Sensitivity Of Quake3 Players Sensitivity Of Quake3 Players - - PowerPoint PPT Presentation

▶
sensitivity of quake3 players sensitivity of quake3
SMART_READER_LITE
LIVE PREVIEW

Sensitivity Of Quake3 Players Sensitivity Of Quake3 Players - - PowerPoint PPT Presentation

Dec 20, 2022 117 likes •222 views

Sensitivity Of Quake3 Players Sensitivity Of Quake3 Players Sensitivity Of Quake3 Players Sensitivity Of Quake3 Players To Netw ork Latency and Jitter To Netw ork Latency and Jitter To Netw ork Latency and Jitter To Netw ork Latency and

slide-1
SLIDE 1

From the incomplete-but-fun-research-department

Page 1

gj_armitage@yahoo.com 11/1/01 SIGCOMM Internet Measurement Workshop (poster)

Sensitivity Of Quake3 Players Sensitivity Of Quake3 Players Sensitivity Of Quake3 Players Sensitivity Of Quake3 Players To Netw ork Latency and Jitter To Netw ork Latency and Jitter To Netw ork Latency and Jitter To Netw ork Latency and Jitter

An incomplete, experimental look at the impact of network conditions on a player's choice of server for multiplayer, networked games

(Oh, and something fun to do as well....)

Grenville Armitage

gj_armitage@yahoo.com

  • Nov. 1st, 2001
slide-2
SLIDE 2

From the incomplete-but-fun-research-department

Page 2

gj_armitage@yahoo.com 11/1/01 SIGCOMM Internet Measurement Workshop (poster)

Introduction

  • Qualitative assertion: Low latency and jitter are

desirable for real-time, interactive games

  • Quantitative assessments: Rare, yet useful to ISPs

and game hosting companies

– What is the latency radius within which I'll find my primary

population of players?

  • This project attempts to correlate observed player

activity with network conditions

– Specific context: Quake III Arena, a networked, multiplayer

'first person shooter' (FPS) game

  • Hope others will embark on similar research

– This project is self-funded, donated resources

slide-3
SLIDE 3

From the incomplete-but-fun-research-department

Page 3

gj_armitage@yahoo.com 11/1/01 SIGCOMM Internet Measurement Workshop (poster)

Test Environment

Californian server London server 147ms Players from everywhere

  • n Internet

University College London Palo Alto

Hypothesis: Methodology: Reality:

  • Players will prefer lower 'ping' times

to servers

  • Server usage patterns will reflect

topological locality of players

  • Establish two QuakeIII servers that

appear identical to client-side selection process

  • Log players, their IP addresses, and

in-game 'ping' samples over period

  • f months
  • Assess topological locality of

players, and distribution of observed ping values.

  • Californian server: 600MHz Celeron,

128MB, FreeBSD4.2, T1 link to PAIX

(hosted in Palo Alto)

  • London server: 900MHz Athlon,

128MB, Linux kernel 2.4.2, 10Mb link to UK net (hosted at University College London)

  • Both servers advertised their

location as "Palo Alto, California"

slide-4
SLIDE 4

From the incomplete-but-fun-research-department

Page 4

gj_armitage@yahoo.com 11/1/01 SIGCOMM Internet Measurement Workshop (poster)

Quick Stats....

Duration of Trials:

  • Californian server:

May 17 to Aug 18, 2001 5290 unique clients 338 clients played >= 2hrs each 164 'days' aggregate played time

  • London server:

May 29 to Sep 12, 2001 4232 unique clients 131 clients played >= 2hrs each 77 'days' aggregate played time

Common server details:

  • Quake III version 1.17 (linux binary)
  • Same 6 maps, fixed cycle sequence
  • 20 minutes per map
  • Up to 6 remote players
  • 2 permanent 'bots' to attract players
  • Identical registration with master

server (clients see latency as only difference)

  • Server-side 'ping' sampled everytime

player runs over an object, dies, or kills another player

Donated resources:

  • Tristan Henderson supported server at UCL
  • Brian Reid supported server in Palo Alto

125 150 175 200 225 250 20 40 60 80 100 120 140 160 180

Total Played Time on Californian Server

Day Of Year Days Played

140 150 160 170 180 190 200 210 220 230 240 250 260 10 20 30 40 50 60 70 80

Total Played Time on London Server

Day Of Year Days Played

slide-5
SLIDE 5

From the incomplete-but-fun-research-department

Page 5

gj_armitage@yahoo.com 11/1/01 SIGCOMM Internet Measurement Workshop (poster)

Popular Latencies

Median 'ping' per game:

  • Each player's 'ping' sampled > 10 times

per game

  • Median values per player per game
  • Cumulative plot reflects most frequently

appearing median ping values

  • California and London curves similar

50 100 150 200 250 300 350 10 20 30 40 50 60 70 80 90 100

Cumulative Median Ping

California 10 London 10 California 1 London 1

Median Ping (ms) Total %

Players who picked up at least 1 item per minute (minimal activity) California 1: 80% < ~196ms London 1: 80% < ~210ms Players who picked up at least 10 items per minute (reasonably active) California 10: 80% < ~158ms London 10: 80% < ~182ms

But what does this prove?

  • Perhaps nothing!

.... if most of the Internet is less than 250ms from anywhere central

  • Need evidence of regional locality...
slide-6
SLIDE 6

From the incomplete-but-fun-research-department

Page 6

gj_armitage@yahoo.com 11/1/01 SIGCOMM Internet Measurement Workshop (poster)

0 . 5 1 1 . 5 2 2 . 5 3 3 . 5 4 4 . 5 5 5 . 5 6 6 . 5 7 0 . 2 0 . 4 0 . 6 0 . 8 1 1 . 2 1 . 4 1 . 6 1 . 8

W e e k l y U s e

C a l i f o r n i a L o n d o n

D a y o f W e e k ( C a l i f o r n i a n t i m e ) % P l a y e d T i m e

Evidence of Locality # 1

Cyclical usage patterns:

Sunday Saturday

2 4 6 8 10 12 14 16 18 20 22 24 0.5 1 1.5 2 2.5 3 3.5 4 4.5 5

Daily Use

California London

Time of Day (Californian time) % Played Time

  • Usage patterns peak at different times,

different demographics

  • Peaks reflect afternoon and evening of

their respective locations

  • London 8 hours ahead of Palo Alto
  • Servers attract regional players
  • Supports hypothesis that clients prefer

'closer' server, other things being equal

slide-7
SLIDE 7

From the incomplete-but-fun-research-department

Page 7

gj_armitage@yahoo.com 11/1/01 SIGCOMM Internet Measurement Workshop (poster)

Evidence of Locality #2

The Origin of Players:

  • Based on reverse lookups
  • n each player's IP

address:

Californian server: mostly North America London server: mostly Europe and US East Coast

  • Since each server was
  • therwise identical, latency

seems plausible as the client-

  • bservable metric on which a

player chooses their server

Using active players who picked up at least 10 items per minute during each game:

Rank Calforinia Games/Time(min) Calforinia Origin London Games/Time London Origin 1 323 / 3005 .ed.shawcable.net 108 / 1027 .pit.adelphia.net 2 192 / 2072 .cruzio.com 73 / 690 .Uni-Mainz.DE 3 124 / 1383 (RogersEAST/@Home) 75 / 679 .upc-d.chello.nl 4 119 / 1246 .018.popsite.net 50 / 606 (telnordia.se) 5 118 / 1221 .tx.home.com 53 / 604 .dyn.optonline.net 6 150 / 1200 .mediaone.net 44 / 565 (Rogers EAST/@Home) 7 132 / 1178 .pit.adelphia.net 35 / 463 .dyn.optonline.net 8 115 / 1151 .socal.rr.com 53 / 448 .dialup.tiscalinet.it 9 87 / 980 .pa.home.com 34 / 430 .pa.home.com 10 93 / 938 .sfba.home.com 20 / 288 .tx.home.com 11 69 / 799 .hsia.telus.net 24 / 273 .btinternet.com

() bracketed origins involved looking up 'whois' database after .in-addr.arpa failed.

Table above shows origins of top 11 players on each

  • server. Outside the top 11, the Californian server

also saw dedicated players from ".jp" while the London server saw dedicated ".nl" and ".uk" players. There is also cross-over by players equidistant from either server.

slide-8
SLIDE 8

From the incomplete-but-fun-research-department

Page 8

gj_armitage@yahoo.com 11/1/01 SIGCOMM Internet Measurement Workshop (poster)

Player effectiveness

50 100 150 200 250 300 350 400 0.75 1 1.25 1.5 1.75 2 2.25 2.5 2.75 3 3.25 3.5

Frag(kill) Rate vs Median Ping

Californian London

Median Ping (ms) Frags/minute

The aim is fragging

there is no other reason to play...

  • Skill and response time

influence a player's ability to frag (kill) others in the game

  • Response time has human and

network components

  • Average frag rate vs median

ping hints at the negative impact of high latency

  • A player with 45ms ping could

average 1 frag/min better than player with 200ms ping

  • "Well, duh?"
slide-9
SLIDE 9

From the incomplete-but-fun-research-department

Page 9

gj_armitage@yahoo.com 11/1/01 SIGCOMM Internet Measurement Workshop (poster)

Concluding thoughts....

Learn anything useful?

  • Players will tend to self-select

servers within 200ms 'radius'

  • Two servers (separated by 147ms, distinct

timezones and regional player populations) appear to validate this conclusion

  • Caveat: server ping estimates are only

approximates

  • Helps identify potential player

population relative to server(s)

Why is Jitter missing?

  • Testbed's ping sampling too

coarse (10+ samples/minute)

  • Lacked resources to deploy

revised sampling method (20+ samples/second)

  • Jitter impact may be significant

(hand-eye co-ordination adapts better to constant latency)

Looking forward....

  • Move to Half-Life or CounterStrike, dump QuakeIII
  • Instrument servers to track packet loss and jitter
  • No resources: I need multiple sites to host new

servers with more accurate ping sampling