SlideShare a Scribd company logo
1 of 16
Download to read offline
for Mixed Contention/Cut-Through
Marat Zhanikeev
maratishe@gmail.com
maratishe.github.io
2016/11/18@PN研@KDDI研
The Switchboard
PDF: bit.do/161118
Traffic Engineering Problem
#STEP
#TE #TrafficEngineering
#OSPF
#cut-through
#contention
#SDNOutput Channels
.
Commutators are Back (as robots)
• all the technology is already there, we just need to start using it
• basically, switching robotics
◦ this paper proposed the Switchboard Traffic Engineering Problem
(STEP)
Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 2/16
...
2/16
.
Cut-Through Mode as Basis for STEP
C: Cut Through
Check,
etc. Q: Queue
D: Drop
QoS
classes
Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 3/16
...
3/16
.
STEP (1)
• each outgoing port gets multiple slots, i.e. the n-by-m switchboard
• can be implemented as multiple ethernet ports, fiber wavelengths, etc.
A switch
4-port
switchPhysical Logical Switchboard
n×m
switching
matrix
xth port,
y slots n ports
m slots
Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 4/16
...
4/16
.
STEP (2) The Weight Setting Problem
• 1st element: weights per slot, the same way as in the OSPF problem
• 2nd element: migrations of some slots to other outgoing ports
Switchboard
n×m
switching
matrix
n ports
m slots
Occupied/used slot
Empty slot
Migration
(1:3 to 3:2)
w11 w21
wnm
wn1…
…
…
Weight setting
Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 5/16
...
5/16
.
Formulations (1) OSPF Cases
• unit demand as source s, destination d, volume v, time t, and sometimes optical
wavelength λ, can be written as Ti = ⟨s, d, v, t⟩
• traditional/OSPF : Ti = ⟨s, d, v⟩ → ⟨s, a, b, ..., d⟩
• optimal w/out switching : Ti = ⟨s, d, v⟩ → ⟨s, λ⟩
• optical with switching : Ti = ⟨s, d, v⟩ → ⟨s, λs, λa, λb, ...⟩
• e2e circuits : Ti = ⟨s, d, v, t1, t2⟩ → ⟨s, λ, t⟩
Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 6/16
...
6/16
.
Formulations (2) The STEP Problem
• M load spread across n outgoing ports, each with m slots (n-by-m switchboard)
◦ unit of load is flowsize vi
• load aggregated per slot xy : Lxy = max
{
vi
}
xy
, i ∈ xy
• fitness of the slot xy : Fxy = wxyLxy
• aggregate slots into ports as potential : Px =
∑ {Fj
Vj
}
y
, j ∈ x
• optimize (w/out migrations) : minimize max
{
P
}
x
subject of x ≤ n
• optimize (with migrations) : minimize a · max
{
P
}
x
+ (1 − a) ·
∑
i∈m Ci
◦ .... subject of x ≤ n, a ≤ 1, m ≤ Q.
Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 7/16
...
7/16
.
Experiment (1) Setup
0 20 40 60 80 100
Decreasing order
0
0.35
0.7
1.05
1.4
1.75
2.1
2.45
2.8
log(value)
Class A
Class B
Class C
Class D
Class E • hotspot distributions for
picking weights -- same as
in OSPF, (i.e. large flows repel other flows)
• use WIDE packet traces for
real packets/flows
• otherwise, the same as in
OSPF -- just optimize the
weights
Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 8/16
...
8/16
.
Experiment (2) Results
0 1 2 3 4 5 6
X (port) + Y (slot) coordinate
9560
9600
9640
9680
9720
9760
9800
Loadindex(logofhotspot)
1
1
1
2
2
2
3
3
3
4
4
4
5
5
5
1
1
1
2 2
2
3
3
3
4
4
4
5
5
5
Method : real
0 1 2 3 4 5 6
X (port) + Y (slot) coordinate
9560
9600
9640
9680
9720
9760
9800
Loadindex(logofhotspot)
1
1
1
1
1
2
2
2
3
3
3
4
4
4
51
1
1
2
2
2
3
3
3
3
34
4
4
5
Method : optimal
Hotspot class : D
• real = based on real traces and not
optimized
• optimal is the optimized version of
the switchboard
• visual effect: STEP spreads the
traffic across ports
Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 9/16
...
9/16
.
Experiment (3) Layouts (good)
0 2 4 6 8 10 12 14
Decreasing order
0
2
4
6
8
10
log(1+fitness)
before
before#10.6
hotclass#E
migrations#5
10.4
0
2.5
10
10.5
3.1
0
0
10.6
10.4
0
3.1
9.9
10.1
7.8
before
0 5 10 15 20 25
Decreasing order
0
2
4
6
8
10
log(1+fitness)
after
after#10.6 (diff#-0.1)
hotclass#E
migrations#5
10.4
0
2.5
0
10
0
0
3.1
0
10.4
0
0
10.6
0
0
0
0
0
0
10.5
9.9
10.1
7.8
0
3.1
after
Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 10/16
...
10/16
.
Experiment (4) Layouts (bad)
0 2 4 6 8 10 12 14
Decreasing order
0
2
4
6
8
10
log(1+fitness)
before
before#10.7
6.2
10
6.7
8.6
9.3
9.3
9.8
0
5.7
0
0
10.7
0
0
9.8
before
0 5 10 15 20 25
Decreasing order
0
2
4
6
8
10
log(1+fitness)
after
after#10.7 (diff#0)
6.2
10
6.7
0
0
8.6
9.3
9.3
0
0
0
0
5.7
0
0
0
0
10.7
0
0
0
0
9.8
9.8
0
after
Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 11/16
...
11/16
.
Summary
• cut-through circuits are possible even under a large number of flows
• will work with 2+ independent outgoing ports
• future steps: actually build a switching robot
Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 12/16
...
12/16
.
That’s all, thank you ...
Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 13/16
...
13/16
.
STEP is NOT a scheduling problem
Line=
outgoing
port
Overhead =
contention
No. of flows
Line=
outgoing
port
Overhead
Scheduling
Traditional
Circuits
Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 14/16
...
14/16
.
Future NOC...
• ... will manage a pool of packet and circuit ports
NOC
Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 15/16
...
15/16
.
STEP in the Hotspot Context
• version 1: map all heavy hitter flows as circuits
• version 2: offer a paid service that some of the bulk transfer services can
use
eziswolF
Decreasing flow size
TopN
parameter
In Out
Switch
Circuits
Packets
Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 16/16
...
16/16

More Related Content

Similar to The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels

Delay Calculation in CMOS Chips Using Logical Effort by Prof. Akhil Masurkar
Delay Calculation in CMOS Chips Using Logical Effort by Prof. Akhil MasurkarDelay Calculation in CMOS Chips Using Logical Effort by Prof. Akhil Masurkar
Delay Calculation in CMOS Chips Using Logical Effort by Prof. Akhil MasurkarAkhil Masurkar
 
The Next Generation of Networks is all about Hotspot Distributions and Cut-Th...
The Next Generation of Networks is all about Hotspot Distributions and Cut-Th...The Next Generation of Networks is all about Hotspot Distributions and Cut-Th...
The Next Generation of Networks is all about Hotspot Distributions and Cut-Th...Tokyo University of Science
 
Complexity Resolution Control for Context Based on Metromaps
Complexity Resolution Control for Context Based on MetromapsComplexity Resolution Control for Context Based on Metromaps
Complexity Resolution Control for Context Based on MetromapsTokyo University of Science
 
Cisco systems hacking layer 2 ethernet switches
Cisco systems   hacking layer 2 ethernet switchesCisco systems   hacking layer 2 ethernet switches
Cisco systems hacking layer 2 ethernet switchesKJ Savaliya
 
Hacking Layer 2 - Enthernet Switcher Hacking Countermeasures.
Hacking Layer 2 - Enthernet Switcher Hacking Countermeasures.Hacking Layer 2 - Enthernet Switcher Hacking Countermeasures.
Hacking Layer 2 - Enthernet Switcher Hacking Countermeasures.Sumutiu Marius
 
tau 2015 spyrou fpga timing
tau 2015 spyrou fpga timingtau 2015 spyrou fpga timing
tau 2015 spyrou fpga timingTom Spyrou
 
CMOS Topic 6 -_designing_combinational_logic_circuits
CMOS Topic 6 -_designing_combinational_logic_circuitsCMOS Topic 6 -_designing_combinational_logic_circuits
CMOS Topic 6 -_designing_combinational_logic_circuitsIkhwan_Fakrudin
 
Ch 02 --- sdn and openflow architecture
Ch 02 --- sdn and openflow architectureCh 02 --- sdn and openflow architecture
Ch 02 --- sdn and openflow architectureYoram Orzach
 
Circuit Emulation for Bulk Transfers in Distributed Storage and Clouds
Circuit Emulation for Bulk Transfers in Distributed Storage and CloudsCircuit Emulation for Bulk Transfers in Distributed Storage and Clouds
Circuit Emulation for Bulk Transfers in Distributed Storage and CloudsTokyo University of Science
 
On a Hybrid Packets-and-Circuits Switching Logic
On a Hybrid Packets-and-Circuits Switching LogicOn a Hybrid Packets-and-Circuits Switching Logic
On a Hybrid Packets-and-Circuits Switching LogicTokyo University of Science
 
Can We Emulate Local Circuit Switching in Cloud Storage?
Can We Emulate Local Circuit Switching in Cloud Storage?Can We Emulate Local Circuit Switching in Cloud Storage?
Can We Emulate Local Circuit Switching in Cloud Storage?Tokyo University of Science
 
A Simple Communication System Design Lab #4 with MATLAB Simulink
A Simple Communication System Design Lab #4 with MATLAB SimulinkA Simple Communication System Design Lab #4 with MATLAB Simulink
A Simple Communication System Design Lab #4 with MATLAB SimulinkJaewook. Kang
 
Pushing the limits of Controller Area Network (CAN)
Pushing the limits of Controller Area Network (CAN)Pushing the limits of Controller Area Network (CAN)
Pushing the limits of Controller Area Network (CAN)RealTime-at-Work (RTaW)
 
A City Traffic Model for Optical Circuit Switching in Data Centers
A City Traffic Model for Optical Circuit Switching in Data CentersA City Traffic Model for Optical Circuit Switching in Data Centers
A City Traffic Model for Optical Circuit Switching in Data CentersTokyo University of Science
 
Megamodeling of Complex, Distributed, Heterogeneous CPS Systems
Megamodeling of Complex, Distributed, Heterogeneous CPS SystemsMegamodeling of Complex, Distributed, Heterogeneous CPS Systems
Megamodeling of Complex, Distributed, Heterogeneous CPS SystemsEugenio Villar
 
ACM DEBS Grand Challenge: Continuous Analytics on Geospatial Data Streams wit...
ACM DEBS Grand Challenge: Continuous Analytics on Geospatial Data Streams wit...ACM DEBS Grand Challenge: Continuous Analytics on Geospatial Data Streams wit...
ACM DEBS Grand Challenge: Continuous Analytics on Geospatial Data Streams wit...Srinath Perera
 

Similar to The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels (20)

Delay Calculation in CMOS Chips Using Logical Effort by Prof. Akhil Masurkar
Delay Calculation in CMOS Chips Using Logical Effort by Prof. Akhil MasurkarDelay Calculation in CMOS Chips Using Logical Effort by Prof. Akhil Masurkar
Delay Calculation in CMOS Chips Using Logical Effort by Prof. Akhil Masurkar
 
The Next Generation of Networks is all about Hotspot Distributions and Cut-Th...
The Next Generation of Networks is all about Hotspot Distributions and Cut-Th...The Next Generation of Networks is all about Hotspot Distributions and Cut-Th...
The Next Generation of Networks is all about Hotspot Distributions and Cut-Th...
 
Complexity Resolution Control for Context Based on Metromaps
Complexity Resolution Control for Context Based on MetromapsComplexity Resolution Control for Context Based on Metromaps
Complexity Resolution Control for Context Based on Metromaps
 
Cisco systems hacking layer 2 ethernet switches
Cisco systems   hacking layer 2 ethernet switchesCisco systems   hacking layer 2 ethernet switches
Cisco systems hacking layer 2 ethernet switches
 
Hacking Layer 2 - Enthernet Switcher Hacking Countermeasures.
Hacking Layer 2 - Enthernet Switcher Hacking Countermeasures.Hacking Layer 2 - Enthernet Switcher Hacking Countermeasures.
Hacking Layer 2 - Enthernet Switcher Hacking Countermeasures.
 
CS4961-L9.ppt
CS4961-L9.pptCS4961-L9.ppt
CS4961-L9.ppt
 
tau 2015 spyrou fpga timing
tau 2015 spyrou fpga timingtau 2015 spyrou fpga timing
tau 2015 spyrou fpga timing
 
CMOS Topic 6 -_designing_combinational_logic_circuits
CMOS Topic 6 -_designing_combinational_logic_circuitsCMOS Topic 6 -_designing_combinational_logic_circuits
CMOS Topic 6 -_designing_combinational_logic_circuits
 
Ch 02 --- sdn and openflow architecture
Ch 02 --- sdn and openflow architectureCh 02 --- sdn and openflow architecture
Ch 02 --- sdn and openflow architecture
 
Circuit Emulation for Bulk Transfers in Distributed Storage and Clouds
Circuit Emulation for Bulk Transfers in Distributed Storage and CloudsCircuit Emulation for Bulk Transfers in Distributed Storage and Clouds
Circuit Emulation for Bulk Transfers in Distributed Storage and Clouds
 
lect501.ppt
lect501.pptlect501.ppt
lect501.ppt
 
On a Hybrid Packets-and-Circuits Switching Logic
On a Hybrid Packets-and-Circuits Switching LogicOn a Hybrid Packets-and-Circuits Switching Logic
On a Hybrid Packets-and-Circuits Switching Logic
 
Can We Emulate Local Circuit Switching in Cloud Storage?
Can We Emulate Local Circuit Switching in Cloud Storage?Can We Emulate Local Circuit Switching in Cloud Storage?
Can We Emulate Local Circuit Switching in Cloud Storage?
 
A Simple Communication System Design Lab #4 with MATLAB Simulink
A Simple Communication System Design Lab #4 with MATLAB SimulinkA Simple Communication System Design Lab #4 with MATLAB Simulink
A Simple Communication System Design Lab #4 with MATLAB Simulink
 
Pushing the limits of Controller Area Network (CAN)
Pushing the limits of Controller Area Network (CAN)Pushing the limits of Controller Area Network (CAN)
Pushing the limits of Controller Area Network (CAN)
 
lec23Concl.ppt
lec23Concl.pptlec23Concl.ppt
lec23Concl.ppt
 
A City Traffic Model for Optical Circuit Switching in Data Centers
A City Traffic Model for Optical Circuit Switching in Data CentersA City Traffic Model for Optical Circuit Switching in Data Centers
A City Traffic Model for Optical Circuit Switching in Data Centers
 
Megamodeling of Complex, Distributed, Heterogeneous CPS Systems
Megamodeling of Complex, Distributed, Heterogeneous CPS SystemsMegamodeling of Complex, Distributed, Heterogeneous CPS Systems
Megamodeling of Complex, Distributed, Heterogeneous CPS Systems
 
ACM DEBS Grand Challenge: Continuous Analytics on Geospatial Data Streams wit...
ACM DEBS Grand Challenge: Continuous Analytics on Geospatial Data Streams wit...ACM DEBS Grand Challenge: Continuous Analytics on Geospatial Data Streams wit...
ACM DEBS Grand Challenge: Continuous Analytics on Geospatial Data Streams wit...
 
Csp scala wixmeetup2016
Csp scala wixmeetup2016Csp scala wixmeetup2016
Csp scala wixmeetup2016
 

More from Tokyo University of Science

A Method for Cloud-Assisted Secure Wireless Grouping of Client Devices at Net...
A Method for Cloud-Assisted Secure Wireless Grouping of Client Devices at Net...A Method for Cloud-Assisted Secure Wireless Grouping of Client Devices at Net...
A Method for Cloud-Assisted Secure Wireless Grouping of Client Devices at Net...Tokyo University of Science
 
Ultrasound Relative Positioning for IoT Devices in Dense Wireless Spaces
Ultrasound Relative Positioning for IoT Devices in Dense Wireless SpacesUltrasound Relative Positioning for IoT Devices in Dense Wireless Spaces
Ultrasound Relative Positioning for IoT Devices in Dense Wireless SpacesTokyo University of Science
 
Towards a Packet Traffic Genome Project as a Method for Realtime Sub-Flow Tra...
Towards a Packet Traffic Genome Project as a Method for Realtime Sub-Flow Tra...Towards a Packet Traffic Genome Project as a Method for Realtime Sub-Flow Tra...
Towards a Packet Traffic Genome Project as a Method for Realtime Sub-Flow Tra...Tokyo University of Science
 
What if We Atomize Student Data and Apps and Put Them on Docker Containers?
What if We Atomize Student Data and Apps and Put Them on Docker Containers?What if We Atomize Student Data and Apps and Put Them on Docker Containers?
What if We Atomize Student Data and Apps and Put Them on Docker Containers?Tokyo University of Science
 
Large-Scale Crowdsourcing by Vehicular Data Packets in a Sparse Roadside Infr...
Large-Scale Crowdsourcing by Vehicular Data Packets in a Sparse Roadside Infr...Large-Scale Crowdsourcing by Vehicular Data Packets in a Sparse Roadside Infr...
Large-Scale Crowdsourcing by Vehicular Data Packets in a Sparse Roadside Infr...Tokyo University of Science
 
On Performance Under Hotspots in Hadoop versus Bigdata Replay Platforms
On Performance Under Hotspots in Hadoop versus Bigdata Replay PlatformsOn Performance Under Hotspots in Hadoop versus Bigdata Replay Platforms
On Performance Under Hotspots in Hadoop versus Bigdata Replay PlatformsTokyo University of Science
 
Taking the Step from Software to Product Development \\ when teaching PBL at ...
Taking the Step from Software to Product Development \\ when teaching PBL at ...Taking the Step from Software to Product Development \\ when teaching PBL at ...
Taking the Step from Software to Product Development \\ when teaching PBL at ...Tokyo University of Science
 
Design and Implementation of a 3-Party Cloud-Backed Handshake for Secure Grou...
Design and Implementation of a 3-Party Cloud-Backed Handshake for Secure Grou...Design and Implementation of a 3-Party Cloud-Backed Handshake for Secure Grou...
Design and Implementation of a 3-Party Cloud-Backed Handshake for Secure Grou...Tokyo University of Science
 
The Switchboard Optimization Problem and Heuristics for Cut-Through Networking
The Switchboard Optimization Problem and Heuristics for Cut-Through NetworkingThe Switchboard Optimization Problem and Heuristics for Cut-Through Networking
The Switchboard Optimization Problem and Heuristics for Cut-Through NetworkingTokyo University of Science
 
Bulk-n-Pick Method for One-to-Many Data Transfer in Dense Wireless Spaces
Bulk-n-Pick Method for One-to-Many Data Transfer in Dense Wireless SpacesBulk-n-Pick Method for One-to-Many Data Transfer in Dense Wireless Spaces
Bulk-n-Pick Method for One-to-Many Data Transfer in Dense Wireless SpacesTokyo University of Science
 
Fog Cloud Caching at Network Edge via Local Hardware Awareness Spaces
Fog Cloud Caching at Network Edge via Local Hardware Awareness SpacesFog Cloud Caching at Network Edge via Local Hardware Awareness Spaces
Fog Cloud Caching at Network Edge via Local Hardware Awareness SpacesTokyo University of Science
 
Image-Related Uses for Roadside Infrastructure \\ based on Wireless Beacons
Image-Related Uses for Roadside Infrastructure \\ based on Wireless BeaconsImage-Related Uses for Roadside Infrastructure \\ based on Wireless Beacons
Image-Related Uses for Roadside Infrastructure \\ based on Wireless BeaconsTokyo University of Science
 
The Declarative-Coordinated Model for Self-Optimization of Service Networks
The Declarative-Coordinated Model for Self-Optimization of Service NetworksThe Declarative-Coordinated Model for Self-Optimization of Service Networks
The Declarative-Coordinated Model for Self-Optimization of Service NetworksTokyo University of Science
 
3-Way Scripts as a Practical Platform for Secure Distributed Code in Clouds
3-Way Scripts as a Practical Platform for Secure Distributed Code in Clouds3-Way Scripts as a Practical Platform for Secure Distributed Code in Clouds
3-Way Scripts as a Practical Platform for Secure Distributed Code in CloudsTokyo University of Science
 
3-Way Scripts as a Base Unit for Flexible Scale-Out Code
3-Way Scripts as a Base Unit for Flexible Scale-Out Code3-Way Scripts as a Base Unit for Flexible Scale-Out Code
3-Way Scripts as a Base Unit for Flexible Scale-Out CodeTokyo University of Science
 
Towards Social Robotics on Smartphones with Simple XYZV Sensor Feedback
Towards Social Robotics on Smartphones with Simple XYZV Sensor FeedbackTowards Social Robotics on Smartphones with Simple XYZV Sensor Feedback
Towards Social Robotics on Smartphones with Simple XYZV Sensor FeedbackTokyo University of Science
 
Back to Rings but not Tokens: Physical and Logical Designs for Distributed Fi...
Back to Rings but not Tokens: Physical and Logical Designs for Distributed Fi...Back to Rings but not Tokens: Physical and Logical Designs for Distributed Fi...
Back to Rings but not Tokens: Physical and Logical Designs for Distributed Fi...Tokyo University of Science
 
Browser Visualization using PNGs Generated by HTML5 Workers on Multicore
Browser Visualization using PNGs Generated by HTML5 Workers on MulticoreBrowser Visualization using PNGs Generated by HTML5 Workers on Multicore
Browser Visualization using PNGs Generated by HTML5 Workers on MulticoreTokyo University of Science
 
Population Management in Clouds is a Do-It-Yourself Technology
Population Management in Clouds is a Do-It-Yourself TechnologyPopulation Management in Clouds is a Do-It-Yourself Technology
Population Management in Clouds is a Do-It-Yourself TechnologyTokyo University of Science
 
Irregularity Countermeasures in Massively Parallel BigData Processors
Irregularity Countermeasures in Massively Parallel BigData ProcessorsIrregularity Countermeasures in Massively Parallel BigData Processors
Irregularity Countermeasures in Massively Parallel BigData ProcessorsTokyo University of Science
 

More from Tokyo University of Science (20)

A Method for Cloud-Assisted Secure Wireless Grouping of Client Devices at Net...
A Method for Cloud-Assisted Secure Wireless Grouping of Client Devices at Net...A Method for Cloud-Assisted Secure Wireless Grouping of Client Devices at Net...
A Method for Cloud-Assisted Secure Wireless Grouping of Client Devices at Net...
 
Ultrasound Relative Positioning for IoT Devices in Dense Wireless Spaces
Ultrasound Relative Positioning for IoT Devices in Dense Wireless SpacesUltrasound Relative Positioning for IoT Devices in Dense Wireless Spaces
Ultrasound Relative Positioning for IoT Devices in Dense Wireless Spaces
 
Towards a Packet Traffic Genome Project as a Method for Realtime Sub-Flow Tra...
Towards a Packet Traffic Genome Project as a Method for Realtime Sub-Flow Tra...Towards a Packet Traffic Genome Project as a Method for Realtime Sub-Flow Tra...
Towards a Packet Traffic Genome Project as a Method for Realtime Sub-Flow Tra...
 
What if We Atomize Student Data and Apps and Put Them on Docker Containers?
What if We Atomize Student Data and Apps and Put Them on Docker Containers?What if We Atomize Student Data and Apps and Put Them on Docker Containers?
What if We Atomize Student Data and Apps and Put Them on Docker Containers?
 
Large-Scale Crowdsourcing by Vehicular Data Packets in a Sparse Roadside Infr...
Large-Scale Crowdsourcing by Vehicular Data Packets in a Sparse Roadside Infr...Large-Scale Crowdsourcing by Vehicular Data Packets in a Sparse Roadside Infr...
Large-Scale Crowdsourcing by Vehicular Data Packets in a Sparse Roadside Infr...
 
On Performance Under Hotspots in Hadoop versus Bigdata Replay Platforms
On Performance Under Hotspots in Hadoop versus Bigdata Replay PlatformsOn Performance Under Hotspots in Hadoop versus Bigdata Replay Platforms
On Performance Under Hotspots in Hadoop versus Bigdata Replay Platforms
 
Taking the Step from Software to Product Development \\ when teaching PBL at ...
Taking the Step from Software to Product Development \\ when teaching PBL at ...Taking the Step from Software to Product Development \\ when teaching PBL at ...
Taking the Step from Software to Product Development \\ when teaching PBL at ...
 
Design and Implementation of a 3-Party Cloud-Backed Handshake for Secure Grou...
Design and Implementation of a 3-Party Cloud-Backed Handshake for Secure Grou...Design and Implementation of a 3-Party Cloud-Backed Handshake for Secure Grou...
Design and Implementation of a 3-Party Cloud-Backed Handshake for Secure Grou...
 
The Switchboard Optimization Problem and Heuristics for Cut-Through Networking
The Switchboard Optimization Problem and Heuristics for Cut-Through NetworkingThe Switchboard Optimization Problem and Heuristics for Cut-Through Networking
The Switchboard Optimization Problem and Heuristics for Cut-Through Networking
 
Bulk-n-Pick Method for One-to-Many Data Transfer in Dense Wireless Spaces
Bulk-n-Pick Method for One-to-Many Data Transfer in Dense Wireless SpacesBulk-n-Pick Method for One-to-Many Data Transfer in Dense Wireless Spaces
Bulk-n-Pick Method for One-to-Many Data Transfer in Dense Wireless Spaces
 
Fog Cloud Caching at Network Edge via Local Hardware Awareness Spaces
Fog Cloud Caching at Network Edge via Local Hardware Awareness SpacesFog Cloud Caching at Network Edge via Local Hardware Awareness Spaces
Fog Cloud Caching at Network Edge via Local Hardware Awareness Spaces
 
Image-Related Uses for Roadside Infrastructure \\ based on Wireless Beacons
Image-Related Uses for Roadside Infrastructure \\ based on Wireless BeaconsImage-Related Uses for Roadside Infrastructure \\ based on Wireless Beacons
Image-Related Uses for Roadside Infrastructure \\ based on Wireless Beacons
 
The Declarative-Coordinated Model for Self-Optimization of Service Networks
The Declarative-Coordinated Model for Self-Optimization of Service NetworksThe Declarative-Coordinated Model for Self-Optimization of Service Networks
The Declarative-Coordinated Model for Self-Optimization of Service Networks
 
3-Way Scripts as a Practical Platform for Secure Distributed Code in Clouds
3-Way Scripts as a Practical Platform for Secure Distributed Code in Clouds3-Way Scripts as a Practical Platform for Secure Distributed Code in Clouds
3-Way Scripts as a Practical Platform for Secure Distributed Code in Clouds
 
3-Way Scripts as a Base Unit for Flexible Scale-Out Code
3-Way Scripts as a Base Unit for Flexible Scale-Out Code3-Way Scripts as a Base Unit for Flexible Scale-Out Code
3-Way Scripts as a Base Unit for Flexible Scale-Out Code
 
Towards Social Robotics on Smartphones with Simple XYZV Sensor Feedback
Towards Social Robotics on Smartphones with Simple XYZV Sensor FeedbackTowards Social Robotics on Smartphones with Simple XYZV Sensor Feedback
Towards Social Robotics on Smartphones with Simple XYZV Sensor Feedback
 
Back to Rings but not Tokens: Physical and Logical Designs for Distributed Fi...
Back to Rings but not Tokens: Physical and Logical Designs for Distributed Fi...Back to Rings but not Tokens: Physical and Logical Designs for Distributed Fi...
Back to Rings but not Tokens: Physical and Logical Designs for Distributed Fi...
 
Browser Visualization using PNGs Generated by HTML5 Workers on Multicore
Browser Visualization using PNGs Generated by HTML5 Workers on MulticoreBrowser Visualization using PNGs Generated by HTML5 Workers on Multicore
Browser Visualization using PNGs Generated by HTML5 Workers on Multicore
 
Population Management in Clouds is a Do-It-Yourself Technology
Population Management in Clouds is a Do-It-Yourself TechnologyPopulation Management in Clouds is a Do-It-Yourself Technology
Population Management in Clouds is a Do-It-Yourself Technology
 
Irregularity Countermeasures in Massively Parallel BigData Processors
Irregularity Countermeasures in Massively Parallel BigData ProcessorsIrregularity Countermeasures in Massively Parallel BigData Processors
Irregularity Countermeasures in Massively Parallel BigData Processors
 

Recently uploaded

Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native ApplicationsWSO2
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdflior mazor
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MIND CTI
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...DianaGray10
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProduct Anonymous
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...apidays
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Jeffrey Haguewood
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)wesley chun
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CVKhem
 
AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024The Digital Insurer
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyKhushali Kathiriya
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century educationjfdjdjcjdnsjd
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FMESafe Software
 
Ransomware_Q4_2023. The report. [EN].pdf
Ransomware_Q4_2023. The report. [EN].pdfRansomware_Q4_2023. The report. [EN].pdf
Ransomware_Q4_2023. The report. [EN].pdfOverkill Security
 
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
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processorsdebabhi2
 
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu SubbuApidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbuapidays
 
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
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?Igalia
 

Recently uploaded (20)

Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
 
AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
Ransomware_Q4_2023. The report. [EN].pdf
Ransomware_Q4_2023. The report. [EN].pdfRansomware_Q4_2023. The report. [EN].pdf
Ransomware_Q4_2023. The report. [EN].pdf
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu SubbuApidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
 
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
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
 

The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels

  • 1. for Mixed Contention/Cut-Through Marat Zhanikeev maratishe@gmail.com maratishe.github.io 2016/11/18@PN研@KDDI研 The Switchboard PDF: bit.do/161118 Traffic Engineering Problem #STEP #TE #TrafficEngineering #OSPF #cut-through #contention #SDNOutput Channels
  • 2. . Commutators are Back (as robots) • all the technology is already there, we just need to start using it • basically, switching robotics ◦ this paper proposed the Switchboard Traffic Engineering Problem (STEP) Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 2/16 ... 2/16
  • 3. . Cut-Through Mode as Basis for STEP C: Cut Through Check, etc. Q: Queue D: Drop QoS classes Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 3/16 ... 3/16
  • 4. . STEP (1) • each outgoing port gets multiple slots, i.e. the n-by-m switchboard • can be implemented as multiple ethernet ports, fiber wavelengths, etc. A switch 4-port switchPhysical Logical Switchboard n×m switching matrix xth port, y slots n ports m slots Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 4/16 ... 4/16
  • 5. . STEP (2) The Weight Setting Problem • 1st element: weights per slot, the same way as in the OSPF problem • 2nd element: migrations of some slots to other outgoing ports Switchboard n×m switching matrix n ports m slots Occupied/used slot Empty slot Migration (1:3 to 3:2) w11 w21 wnm wn1… … … Weight setting Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 5/16 ... 5/16
  • 6. . Formulations (1) OSPF Cases • unit demand as source s, destination d, volume v, time t, and sometimes optical wavelength λ, can be written as Ti = ⟨s, d, v, t⟩ • traditional/OSPF : Ti = ⟨s, d, v⟩ → ⟨s, a, b, ..., d⟩ • optimal w/out switching : Ti = ⟨s, d, v⟩ → ⟨s, λ⟩ • optical with switching : Ti = ⟨s, d, v⟩ → ⟨s, λs, λa, λb, ...⟩ • e2e circuits : Ti = ⟨s, d, v, t1, t2⟩ → ⟨s, λ, t⟩ Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 6/16 ... 6/16
  • 7. . Formulations (2) The STEP Problem • M load spread across n outgoing ports, each with m slots (n-by-m switchboard) ◦ unit of load is flowsize vi • load aggregated per slot xy : Lxy = max { vi } xy , i ∈ xy • fitness of the slot xy : Fxy = wxyLxy • aggregate slots into ports as potential : Px = ∑ {Fj Vj } y , j ∈ x • optimize (w/out migrations) : minimize max { P } x subject of x ≤ n • optimize (with migrations) : minimize a · max { P } x + (1 − a) · ∑ i∈m Ci ◦ .... subject of x ≤ n, a ≤ 1, m ≤ Q. Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 7/16 ... 7/16
  • 8. . Experiment (1) Setup 0 20 40 60 80 100 Decreasing order 0 0.35 0.7 1.05 1.4 1.75 2.1 2.45 2.8 log(value) Class A Class B Class C Class D Class E • hotspot distributions for picking weights -- same as in OSPF, (i.e. large flows repel other flows) • use WIDE packet traces for real packets/flows • otherwise, the same as in OSPF -- just optimize the weights Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 8/16 ... 8/16
  • 9. . Experiment (2) Results 0 1 2 3 4 5 6 X (port) + Y (slot) coordinate 9560 9600 9640 9680 9720 9760 9800 Loadindex(logofhotspot) 1 1 1 2 2 2 3 3 3 4 4 4 5 5 5 1 1 1 2 2 2 3 3 3 4 4 4 5 5 5 Method : real 0 1 2 3 4 5 6 X (port) + Y (slot) coordinate 9560 9600 9640 9680 9720 9760 9800 Loadindex(logofhotspot) 1 1 1 1 1 2 2 2 3 3 3 4 4 4 51 1 1 2 2 2 3 3 3 3 34 4 4 5 Method : optimal Hotspot class : D • real = based on real traces and not optimized • optimal is the optimized version of the switchboard • visual effect: STEP spreads the traffic across ports Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 9/16 ... 9/16
  • 10. . Experiment (3) Layouts (good) 0 2 4 6 8 10 12 14 Decreasing order 0 2 4 6 8 10 log(1+fitness) before before#10.6 hotclass#E migrations#5 10.4 0 2.5 10 10.5 3.1 0 0 10.6 10.4 0 3.1 9.9 10.1 7.8 before 0 5 10 15 20 25 Decreasing order 0 2 4 6 8 10 log(1+fitness) after after#10.6 (diff#-0.1) hotclass#E migrations#5 10.4 0 2.5 0 10 0 0 3.1 0 10.4 0 0 10.6 0 0 0 0 0 0 10.5 9.9 10.1 7.8 0 3.1 after Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 10/16 ... 10/16
  • 11. . Experiment (4) Layouts (bad) 0 2 4 6 8 10 12 14 Decreasing order 0 2 4 6 8 10 log(1+fitness) before before#10.7 6.2 10 6.7 8.6 9.3 9.3 9.8 0 5.7 0 0 10.7 0 0 9.8 before 0 5 10 15 20 25 Decreasing order 0 2 4 6 8 10 log(1+fitness) after after#10.7 (diff#0) 6.2 10 6.7 0 0 8.6 9.3 9.3 0 0 0 0 5.7 0 0 0 0 10.7 0 0 0 0 9.8 9.8 0 after Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 11/16 ... 11/16
  • 12. . Summary • cut-through circuits are possible even under a large number of flows • will work with 2+ independent outgoing ports • future steps: actually build a switching robot Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 12/16 ... 12/16
  • 13. . That’s all, thank you ... Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 13/16 ... 13/16
  • 14. . STEP is NOT a scheduling problem Line= outgoing port Overhead = contention No. of flows Line= outgoing port Overhead Scheduling Traditional Circuits Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 14/16 ... 14/16
  • 15. . Future NOC... • ... will manage a pool of packet and circuit ports NOC Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 15/16 ... 15/16
  • 16. . STEP in the Hotspot Context • version 1: map all heavy hitter flows as circuits • version 2: offer a paid service that some of the bulk transfer services can use eziswolF Decreasing flow size TopN parameter In Out Switch Circuits Packets Marat Zhanikeev -- maratishe@gmail.com The Switchboard Traffic Engineering Problem for Mixed Contention/Cut-Through Output Channels 16/16 ... 16/16