributed system...Tackling non-determinism in Hadoop - Testing and debugging distributed system...
Tackling non-determinism in Hadoop - Testing and debugging distributed system...Akihiro Suda
 
Gears of Perforce: AAA Game Development Challenges
Gears of Perforce: AAA Game Development ChallengesGears of Perforce: AAA Game Development Challenges
Gears of Perforce: AAA Game Development ChallengesPerforce
 
High performace network of Cloud Native Taiwan User Group
High performace network of Cloud Native Taiwan User GroupHigh performace network of Cloud Native Taiwan User Group
High performace network of Cloud Native Taiwan User GroupHungWei Chiu
 
Erasure Code at Scale - Thomas William Byrne
Erasure Code at Scale - Thomas William ByrneErasure Code at Scale - Thomas William Byrne
Erasure Code at Scale - Thomas William ByrneCeph Community
 
Introduction to DPDK
Introduction to DPDKIntroduction to DPDK
Introduction to DPDKKernel TLV
 
Introducing Container Technology to TSUBAME3.0 Supercomputer
Introducing Container Technology to TSUBAME3.0 SupercomputerIntroducing Container Technology to TSUBAME3.0 Supercomputer
Introducing Container Technology to TSUBAME3.0 SupercomputerAkihiro Nomura
 
Sanger OpenStack presentation March 2017
Sanger OpenStack presentation March 2017Sanger OpenStack presentation March 2017
Sanger OpenStack presentation March 2017Dave Holland
 
From 1000/day to 1000/sec: The Evolution of Incapsula's BIG DATA System [Surg...
From 1000/day to 1000/sec: The Evolution of Incapsula's BIG DATA System [Surg...From 1000/day to 1000/sec: The Evolution of Incapsula's BIG DATA System [Surg...
From 1000/day to 1000/sec: The Evolution of Incapsula's BIG DATA System [Surg...Imperva Incapsula
 
DPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitch
DPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitchDPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitch
DPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitchJim St. Leger
 
Using OpenStack Swift for Extreme Data Durability
 Using OpenStack Swift for Extreme Data Durability Using OpenStack Swift for Extreme Data Durability
Using OpenStack Swift for Extreme Data DurabilityChristian Schwede
 
"Making Computer Vision Software Run Fast on Your Embedded Platform," a Prese...
"Making Computer Vision Software Run Fast on Your Embedded Platform," a Prese..."Making Computer Vision Software Run Fast on Your Embedded Platform," a Prese...
"Making Computer Vision Software Run Fast on Your Embedded Platform," a Prese...Edge AI and Vision Alliance
 
Sheepdog Status Report
Sheepdog Status ReportSheepdog Status Report
Sheepdog Status ReportLiu Yuan
 
Open stack in action cern _openstack_accelerating_science
Open stack in action  cern _openstack_accelerating_scienceOpen stack in action  cern _openstack_accelerating_science
Open stack in action cern _openstack_accelerating_scienceeNovance
 
Snabb Switch: Riding the HPC wave to simpler, better network appliances (FOSD...
Snabb Switch: Riding the HPC wave to simpler, better network appliances (FOSD...Snabb Switch: Riding the HPC wave to simpler, better network appliances (FOSD...
Snabb Switch: Riding the HPC wave to simpler, better network appliances (FOSD...Igalia
 
HeapStats: Troubleshooting with Serviceability and the New Runtime Monitoring...
HeapStats: Troubleshooting with Serviceability and the New Runtime Monitoring...HeapStats: Troubleshooting with Serviceability and the New Runtime Monitoring...
HeapStats: Troubleshooting with Serviceability and the New Runtime Monitoring...Yuji Kubota
 
Kubernetes @ Squarespace (SRE Portland Meetup October 2017)
Kubernetes @ Squarespace (SRE Portland Meetup October 2017)Kubernetes @ Squarespace (SRE Portland Meetup October 2017)
Kubernetes @ Squarespace (SRE Portland Meetup October 2017)Kevin Lynch
 
OpenStack Summit Tokyo - Know-how of Challlenging Deploy/Operation NTT DOCOMO...
OpenStack Summit Tokyo - Know-how of Challlenging Deploy/Operation NTT DOCOMO...OpenStack Summit Tokyo - Know-how of Challlenging Deploy/Operation NTT DOCOMO...
OpenStack Summit Tokyo - Know-how of Challlenging Deploy/Operation NTT DOCOMO...Masaaki Nakagawa
 
DatEngConf SF16 - Apache Kudu: Fast Analytics on Fast Data
DatEngConf SF16 - Apache Kudu: Fast Analytics on Fast DataDatEngConf SF16 - Apache Kudu: Fast Analytics on Fast Data
DatEngConf SF16 - Apache Kudu: Fast Analytics on Fast DataHakka Labs
 

Similar a More Efficient Object Replication in OpenStack Summit Juno (20)

Netflix Open Source Meetup Season 4 Episode 2
Netflix Open Source Meetup Season 4 Episode 2Netflix Open Source Meetup Season 4 Episode 2
Netflix Open Source Meetup Season 4 Episode 2
 
[db tech showcase Tokyo 2014] C32: Hadoop最前線 - 開発の現場から by NTT 小沢健史
[db tech showcase Tokyo 2014] C32: Hadoop最前線 - 開発の現場から  by NTT 小沢健史[db tech showcase Tokyo 2014] C32: Hadoop最前線 - 開発の現場から  by NTT 小沢健史
[db tech showcase Tokyo 2014] C32: Hadoop最前線 - 開発の現場から by NTT 小沢健史
 
Tackling non-determinism in Hadoop - Testing and debugging distributed system...
Tackling non-determinism in Hadoop - Testing and debugging distributed system...Tackling non-determinism in Hadoop - Testing and debugging distributed system...
Tackling non-determinism in Hadoop - Testing and debugging distributed system...
 
Gears of Perforce: AAA Game Development Challenges
Gears of Perforce: AAA Game Development ChallengesGears of Perforce: AAA Game Development Challenges
Gears of Perforce: AAA Game Development Challenges
 
High performace network of Cloud Native Taiwan User Group
High performace network of Cloud Native Taiwan User GroupHigh performace network of Cloud Native Taiwan User Group
High performace network of Cloud Native Taiwan User Group
 
Erasure Code at Scale - Thomas William Byrne
Erasure Code at Scale - Thomas William ByrneErasure Code at Scale - Thomas William Byrne
Erasure Code at Scale - Thomas William Byrne
 
Introduction to DPDK
Introduction to DPDKIntroduction to DPDK
Introduction to DPDK
 
Introducing Container Technology to TSUBAME3.0 Supercomputer
Introducing Container Technology to TSUBAME3.0 SupercomputerIntroducing Container Technology to TSUBAME3.0 Supercomputer
Introducing Container Technology to TSUBAME3.0 Supercomputer
 
Sanger OpenStack presentation March 2017
Sanger OpenStack presentation March 2017Sanger OpenStack presentation March 2017
Sanger OpenStack presentation March 2017
 
From 1000/day to 1000/sec: The Evolution of Incapsula's BIG DATA System [Surg...
From 1000/day to 1000/sec: The Evolution of Incapsula's BIG DATA System [Surg...From 1000/day to 1000/sec: The Evolution of Incapsula's BIG DATA System [Surg...
From 1000/day to 1000/sec: The Evolution of Incapsula's BIG DATA System [Surg...
 
DPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitch
DPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitchDPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitch
DPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitch
 
Using OpenStack Swift for Extreme Data Durability
 Using OpenStack Swift for Extreme Data Durability Using OpenStack Swift for Extreme Data Durability
Using OpenStack Swift for Extreme Data Durability
 
"Making Computer Vision Software Run Fast on Your Embedded Platform," a Prese...
"Making Computer Vision Software Run Fast on Your Embedded Platform," a Prese..."Making Computer Vision Software Run Fast on Your Embedded Platform," a Prese...
"Making Computer Vision Software Run Fast on Your Embedded Platform," a Prese...
 
Sheepdog Status Report
Sheepdog Status ReportSheepdog Status Report
Sheepdog Status Report
 
Open stack in action cern _openstack_accelerating_science
Open stack in action  cern _openstack_accelerating_scienceOpen stack in action  cern _openstack_accelerating_science
Open stack in action cern _openstack_accelerating_science
 
Snabb Switch: Riding the HPC wave to simpler, better network appliances (FOSD...
Snabb Switch: Riding the HPC wave to simpler, better network appliances (FOSD...Snabb Switch: Riding the HPC wave to simpler, better network appliances (FOSD...
Snabb Switch: Riding the HPC wave to simpler, better network appliances (FOSD...
 
HeapStats: Troubleshooting with Serviceability and the New Runtime Monitoring...
HeapStats: Troubleshooting with Serviceability and the New Runtime Monitoring...HeapStats: Troubleshooting with Serviceability and the New Runtime Monitoring...
HeapStats: Troubleshooting with Serviceability and the New Runtime Monitoring...
 
Kubernetes @ Squarespace (SRE Portland Meetup October 2017)
Kubernetes @ Squarespace (SRE Portland Meetup October 2017)Kubernetes @ Squarespace (SRE Portland Meetup October 2017)
Kubernetes @ Squarespace (SRE Portland Meetup October 2017)
 
OpenStack Summit Tokyo - Know-how of Challlenging Deploy/Operation NTT DOCOMO...
OpenStack Summit Tokyo - Know-how of Challlenging Deploy/Operation NTT DOCOMO...OpenStack Summit Tokyo - Know-how of Challlenging Deploy/Operation NTT DOCOMO...
OpenStack Summit Tokyo - Know-how of Challlenging Deploy/Operation NTT DOCOMO...
 
DatEngConf SF16 - Apache Kudu: Fast Analytics on Fast Data
DatEngConf SF16 - Apache Kudu: Fast Analytics on Fast DataDatEngConf SF16 - Apache Kudu: Fast Analytics on Fast Data
DatEngConf SF16 - Apache Kudu: Fast Analytics on Fast Data
 

Más de Kota Tsuyuzaki

Storlets Project Update for Train
Storlets Project Update for TrainStorlets Project Update for Train
Storlets Project Update for TrainKota Tsuyuzaki
 
Project Updates Storlets Denver 2019
Project Updates Storlets Denver 2019Project Updates Storlets Denver 2019
Project Updates Storlets Denver 2019Kota Tsuyuzaki
 
NVIDIA/deepopsを触ってみた話
NVIDIA/deepopsを触ってみた話NVIDIA/deepopsを触ってみた話
NVIDIA/deepopsを触ってみた話Kota Tsuyuzaki
 
OpenStack Swift Introduction 2019
OpenStack Swift Introduction 2019OpenStack Swift Introduction 2019
OpenStack Swift Introduction 2019Kota Tsuyuzaki
 
Case Study: Large Scale Deployment for Machine Learning with Highspeed Storage
Case Study: Large Scale Deployment for Machine Learning with Highspeed StorageCase Study: Large Scale Deployment for Machine Learning with Highspeed Storage
Case Study: Large Scale Deployment for Machine Learning with Highspeed StorageKota Tsuyuzaki
 
OpenStack Summit Storlets Project Update Queens
OpenStack Summit Storlets Project Update QueensOpenStack Summit Storlets Project Update Queens
OpenStack Summit Storlets Project Update QueensKota Tsuyuzaki
 
OpenStack Swiftの最新機能とStorlets
OpenStack Swiftの最新機能とStorletsOpenStack Swiftの最新機能とStorlets
OpenStack Swiftの最新機能とStorletsKota Tsuyuzaki
 
Using Storlets/Docker For Large Scale Image Processing
Using Storlets/Docker For Large Scale Image ProcessingUsing Storlets/Docker For Large Scale Image Processing
Using Storlets/Docker For Large Scale Image ProcessingKota Tsuyuzaki
 
OpenStack Summit Vancouver Swift 報告
OpenStack Summit Vancouver Swift 報告OpenStack Summit Vancouver Swift 報告
OpenStack Summit Vancouver Swift 報告Kota Tsuyuzaki
 
Container Listing Update (Liberty Swift Design Summit)
Container Listing Update (Liberty Swift Design Summit)Container Listing Update (Liberty Swift Design Summit)
Container Listing Update (Liberty Swift Design Summit)Kota Tsuyuzaki
 

Más de Kota Tsuyuzaki (11)

Storlets Project Update for Train
Storlets Project Update for TrainStorlets Project Update for Train
Storlets Project Update for Train
 
Project Updates Storlets Denver 2019
Project Updates Storlets Denver 2019Project Updates Storlets Denver 2019
Project Updates Storlets Denver 2019
 
NVIDIA/deepopsを触ってみた話
NVIDIA/deepopsを触ってみた話NVIDIA/deepopsを触ってみた話
NVIDIA/deepopsを触ってみた話
 
OpenStack Swift Introduction 2019
OpenStack Swift Introduction 2019OpenStack Swift Introduction 2019
OpenStack Swift Introduction 2019
 
Case Study: Large Scale Deployment for Machine Learning with Highspeed Storage
Case Study: Large Scale Deployment for Machine Learning with Highspeed StorageCase Study: Large Scale Deployment for Machine Learning with Highspeed Storage
Case Study: Large Scale Deployment for Machine Learning with Highspeed Storage
 
OpenStack Summit Storlets Project Update Queens
OpenStack Summit Storlets Project Update QueensOpenStack Summit Storlets Project Update Queens
OpenStack Summit Storlets Project Update Queens
 
OpenStack Swiftの最新機能とStorlets
OpenStack Swiftの最新機能とStorletsOpenStack Swiftの最新機能とStorlets
OpenStack Swiftの最新機能とStorlets
 
Using Storlets/Docker For Large Scale Image Processing
Using Storlets/Docker For Large Scale Image ProcessingUsing Storlets/Docker For Large Scale Image Processing
Using Storlets/Docker For Large Scale Image Processing
 
OpenStack Swift紹介
OpenStack Swift紹介OpenStack Swift紹介
OpenStack Swift紹介
 
OpenStack Summit Vancouver Swift 報告
OpenStack Summit Vancouver Swift 報告OpenStack Summit Vancouver Swift 報告
OpenStack Summit Vancouver Swift 報告
 
Container Listing Update (Liberty Swift Design Summit)
Container Listing Update (Liberty Swift Design Summit)Container Listing Update (Liberty Swift Design Summit)
Container Listing Update (Liberty Swift Design Summit)
 

Último

08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slidespraypatel2
 
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 WorkerThousandEyes
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024The Digital Insurer
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Paola De la Torre
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024The Digital Insurer
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Enterprise Knowledge
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slidevu2urc
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Scriptwesley chun
 
Developing An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilDeveloping An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilV3cube
 
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 2024The Digital Insurer
 
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsTop 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsRoshan Dwivedi
 
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...gurkirankumar98700
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountPuma Security, LLC
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking MenDelhi Call girls
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdfhans926745
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking MenDelhi Call girls
 
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 2024The Digital Insurer
 

Último (20)

08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
 
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
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Developing An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilDeveloping An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of Brazil
 
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
 
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsTop 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
 
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path Mount
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
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
 

More Efficient Object Replication in OpenStack Summit Juno

  • 1. Copyright©2014 NTT corp. All Rights Reserved. Developing More Efficient Object Replication on OpenStack Swift 2014/05/16 (OpenStack Juno Design Summit) Kota Tsuyuzaki Developer (Swift ATC) Advanced Information Processing Technology SE Project NTT Software Innovation Center Copyright(c)2009-2014 NTT CORPORATION. All Rights Reserved.
  • 2. 2Copyright©2014 NTT corp. All Rights Reserved. 1. Global Distributed Cluster 2. More Efficient Object Replication 3. Benchmark Analysis Etherpad: https://etherpad.openstack.org/p/juno_swift _object_replication Extra: ssync issue Outline
  • 3. 3Copyright©2014 NTT corp. All Rights Reserved. Demands: • World Wide Services • Capacity Optimization • Disaster Recovery Solution: • Global Distributed Cluster 1. Global Distributed Cluster
  • 4. 4Copyright©2014 NTT corp. All Rights Reserved. Network Issues: 1. Global Distributed Cluster ・High Latency ・Narrow ・Expensive tens of ~ 100 ms 1~10Gbps $15000/Gbps/mo
  • 5. 5Copyright©2014 NTT corp. All Rights Reserved. Network Issues: 1. Global Distributed Cluster ・High Latency Excellent -> Regions -> Affinity Controls Region1 Region2 from SwiftStack Blog https://swiftstack.com/blog/
  • 6. 6Copyright©2014 NTT corp. All Rights Reserved. Network Issues: 1. Global Distributed Cluster ・Narrow ・Expensive Not So Enough -> ??? -> ??? • Large Amounts of Transfer • Replication Delay
  • 7. 7Copyright©2014 NTT corp. All Rights Reserved. Objective: Reducing The Amounts of Replication Network Transfer between Regions (focus on Narrow Network) 2. More Efficient Object Replication
  • 8. 8Copyright©2014 NTT corp. All Rights Reserved. 2. More Efficient Object Replication Current Behavior
  • 9. 9Copyright©2014 NTT corp. All Rights Reserved. Current: Model: 2 Regions 3 Replicas with Write Affinity 2. More Efficient Object Replication Region1 Network between Regions Region2 User Internet PUT object Primary Handoff
  • 10. 10Copyright©2014 NTT corp. All Rights Reserved. Current: Model: 2 Regions 3 Replicas with Write Affinity 2. More Efficient Object Replication Region1 Network between Regions Region2 User Internet Primary Handoff Unfortunately Copy Twice or More
  • 11. 11Copyright©2014 NTT corp. All Rights Reserved. 2. More Efficient Object Replication Proposed Approach
  • 12. 12Copyright©2014 NTT corp. All Rights Reserved. Approach: • Only push to one remote based on affinity • Request to sync to others from the remote • Change only few codes in object-replicator and object- server 2. More Efficient Object Replication Region1 Network between Regions Region2 Only push to one remote Sync to others
  • 13. 13Copyright©2014 NTT corp. All Rights Reserved. 2. More Efficient Object Replication *Additional code[Object-Replicator] find local part suffixes for each: find other primary locations check remote if not in remote: if (remote region is local) or (remote region not in synced region): push data create remote suffix with request to sync in remote region add remote region to synced region [Object-Server (REPLICATE)] create local suffix if sync request in header: push data to requested remotes
  • 14. 14Copyright©2014 NTT corp. All Rights Reserved. Objective: • Analyze Replication Performance • Total transferred data amount • Average network bandwidth between region • One pass time 3. Performance Analysis
  • 15. 15Copyright©2014 NTT corp. All Rights Reserved. Model: • 2 Regions 3 Replicas • 1 Gate Way Node(GW) between Regions Scenario: • Shaping GW Network as 1Gbps • Stop object-replicator • Load objects with Write Affinity • 1Gbps -> 8MB * 5,000 (40GB total) • Run object-replicator with once mode (32 concurrency) Benchmark Patterns: • Original (ssync) • Proposed (ssync, rsync) 3. Benchmark Scenario
  • 16. 16Copyright©2014 NTT corp. All Rights Reserved. 3. Benchmark Environment Storage1 Storage2 Infiniband switch (LAN) Region 1 Region 2 Proxy x 36 x 36 Infiniband switch (LAN) Storage3 Storage4 x 36 x 36 GW 20Gbps 20Gbps 20Gbps (1G) 20Gbps 20Gbps Client Ethernet Storage: CPU: 2 * Intel X5650 2.67GHz (6 core * HT) MEM: 48GB RAM NIC: 20Gbps Infiniband Disks: 3TB SATA (7,200 rpm) x 36 disks GW: CPU: 2 * Intel X5650 2.67GHz (6 core * HT) MEM: 64GB RAM NIC: 2 * 20Gbps Infiniband (Shaping 1G) 20Gbps (1G)
  • 17. 17Copyright©2014 NTT corp. All Rights Reserved. 3. Result (w/1Gbps shaping) 0 100 200 300 400 500 600 Original Proposed (ssync) Proposed (rsync) elapsedtime(sec) One Replication Pass Time (1Gps) 0 10 20 30 40 50 60 70 Original Proposed (ssync) Proposed (rsync) TransferredDataAmount(GB) Transferred Data on One Pass (1Gps) 0 0.2 0.4 0.6 0.8 1 Original Proposed (ssync) Proposed (rsync) AverageNEtworkBandwidth (Gbps) Average Network Bandwidth (1Gps) - Good Reduction in Transferred Data Amount - Little decreasing appeared in Average Network Bandwidth - Good Reduction in One Pass Time -- ssync is more efficient than rsync. -- Proposed algorithm has small overhead with waiting node syncing. -- Enable to ensure sync all primary nodes with a shorter time and smaller amount of data transfer. Very Good! Very Good! Little decreasing40GB * 3 replica / 2 = 60GB 1 / 3 has 2 copy in region2 40 GB = theoretical value
  • 18. 18Copyright©2014 NTT corp. All Rights Reserved. 1. Global Distributed Cluster • Efficient Replication Needs 2. More Efficient Object Replication • Affinity based approach • Only push to one remote 3. Benchmark Analysis • Good reduction of data transfer • Little overhead in One Pass Time acknowledgment: Swiftstack members, Ken Igarachi, Yohei Hayashi, Takashi Shito, Hiromichi Ito, Naoto Nishizono Conclusion
  • 19. 19Copyright©2014 NTT corp. All Rights Reserved. • Is ensuring syncing all nodes needed? • Request to sync at that time of replicate: • Pros: Able to ensure to sync all replica • Cons: Little overhead to wait syncing • Not to request to sync, update the replica asynchronously: • Pros: To be simple • Cons: Unable to ensure to sync all replica • Good way to sync other nodes in Object-Server • Naïve (but very simple): • Use object-replicator instance with unnecessary wasted information. (e.g. Ring) • Complex: • Create syncing function or class for object-server • Are there more efficient ways? Discussions current current
  • 20. 20Copyright©2014 NTT corp. All Rights Reserved. Kota Tsuyuzaki IRC: Kota tsuyuzaki.kota@lab.ntt.co.jp
  • 21. 21Copyright©2014 NTT corp. All Rights Reserved. Ssync: • Replication process improvement based on HTTP • Replacement of rsync (designed to be slimmer) • Sender / Receiver Model Issue: • Performance of parallel i/o (might be) caused by evenlet • Disable to access local disk in parallel (maybe, by constraint of Python VM) • Slower than rsync in my experiment • Possible Solution: • Launch sender as subprocess to allow using another CPU core for disk read similar with rsync. • When using os.fork(), performance became better to around same as rsync. Extra: Ssync issue