Check out the new USENIX Web site. next up previous
Next: Games and interactive application Up: Potential for multiplexing gain Previous: Potential for multiplexing gain


Game workloads are synchronized

There are two ways games can be multiplexed with each other. One way would be to coarsely and statically assign physical servers to particular games based on the popularity of the game. Results from Section 4 clearly show that this can provide a lot of benefit for game companies. Another way would be to dynamically re-allocate servers based on instantaneous demand for a particular game. An implicit assumption that gives value to the latter method is that different games have usage patterns that are substantially different. Thus, rather than have each game provision server resources based on the peak usage of their game, server resources would be provisioned for the global peak.


{\tablename} 2: Mean player populations for week of May 23, 2004
Game Average number of players
Half-Life 80324
America's Army 5791
Battlefield 1942 5402
Neverwinter Nights 4579


In order to investigate the extent to which different games can be multiplexed with each other, we examined the aggregate player populations of four popular games. The games examined include FPS games (Half-Life, Battlefield 1942, and America's Army), as well as an MMORPG (Neverwinter Nights). Player populations of these games were collected over a one week period (Sunday May 23, 2004 to Saturday May 29, 2004) from the GameSpy trace. In order to compare the games directly, independent of their popularity, each game's population data was normalized by the mean population for that particular game during the week. Table 2 lists the mean player populations for the four games examined. Figure 11 plots the normalized player loads for the four games during the one week period. As the figure shows, player populations fluctuate significantly based on the time of day from lows close to half of the mean to peaks close to twice the mean. In addition, populations across games have peaks in close proximity to each other, making it difficult to achieve significant statistical multiplexing gain between different games. Finally, as indicated in the FFTs from Figure 8, games show slight peaks on the weekends with slightly more players on-line than during the week.

{\figurename} 11: Aggregate normalized load across four popular games for week of May 23, 2004
\includegraphics[width=0.45\textwidth]{figures/normal_games}


{\tablename} 3: Web site logs for week of August 13, 2001
North American cereal manufacturer
Start time Mon Aug 13 2001
End time Sun Aug 19 2001
Total requests 10,368,896
Content transferred 59.6 GB
 
North American credit card company
Start time Tue Aug 14 2001
End time Mon Aug 20 2001
Total requests 112,590,195
Content transferred 366.4 GB
 
International beverage manufacturer
Start time Tue Aug 14 2001
End time Sat Aug 18 2001
Total requests 11,932,946
Geographically resolvable 11,829,429
Content transferred 51.1 GB


{\figurename} 12: Aggregate normalized load between Half-Life and commercial web sites
\includegraphics[width=0.30\textwidth]{figures/kelloggs_hl} \includegraphics[width=0.305\textwidth]{figures/discover_hl} \includegraphics[width=0.30\textwidth]{figures/coke_hl}
(a) North American cereal (b) North American credit (c) International beverage
manufacturer card company manufacturer


next up previous
Next: Games and interactive application Up: Potential for multiplexing gain Previous: Potential for multiplexing gain
2005-08-10