Breakthrough of Mobile Gaming. 2. Windows Phone 7. Top 10+ apps are games.
John Carmack (Wolfenstein 3D, Doom, Quake)… “multiplayer in some form is ...
Battling demons and vampires on your lunch break…
Switchboard: A Matchmaking System for Multiplayer Mobile Games Justin Manweiler, Sharad Agarwal, Ming Zhang, Romit Roy Choudhury, Paramvir Bahl ACM MobiSys 2011
Breakthrough of Mobile Gaming iPhone
App
Store
350K
applica,ons
47%
Time
on
20%
apps,
80%
downloads
Windows
Phone
7
Top
10+
apps
are
games
Mobile
Apps
Spent
Gaming
John Carmack (Wolfenstein 3D, Doom, Quake)… “multiplayer in some form is where the breakthrough, platform-defining things are going to happen in the mobile space” 2
Mobile Games: Now and Tomorrow Increasing
Interac6vity
Single‐player
Mobile
(mobile
today)
Mul6player
Turn‐based
(mobile
today)
Mul6player
Fast‐ac6on
(mobile
soon)
3
Key Challenge Bandwidth
is
fine:
250
kbps
to
host
16‐player
Halo
3
game
Game
Type
Latency
Threshold
Delay
bounds
are
much
6ghter
First‐person,
Racing
≈
100
ms
Sports,
Role‐playing
≈
500
ms
Challenge:
find
groups
of
peers
than
can
play
well
together
Real‐,me
Strategy
≈
1000
ms
4
The Matchmaking Problem Connection Latency
End-to-end Latency Threshold
Match
to
sa+sfy
total
delay
bounds
Clients
5
Instability in a Static Environment Median
Latency
(ms)
310
290
270
250
Due
to
instability,
must
consider
latency
distribu6on
230
210
190
170
150
9:36
9:50
10:04
10:19
10:33
10:48
11:02
11:16
11:31
11:45
12:00
Time
of
Day
(AM)
6
End-to-end Latency over 3G First‐person
Shoot.
1
Racing
Sports
Real‐6me
Strategy
Empirical
CDF
0.8
Peer‐to‐peer
reduces
latency
and
is
cost‐effec6ve
0.6
AT&T
to
AT&T
Direct
AT&T
to
AT&T
via
Bing
AT&T
to
AT&T
via
Duke
AT&T
to
AT&T
via
UW
0.4
0.2
0
0
100
200
300
RTT
(in
ms)
400
500
600
7
The Matchmaking Problem Targe,ng
3G:
play
anywhere
Link
Performance
Latency
not
Bandwidth
interac+vity
is
key
Grouping
Measurement
/
PredicTon
at
game
+mescales
P2P
Scalability
8
Requirements for 3G Matchmaking ● Latency estimation has to be accurate Or
games
will
be
unplayable
/
fail
● Grouping has to be fast Or
impa,ent
users
will
give
up
before
a
game
is
ini,ated
● Matchmaking has to be scalable For
game
servers
For
the
cellular
network
For
user
mobile
devices
9
State of the Art ● Latency estimation Pyxida,
stable
network
coordinates;
Ledlie
et
al.
[NSDI
07]
Vivaldi,
distributed
latency
est.;
Dabek
et
al.
[SIGCOMM
04]
Latency
es,ma,on
and
matchmaking
are
● Game matchmaking for wired networks established
for
wired
networks
Htrae,
game
matchmaking
in
wired
networks;
Agarwal
et
al.
[SIGCOMM
09]
● General 3G network performance 3GTest
w/
30K
users;
Huang
et
al.
[MobiSys
2010]
Interac,ons
with
applica,ons;
Liu
et
al.
[MobiCom
08]
Empirical
3G
performance;
Tan
et
al.
[InfoCom
07]
TCP/IP
over
3G;
Chan
&
Ramjee
[MobiCom
02]
10
A “Black Box” for Game Developers IP
network
Internet
GGSN
“Black
Box”
GGSN
SGSN
SGSN
RNC
RNC
End‐to‐end
Performance
Crowdsourced
Link
Performance
Measurement
(over
6me)
11
Crowdsourcing 3G over Time Latency Similarity by Time
Time
12
Crowdsourcing 3G over Space
Latency Similarity by Distance
13
Can we crowdsource HSDPA 3G? ● How does 3G performance vary over time? How
quickly
do
old
measurements
“expire”?
How
many
measurements
needed
to
characterize
the
latency
distribu,on?
Details
of
parameter
space
lem
for
the
paper
…
(our
goal
is
not
to
iden6fy
the
exact
causes)
● How does 3G performance vary over space? Signal
strength?
Mobility
speed?
Phones
under
same
cell
tower?
Same
part
of
the
cellular
network?
…
14
Methodology ● Platform Windows
Mobile
and
Android
phones
HSDPA
3G
on
AT&T
and
T‐Mobile
● Carefully deployed phones Con,nuous
measurements
Simultaneous,
synchronized
traces
at
mul,ple
sites
● Several locations Princeville,
Hawaii
Redmond
and
Seanle,
Washington
Durham
and
Raleigh,
North
Carolina
Los
Angeles,
California
15
Stability over Time (in a Static Environment) Redmond,
AT&T,
15m
Intervals
1
Empirical
CDF
0.8
0.6
0.4
Live
characteriza,on
is
necessary
and
is
feasible
Performance
drims
over
longer
,me
periods
Black
line
represents
phone
1
(all
other
lines
phone
2)
0.2
0
120
Similar
latencies
under
the
same
tower
140
160
180
200
RTT
(Msec)
220
240
16
Stability over Space (at the same time) Similarity
at
the
same
cell
tower
Substan,al
varia6on
Divergence
between
nearby
towers
1
Empirical
CDF
0.8
0.6
S‐home
0.4
Latona
U
Village
0.2
Herkimer
Northgate
1st
Ave
0
0
50
100
150
RTT
difference
at
90th
percenTle
(ms)
200
17
Switchboard: crowdsourced matchmaking
Game
Network
TesTng
Service
Switchboard
Cloud
Service
Grouping
Agent
on
MSFT
Azure
Latency
Data
Measurement
Controller
Latency
EsTmator
18
Scalability through Reuse… ● Across Time Stable
distribu,on
over
15‐minute
,me
intervals
● Across Space Phones
can
share
probing
tasks
equitably
for
each
tower
● Across Games Shared
cloud
service
for
any
interac,ve
game
19
Client Matchmaking Delay 1
Empirical
CDF
0.8
0.6
Switchboard
clients
benefit
from
deployment
at
scale
0.4
1
client
arrival/sec
Total
1
client/sec
0.2
10
client
arrival/sec
Total
10
clients/s
0
0
100
200
300
400
500
Time
unTl
placed
in
group
(s)
600
700
20
Conclusion ● Latency: key challenge for fast-action multiplayer ● 3G latency variability makes prediction hard ● Crowdsourcing enables scalable 3G latency estimation ● Switchboard: crowdsourced matchmaking for 3G
21
k
you!
cs.duke.edu/~jgm
[email protected]
