SlideShare une entreprise Scribd logo
1  sur  60
EYWA
Jeong wook-jae(wjjung11@gmail.com)
Jung jung-in(call518@gmail.com)
V0.1.38
EYWA:
Elastic load-balancing & high-availabilitY
Wired virtual network Architecture)
- Beyond OpenStack/DVR & AWS/VPC
1/58EYWA
Confidential
The last remaining issue
2/58EYWA
Confidential
The last remaining issue
3/58EYWA
Contents
1. The conventional Network
Architectures
① Physical Networks
② Virtual (Overlay) Networks
2. The Architecture using Legacy
Protocols
3. EYWA
4. Summary
5. Scenarios (Traffic Flows)
4/58EYWA
① Physical Networks
 The conventional Data center
 Problems & Limitations
 New Data center Network Architectures
 The Comparison of the new Architectures
 Monsoon
 Etc
5/58EYWA
Confidential
The conventional Data center
6/58EYWA
Confidential
Problems & Limitations
1. Fragmentation of Resources
2. No Performance Isolation
3. Poor server to server connectivity
4. Need very high reliability near top of the tree (Single Point of Failure)
70~80% of the packets stay inside the data center
7/58EYWA
Confidential
The Comparison of the new DC Network Architectures
Monsoon VL2 SEATTLE FAT-TREE PortLand SPAIN MOOSE TRILL Dcell Bcube MDCube
Org. MS Research
Univ. of
Princeton
Univ. of California
San Diego
HP
Univ. of
Cambrid
ge
MS Research Asia
Publishing
SIGCOMM
2008
SIGCOMM
2009
SIGCOMM
2008
SIGCOMM
2008
SIGCOMM
2009
NSDI 2010
DC CAVE
S Works
hop
2009
RFC 5556
2009
SIGCOMM
2008
SIGCOMM
2009
CoNEXT
2009
Authors
Albert
Greenberg…
Albert
Greenberg,
Changhoon…
Changhoon
Kim…
M. Al-Fares…
R.N.
Mysore…
J. Mudigon
da,
M. Al-Fare
s…
M. Scott
…
Radia
Perlman
C. GUO… C. GUO…
H. Wu,
C. GUO…
Topology Clos Network Clos Network N/A Fat-Tree Fat-Tree N/A N/A N/A
Bcube Topo
logy
Packetizing
MAC-in-MAC
(802.1ah PBB)
IP-in-IP IP-in-IP(?) IP rewriting
MAC
rewriting
(PMAC)
MAC
rewriting
TRILL Hdr
Load
Spreading
MAC-Rotation ECMP ECMP ECMP ECMP
Multi-path O O X O O O X O
Mod. of
End-Host?
O O X X X O X X O
Mod. of
switches?
O X O
O
(Special HW)
O
(Special
HW)
X
O
(Rbridge)
△
ARP
Directory
Server
Directory
Server
DHT
on
the switches
Fabric
Manager
ESADI
8/58EYWA
Confidential
Monsoon
SWITCH Up-link Port Down-link Port #
Inter. SW N/A 10Gbps X 144 72
Aggr. SW 10Gbps X 72 10Gbps X 72 144
TOR SW 10Gbps X 2 1Gbps X 20 5,184
Monsoon
Agent
9/58EYWA
Confidential
Etc
http://goo.gl/aazXo0
10/58EYWA
② Virtual (Overlay) Networks
 Problems & Limitations
 AWS
 CloudStack
 OpenStack
11/58EYWA
Confidential
Problems & Limitations
1. Public Networks
① High Availability
 SPOF of a single (Virtual or Physical) router
② Load Sharing & Balancing
 The throughput bottleneck of a single router (SNAT/DNAT)
 Scale-up (Physical Router)
 Additional layer-4 load balancing service like AWS ELB
 or additional physical load balancer (scale-up)
③ Traffic Engineering
 Additional waste of network bandwidth
 Increased latency to traverse a single router
2. Private Networks
① Layer 2 network is hard to scale out
 Broadcast
 MAC Flooding
 STP
② VLAN (802.1Q) limit
 VLAN ID limit of 4,094
3. Cost & Scalability
12/58EYWA
Confidential
1. Classic(no VPC) Problems
① No Private network per Tenant
 Higher latency than L2
② No Traffic Isolation per Tenant
 Shared GW with other tenants
2. ELB Limitations
① Layer-4 load balancing only
② TCP only
 Port 25, 80, 443 & 1024~65535
③ Domain name only
 No Static IP & No interoperating with GSLB & Firewall
AWS - Classic & ELB
13/58EYWA
Confidential
3. VPC Limitations
① B-Class(65,536)
 Smaller layer 2 subnetting
② Internet Gateway Bottleneck
③ The limited number of VPC
④ ELB consumes Private IP
⑤ Not extensible L2 network over VPN
AWS - VPC
14/58EYWA
Confidential
CloudStack - Traffic Flows
Tenant A
VM
Tenant B
VM
Tenant-A Public Traffic (Remote VR)
Tenant-A Public Traffic (Local VR)
Tenant-A Private Traffic
Tenant A
VR
Tenant B
VR
VR-B
VR-A
INTERNET
15/58EYWA
Confidential
1. RVM (Router VM): HAProxy-based
① Feature
 Port Forwarding & layer-4 load balancing by RVM
② Algorithm
 Round robin & Least Connection
③ Advantage
 Load balancing without additional component
④ Limitations
 RVM Bottleneck
 Layer-4 load balancing only
2. VPX
① Feature
 Layer-4 load balancing by VPX device
② Algorithm
 Round robin & Least Connection
③ Advantage
 Performance
④ Limitations
 Additional HW
 No Scalable
 Layer-4 load balancing only
CloudStack
16/58EYWA
Confidential
OpenStack
1. Problems
① Dedicated Network Node & Network Node Bottleneck
② By Gartner: OpenStack in the enterprise? Ha ha ha, you must be joking.
 The difference between Amazon and OpenStack, though, is that Amazon's core services such as EC2,
S3, and others are stable, while some of OpenStack's core tech such as its Neutron networking
layer are very, very weak.
 http://www.theregister.co.uk/2013/11/20/gartner_openstack_criticism/
③ By HP: OpenStack’s networking nightmare Neutron was everyone’s fault
 http://www.theregister.co.uk/2014/05/13/openstack_neutron_explainer/
17/58EYWA
Confidential
OpenStack - Neutron/DVR
1. DVR (Distributed Virtual Router)
① https://wiki.openstack.org/wiki/Neutron/DVR
② Limitations
 http://www.slideshare.net/carlbaldwin/dvr-slides
 SNAT is centralized in Network Node.
18/58EYWA
The Architecture using Legacy Protocols
1. Traffic Flows of Architecture
2. Advantages & Limitations
3. (M)VRPP
4. VxLAN
19/58EYWA
Confidential
Traffic Flows
Tenant 1
VM
Tenant 2
VM
Tenant-1 Public Traffic (Orphan)
Tenant-1 Public Traffic (Normal)
Tenant-1 Private Traffic
Tenant 1
VR
Tenant 2
VRVR-1-1
VR-1-2
VR-2-2
VR-2-1
INTERNET
20/58EYWA
Confidential
Advantages
1. Public Network
① Load Sharing & Balancing
 Load Balancing by 254 VRs per tenant
 Scalable
 For Inbound & Outbound Traffic
② High Availability
 HA by 254 VRs per tenant
③ Traffic Engineering
 Save of Network Bandwidth
 Low latency
2. Private Network
① A large number of tenants
 Traffic Isolation by VxLAN (2^24 = 16,777,216)
② Large layer 2 network
 VxLAN
 Multicast instead of Broadcast (VxLAN)
 Decrease in MAC Flooding
21/58EYWA
Confidential
Limitations
1. Public Network
① Performance
 Limited Scalability: Maximum 254 VRs per tenant
② Load Sharing
 Primary back VR’s bottleneck when takeover
 VM’s different default GW IP addresses
③ Traffic Engineering
 Waste of Network Bandwidth for advertisement packets
 VM’s Inefficient default GW
2. Private Network
① Large layer 2 network
 ARP Broadcasting
② Each VR consumes the private IP address pool
22/58EYWA
Confidential
VRRP
23/58EYWA
Confidential
MVRRP
VR01
NIC#1
eth0
eth1
NIC#2
NIC#1
NIC#2
111.2.1.100
10.0.0.1
VR02 eth0
eth1
111.2.1.101
10.0.0.2
VM01
eth0
NIC#1
10.0.1.1/8
VM02
eth0
NIC#1
10.0.1.2/8
VM03
eth0
NIC#1
10.0.1.3/8
VM04
eth0
NIC#1
10.0.1.4/8
VM05
eth0
NIC#1
10.0.1.5/8
VM06
eth0
NIC#1
10.0.1.6/8
Switch 1 Switch 2
Internet
Master for VRID=1
Backup for VRID=2
…
…
Backup for VRID=254
Backup for VRID=1
Master for VRID=2
…
…
Backup for VRID=254VRRP VRID=1
IP: 10.0.0.1
MAC: AAAAAAAAAAAA
VRRP VRID=2
IP: 10.0.0.2
MAC: BBBBBBBBBBBB
…
…
….
VRRP VRID=254
IP: 10.0.0.254
MAC: XXXXXXXXXXXX
①
② ③
④
Switch 1 Table
MAC Port
AAAAAAAAAAAA ①
BBBBBBBBBBBB ②
Switch 2 Table
MAC Port
BBBBBBBBBBBB ④
AAAAAAAAAAAA ③
24/58EYWA
Confidential
VxLAN
25/58EYWA
The EYWA
1. Traffic Flows
2. Advantages
3. The Architecture
4. Demo
5. The Comparison of the new
Architectures
6. Summary
26/58EYWA
Confidential
Traffic Flows on EYWA
Tenant 1
VM
Tenant 2
VM
Tenant-1 Public Traffic (Orphan)
Tenant-1 Public Traffic (Normal)
Tenant-1 Private Traffic
Tenant 1
VR
Tenant 2
VRVR-1-1
VR-1-2
VR-2-2
VR-2-1
INTERNET
27/58EYWA
Confidential
Advantages
1. Public Network
① Load Sharing & Balancing
 Load Balancing by Unlimited VRs
 Scalable
 Load balanced Inbound & Outbound Traffic
② High Availability
 Active-Active structure by Unlimited VRs
③ Traffic Engineering
 Save of Network Bandwidth
 Low latency
2. Private Network
① A large number of tenants
 Traffic Isolation by VXLAN (16,777,216)
② Large layer 2 network
 VxLAN
 Multicast instead of Broadcast (VxLAN)
 Decrease in MAC Flooding
 Agent
 Eliminate Broadcast
3. VM Migration
4. No added Server & H/W
28/58EYWA
Confidential
The Architecture of EYWA
111.2.3.11
10.0.0.21 10.0.0.22
111.2.3.15 111.2.3.111
111.2.3.112
10.0.0.2 10.0.0.3 10.0.0.21
...
10.0.0.20
XXX
...
10.0.0.22 10.0.0.23
111.2.3.113
10.0.0.23
111.2.3.13
VR(Virtual Router) VR-{Tenant}-1 VR-{Tenant}-2(~Unlimited)
Function NAT, LB, VPN, DHCP NAT, LB, VPN
Internet
Public-IP
for VR
Public-IP
for VM
Tenant-A VLAN
Tenant-B VLAN
Tenant A Tenant B
VR-A-1 VR-A-2
GW: 10.0.0.1
VM VM VM VM VM VM
VR-B-1
GW: 10.0.0.1
VR-B-2
GW: 10.0.0.1
VM VM VM
GW: 10.0.0.1
111.2.3.13
HA & LB & Scalable
X
Normal
mode
Orphan
mode
29/58EYWA
Confidential
The Architecture of EYWA
VSe (Common)
VR-A-1
111.2.3.11
10.0.0.1/8
VSi
A
vport-A
VM
VSe (Common) VSe (Common)
Switch (Public Net.)
Switch (Private Net.)
VR-A-2
111.2.3.12
10.0.0.1/8
VR-B-1
111.2.3.21
10.0.0.1/8
VSi
A
vport-A
VM
VSi
B
vport-B
VM
vtep-A vtep-A vtep-B
vnet0
peth0
vnet0
peth0
vnet0
peth0
eth0
eth1
eth0
eth1
eth0
eth1
vnet1
vnet2
peth1 peth1
VSi
A
vport-A
VM
vtep-A
Tenant A
Tenant B
VR-B-2
VSi
B
vport-B
VM
eth0
eth1
111.2.3.22
10.0.0.1/8
AgentAgent ControllerAgent
Orphan Normal
Normal Normal
eth0eth0
vnet1
eth0
vnet3
eth0
vnet1
eth0
vnet2
peth1
vtep-B
30/58EYWA
Confidential
Demo
https://goo.gl/A1dMJ0 (Youtube)
https://goo.gl/wMjCgI (Prezi)
31/58EYWA
Confidential
The Comparison of the Virtual Network Architectures
Component AWS OpenStack CloudStack EYWA
Tenants
(Virtual LAN)
The number of
tenants
?
(5 VPC per tenant in a
region)
224 = 16,777,216 224 = 16,777,216 224 = 16,777,216
Public
Network
Outbound
Router per tenant
One per VPC
(Internet GW)
1
(L3 Agent)
1
(RVM)
Unlimited (VRs)
Router
Deployment
?
All VRs on a
single server
All VRs on
distributed
servers
All VRs on
distributed
servers
HA of Router ? Active-Standby Active-Standby High Available
LB of Router X X X O
SPOF
or
Bottleneck
Internet GW
L3 Agent &
Network
Controller
RVM Nothing
Inbound
LB ELB LBaaS RVM or VPX Unlimited VRs
SPOF
or
Bottleneck
ELB(Default Limit 20) Network Node RVM or VPX Nothing
Private Network Layer 2 Network
Medium
Under B-Class
Small Private
Network
Small Private
Network
Large
A-Class
224 = 16,777,216
Router & LB Internet GW & ELB
L3 Agent &
LBaaS
All-in-one
(RVM)
or
added LB(VPX)
All-in-one
(VRs)
32/58EYWA
Confidential
Summary
1. Advantages
① Cloud Service providers’ view
 A large number of tenants (about 224 = 16,777,216) by using virtual LANs
② Consumers’ view
 Public network service per tenant without throughput bottle-neck and SPOF on
SNAT/DNAT
 Private network (a single large IP subnet) per tenant
2. Architecture
① Scales to support huge data centers with high availability, load balancing and large layer-2
semantics.
② Decentralized scale-out control and data plane.
③ The only component is an agent in every hypervisor host and the agents act as distributed
controller.
3. EYWA can be deployed into all the multi-tenant cloud environments today.
33/58EYWA
Scenarios
34/58EYWA
Confidential
Inbound Load-Balancing VM Scale-out_EYWA
T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#16,777,216
VR#1
…
Server#1
Overload
35/58EYWA
Confidential
Inbound Load-Balancing VM Scale-out_EYWA
T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#16,777,216
VR#1
…
Server#1
T#1
VM#2
Scale-out
36/58EYWA
Confidential
Inbound Load-Balancing VM Scale-out_EYWA
T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#16,777,216
VR#1
T#2
VM#3
T#2
VM#4
T#16,777,216
VM#2…
T#2
VR#2
T#16,777,216
VR#2
… …
Server#1 Server#2
T#1
VM#2
Overload Overload
37/58EYWA
Confidential
Inbound Load-Balancing VM Scale-out_EYWA
T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#16,777,216
VR#1
T#1
VM#3
T#2
VM#3
T#2
VM#4
T#16,777,216
VM#2…
T#2
VR#2
T#16,777,216
VR#2
… …
Server#1 Server#2
T#1
VM#2
Scale-out
38/58EYWA
Confidential
Inbound Load-Balancing VR Scale-out_EYWA
T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#16,777,216
VR#1
T#1
VM#3
T#2
VM#3
T#2
VM#4
T#16,777,216
VM#2…
T#2
VR#2
T#16,777,216
VR#2
… …
Server#1 Server#2
T#1
VM#2
Overload
39/58EYWA
Confidential
Inbound Load-Balancing VR Scale-out_EYWA
T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#16,777,216
VR#1
T#1
VM#3
T#2
VM#3
T#2
VM#4
T#16,777,216
VM#2…
T#2
VR#2
T#16,777,216
VR#2
… …
Server#1 Server#2
T#1
VM#2
T#1
VR#2
Scale-out
40/58EYWA
Confidential
Inbound High-Availability VR Scale-in(or Fail-over)_EYWA
T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#16,777,216
VR#1
T#1
VM#3
T#2
VM#3
T#2
VM#4
T#16,777,216
VM#2…
T#2
VR#2
T#16,777,216
VR#2
… …
Server#1 Server#2
T#1
VM#2
T#1
VR#2
41/58EYWA
Confidential
Inbound High-Availability VR Scale-in(or Fail-over)_EYWA
T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#16,777,216
VR#1
T#1
VM#3
T#2
VM#3
T#2
VM#4
T#16,777,216
VM#2…
T#2
VR#2
T#16,777,216
VR#2
… …
Server#1 Server#2
T#1
VM#2
T#1
VR#2
XScale-in
(Fail)
42/58EYWA
Confidential
Inbound LB & HA VM Migration(Orphan)_EYWA
T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#16,777,216
VR#1
T#1
VM#1
T#2
VM#3
T#2
VM#4
T#16,777,216
VM#2…
T#2
VR#2
T#16,777,216
VR#2
… …
Server#1 Server#2
T#1
VM#2
43/58EYWA
Confidential
Inbound LB & HA VM Migration(Orphan)_EYWA
T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#16,777,216
VR#1
T#1
VM#1
T#2
VM#3
T#2
VM#4
T#16,777,216
VM#2…
T#2
VR#2
T#16,777,216
VR#2
… …
Server#1 Server#2
T#1
VM#2
44/58EYWA
Confidential
Inbound LB & HA VM Migration(Normal)_EYWA
T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#16,777,216
VR#1
T#1
VM#1
T#2
VM#3
T#2
VM#4
T#16,777,216
VM#2…
T#2
VR#2
T#16,777,216
VR#2
… …
Server#1 Server#2
T#1
VM#2
T#1
VR#2
T#1
VM#3
45/58EYWA
Confidential
Inbound LB & HA VM Migration(Normal)_EYWA
T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#16,777,216
VR#1
T#1
VM#1
T#2
VM#3
T#2
VM#4
T#16,777,216
VM#2…
T#2
VR#2
T#16,777,216
VR#2
… …
Server#1 Server#2
T#1
VM#2
T#1
VR#2
T#1
VM#3
46/58EYWA
Confidential
Inbound LB & HA VR Limitations_EYWA
…T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#1
VM#
16,777
,213
T#2
VM#1
6,777,
212
T#2
VM#1
6,777,
213
T#16,777,216
VM#16,777,213
T#16,777,216
VR#
∞
… …
Server#1 Server#???,???
T#1
VM#2
T#2
VR#
∞
47/58EYWA
Confidential
Inbound LB & HA Limitations_OpenStack LBaaS
…T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VM#
16,777
,213
T#2
VM#1
6,777,
212
T#2
VM#1
6,777,
213
T#16,777,216
VM#16,777,213
…
Network controller Server#???,???
T#1
VM#2
T#1
VR#3
T#1
VR#2
T#1
VR#1
T#16,777,216
VR#2
T#16,777,216
VR#1
T#2
VR#2
T#2
VR#1
N/W Controller
Bottleneck
48/58EYWA
Confidential
Outbound Load-Balancing VR Scale-out_EYWA
T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#16,777,216
VR#1
T#1
VM#3
T#2
VM#3
T#2
VM#4
T#16,777,216
VM#2…
T#2
VR#2
T#16,777,216
VR#2
… …
Server#1 Server#2
T#1
VM#2
Overload10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1
49/58EYWA
Confidential
Outbound Load-Balancing VR Scale-out_EYWA
T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#16,777,216
VR#1
T#1
VM#3
T#2
VM#3
T#2
VM#4
T#16,777,216
VM#2…
T#1
VR#2
T#2
VR#2
T#16,777,216
VR#2
… …
Server#1 Server#2
T#1
VM#2
Scale-out
10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1
50/58EYWA
Confidential
Outbound High-Availability VR Scale-in(or Fail-over)_EYWA
T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#16,777,216
VR#1
T#1
VM#3
T#2
VM#3
T#2
VM#4
T#16,777,216
VM#2…
T#1
VR#2
T#2
VR#2
T#16,777,216
VR#2
… …
Server#1 Server#2
T#1
VM#2
10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1
51/58EYWA
Confidential
Outbound High-Availability VR Scale-in(or Fail-over)_EYWA
T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#16,777,216
VR#1
T#1
VM#3
T#2
VM#3
T#2
VM#4
T#16,777,216
VM#2…
T#1
VR#2
T#2
VR#2
T#16,777,216
VR#2
… …
Server#1 Server#2
T#1
VM#2
Scale-in
(Fail)
X10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1
52/58EYWA
Confidential
Outbound LB & HA VM Migration(Orphan)_EYWA
T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#16,777,216
VR#1
T#1
VM#1
T#2
VM#3
T#2
VM#4
T#16,777,216
VM#2…
T#2
VR#2
T#16,777,216
VR#2
… …
Server#1 Server#2
T#1
VM#2
10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1
53/58EYWA
Confidential
Outbound LB & HA VM Migration(Orphan)_EYWA
T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#16,777,216
VR#1
T#1
VM#1
T#2
VM#3
T#2
VM#4
T#16,777,216
VM#2…
T#2
VR#2
T#16,777,216
VR#2
… …
Server#1 Server#2
T#1
VM#2
10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1
54/58EYWA
Confidential
Outbound LB & HA VM Migration(Normal)_EYWA
T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#16,777,216
VR#1
T#1
VM#1
T#2
VM#3
T#2
VM#4
T#16,777,216
VM#2…
T#2
VR#2
T#16,777,216
VR#2
… …
Server#1 Server#2
T#1
VM#2
T#1
VR#2
10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1
T#1
VM#3
55/58EYWA
Confidential
Outbound LB & HA VM Migration(Normal)_EYWA
T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#16,777,216
VR#1
T#1
VM#1
T#2
VM#3
T#2
VM#4
T#16,777,216
VM#2…
T#2
VR#2
T#16,777,216
VR#2
… …
Server#1 Server#2
T#1
VM#2
T#1
VR#2
10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1
T#1
VM#3
56/58EYWA
Confidential
Outbound LB & HA VM Migration_OpenStack
T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#16,777,216
VR#1
T#1
VM#1
T#2
VM#3
T#2
VM#4
T#16,777,216
VM#2…
…
Network Controller Server#2
T#1
VM#2
10.0.0.1 10.0.0.1 10.0.0.1
T#1
VM#3
N/W Controller
Bottleneck
VR
Bottleneck
Waste of
Bandwidth
57/58EYWA
Confidential
Outbound LB & HA VR Limitations_EYWA
T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#1
VM#1
6,777,
213
T#2
VM#1
6,777,
212
T#2
VM#1
6,777,
213
T#16,777,216
VM#16,777,21
3
…
T#2
VR#
∞
T#16,777,216
VR#
∞
… …
Server#1 Server#???,???
T#1
VM#2
10.0.0.1 10.0.0.1 10.0.0.1
10.0.0.1
…
58/58EYWA
Confidential
Outbound LB & HA VR Limitations_OpenStack
T#1
VM#1
T#2
VM#1
T#2
VM#2
T#16,777,216
VM#1…
T#1
VR#1
T#2
VR#1
T#1
VM#1
6,777,
213
T#16,777,216
VM#16,777,21
3
…
T#16,777,216
VR#1
…
Network Controller Server#???,???
T#1
VM#2
10.0.0.1 10.0.0.1
N/W Controller
Bottleneck
VR
Bottleneck
10.0.0.1
T#2
VM#1
6,777,
212
T#2
VM#1
6,777,
213
Waste of
Bandwidth
59/58EYWA
Thank You.

Contenu connexe

Tendances

Operationalizing EVPN in the Data Center: Part 2
Operationalizing EVPN in the Data Center: Part 2Operationalizing EVPN in the Data Center: Part 2
Operationalizing EVPN in the Data Center: Part 2Cumulus Networks
 
Demystifying EVPN in the data center: Part 1 in 2 episode series
Demystifying EVPN in the data center: Part 1 in 2 episode seriesDemystifying EVPN in the data center: Part 1 in 2 episode series
Demystifying EVPN in the data center: Part 1 in 2 episode seriesCumulus Networks
 
Ipv6 deployment at the university of warwick - networkshop44
Ipv6 deployment at the university of warwick - networkshop44Ipv6 deployment at the university of warwick - networkshop44
Ipv6 deployment at the university of warwick - networkshop44Jisc
 
vPC techonology for full ha from dc core to baremetel server.
vPC techonology for full ha from dc core to baremetel server.vPC techonology for full ha from dc core to baremetel server.
vPC techonology for full ha from dc core to baremetel server.Ajeet Singh
 
Vxlan deep dive session rev0.5 final
Vxlan deep dive session rev0.5   finalVxlan deep dive session rev0.5   final
Vxlan deep dive session rev0.5 finalKwonSun Bae
 
Presentation on MPLS (Multi Protocol Label Switching)
Presentation on MPLS (Multi Protocol Label Switching)Presentation on MPLS (Multi Protocol Label Switching)
Presentation on MPLS (Multi Protocol Label Switching)BalaMurugan948
 
Segment Routing
Segment RoutingSegment Routing
Segment RoutingAPNIC
 
Configuration & Routing of Clos Networks
Configuration & Routing of Clos NetworksConfiguration & Routing of Clos Networks
Configuration & Routing of Clos NetworksCumulus Networks
 
MPLS (Multi-Protocol Label Switching)
MPLS  (Multi-Protocol Label Switching)MPLS  (Multi-Protocol Label Switching)
MPLS (Multi-Protocol Label Switching)NetProtocol Xpert
 
Virtualizing the Network to enable a Software Defined Infrastructure (SDI)
Virtualizing the Network to enable a Software Defined Infrastructure (SDI)Virtualizing the Network to enable a Software Defined Infrastructure (SDI)
Virtualizing the Network to enable a Software Defined Infrastructure (SDI)Odinot Stanislas
 
Advanced Topics and Future Directions in MPLS
Advanced Topics and Future Directions in MPLS Advanced Topics and Future Directions in MPLS
Advanced Topics and Future Directions in MPLS Cisco Canada
 
Software Defined Networking (SDN)
Software Defined Networking (SDN)Software Defined Networking (SDN)
Software Defined Networking (SDN)NetProtocol Xpert
 
Demystifying Networking Webinar Series- Routing on the Host
Demystifying Networking Webinar Series- Routing on the HostDemystifying Networking Webinar Series- Routing on the Host
Demystifying Networking Webinar Series- Routing on the HostCumulus Networks
 
OPNFV Service Function Chaining
OPNFV Service Function ChainingOPNFV Service Function Chaining
OPNFV Service Function ChainingOPNFV
 
LAN Switching and Wireless: Ch2 - Basic Switch Concepts and Configuration
LAN Switching and Wireless: Ch2 - Basic Switch Concepts and ConfigurationLAN Switching and Wireless: Ch2 - Basic Switch Concepts and Configuration
LAN Switching and Wireless: Ch2 - Basic Switch Concepts and ConfigurationAbdelkhalik Mosa
 
SDN Traffic Engineering, A Natural Evolution
SDN Traffic Engineering, A Natural EvolutionSDN Traffic Engineering, A Natural Evolution
SDN Traffic Engineering, A Natural EvolutionAPNIC
 

Tendances (20)

Operationalizing EVPN in the Data Center: Part 2
Operationalizing EVPN in the Data Center: Part 2Operationalizing EVPN in the Data Center: Part 2
Operationalizing EVPN in the Data Center: Part 2
 
Demystifying EVPN in the data center: Part 1 in 2 episode series
Demystifying EVPN in the data center: Part 1 in 2 episode seriesDemystifying EVPN in the data center: Part 1 in 2 episode series
Demystifying EVPN in the data center: Part 1 in 2 episode series
 
Ipv6 deployment at the university of warwick - networkshop44
Ipv6 deployment at the university of warwick - networkshop44Ipv6 deployment at the university of warwick - networkshop44
Ipv6 deployment at the university of warwick - networkshop44
 
Mpls
MplsMpls
Mpls
 
EVPN Introduction
EVPN IntroductionEVPN Introduction
EVPN Introduction
 
vPC techonology for full ha from dc core to baremetel server.
vPC techonology for full ha from dc core to baremetel server.vPC techonology for full ha from dc core to baremetel server.
vPC techonology for full ha from dc core to baremetel server.
 
Vxlan deep dive session rev0.5 final
Vxlan deep dive session rev0.5   finalVxlan deep dive session rev0.5   final
Vxlan deep dive session rev0.5 final
 
Presentation on MPLS (Multi Protocol Label Switching)
Presentation on MPLS (Multi Protocol Label Switching)Presentation on MPLS (Multi Protocol Label Switching)
Presentation on MPLS (Multi Protocol Label Switching)
 
Segment Routing
Segment RoutingSegment Routing
Segment Routing
 
Configuration & Routing of Clos Networks
Configuration & Routing of Clos NetworksConfiguration & Routing of Clos Networks
Configuration & Routing of Clos Networks
 
OpenFlow Overview
OpenFlow OverviewOpenFlow Overview
OpenFlow Overview
 
MPLS (Multi-Protocol Label Switching)
MPLS  (Multi-Protocol Label Switching)MPLS  (Multi-Protocol Label Switching)
MPLS (Multi-Protocol Label Switching)
 
Virtualizing the Network to enable a Software Defined Infrastructure (SDI)
Virtualizing the Network to enable a Software Defined Infrastructure (SDI)Virtualizing the Network to enable a Software Defined Infrastructure (SDI)
Virtualizing the Network to enable a Software Defined Infrastructure (SDI)
 
Advanced Topics and Future Directions in MPLS
Advanced Topics and Future Directions in MPLS Advanced Topics and Future Directions in MPLS
Advanced Topics and Future Directions in MPLS
 
Software Defined Networking (SDN)
Software Defined Networking (SDN)Software Defined Networking (SDN)
Software Defined Networking (SDN)
 
Demystifying Networking Webinar Series- Routing on the Host
Demystifying Networking Webinar Series- Routing on the HostDemystifying Networking Webinar Series- Routing on the Host
Demystifying Networking Webinar Series- Routing on the Host
 
OPNFV Service Function Chaining
OPNFV Service Function ChainingOPNFV Service Function Chaining
OPNFV Service Function Chaining
 
LAN Switching and Wireless: Ch2 - Basic Switch Concepts and Configuration
LAN Switching and Wireless: Ch2 - Basic Switch Concepts and ConfigurationLAN Switching and Wireless: Ch2 - Basic Switch Concepts and Configuration
LAN Switching and Wireless: Ch2 - Basic Switch Concepts and Configuration
 
SEGMENT Routing
SEGMENT RoutingSEGMENT Routing
SEGMENT Routing
 
SDN Traffic Engineering, A Natural Evolution
SDN Traffic Engineering, A Natural EvolutionSDN Traffic Engineering, A Natural Evolution
SDN Traffic Engineering, A Natural Evolution
 

Similaire à EYWA (Elastic load-balancing & high-availabilitY Wired virtual network Architecture)

EYWA Presentation v0.1.27
EYWA Presentation v0.1.27EYWA Presentation v0.1.27
EYWA Presentation v0.1.27JungIn Jung
 
Network Virtualization for Cloud Services Infrastructure
Network Virtualization for Cloud Services InfrastructureNetwork Virtualization for Cloud Services Infrastructure
Network Virtualization for Cloud Services InfrastructureShahryar Ali
 
OpenNebula - Mellanox Considerations for Smart Cloud
OpenNebula - Mellanox Considerations for Smart CloudOpenNebula - Mellanox Considerations for Smart Cloud
OpenNebula - Mellanox Considerations for Smart CloudOpenNebula Project
 
ProgrammableFlow for Open Virtualized Data Center Network
ProgrammableFlow for Open Virtualized Data Center NetworkProgrammableFlow for Open Virtualized Data Center Network
ProgrammableFlow for Open Virtualized Data Center NetworkOpen Networking Summits
 
MidoNet Overview - OpenStack and SDN integration
MidoNet Overview - OpenStack and SDN integrationMidoNet Overview - OpenStack and SDN integration
MidoNet Overview - OpenStack and SDN integrationAkhilesh Dhawan
 
Network Monitoring in the age of the Cloud
Network Monitoring in the age of the CloudNetwork Monitoring in the age of the Cloud
Network Monitoring in the age of the CloudAugusto Ciuffoletti
 
Openstack Neutron Insights
Openstack Neutron InsightsOpenstack Neutron Insights
Openstack Neutron InsightsAtul Pandey
 
Midokura OpenStack Day Korea Talk: MidoNet Open Source Network Virtualization...
Midokura OpenStack Day Korea Talk: MidoNet Open Source Network Virtualization...Midokura OpenStack Day Korea Talk: MidoNet Open Source Network Virtualization...
Midokura OpenStack Day Korea Talk: MidoNet Open Source Network Virtualization...Dan Mihai Dumitriu
 
Network Virtualization using Shortest Path Bridging
Network Virtualization using Shortest Path Bridging Network Virtualization using Shortest Path Bridging
Network Virtualization using Shortest Path Bridging Motty Ben Atia
 
OpenStack Networking and Automation
OpenStack Networking and AutomationOpenStack Networking and Automation
OpenStack Networking and AutomationAdam Johnson
 
PLNOG15: Is there something less complicated than connecting two LAN networks...
PLNOG15: Is there something less complicated than connecting two LAN networks...PLNOG15: Is there something less complicated than connecting two LAN networks...
PLNOG15: Is there something less complicated than connecting two LAN networks...PROIDEA
 
Imperfection_Is_Beautiful.111_2016_04_13_19_07_54_722
Imperfection_Is_Beautiful.111_2016_04_13_19_07_54_722Imperfection_Is_Beautiful.111_2016_04_13_19_07_54_722
Imperfection_Is_Beautiful.111_2016_04_13_19_07_54_722Prince Mishra
 
Eywa - Cloud Network Architecture 20180625(20150907)(compact)
Eywa - Cloud Network Architecture 20180625(20150907)(compact)Eywa - Cloud Network Architecture 20180625(20150907)(compact)
Eywa - Cloud Network Architecture 20180625(20150907)(compact)JungIn Jung
 
PLNOG 8: Piotr Głaska - Data Center Networking - Trends and suggestions
PLNOG 8: Piotr Głaska -  Data Center Networking - Trends and suggestions PLNOG 8: Piotr Głaska -  Data Center Networking - Trends and suggestions
PLNOG 8: Piotr Głaska - Data Center Networking - Trends and suggestions PROIDEA
 
PLNOG 5: Piotr Szołkowski - Data Center i nie tylko...
PLNOG 5: Piotr Szołkowski - Data Center i nie tylko...PLNOG 5: Piotr Szołkowski - Data Center i nie tylko...
PLNOG 5: Piotr Szołkowski - Data Center i nie tylko...PROIDEA
 
MidoNet gives OpenStack Neutron a Boost
MidoNet gives OpenStack Neutron a BoostMidoNet gives OpenStack Neutron a Boost
MidoNet gives OpenStack Neutron a BoostOpenStack_Online
 
Understanding network and service virtualization
Understanding network and service virtualizationUnderstanding network and service virtualization
Understanding network and service virtualizationSDN Hub
 

Similaire à EYWA (Elastic load-balancing & high-availabilitY Wired virtual network Architecture) (20)

EYWA Presentation v0.1.27
EYWA Presentation v0.1.27EYWA Presentation v0.1.27
EYWA Presentation v0.1.27
 
Network Virtualization for Cloud Services Infrastructure
Network Virtualization for Cloud Services InfrastructureNetwork Virtualization for Cloud Services Infrastructure
Network Virtualization for Cloud Services Infrastructure
 
OpenNebula - Mellanox Considerations for Smart Cloud
OpenNebula - Mellanox Considerations for Smart CloudOpenNebula - Mellanox Considerations for Smart Cloud
OpenNebula - Mellanox Considerations for Smart Cloud
 
10 sdn-vir-6up
10 sdn-vir-6up10 sdn-vir-6up
10 sdn-vir-6up
 
ProgrammableFlow for Open Virtualized Data Center Network
ProgrammableFlow for Open Virtualized Data Center NetworkProgrammableFlow for Open Virtualized Data Center Network
ProgrammableFlow for Open Virtualized Data Center Network
 
MidoNet Overview - OpenStack and SDN integration
MidoNet Overview - OpenStack and SDN integrationMidoNet Overview - OpenStack and SDN integration
MidoNet Overview - OpenStack and SDN integration
 
Network Monitoring in the age of the Cloud
Network Monitoring in the age of the CloudNetwork Monitoring in the age of the Cloud
Network Monitoring in the age of the Cloud
 
Openstack Neutron Insights
Openstack Neutron InsightsOpenstack Neutron Insights
Openstack Neutron Insights
 
Midokura OpenStack Day Korea Talk: MidoNet Open Source Network Virtualization...
Midokura OpenStack Day Korea Talk: MidoNet Open Source Network Virtualization...Midokura OpenStack Day Korea Talk: MidoNet Open Source Network Virtualization...
Midokura OpenStack Day Korea Talk: MidoNet Open Source Network Virtualization...
 
Network Virtualization using Shortest Path Bridging
Network Virtualization using Shortest Path Bridging Network Virtualization using Shortest Path Bridging
Network Virtualization using Shortest Path Bridging
 
OpenStack Networking and Automation
OpenStack Networking and AutomationOpenStack Networking and Automation
OpenStack Networking and Automation
 
PLNOG15: Is there something less complicated than connecting two LAN networks...
PLNOG15: Is there something less complicated than connecting two LAN networks...PLNOG15: Is there something less complicated than connecting two LAN networks...
PLNOG15: Is there something less complicated than connecting two LAN networks...
 
Imperfection_Is_Beautiful.111_2016_04_13_19_07_54_722
Imperfection_Is_Beautiful.111_2016_04_13_19_07_54_722Imperfection_Is_Beautiful.111_2016_04_13_19_07_54_722
Imperfection_Is_Beautiful.111_2016_04_13_19_07_54_722
 
Eywa - Cloud Network Architecture 20180625(20150907)(compact)
Eywa - Cloud Network Architecture 20180625(20150907)(compact)Eywa - Cloud Network Architecture 20180625(20150907)(compact)
Eywa - Cloud Network Architecture 20180625(20150907)(compact)
 
CloudStack and SDN
CloudStack and SDNCloudStack and SDN
CloudStack and SDN
 
PLNOG 8: Piotr Głaska - Data Center Networking - Trends and suggestions
PLNOG 8: Piotr Głaska -  Data Center Networking - Trends and suggestions PLNOG 8: Piotr Głaska -  Data Center Networking - Trends and suggestions
PLNOG 8: Piotr Głaska - Data Center Networking - Trends and suggestions
 
PLNOG 5: Piotr Szołkowski - Data Center i nie tylko...
PLNOG 5: Piotr Szołkowski - Data Center i nie tylko...PLNOG 5: Piotr Szołkowski - Data Center i nie tylko...
PLNOG 5: Piotr Szołkowski - Data Center i nie tylko...
 
MidoNet gives OpenStack Neutron a Boost
MidoNet gives OpenStack Neutron a BoostMidoNet gives OpenStack Neutron a Boost
MidoNet gives OpenStack Neutron a Boost
 
10209
1020910209
10209
 
Understanding network and service virtualization
Understanding network and service virtualizationUnderstanding network and service virtualization
Understanding network and service virtualization
 

Dernier

Emixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native developmentEmixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native developmentPim van der Noll
 
Data governance with Unity Catalog Presentation
Data governance with Unity Catalog PresentationData governance with Unity Catalog Presentation
Data governance with Unity Catalog PresentationKnoldus Inc.
 
Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...
Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...
Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...Scott Andery
 
Decarbonising Buildings: Making a net-zero built environment a reality
Decarbonising Buildings: Making a net-zero built environment a realityDecarbonising Buildings: Making a net-zero built environment a reality
Decarbonising Buildings: Making a net-zero built environment a realityIES VE
 
Sample pptx for embedding into website for demo
Sample pptx for embedding into website for demoSample pptx for embedding into website for demo
Sample pptx for embedding into website for demoHarshalMandlekar2
 
Scale your database traffic with Read & Write split using MySQL Router
Scale your database traffic with Read & Write split using MySQL RouterScale your database traffic with Read & Write split using MySQL Router
Scale your database traffic with Read & Write split using MySQL RouterMydbops
 
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024BookNet Canada
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsSergiu Bodiu
 
Moving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdfMoving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdfLoriGlavin3
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsPixlogix Infotech
 
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxThe Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxLoriGlavin3
 
How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.Curtis Poe
 
Generative Artificial Intelligence: How generative AI works.pdf
Generative Artificial Intelligence: How generative AI works.pdfGenerative Artificial Intelligence: How generative AI works.pdf
Generative Artificial Intelligence: How generative AI works.pdfIngrid Airi González
 
Unleashing Real-time Insights with ClickHouse_ Navigating the Landscape in 20...
Unleashing Real-time Insights with ClickHouse_ Navigating the Landscape in 20...Unleashing Real-time Insights with ClickHouse_ Navigating the Landscape in 20...
Unleashing Real-time Insights with ClickHouse_ Navigating the Landscape in 20...Alkin Tezuysal
 
Arizona Broadband Policy Past, Present, and Future Presentation 3/25/24
Arizona Broadband Policy Past, Present, and Future Presentation 3/25/24Arizona Broadband Policy Past, Present, and Future Presentation 3/25/24
Arizona Broadband Policy Past, Present, and Future Presentation 3/25/24Mark Goldstein
 
(How to Program) Paul Deitel, Harvey Deitel-Java How to Program, Early Object...
(How to Program) Paul Deitel, Harvey Deitel-Java How to Program, Early Object...(How to Program) Paul Deitel, Harvey Deitel-Java How to Program, Early Object...
(How to Program) Paul Deitel, Harvey Deitel-Java How to Program, Early Object...AliaaTarek5
 
A Journey Into the Emotions of Software Developers
A Journey Into the Emotions of Software DevelopersA Journey Into the Emotions of Software Developers
A Journey Into the Emotions of Software DevelopersNicole Novielli
 
Rise of the Machines: Known As Drones...
Rise of the Machines: Known As Drones...Rise of the Machines: Known As Drones...
Rise of the Machines: Known As Drones...Rick Flair
 
Long journey of Ruby standard library at RubyConf AU 2024
Long journey of Ruby standard library at RubyConf AU 2024Long journey of Ruby standard library at RubyConf AU 2024
Long journey of Ruby standard library at RubyConf AU 2024Hiroshi SHIBATA
 
What is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfWhat is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfMounikaPolabathina
 

Dernier (20)

Emixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native developmentEmixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native development
 
Data governance with Unity Catalog Presentation
Data governance with Unity Catalog PresentationData governance with Unity Catalog Presentation
Data governance with Unity Catalog Presentation
 
Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...
Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...
Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...
 
Decarbonising Buildings: Making a net-zero built environment a reality
Decarbonising Buildings: Making a net-zero built environment a realityDecarbonising Buildings: Making a net-zero built environment a reality
Decarbonising Buildings: Making a net-zero built environment a reality
 
Sample pptx for embedding into website for demo
Sample pptx for embedding into website for demoSample pptx for embedding into website for demo
Sample pptx for embedding into website for demo
 
Scale your database traffic with Read & Write split using MySQL Router
Scale your database traffic with Read & Write split using MySQL RouterScale your database traffic with Read & Write split using MySQL Router
Scale your database traffic with Read & Write split using MySQL Router
 
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platforms
 
Moving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdfMoving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdf
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and Cons
 
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxThe Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
 
How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.
 
Generative Artificial Intelligence: How generative AI works.pdf
Generative Artificial Intelligence: How generative AI works.pdfGenerative Artificial Intelligence: How generative AI works.pdf
Generative Artificial Intelligence: How generative AI works.pdf
 
Unleashing Real-time Insights with ClickHouse_ Navigating the Landscape in 20...
Unleashing Real-time Insights with ClickHouse_ Navigating the Landscape in 20...Unleashing Real-time Insights with ClickHouse_ Navigating the Landscape in 20...
Unleashing Real-time Insights with ClickHouse_ Navigating the Landscape in 20...
 
Arizona Broadband Policy Past, Present, and Future Presentation 3/25/24
Arizona Broadband Policy Past, Present, and Future Presentation 3/25/24Arizona Broadband Policy Past, Present, and Future Presentation 3/25/24
Arizona Broadband Policy Past, Present, and Future Presentation 3/25/24
 
(How to Program) Paul Deitel, Harvey Deitel-Java How to Program, Early Object...
(How to Program) Paul Deitel, Harvey Deitel-Java How to Program, Early Object...(How to Program) Paul Deitel, Harvey Deitel-Java How to Program, Early Object...
(How to Program) Paul Deitel, Harvey Deitel-Java How to Program, Early Object...
 
A Journey Into the Emotions of Software Developers
A Journey Into the Emotions of Software DevelopersA Journey Into the Emotions of Software Developers
A Journey Into the Emotions of Software Developers
 
Rise of the Machines: Known As Drones...
Rise of the Machines: Known As Drones...Rise of the Machines: Known As Drones...
Rise of the Machines: Known As Drones...
 
Long journey of Ruby standard library at RubyConf AU 2024
Long journey of Ruby standard library at RubyConf AU 2024Long journey of Ruby standard library at RubyConf AU 2024
Long journey of Ruby standard library at RubyConf AU 2024
 
What is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfWhat is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdf
 

EYWA (Elastic load-balancing & high-availabilitY Wired virtual network Architecture)

  • 1. EYWA Jeong wook-jae(wjjung11@gmail.com) Jung jung-in(call518@gmail.com) V0.1.38 EYWA: Elastic load-balancing & high-availabilitY Wired virtual network Architecture) - Beyond OpenStack/DVR & AWS/VPC
  • 4. 3/58EYWA Contents 1. The conventional Network Architectures ① Physical Networks ② Virtual (Overlay) Networks 2. The Architecture using Legacy Protocols 3. EYWA 4. Summary 5. Scenarios (Traffic Flows)
  • 5. 4/58EYWA ① Physical Networks  The conventional Data center  Problems & Limitations  New Data center Network Architectures  The Comparison of the new Architectures  Monsoon  Etc
  • 7. 6/58EYWA Confidential Problems & Limitations 1. Fragmentation of Resources 2. No Performance Isolation 3. Poor server to server connectivity 4. Need very high reliability near top of the tree (Single Point of Failure) 70~80% of the packets stay inside the data center
  • 8. 7/58EYWA Confidential The Comparison of the new DC Network Architectures Monsoon VL2 SEATTLE FAT-TREE PortLand SPAIN MOOSE TRILL Dcell Bcube MDCube Org. MS Research Univ. of Princeton Univ. of California San Diego HP Univ. of Cambrid ge MS Research Asia Publishing SIGCOMM 2008 SIGCOMM 2009 SIGCOMM 2008 SIGCOMM 2008 SIGCOMM 2009 NSDI 2010 DC CAVE S Works hop 2009 RFC 5556 2009 SIGCOMM 2008 SIGCOMM 2009 CoNEXT 2009 Authors Albert Greenberg… Albert Greenberg, Changhoon… Changhoon Kim… M. Al-Fares… R.N. Mysore… J. Mudigon da, M. Al-Fare s… M. Scott … Radia Perlman C. GUO… C. GUO… H. Wu, C. GUO… Topology Clos Network Clos Network N/A Fat-Tree Fat-Tree N/A N/A N/A Bcube Topo logy Packetizing MAC-in-MAC (802.1ah PBB) IP-in-IP IP-in-IP(?) IP rewriting MAC rewriting (PMAC) MAC rewriting TRILL Hdr Load Spreading MAC-Rotation ECMP ECMP ECMP ECMP Multi-path O O X O O O X O Mod. of End-Host? O O X X X O X X O Mod. of switches? O X O O (Special HW) O (Special HW) X O (Rbridge) △ ARP Directory Server Directory Server DHT on the switches Fabric Manager ESADI
  • 9. 8/58EYWA Confidential Monsoon SWITCH Up-link Port Down-link Port # Inter. SW N/A 10Gbps X 144 72 Aggr. SW 10Gbps X 72 10Gbps X 72 144 TOR SW 10Gbps X 2 1Gbps X 20 5,184 Monsoon Agent
  • 11. 10/58EYWA ② Virtual (Overlay) Networks  Problems & Limitations  AWS  CloudStack  OpenStack
  • 12. 11/58EYWA Confidential Problems & Limitations 1. Public Networks ① High Availability  SPOF of a single (Virtual or Physical) router ② Load Sharing & Balancing  The throughput bottleneck of a single router (SNAT/DNAT)  Scale-up (Physical Router)  Additional layer-4 load balancing service like AWS ELB  or additional physical load balancer (scale-up) ③ Traffic Engineering  Additional waste of network bandwidth  Increased latency to traverse a single router 2. Private Networks ① Layer 2 network is hard to scale out  Broadcast  MAC Flooding  STP ② VLAN (802.1Q) limit  VLAN ID limit of 4,094 3. Cost & Scalability
  • 13. 12/58EYWA Confidential 1. Classic(no VPC) Problems ① No Private network per Tenant  Higher latency than L2 ② No Traffic Isolation per Tenant  Shared GW with other tenants 2. ELB Limitations ① Layer-4 load balancing only ② TCP only  Port 25, 80, 443 & 1024~65535 ③ Domain name only  No Static IP & No interoperating with GSLB & Firewall AWS - Classic & ELB
  • 14. 13/58EYWA Confidential 3. VPC Limitations ① B-Class(65,536)  Smaller layer 2 subnetting ② Internet Gateway Bottleneck ③ The limited number of VPC ④ ELB consumes Private IP ⑤ Not extensible L2 network over VPN AWS - VPC
  • 15. 14/58EYWA Confidential CloudStack - Traffic Flows Tenant A VM Tenant B VM Tenant-A Public Traffic (Remote VR) Tenant-A Public Traffic (Local VR) Tenant-A Private Traffic Tenant A VR Tenant B VR VR-B VR-A INTERNET
  • 16. 15/58EYWA Confidential 1. RVM (Router VM): HAProxy-based ① Feature  Port Forwarding & layer-4 load balancing by RVM ② Algorithm  Round robin & Least Connection ③ Advantage  Load balancing without additional component ④ Limitations  RVM Bottleneck  Layer-4 load balancing only 2. VPX ① Feature  Layer-4 load balancing by VPX device ② Algorithm  Round robin & Least Connection ③ Advantage  Performance ④ Limitations  Additional HW  No Scalable  Layer-4 load balancing only CloudStack
  • 17. 16/58EYWA Confidential OpenStack 1. Problems ① Dedicated Network Node & Network Node Bottleneck ② By Gartner: OpenStack in the enterprise? Ha ha ha, you must be joking.  The difference between Amazon and OpenStack, though, is that Amazon's core services such as EC2, S3, and others are stable, while some of OpenStack's core tech such as its Neutron networking layer are very, very weak.  http://www.theregister.co.uk/2013/11/20/gartner_openstack_criticism/ ③ By HP: OpenStack’s networking nightmare Neutron was everyone’s fault  http://www.theregister.co.uk/2014/05/13/openstack_neutron_explainer/
  • 18. 17/58EYWA Confidential OpenStack - Neutron/DVR 1. DVR (Distributed Virtual Router) ① https://wiki.openstack.org/wiki/Neutron/DVR ② Limitations  http://www.slideshare.net/carlbaldwin/dvr-slides  SNAT is centralized in Network Node.
  • 19. 18/58EYWA The Architecture using Legacy Protocols 1. Traffic Flows of Architecture 2. Advantages & Limitations 3. (M)VRPP 4. VxLAN
  • 20. 19/58EYWA Confidential Traffic Flows Tenant 1 VM Tenant 2 VM Tenant-1 Public Traffic (Orphan) Tenant-1 Public Traffic (Normal) Tenant-1 Private Traffic Tenant 1 VR Tenant 2 VRVR-1-1 VR-1-2 VR-2-2 VR-2-1 INTERNET
  • 21. 20/58EYWA Confidential Advantages 1. Public Network ① Load Sharing & Balancing  Load Balancing by 254 VRs per tenant  Scalable  For Inbound & Outbound Traffic ② High Availability  HA by 254 VRs per tenant ③ Traffic Engineering  Save of Network Bandwidth  Low latency 2. Private Network ① A large number of tenants  Traffic Isolation by VxLAN (2^24 = 16,777,216) ② Large layer 2 network  VxLAN  Multicast instead of Broadcast (VxLAN)  Decrease in MAC Flooding
  • 22. 21/58EYWA Confidential Limitations 1. Public Network ① Performance  Limited Scalability: Maximum 254 VRs per tenant ② Load Sharing  Primary back VR’s bottleneck when takeover  VM’s different default GW IP addresses ③ Traffic Engineering  Waste of Network Bandwidth for advertisement packets  VM’s Inefficient default GW 2. Private Network ① Large layer 2 network  ARP Broadcasting ② Each VR consumes the private IP address pool
  • 24. 23/58EYWA Confidential MVRRP VR01 NIC#1 eth0 eth1 NIC#2 NIC#1 NIC#2 111.2.1.100 10.0.0.1 VR02 eth0 eth1 111.2.1.101 10.0.0.2 VM01 eth0 NIC#1 10.0.1.1/8 VM02 eth0 NIC#1 10.0.1.2/8 VM03 eth0 NIC#1 10.0.1.3/8 VM04 eth0 NIC#1 10.0.1.4/8 VM05 eth0 NIC#1 10.0.1.5/8 VM06 eth0 NIC#1 10.0.1.6/8 Switch 1 Switch 2 Internet Master for VRID=1 Backup for VRID=2 … … Backup for VRID=254 Backup for VRID=1 Master for VRID=2 … … Backup for VRID=254VRRP VRID=1 IP: 10.0.0.1 MAC: AAAAAAAAAAAA VRRP VRID=2 IP: 10.0.0.2 MAC: BBBBBBBBBBBB … … …. VRRP VRID=254 IP: 10.0.0.254 MAC: XXXXXXXXXXXX ① ② ③ ④ Switch 1 Table MAC Port AAAAAAAAAAAA ① BBBBBBBBBBBB ② Switch 2 Table MAC Port BBBBBBBBBBBB ④ AAAAAAAAAAAA ③
  • 26. 25/58EYWA The EYWA 1. Traffic Flows 2. Advantages 3. The Architecture 4. Demo 5. The Comparison of the new Architectures 6. Summary
  • 27. 26/58EYWA Confidential Traffic Flows on EYWA Tenant 1 VM Tenant 2 VM Tenant-1 Public Traffic (Orphan) Tenant-1 Public Traffic (Normal) Tenant-1 Private Traffic Tenant 1 VR Tenant 2 VRVR-1-1 VR-1-2 VR-2-2 VR-2-1 INTERNET
  • 28. 27/58EYWA Confidential Advantages 1. Public Network ① Load Sharing & Balancing  Load Balancing by Unlimited VRs  Scalable  Load balanced Inbound & Outbound Traffic ② High Availability  Active-Active structure by Unlimited VRs ③ Traffic Engineering  Save of Network Bandwidth  Low latency 2. Private Network ① A large number of tenants  Traffic Isolation by VXLAN (16,777,216) ② Large layer 2 network  VxLAN  Multicast instead of Broadcast (VxLAN)  Decrease in MAC Flooding  Agent  Eliminate Broadcast 3. VM Migration 4. No added Server & H/W
  • 29. 28/58EYWA Confidential The Architecture of EYWA 111.2.3.11 10.0.0.21 10.0.0.22 111.2.3.15 111.2.3.111 111.2.3.112 10.0.0.2 10.0.0.3 10.0.0.21 ... 10.0.0.20 XXX ... 10.0.0.22 10.0.0.23 111.2.3.113 10.0.0.23 111.2.3.13 VR(Virtual Router) VR-{Tenant}-1 VR-{Tenant}-2(~Unlimited) Function NAT, LB, VPN, DHCP NAT, LB, VPN Internet Public-IP for VR Public-IP for VM Tenant-A VLAN Tenant-B VLAN Tenant A Tenant B VR-A-1 VR-A-2 GW: 10.0.0.1 VM VM VM VM VM VM VR-B-1 GW: 10.0.0.1 VR-B-2 GW: 10.0.0.1 VM VM VM GW: 10.0.0.1 111.2.3.13 HA & LB & Scalable X Normal mode Orphan mode
  • 30. 29/58EYWA Confidential The Architecture of EYWA VSe (Common) VR-A-1 111.2.3.11 10.0.0.1/8 VSi A vport-A VM VSe (Common) VSe (Common) Switch (Public Net.) Switch (Private Net.) VR-A-2 111.2.3.12 10.0.0.1/8 VR-B-1 111.2.3.21 10.0.0.1/8 VSi A vport-A VM VSi B vport-B VM vtep-A vtep-A vtep-B vnet0 peth0 vnet0 peth0 vnet0 peth0 eth0 eth1 eth0 eth1 eth0 eth1 vnet1 vnet2 peth1 peth1 VSi A vport-A VM vtep-A Tenant A Tenant B VR-B-2 VSi B vport-B VM eth0 eth1 111.2.3.22 10.0.0.1/8 AgentAgent ControllerAgent Orphan Normal Normal Normal eth0eth0 vnet1 eth0 vnet3 eth0 vnet1 eth0 vnet2 peth1 vtep-B
  • 32. 31/58EYWA Confidential The Comparison of the Virtual Network Architectures Component AWS OpenStack CloudStack EYWA Tenants (Virtual LAN) The number of tenants ? (5 VPC per tenant in a region) 224 = 16,777,216 224 = 16,777,216 224 = 16,777,216 Public Network Outbound Router per tenant One per VPC (Internet GW) 1 (L3 Agent) 1 (RVM) Unlimited (VRs) Router Deployment ? All VRs on a single server All VRs on distributed servers All VRs on distributed servers HA of Router ? Active-Standby Active-Standby High Available LB of Router X X X O SPOF or Bottleneck Internet GW L3 Agent & Network Controller RVM Nothing Inbound LB ELB LBaaS RVM or VPX Unlimited VRs SPOF or Bottleneck ELB(Default Limit 20) Network Node RVM or VPX Nothing Private Network Layer 2 Network Medium Under B-Class Small Private Network Small Private Network Large A-Class 224 = 16,777,216 Router & LB Internet GW & ELB L3 Agent & LBaaS All-in-one (RVM) or added LB(VPX) All-in-one (VRs)
  • 33. 32/58EYWA Confidential Summary 1. Advantages ① Cloud Service providers’ view  A large number of tenants (about 224 = 16,777,216) by using virtual LANs ② Consumers’ view  Public network service per tenant without throughput bottle-neck and SPOF on SNAT/DNAT  Private network (a single large IP subnet) per tenant 2. Architecture ① Scales to support huge data centers with high availability, load balancing and large layer-2 semantics. ② Decentralized scale-out control and data plane. ③ The only component is an agent in every hypervisor host and the agents act as distributed controller. 3. EYWA can be deployed into all the multi-tenant cloud environments today.
  • 35. 34/58EYWA Confidential Inbound Load-Balancing VM Scale-out_EYWA T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#16,777,216 VR#1 … Server#1 Overload
  • 36. 35/58EYWA Confidential Inbound Load-Balancing VM Scale-out_EYWA T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#16,777,216 VR#1 … Server#1 T#1 VM#2 Scale-out
  • 37. 36/58EYWA Confidential Inbound Load-Balancing VM Scale-out_EYWA T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#16,777,216 VR#1 T#2 VM#3 T#2 VM#4 T#16,777,216 VM#2… T#2 VR#2 T#16,777,216 VR#2 … … Server#1 Server#2 T#1 VM#2 Overload Overload
  • 38. 37/58EYWA Confidential Inbound Load-Balancing VM Scale-out_EYWA T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#16,777,216 VR#1 T#1 VM#3 T#2 VM#3 T#2 VM#4 T#16,777,216 VM#2… T#2 VR#2 T#16,777,216 VR#2 … … Server#1 Server#2 T#1 VM#2 Scale-out
  • 39. 38/58EYWA Confidential Inbound Load-Balancing VR Scale-out_EYWA T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#16,777,216 VR#1 T#1 VM#3 T#2 VM#3 T#2 VM#4 T#16,777,216 VM#2… T#2 VR#2 T#16,777,216 VR#2 … … Server#1 Server#2 T#1 VM#2 Overload
  • 40. 39/58EYWA Confidential Inbound Load-Balancing VR Scale-out_EYWA T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#16,777,216 VR#1 T#1 VM#3 T#2 VM#3 T#2 VM#4 T#16,777,216 VM#2… T#2 VR#2 T#16,777,216 VR#2 … … Server#1 Server#2 T#1 VM#2 T#1 VR#2 Scale-out
  • 41. 40/58EYWA Confidential Inbound High-Availability VR Scale-in(or Fail-over)_EYWA T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#16,777,216 VR#1 T#1 VM#3 T#2 VM#3 T#2 VM#4 T#16,777,216 VM#2… T#2 VR#2 T#16,777,216 VR#2 … … Server#1 Server#2 T#1 VM#2 T#1 VR#2
  • 42. 41/58EYWA Confidential Inbound High-Availability VR Scale-in(or Fail-over)_EYWA T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#16,777,216 VR#1 T#1 VM#3 T#2 VM#3 T#2 VM#4 T#16,777,216 VM#2… T#2 VR#2 T#16,777,216 VR#2 … … Server#1 Server#2 T#1 VM#2 T#1 VR#2 XScale-in (Fail)
  • 43. 42/58EYWA Confidential Inbound LB & HA VM Migration(Orphan)_EYWA T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#16,777,216 VR#1 T#1 VM#1 T#2 VM#3 T#2 VM#4 T#16,777,216 VM#2… T#2 VR#2 T#16,777,216 VR#2 … … Server#1 Server#2 T#1 VM#2
  • 44. 43/58EYWA Confidential Inbound LB & HA VM Migration(Orphan)_EYWA T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#16,777,216 VR#1 T#1 VM#1 T#2 VM#3 T#2 VM#4 T#16,777,216 VM#2… T#2 VR#2 T#16,777,216 VR#2 … … Server#1 Server#2 T#1 VM#2
  • 45. 44/58EYWA Confidential Inbound LB & HA VM Migration(Normal)_EYWA T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#16,777,216 VR#1 T#1 VM#1 T#2 VM#3 T#2 VM#4 T#16,777,216 VM#2… T#2 VR#2 T#16,777,216 VR#2 … … Server#1 Server#2 T#1 VM#2 T#1 VR#2 T#1 VM#3
  • 46. 45/58EYWA Confidential Inbound LB & HA VM Migration(Normal)_EYWA T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#16,777,216 VR#1 T#1 VM#1 T#2 VM#3 T#2 VM#4 T#16,777,216 VM#2… T#2 VR#2 T#16,777,216 VR#2 … … Server#1 Server#2 T#1 VM#2 T#1 VR#2 T#1 VM#3
  • 47. 46/58EYWA Confidential Inbound LB & HA VR Limitations_EYWA …T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#1 VM# 16,777 ,213 T#2 VM#1 6,777, 212 T#2 VM#1 6,777, 213 T#16,777,216 VM#16,777,213 T#16,777,216 VR# ∞ … … Server#1 Server#???,??? T#1 VM#2 T#2 VR# ∞
  • 48. 47/58EYWA Confidential Inbound LB & HA Limitations_OpenStack LBaaS …T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VM# 16,777 ,213 T#2 VM#1 6,777, 212 T#2 VM#1 6,777, 213 T#16,777,216 VM#16,777,213 … Network controller Server#???,??? T#1 VM#2 T#1 VR#3 T#1 VR#2 T#1 VR#1 T#16,777,216 VR#2 T#16,777,216 VR#1 T#2 VR#2 T#2 VR#1 N/W Controller Bottleneck
  • 49. 48/58EYWA Confidential Outbound Load-Balancing VR Scale-out_EYWA T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#16,777,216 VR#1 T#1 VM#3 T#2 VM#3 T#2 VM#4 T#16,777,216 VM#2… T#2 VR#2 T#16,777,216 VR#2 … … Server#1 Server#2 T#1 VM#2 Overload10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1
  • 50. 49/58EYWA Confidential Outbound Load-Balancing VR Scale-out_EYWA T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#16,777,216 VR#1 T#1 VM#3 T#2 VM#3 T#2 VM#4 T#16,777,216 VM#2… T#1 VR#2 T#2 VR#2 T#16,777,216 VR#2 … … Server#1 Server#2 T#1 VM#2 Scale-out 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1
  • 51. 50/58EYWA Confidential Outbound High-Availability VR Scale-in(or Fail-over)_EYWA T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#16,777,216 VR#1 T#1 VM#3 T#2 VM#3 T#2 VM#4 T#16,777,216 VM#2… T#1 VR#2 T#2 VR#2 T#16,777,216 VR#2 … … Server#1 Server#2 T#1 VM#2 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1
  • 52. 51/58EYWA Confidential Outbound High-Availability VR Scale-in(or Fail-over)_EYWA T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#16,777,216 VR#1 T#1 VM#3 T#2 VM#3 T#2 VM#4 T#16,777,216 VM#2… T#1 VR#2 T#2 VR#2 T#16,777,216 VR#2 … … Server#1 Server#2 T#1 VM#2 Scale-in (Fail) X10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1
  • 53. 52/58EYWA Confidential Outbound LB & HA VM Migration(Orphan)_EYWA T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#16,777,216 VR#1 T#1 VM#1 T#2 VM#3 T#2 VM#4 T#16,777,216 VM#2… T#2 VR#2 T#16,777,216 VR#2 … … Server#1 Server#2 T#1 VM#2 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1
  • 54. 53/58EYWA Confidential Outbound LB & HA VM Migration(Orphan)_EYWA T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#16,777,216 VR#1 T#1 VM#1 T#2 VM#3 T#2 VM#4 T#16,777,216 VM#2… T#2 VR#2 T#16,777,216 VR#2 … … Server#1 Server#2 T#1 VM#2 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1
  • 55. 54/58EYWA Confidential Outbound LB & HA VM Migration(Normal)_EYWA T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#16,777,216 VR#1 T#1 VM#1 T#2 VM#3 T#2 VM#4 T#16,777,216 VM#2… T#2 VR#2 T#16,777,216 VR#2 … … Server#1 Server#2 T#1 VM#2 T#1 VR#2 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 T#1 VM#3
  • 56. 55/58EYWA Confidential Outbound LB & HA VM Migration(Normal)_EYWA T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#16,777,216 VR#1 T#1 VM#1 T#2 VM#3 T#2 VM#4 T#16,777,216 VM#2… T#2 VR#2 T#16,777,216 VR#2 … … Server#1 Server#2 T#1 VM#2 T#1 VR#2 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 T#1 VM#3
  • 57. 56/58EYWA Confidential Outbound LB & HA VM Migration_OpenStack T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#16,777,216 VR#1 T#1 VM#1 T#2 VM#3 T#2 VM#4 T#16,777,216 VM#2… … Network Controller Server#2 T#1 VM#2 10.0.0.1 10.0.0.1 10.0.0.1 T#1 VM#3 N/W Controller Bottleneck VR Bottleneck Waste of Bandwidth
  • 58. 57/58EYWA Confidential Outbound LB & HA VR Limitations_EYWA T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#1 VM#1 6,777, 213 T#2 VM#1 6,777, 212 T#2 VM#1 6,777, 213 T#16,777,216 VM#16,777,21 3 … T#2 VR# ∞ T#16,777,216 VR# ∞ … … Server#1 Server#???,??? T#1 VM#2 10.0.0.1 10.0.0.1 10.0.0.1 10.0.0.1 …
  • 59. 58/58EYWA Confidential Outbound LB & HA VR Limitations_OpenStack T#1 VM#1 T#2 VM#1 T#2 VM#2 T#16,777,216 VM#1… T#1 VR#1 T#2 VR#1 T#1 VM#1 6,777, 213 T#16,777,216 VM#16,777,21 3 … T#16,777,216 VR#1 … Network Controller Server#???,??? T#1 VM#2 10.0.0.1 10.0.0.1 N/W Controller Bottleneck VR Bottleneck 10.0.0.1 T#2 VM#1 6,777, 212 T#2 VM#1 6,777, 213 Waste of Bandwidth