Motivation System Evaluation Ricochet: Lateral Error Correction for Time-Critical Multicast Mahesh Balakrishnan 1 , Ken Birman 1 , Amar Phanishayee 2 , Stefan Pleisch 1 1 Cornell University, Ithaca, NY 2 Carnegie Mellon University, Pittsburgh, PA Mahesh Balakrishnan Ricochet: Lateral Error Correction for Time-Critical Multicast
40
Embed
Ricochet: Lateral Error Correction for Time-Critical Multicastamarp/papers/presentations/nsdi-ricochet/nsdi-fin… · Motivation System Evaluation Design Space Receiver-Based FEC
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Receivers generate XORs ofincoming multicast packets ...... and exchange with otherreceiversA receiver can recover from atmost one missing packet in anXOR
EKer
nel B
uffe
r
Ker
nel B
uffe
r
App Buffer App Buffer
B C ED FXOR
A B C D
X
Mahesh Balakrishnan Ricochet: Lateral Error Correction for Time-Critical Multicast
Overheads:Membership State:# of intersections < # of known nodes.Computational:XORs are fast... 150-300 ms per packet.Bandwidth:(r , c) =⇒ c
r+c repair overhead.
Group Membership Service: Any old one works.
Mahesh Balakrishnan Ricochet: Lateral Error Correction for Time-Critical Multicast
MotivationSystem
Evaluation
Experimental Evaluation
Cornell Cluster: 64 1.3 Ghz nodesJava Implementation running on Linux 2.6.12Three Loss Models: {Uniform, Burst, Markov}Grouping Parameters: g ∗ s = d ∗ n
g: Number of Groups in Systems: Average Size of Groupd: Groups joined by each Noden: Number of Nodes in System
Each node joins d randomly selected groups from g groups
Mahesh Balakrishnan Ricochet: Lateral Error Correction for Time-Critical Multicast
MotivationSystem
Evaluation
Where does loss occur in a Datacenter?
Packet Loss occurs at end-hosts: independent and bursty
0
20
40
60
80
100
1801601401201008060
burs
t len
gth
(pac
kets
) receiver r1: loss bursts in A and Breceiver r1: data bursts in A and B
0
20
40
60
80
100
1801601401201008060
burs
t len
gth
(pac
kets
)
time in seconds
receiver r2: loss bursts in Areceiver r2: data bursts in A
Mahesh Balakrishnan Ricochet: Lateral Error Correction for Time-Critical Multicast
Mahesh
Text Box
Overloaded Node
Mahesh
Text Box
Lightly Loaded Node
Mahesh
Text Box
Traffic Bursts
Mahesh
Line
Mahesh
Line
Mahesh
Text Box
Loss Bursts
MotivationSystem
Evaluation
Distribution of Recovery Latency16 Nodes, 128 groups per node, 10 nodes per group, Uniform *% Loss
0
10
20
30
40
50
0 50 100 150 200 250
Rec
over
y Pe
rcen
tage
Milliseconds
96.8% LEC + 3.2% NAK
0
10
20
30
40
50
0 50 100 150 200 250
Rec
over
y Pe
rcen
tage
Milliseconds
92% LEC + 8% NAK
0
10
20
30
40
50
0 50 100 150 200 250
Rec
over
y Pe
rcen
tage
Milliseconds
84% LEC + 16% NAK
(a) 10% Loss Rate (b) 15% Loss Rate (c) 20% Loss Rate
Most lost packets recovered < 50ms by LEC.Remainder via reactive NAKs.
Claim: Ricochet is reliable and time-critical.
Mahesh Balakrishnan Ricochet: Lateral Error Correction for Time-Critical Multicast
Mahesh
Text Box
LEC
Mahesh
Line
Mahesh
Text Box
NAK
Mahesh
Line
MotivationSystem
Evaluation
Scalability in Groups64 nodes, * groups per node, 10 nodes per group, Loss Model: Uniform 1%
90
92
94
96
98
100
2 4 8 16 32 64 128 256 512 1024
LE
C R
ecov
ery
Perc
enta
ge
Groups per Node (Log Scale)
Recovery %
0
10000
20000
30000
40000
50000
2 4 8 16 32 64 128 256 512 1024M
icro
seco
nds
Groups per Node (Log Scale)
Average Recovery Latency
Claim: Ricochet scales to hundreds of groups. Comparison: at128 groups, SRM latency was 8 seconds. 400 times slower!
Mahesh Balakrishnan Ricochet: Lateral Error Correction for Time-Critical Multicast
MotivationSystem
Evaluation
CPU time and XORs per data packet64 nodes, * groups per node, 10 nodes per group, Loss Model: Uniform 1%
0
50
100
150
200
250
300
350
400
450
2 4 8 16 32 64 128 256 512 1024
Mic
rose
cond
s
Groups per Node (Log Scale)
Updating Repair BinsData Packet Accounting
Waiting in BufferXOR
0
1
2
3
4
5
2 4 8 16 32 64 128 256 512 1024N
umbe
r
Groups per Node (Log Scale)
XORs per Data Packet
Claim: Ricochet is lightweight=⇒ Time-Critical Apps can run over it
Mahesh Balakrishnan Ricochet: Lateral Error Correction for Time-Critical Multicast
MotivationSystem
Evaluation
Resilience to Burstiness64 nodes, 128 groups per node, 10 nodes per group, Loss Model: Bursty 1%
Stagger of i : Encode every i th packetStagger 6, burst of 100 packets =⇒ 90% recovered at 50 ms!
Mahesh Balakrishnan Ricochet: Lateral Error Correction for Time-Critical Multicast
MotivationSystem
Evaluation
Conclusion
Multicast in Datacenters:large numbers of low-rate groupsaggregate load can be high, causing packet loss
Ricochet is the first protocol to scale in the number ofgroups in the systemLayered under high-level platforms: Tempest, Axis2Available for download:http://www.cs.cornell.edu/projects/quicksilver/Ricochet.html
Mahesh Balakrishnan Ricochet: Lateral Error Correction for Time-Critical Multicast
MotivationSystem
Evaluation
Overflow
Mahesh Balakrishnan Ricochet: Lateral Error Correction for Time-Critical Multicast
MotivationSystem
Evaluation
Impact of Loss Rate on LEC64 nodes, 128 groups per node, 10 nodes per group, Loss Model: *