OSDI 2002 Boston, MA 1
The Effectiveness of Request Redirection on CDN
Robustness
Limin WangVivek Pai and Larry Peterson
Princeton University
December 11, 2002 5th OSDI, Boston, MA 2
Motivation
Server infrastructure criticalFailures are noticeableConsequences are seriousCDNs are commonly used
Robust service under heavy loadNews items, flash crowdsOverload-style attacks (DDoS)
We can exploit CDNs for this
December 11, 2002 5th OSDI, Boston, MA 3
BBB.COM
WWW Service
client
December 11, 2002 5th OSDI, Boston, MA 4
Content Distribution Networks
BBB.COM
client server surrogate
B
B
B
B
B
B
cache
A
A
A
A
A
A
AAA.COM
C
C
C
C
C
C
CCC.COM
redirector
December 11, 2002 5th OSDI, Boston, MA 5
Partial Replication on CDN
BBB.COM
client server surrogate
B
B
B
B
A
A
A
A
AAA.COM
C
C
C
B B
A
A
C
C
C
CCC.COM
redirector
December 11, 2002 5th OSDI, Boston, MA 6
Partial Replication on CDN
BBB.COM
client server surrogate
B
B
B
B
A
A
A
A
AAA.COM
C
C
C
C
CCC.COM
redirector
December 11, 2002 5th OSDI, Boston, MA 7
Factors Affecting Redirection
GoalsIncrease system throughput under loadReduce response latency perceived by clients
Server loadPick least loaded server
Network proximity Pick closest server
Cache localityPick server just served the object
What’s the tradeoff across different loads?
Often conflict
December 11, 2002 5th OSDI, Boston, MA 8
Contributions
New Class of CDN Redirection Strategies: Fine Dynamic Replication (FDR)
Selectively replicates URLsBalances load, locality, bandwidth and proximity60-91% throughput improvementDeters DDoS, absorbs flash crowds naturally
New Hybrid Simulator: NS-2 + LogSimEnd-to-end — from SYN to sync()Large scale simulations
• 128 servers, 1000+ clients, ~70,000 req/sec
December 11, 2002 5th OSDI, Boston, MA 9
Outline
Motivation and ContributionsDesign Space of Redirection StrategiesEvaluation MethodologyExperimental ResultsConclusions and Ongoing Work
December 11, 2002 5th OSDI, Boston, MA 10
Redirection Decision Dimensions
URL Hashing – decentralized, coherentDifferent hashing schemes
ReplicationMore replicas closer replicasToo many replicas working set overload
Load knowledgeHow accurate?
December 11, 2002 5th OSDI, Boston, MA 11
Background: Hashing Algorithms
Consistent Hashing (CHash)hash(svr1), … hash(svrN)hash(URL)select “closest” server
Highest Random Weight (HRW)hash(URL, svr1), … hash(URL, svrN)sort hash values, get ordered server listselect server with highest hash value
December 11, 2002 5th OSDI, Boston, MA 12
Strategies: Random
Random (Rand)Requests randomly sent to surrogatesBaseline caseAssumes no pathological behavior
December 11, 2002 5th OSDI, Boston, MA 13
Strategies: Static Replication
Replicated Consistent Hashing (R-CHash)Each URL hashed to a fixed # of replicasFor each request, randomly selects one replicaSimilar to Karger’s Consistent Hashing paper
Replicated Highest Random Weight (R-HRW)
Similar to R-CHash, but use HRW hashingMinimizes two URLs having same set of replicas
Approximates best published CDN algorithmsImprove locality over Random
December 11, 2002 5th OSDI, Boston, MA 14
Strategies: Static + Load
Load-Aware Static Replication (fine grained)LR-CHash
Estimates server load at redirectorsPicks up least-loaded server from server set
LR-HRWCounterpart of LR-CHash
Approximates CDN’s best load balancing behavior
December 11, 2002 5th OSDI, Boston, MA 15
Strategies: Dynamic Replication (New)
Coarse Dynamic Replication (CDR)HRW hashing ordered server listWalks list to find acceptably loaded server# of replicas based on server load (estimated locally)
Fine Dynamic Replication (FDR) # of replicas based on URL popularity, tooFDR-Global, reference scheme with global load info
Dynamically balance load and locality
December 11, 2002 5th OSDI, Boston, MA 16
Summary of StrategiesCategory
Strategy Hashing Scheme Dynamic Server set?
Load aware
?CHash HRW
Random Random
StaticR-CHash R-HRW
Static +Load
LR-CHash LR-HRW
Dynamic
CDR FDR
Network Proximity
NPR-CHash NPLR-CHash
NP-FDR
December 11, 2002 5th OSDI, Boston, MA 17
Evaluation Methodology
SimulationsMerge NS-2 and LogSimSYN to sync(), in detail
Work LoadNormal load• 1000 clients replaying Rice Trace
Flash crowds• 10-80% of 1000 clients hitting 10 URLs• Rest clients replaying Rice Trace
December 11, 2002 5th OSDI, Boston, MA 18
Simulation: Topology
PA CA
WA
SD CA
TX
NECO
GA
MAMIIL
R DC
R
R
RR R
R
R
R
R RR
R R
R
R
R
S
C
S
S
S S
S S S
S
CC C
C
C C C
C
C CC
C
– Server, – Client, – RouterS C R
128 servers, 1000 clients
December 11, 2002 5th OSDI, Boston, MA 19
Capacity: Normal Load (64 svrs, 1000 clnts)
9.3
20.418.5
25.4 25.4
32.6 33.2 33.2
0
5
10
15
20
25
30
35
40
Ag
gre
gate
Syste
m C
ap
acity (K
req
s/s
ec) .
Rand R-CHash R-HRW LR-CHash
LR-HRW CDR FDR FDR-Global
StaticStatic
+ Load Dynamic
December 11, 2002 5th OSDI, Boston, MA 20
Latency Measurement Points
9.3
20.418.5
25.4 25.4
32.6 33.2 33.2
0
5
10
15
20
25
30
35
40
Ag
gre
gate
Syste
m C
ap
acity (K
req
s/s
ec) .
Rand R-CHash R-HRW LR-CHash
LR-HRW CDR FDR FDR-Global
StaticStatic
+ Load Dynamic
December 11, 2002 5th OSDI, Boston, MA 21
Latency: Normal Load, (64 svrs, 1000 clnts)
0
20
40
60
80
100
0.1 1 10 100Response Time (Seconds)
Cu
mu
lati
ve P
erc
en
tag
e .
LR-HRW LR-CHash R-HRW R-CHash FDR CDR Rand
Random Max:9.3K req/s
December 11, 2002 5th OSDI, Boston, MA 22
Latency: Normal Load, (64 svrs, 1000 clnts)
0
20
40
60
80
100
0.1 1 10 100Response Time (Seconds)
Cu
mu
lati
ve P
erc
en
tag
e .
LR-HRW LR-CHash FDR CDR
Static+Load (LR-HRW) Max: 25.4K req/s
December 11, 2002 5th OSDI, Boston, MA 23
Handle Tail Separately (99% file
530KB)
0
20
40
60
80
100
0.1 1 10 100Response Time (Seconds)
Cu
mu
lati
ve P
erc
en
tag
e .
LR-HRW CDR-Tail-Static CDR
Static+Load (LR-HRW) Max: 25.4K req/s
December 11, 2002 5th OSDI, Boston, MA 24
Server Resource Utilization (64 svrs)
UtilizationScheme
Max Thpt (Kreq/s)
DISK(%) CPU(%)
Mean Stddev
Mean Stddev
Random 9.3 100.0 0.00 21.03 1.36
R-CHash 20.4 99.15 3.89 57.88 18.36
R-HRW 18.5 99.74 1.26 47.88 15.33
LR-CHash 25.4 97.83 12.51 59.48 18.85
LR-HRW 25.4 99.00 5.94 58.43 16.56
CDR 32.6 36.10 25.18 90.07 11.78
FDR 33.2 33.96 20.38 93.86 7.58
FDR-Global
33.2 17.60 15.43 91.93 11.81Under Normal Work Load at Individual Maximum Capacity
December 11, 2002 5th OSDI, Boston, MA 25
Conclusions
New dynamic schemes work best60-91% improvement versus standard CDNWithout sacrificing latencies Scale well, successful attacks more difficult
Bottleneck shifts from Disk to CPU/NetworkDesired – shows selective replication works
More results in the paperNormal workloads, flash crowd/DDoS trafficNetwork Proximity and HeterogeneityLarge file effects
December 11, 2002 5th OSDI, Boston, MA 26
Ongoing Work
PlanetLab deployment (CoDeeN networks)Intel-funded overlay network, academic testing CDNCurrently running on 12 sites using proxy serversEarly stage, many more to do
Traffic monitoring, capacity test, server management …
More simulationsLarger scale, faster simulated serversMore topologies (power-law, etc)More traces, more elaborate client request model
December 11, 2002 5th OSDI, Boston, MA 27
Thank you!
For More Informationhttp://www.cs.princeton.edu/nsg/cdn
AcknowledgementsHP/Compaq/Intel
AlphaServer ES-40, 8GB RAMrx4610 Server, Itanium, 16GB RAM
iMimicDataReactor Proxy Servers
December 11, 2002 5th OSDI, Boston, MA 28
Capacity Scalability
01020304050607080
0 16 32 48 64 80 96 112 128# Servers
Ag
gre
gat
e S
yste
m C
apac
ity
(Kre
qs/
sec)
.
FDR CDR LR-HRW LR-CHashR-HRW R-CHash Rand
Normal Load, 1000 normal clients
December 11, 2002 5th OSDI, Boston, MA 29
Various Flash Crowds (32 servers)
1 victim file, 1KB 10 victim files, avg 6KB
0
5
10
15
20
25
30
35
40
100 200 300 400 500 600 700 800# Intensive Clients (total clients 1000)
Aggre
gate
Syste
m Ca
pacit
y ( K
reqs/s
ec)
.
FDR CDR LR-HRW LR-CHashR-HRW R-CHash Rand
0
5
10
15
20
25
30
35
40
100 200 300 400 500 600 700 800# Intensive Clients (total clients 1000)
Aggre
gate
Syste
m Ca
pacit
y ( K
reqs/s
ec)
.
FDR CDR LR-HRW LR-CHashR-HRW R-CHash Rand
December 11, 2002 5th OSDI, Boston, MA 30
Capacity: Flash Crowd, 64 Servers
11.2
19.8 19.8
31 31
37.8 37.8 38.6
0
5
10
15
20
25
30
35
40
45
Ag
gre
gate
Syste
m C
ap
acity (K
req
s/s
ec) .
Rand R-CHash R-HRW LR-CHash
LR-HRW CDR FDR FDR-Global
750 normal clients, 250 intensive clients
Static Static
+ Load Dynamic