Upload
doanque
View
225
Download
0
Embed Size (px)
Citation preview
SCDA: Efficient SLA-aware Cloud DatacenterArchitecture
Debish Fesehaye 1 and Klara Nahrstedt 2
1 Neustar Technology Foundry,Neustar Inc.
2 Dept. of Computer Science,University of Illinois at Urbana-Champaign
IEEE Cloud 2014, Anchorage, Alaska
Debish & Klara SLA-aware Cloud Datacenter Architecture 1/ 1
Introduction and Motivation
Exponential growth of online content
Expected to grow 40-45% a year*
Content users have diverse QoS requerements
Diverse service level agreemenent (SLA)
Network and server loads are very dynamic
Limited resource capacities (link bandwidth, server storage,processing, energy)
*Craig Labovitz: http: // www. monkey. org/ ~ labovit/ papers/ gpf_ 2011. pdf
Debish & Klara SLA-aware Cloud Datacenter Architecture 2/ 1
Introduction and Motivation
Exponential growth of online content
Expected to grow 40-45% a year*
Content users have diverse QoS requerements
Diverse service level agreemenent (SLA)
Network and server loads are very dynamic
Limited resource capacities (link bandwidth, server storage,processing, energy)
*Craig Labovitz: http: // www. monkey. org/ ~ labovit/ papers/ gpf_ 2011. pdf
Consequences
Many challenges on how to deal with traffic congestion & routing.
Debish & Klara SLA-aware Cloud Datacenter Architecture 2/ 1
Challenges: Cloud Datacenter Networks
Problems:
Where to store content &retrieve it from (which path)and at what rate?
Source/DestinationClient
Source/DestinationServers
. . . . . . . . .
. . .
. . .
. . . . . .
path
path
Cross traffic
������
������
����������������
���������
���������
����������������
��������
��������
��������������������
������������
������������
����
��������
���������
���������
����
��������
���������
���������
����������������
������
������
������
������
������
������
������
������
������
������
������
������
������
������
������
������
������
������
������
������
������
������
������
������
Ethernet Switch Ethernet
SwitchEthernet
Switch
SwitchEthernet
SwitchEthernet
SwitchEthernet
Challenges (Constraints):
Network level Max/Min fairness
Fully and fairly utilizing resource as
long as there is demand for it.
QoS provisioning
Detect network level SLAviolation
Less infrastructure changes
Metadata management
Power efficiency
Debish & Klara SLA-aware Cloud Datacenter Architecture 3/ 1
Challenges: Cloud Datacenter Networks
Problems:
Where to store content &retrieve it from (which path)and at what rate?
Source/DestinationClient
Source/DestinationServers
. . . . . . . . .
. . .
. . .
. . . . . .
path
path
Cross traffic
������
������
����������������
���������
���������
����������������
��������
��������
��������������������
������������
������������
����
��������
���������
���������
����
��������
���������
���������
����������������
������
������
������
������
������
������
������
������
������
������
������
������
������
������
������
������
������
������
������
������
������
������
������
������
Ethernet Switch Ethernet
SwitchEthernet
Switch
SwitchEthernet
SwitchEthernet
SwitchEthernet
Challenges (Constraints):
Network level Max/Min fairness
Fully and fairly utilizing resource as
long as there is demand for it.
QoS provisioning
Detect network level SLAviolation
Less infrastructure changes
Metadata management
Power efficiency
Problem summary
How to best avoid congestion and minimize data transfer time?
Debish & Klara SLA-aware Cloud Datacenter Architecture 3/ 1
Existing Work (Related Work)
CDNs (Akamai):
Server selection based on proximity and latencyNot based on best content transfer rates and lowest delays
Cloud Center Architectures:
VL2 (A Scalable and Flexible Data Center Network)Hedera (Dynamic Flow Scheduling for Data Center Networks)Random server selection using TCP (RandTCP)Higher content transfer times than necessary.Do not detect SLA violation in realtime.No max/min resource allocation.
GFS/HDFS
Lack support to multiple NNSPotential single point of failure
Debish & Klara SLA-aware Cloud Datacenter Architecture 4/ 1
Existing Work (Related Work)
CDNs (Akamai):
Server selection based on proximity and latencyNot based on best content transfer rates and lowest delays
Cloud Center Architectures:
VL2 (A Scalable and Flexible Data Center Network)Hedera (Dynamic Flow Scheduling for Data Center Networks)Random server selection using TCP (RandTCP)Higher content transfer times than necessary.Do not detect SLA violation in realtime.No max/min resource allocation.
GFS/HDFS
Lack support to multiple NNSPotential single point of failure
In short
Exiting schemes have major limitations.
Debish & Klara SLA-aware Cloud Datacenter Architecture 4/ 1
Our Approach: Cloud Datacenter Networks (1)
Problems
Debish & Klara SLA-aware Cloud Datacenter Architecture 5/ 1
Our Approach: Cloud Datacenter Networks (1)
Problems
Which path and at what rate?
Debish & Klara SLA-aware Cloud Datacenter Architecture 5/ 1
Our Approach: Cloud Datacenter Networks (1)
Problems
Which path and at what rate?
Solution
Debish & Klara SLA-aware Cloud Datacenter Architecture 5/ 1
Our Approach: Cloud Datacenter Networks (1)
Problems
Which path and at what rate?
Solution
path1path2
Destination/Source Servers
Source/Destination
Server1 Server2
Ethernet Switch
Ethernet Switch
Ethernet Switch
if (Rpath1 > Rpath2)
else
path = path1− > Server = Server1
path = path2− > Server = Server2
R22
R11
Rpath = max(Rpath1,Rpath2)
R12
R21
R01
Rpath1 = min(R01,R11,R12) Rpath2 = min(R01,R21,R22)
Debish & Klara SLA-aware Cloud Datacenter Architecture 5/ 1
Our Approach: Cloud Datacenter Networks (2)
SCDA Components
Primergy Primergy Primergy Primergy
Primergy
PrimergyPrimergyPrimergy
Primergy Primergy
RM RM RM RM RM RM RM RM RM RM
FES
BSBS BS BS BS BS BS BS BS
UCL
RA
RA RA RA RA
RA
RA
NNS NNS NNSBS
NNS
Logical 2 sided
Logical 1 sided
PhysicalSwitch
Ethernet
Switch
Ethernet
Switch
Ethernet
Switch
Ethernet
Switch
Ethernet
Switch
Ethernet
Switch
Ethernet
Notations:
UCL = User client
FES = Front end server
NNS = Name node server
BS = Block (data) server
RM = Resource monitor
RA = Resource allocator
Control Communications
RM ↔ RARA ↔ RA
Debish & Klara SLA-aware Cloud Datacenter Architecture 6/ 1
Our Approach: Cloud Datacenter Networks (2)
SCDA Components
Primergy Primergy Primergy Primergy
Primergy
PrimergyPrimergyPrimergy
Primergy Primergy
RM RM RM RM RM RM RM RM RM RM
FES
BSBS BS BS BS BS BS BS BS
UCL
RA
RA RA RA RA
RA
RA
NNS NNS NNSBS
NNS
Logical 2 sided
Logical 1 sided
PhysicalSwitch
Ethernet
Switch
Ethernet
Switch
Ethernet
Switch
Ethernet
Switch
Ethernet
Switch
Ethernet
Switch
Ethernet
Notations:
UCL = User client
FES = Front end server
NNS = Name node server
BS = Block (data) server
RM = Resource monitor
RA = Resource allocator
Control Communications
RM ↔ RARA ↔ RA
Infrastructure changes
No changes on routers & TCP/IPpacket headers.
Debish & Klara SLA-aware Cloud Datacenter Architecture 6/ 1
Our Approach: Cloud Datacenter Networks (2)
SCDA Components
Primergy Primergy Primergy Primergy
Primergy
PrimergyPrimergyPrimergy
Primergy Primergy
RM RM RM RM RM RM RM RM RM RM
FES
BSBS BS BS BS BS BS BS BS
UCL
RA
RA RA RA RA
RA
RA
NNS NNS NNSBS
NNS
Logical 2 sided
Logical 1 sided
PhysicalSwitch
Ethernet
Switch
Ethernet
Switch
Ethernet
Switch
Ethernet
Switch
Ethernet
Switch
Ethernet
Switch
Ethernet
Notations:
UCL = User client
FES = Front end server
NNS = Name node server
BS = Block (data) server
RM = Resource monitor
RA = Resource allocator
Control Communications
RM ↔ RARA ↔ RA
Infrastructure changes
No changes on routers & TCP/IPpacket headers.
Metadata Mgt
FES and multiple NNSs
Debish & Klara SLA-aware Cloud Datacenter Architecture 6/ 1
Our Approach: Cloud Datacenter Networks (3)
SCDA: Path and path rate
Debish & Klara SLA-aware Cloud Datacenter Architecture 7/ 1
Our Approach: Cloud Datacenter Networks (3)
SCDA: Path and path rate
RM RM
RA
RA
R10d ,u
R11d ,u
R10d ,u
R10d ,u
Kept at RM
Kept at RA
S10d ,u =
∑j S
0jd ,u
S10d ,u
S11d ,u
R20d ,u = max(R10
d ,u, R11d ,u)
R10d ,u = min(max(R00
d ,u, R01d ,u),R
10d ,u)
R01d ,u = min(R01
d ,u,R10d ,u)R00
d ,u = min(R00d ,u,R
10d ,u)
R00d ,u
S01d ,u =
∑i R
01d ,u(i)S00
d ,u =∑
i R00d ,u(i)
R01d ,u
Debish & Klara SLA-aware Cloud Datacenter Architecture 7/ 1
Our Approach: Cloud Datacenter Networks (3)
SCDA: Path and path rate
RM RM
RA
RA
R10d ,u
R11d ,u
R10d ,u
R10d ,u
Kept at RM
Kept at RA
S10d ,u =
∑j S
0jd ,u
S10d ,u
S11d ,u
R20d ,u = max(R10
d ,u, R11d ,u)
R10d ,u = min(max(R00
d ,u, R01d ,u),R
10d ,u)
R01d ,u = min(R01
d ,u,R10d ,u)R00
d ,u = min(R00d ,u,R
10d ,u)
R00d ,u
S01d ,u =
∑i R
01d ,u(i)S00
d ,u =∑
i R00d ,u(i)
R01d ,u
Serving external write request
RM
UCL
FES
NNS
RA
BS
RM
BS7. R
8. rcvw = R BS
10. R UCL
11. R UCL
x RTTUCL12. cwnd = R 1. ID
2. hash(ID)
3. Which BS?
4. This BS.
?BS
?
x RTT
5. ID
6. R
13. Writing.
9. Hi!
Debish & Klara SLA-aware Cloud Datacenter Architecture 7/ 1
Our Approach: Cloud Datacenter Networks (4)
The rate
Rnm = Rnmd ,u = Rd ,u(t) =
Cd,u−qd,u (t−τ)
τ
Nd,u(t−τ)
Max/Min: Fractional flows
Nd ,u(t − τ) =Sd,u(t)
Rd,u(t−τ) =∑Nd,u(t−τ)
j
R jd,u(t)
Rd,u(t−τ)
QoS, SLA check
Sd ,u(t) =∑Nd,u(t−τ)
j ℘jd ,uR
jd ,u(t)
Notations:Cd,u = Link capacity
qd,u(t) = Queue size
τ = Control interval
Nd,u(t) = Number offlows
℘jd,u =
Rjd,u
(t+τ)
Rjd,u
(t)=
Priority weight of flow j
R jd,u(t) = Rate of flow j
Debish & Klara SLA-aware Cloud Datacenter Architecture 8/ 1
Our Approach: Cloud Datacenter Networks (4)
The rate
Rnm = Rnmd ,u = Rd ,u(t) =
Cd,u−qd,u (t−τ)
τ
Nd,u(t−τ)
Max/Min: Fractional flows
Nd ,u(t − τ) =Sd,u(t)
Rd,u(t−τ) =∑Nd,u(t−τ)
j
R jd,u(t)
Rd,u(t−τ)
QoS, SLA check
Sd ,u(t) =∑Nd,u(t−τ)
j ℘jd ,uR
jd ,u(t)
Notations:Cd,u = Link capacity
qd,u(t) = Queue size
τ = Control interval
Nd,u(t) = Number offlows
℘jd,u =
Rjd,u
(t+τ)
Rjd,u
(t)=
Priority weight of flow j
R jd,u(t) = Rate of flow j
Power Efficiency
Select a server with highest rate to power ratio,Rpath
P(t)
For passive contents, select server with Rpath ≥ Rscale (less active)
Debish & Klara SLA-aware Cloud Datacenter Architecture 8/ 1
Our Approach: Cloud Datacenter Networks (5)
SCDA MaxMin fairness example
Cu = 100pkts/sec
qu(t) = 0pkts
τ = 1sec
Nu = 3
R1u (t) = 10,R2
u = 50,R3U = 50 pkts/sec
℘u1 = ℘u
2 = ℘u3 = 1
Ru(t − τ) = 50 pkts/sec
Debish & Klara SLA-aware Cloud Datacenter Architecture 9/ 1
Our Approach: Cloud Datacenter Networks (5)
SCDA MaxMin fairness example
Cu = 100pkts/sec
qu(t) = 0pkts
τ = 1sec
Nu = 3
R1u (t) = 10,R2
u = 50,R3U = 50 pkts/sec
℘u1 = ℘u
2 = ℘u3 = 1
Ru(t − τ) = 50 pkts/sec
100 pkts/sec
10 pkts/sec
50 pkts/sec
50 pkts/sec
Debish & Klara SLA-aware Cloud Datacenter Architecture 9/ 1
Our Approach: Cloud Datacenter Networks (5)
SCDA MaxMin fairness example
Cu = 100pkts/sec
qu(t) = 0pkts
τ = 1sec
Nu = 3
R1u (t) = 10,R2
u = 50,R3U = 50 pkts/sec
℘u1 = ℘u
2 = ℘u3 = 1
Ru(t − τ) = 50 pkts/sec
100 pkts/sec
10 pkts/sec
50 pkts/sec
50 pkts/sec
Then SCDA rate is
R(t) = 1001050+ 50
50+ 50
50
= 45.45 pkts/sec.
Debish & Klara SLA-aware Cloud Datacenter Architecture 9/ 1
Our Approach: Cloud Datacenter Networks (5)
SCDA MaxMin fairness example
Cu = 100pkts/sec
qu(t) = 0pkts
τ = 1sec
Nu = 3
R1u (t) = 10,R2
u = 50,R3U = 50 pkts/sec
℘u1 = ℘u
2 = ℘u3 = 1
Ru(t − τ) = 50 pkts/sec
100 pkts/sec
10 pkts/sec
50 pkts/sec
50 pkts/sec
Then SCDA rate is
R(t) = 1001050+ 50
50+ 50
50
= 45.45 pkts/sec.
Processor sharing (PS):
R(t) = 1003 = 33.33 pkts/sec.
Debish & Klara SLA-aware Cloud Datacenter Architecture 9/ 1
Our Approach: Cloud Datacenter Networks (6)
SCDA MaxMin fairness: EfficientSharing
Our fractional flow approach to achieveMaxMin Fairness is called EfficientSharing (ES).
Given a resource with capacity Xunits/sec to be shared by N sources,
One can also set R(t − τ) = XN, which is
the processor sharing rate.
Each source’s bottleneck fair (ES) sharerate is denoted with R j (t).
We also have R j (t) < R(t − τ) as asource j cannot send higher than itsbottleneck fair share.
Then the ES rate, R(t) can be given as
R(t) = X∑N
j(
Rj (t)R(t−τ)
)= X2
N∑N
jR j (t)
.
Debish & Klara SLA-aware Cloud Datacenter Architecture 10/ 1
Our Approach: Cloud Datacenter Networks (6)
SCDA MaxMin fairness: EfficientSharing
Our fractional flow approach to achieveMaxMin Fairness is called EfficientSharing (ES).
Given a resource with capacity Xunits/sec to be shared by N sources,
One can also set R(t − τ) = XN, which is
the processor sharing rate.
Each source’s bottleneck fair (ES) sharerate is denoted with R j (t).
We also have R j (t) < R(t − τ) as asource j cannot send higher than itsbottleneck fair share.
Then the ES rate, R(t) can be given as
R(t) = X∑N
j(
Rj (t)R(t−τ)
)= X2
N∑N
jR j (t)
.
Then SCDA rate for the example above, inthe first iteration (round) becomes
R(t) = 10010
33.33+ 33.33
33.33+ 33.33
33.33
= 43.48 pkts/sec.
In the second iteration (round)
R(t) = 10010
43.48+ 43.48
43.48+ 43.48
43.48
= 44.84 pkts/sec.
Values of ES rate in next iterations (roundsor RTTs)
44.9842555105713, 44.9984250551231,44.9998425005512, 44.9999842500055,
Debish & Klara SLA-aware Cloud Datacenter Architecture 10/ 1
Our Approach: Cloud Datacenter Networks (6)
SCDA MaxMin fairness: EfficientSharing
Our fractional flow approach to achieveMaxMin Fairness is called EfficientSharing (ES).
Given a resource with capacity Xunits/sec to be shared by N sources,
One can also set R(t − τ) = XN, which is
the processor sharing rate.
Each source’s bottleneck fair (ES) sharerate is denoted with R j (t).
We also have R j (t) < R(t − τ) as asource j cannot send higher than itsbottleneck fair share.
Then the ES rate, R(t) can be given as
R(t) = X∑N
j(
Rj (t)R(t−τ)
)= X2
N∑N
jR j (t)
.
Then SCDA rate for the example above, inthe first iteration (round) becomes
R(t) = 10010
33.33+ 33.33
33.33+ 33.33
33.33
= 43.48 pkts/sec.
In the second iteration (round)
R(t) = 10010
43.48+ 43.48
43.48+ 43.48
43.48
= 44.84 pkts/sec.
Values of ES rate in next iterations (roundsor RTTs)
44.9842555105713, 44.9984250551231,44.9998425005512, 44.9999842500055,
Generalized Efficient Sharing (GES)
With priority weight, ℘j of flow j , the GESrate R(t) can be given as
R(t) = X∑N
j(℘j Rj (t)R(t−τ)
)= X2
N∑N
j℘jR j (t)
. Then
source j ’s weighted share becomes ℘jR(t).
Debish & Klara SLA-aware Cloud Datacenter Architecture 10/ 1
Results: Cloud Datacenter Networks (1)
Network topology
Debish & Klara SLA-aware Cloud Datacenter Architecture 11/ 1
Results: Cloud Datacenter Networks (1)
Network topology
. . . . . . . . .
. . .
. . .
...
1
2
1 1622163
. . . . . .
k
X Gbps
6X Gbps
X Gbps KX Gbps
X Gbps
X GbpsX Gbps
X Gbps
X Gbps
X Gbps
n x 163
n = 10, n = 100
KX Gbps
K < 6
50ms
10ms
��������
��������
������
��������
��������
��������
������
��������
���������
���������
����������������
������������
������������
����
��������
��������
��������
������
��������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
Ethernet Switch Ethernet
SwitchEthernet Switch
SwitchEthernet
SwitchEthernet
SwitchEthernet
Propagation delay of datacenter links is 10µsec.
Debish & Klara SLA-aware Cloud Datacenter Architecture 11/ 1
Results: Cloud Datacenter Networks (1)
Network topology
. . . . . . . . .
. . .
. . .
...
1
2
1 1622163
. . . . . .
k
X Gbps
6X Gbps
X Gbps KX Gbps
X Gbps
X GbpsX Gbps
X Gbps
X Gbps
X Gbps
n x 163
n = 10, n = 100
KX Gbps
K < 6
50ms
10ms
��������
��������
������
��������
��������
��������
������
��������
���������
���������
����������������
������������
������������
����
��������
��������
��������
������
��������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
Ethernet Switch Ethernet
SwitchEthernet Switch
SwitchEthernet
SwitchEthernet
SwitchEthernet
Propagation delay of datacenter links is 10µsec.
SCDA implemented in the NS2 simulator
Using C++ and OTCL
Debish & Klara SLA-aware Cloud Datacenter Architecture 11/ 1
Results: Cloud Datacenter Networks (1)
Network topology
. . . . . . . . .
. . .
. . .
...
1
2
1 1622163
. . . . . .
k
X Gbps
6X Gbps
X Gbps KX Gbps
X Gbps
X GbpsX Gbps
X Gbps
X Gbps
X Gbps
n x 163
n = 10, n = 100
KX Gbps
K < 6
50ms
10ms
��������
��������
������
��������
��������
��������
������
��������
���������
���������
����������������
������������
������������
����
��������
��������
��������
������
��������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
�������
Ethernet Switch Ethernet
SwitchEthernet Switch
SwitchEthernet
SwitchEthernet
SwitchEthernet
Propagation delay of datacenter links is 10µsec.
SCDA implemented in the NS2 simulator
Using C++ and OTCL
Experiments
Expts using video anddatacenter traffic traces
Using Poisson flow arrivaland Pareto file size distns
Comparisons against
schemes based on TCP and
random server selection
(RandTCP) such as
VL2 (A. Greenberg
et. al,
SIGCOMM’09),Hedera (Al-Fares et.
al, NSDI’10).
Debish & Klara SLA-aware Cloud Datacenter Architecture 11/ 1
Results: Cloud Datacenter Networks (2)
Using video traces
Debish & Klara SLA-aware Cloud Datacenter Architecture 12/ 1
Results: Cloud Datacenter Networks (2)
Using video traces
0 2000 4000 6000 8000
10000 12000 14000 16000
10 20 30 40 50 60 70 80 90 100
Avg
. Ins
t. T
hpt (
KB
/sec
)
Simulation time (sec)
RandTCP vs SCDA Instanteneous Average Throughput (KB/sec)
RandTCP Avg Inst ThptSCDA Avg Inst Thpt
0
0.2
0.4
0.6
0.8
1
0 2 4 6 8 10 12
FC
T C
DF
FCT (sec)
Content upload time CDF
RandTCPSCDA
Debish & Klara SLA-aware Cloud Datacenter Architecture 12/ 1
Results: Cloud Datacenter Networks (2)
Using video traces
0 2000 4000 6000 8000
10000 12000 14000 16000
10 20 30 40 50 60 70 80 90 100
Avg
. Ins
t. T
hpt (
KB
/sec
)
Simulation time (sec)
RandTCP vs SCDA Instanteneous Average Throughput (KB/sec)
RandTCP Avg Inst ThptSCDA Avg Inst Thpt
0
0.2
0.4
0.6
0.8
1
0 2 4 6 8 10 12
FC
T C
DF
FCT (sec)
Content upload time CDF
RandTCPSCDA
Using video trace
0
2
4
6
8
10
12
10 20 30 40 50 60 70 80 90
AF
CT
(se
c)
File Size (MB)
Average File completion time (AFCT)
RandTCPSCDA
Debish & Klara SLA-aware Cloud Datacenter Architecture 12/ 1
Results: Cloud Datacenter Networks (2)
Using video traces
0 2000 4000 6000 8000
10000 12000 14000 16000
10 20 30 40 50 60 70 80 90 100
Avg
. Ins
t. T
hpt (
KB
/sec
)
Simulation time (sec)
RandTCP vs SCDA Instanteneous Average Throughput (KB/sec)
RandTCP Avg Inst ThptSCDA Avg Inst Thpt
0
0.2
0.4
0.6
0.8
1
0 2 4 6 8 10 12
FC
T C
DF
FCT (sec)
Content upload time CDF
RandTCPSCDA
Using video trace
0
2
4
6
8
10
12
10 20 30 40 50 60 70 80 90
AF
CT
(se
c)
File Size (MB)
Average File completion time (AFCT)
RandTCPSCDA
Expt Description & Observation
CDN traces for flow arrival (T. Mori et. al,
TMA’10) and sizes (R. Torres et. al, ICDCS’11)
YouTube video and control flows
Arrivals to 20 of 2138 YT servers
X = 0.5Gbps, K = 3
SCDA outperforms existing schemes!
Debish & Klara SLA-aware Cloud Datacenter Architecture 12/ 1
Results: Cloud Datacenter Networks (3)
Using datacenter traces
Debish & Klara SLA-aware Cloud Datacenter Architecture 13/ 1
Results: Cloud Datacenter Networks (3)
Using datacenter traces
0
2
4
6
8
10
12
14
0 1000 2000 3000 4000 5000 6000 7000
AF
CT
(se
c)
File Size (KBytes)
Average File completion time (AFCT)
RandTCPSCDA
0
0.2
0.4
0.6
0.8
1
0 2 4 6 8 10 12
FC
T C
DF
FCT (sec)
Content upload time CDF
RandTCPSCDA
Debish & Klara SLA-aware Cloud Datacenter Architecture 13/ 1
Results: Cloud Datacenter Networks (3)
Using datacenter traces
0
2
4
6
8
10
12
14
0 1000 2000 3000 4000 5000 6000 7000
AF
CT
(se
c)
File Size (KBytes)
Average File completion time (AFCT)
RandTCPSCDA
0
0.2
0.4
0.6
0.8
1
0 2 4 6 8 10 12
FC
T C
DF
FCT (sec)
Content upload time CDF
RandTCPSCDA
Expt Description
Traces for flow arrival (T. Benson et. al,
IMC’10) and file sizes (A. Greenberg et. al,
SIGCOMM’09), X = 1.0Gbps, K = 1
Using Poisson(200 flow/sec) andPareto(500KB, 1.6), X = 0.2Gbps, K = 3
0 10 20 30 40 50 60 70 80 90
0 20 40 60 80 100A
vg. I
nst.
Thp
t (K
B/s
ec)
Simulation time (sec)
RandTCP vs SCDA Instanteneous Average Throughput (KB/sec)
RandTCP Avg Inst ThptSCDA Avg Inst Thpt
Debish & Klara SLA-aware Cloud Datacenter Architecture 13/ 1
Results: Cloud Datacenter Networks (3)
Using datacenter traces
0
2
4
6
8
10
12
14
0 1000 2000 3000 4000 5000 6000 7000
AF
CT
(se
c)
File Size (KBytes)
Average File completion time (AFCT)
RandTCPSCDA
0
0.2
0.4
0.6
0.8
1
0 2 4 6 8 10 12
FC
T C
DF
FCT (sec)
Content upload time CDF
RandTCPSCDA
Expt Description
Traces for flow arrival (T. Benson et. al,
IMC’10) and file sizes (A. Greenberg et. al,
SIGCOMM’09), X = 1.0Gbps, K = 1
Using Poisson(200 flow/sec) andPareto(500KB, 1.6), X = 0.2Gbps, K = 3
0 10 20 30 40 50 60 70 80 90
0 20 40 60 80 100A
vg. I
nst.
Thp
t (K
B/s
ec)
Simulation time (sec)
RandTCP vs SCDA Instanteneous Average Throughput (KB/sec)
RandTCP Avg Inst ThptSCDA Avg Inst Thpt
Observation
SCDA outperforms existing schemes!
Debish & Klara SLA-aware Cloud Datacenter Architecture 13/ 1
Conclusion and Future Work
We designed SCDA achieving:
Lower content transfer timesHigher throughputNetwork wide max/min fairnessDetection of SLA violation in realtimeScalablity: multiple NNS, RM and RA running in parallelNo need to change routers and TCP/IP
We implemented SCDA in NS2 simulator (C++ and otcl)
SCDA outperforms by upto 60% and 50% respectively
Other features of SCDA
Content specific server selectionMore energy efficient server selectionMulti resource allocation scheme
Future work: Large scale implementation and testing
Debish & Klara SLA-aware Cloud Datacenter Architecture 14/ 1