Added some more text/image text for 5.1 (Stats)

This commit is contained in:
Jonatan Pålsson 2011-05-10 09:38:25 +02:00
parent a64370c2aa
commit e660defb88

View file

@ -7431,11 +7431,11 @@ name "chap:Results-and-discussion"
\end_layout
\begin_layout Standard
In this chapter the results of the GGS prototype is presented and discussed.
The results of the testing is presented with both graphical and textual
In this chapter the results of the GGS prototype are presented and discussed.
The results of the testing are presented with both graphical and textual
content.
Together with the test data there are thoughts about how future improvements
to the prototype could look like.
Finally thoughts about how future improvements to the prototype could look
like are given.
\end_layout
\begin_layout Section
@ -7454,32 +7454,110 @@ Mention the hardware which the GGS was run on; A Thinkpad T410 with a core
\end_layout
\begin_layout Standard
The testing of the GGS prototype occurred in two sessions, one session where
the system was tested with clients that were using mnesia and one session
with clients that did not use mnesia.
The data that were measured during both test sessions where how many messages
per second the server could handle, during the second test session the
delay between the server and the clients also was measured.
There was also a testing session where the number of clients were measured,
\begin_inset Note Note
status open
\begin_layout Plain Layout
The testing of the GGS prototype occurred in two sessions
\end_layout
\end_inset
Testing of the GGS took place in two separate sessions.
The first session simulates a highly demanding application, the second
session simulated a less demanding application.
The highly demanding application is a real time game which does several
asynchronous database writes each second.
The less demanding application does not perform any database reads or writes.
\end_layout
\begin_layout Standard
Each of the two simulations use JavaScript as the GDL.
The JavaScript is run through Google V8.
The database module uses Mnesia.
\end_layout
\begin_layout Standard
During the sessions two measurements were recorded.
\end_layout
\begin_layout Itemize
\series bold
Messages per second
\series default
is used to see how many incoming and outgoing messages the server can process
each second.
The results of the messages per second testing are shown in figure
\begin_inset CommandInset ref
LatexCommand ref
reference "fig:msg-per-sec-MNESIA"
\end_inset
.
\end_layout
\begin_layout Itemize
\series bold
Latency between server and client
\series default
is used to measure the round-trip time for a message travelling between
the client and server.
This measurement is used to determine how many players the server can handle
while still providing a playable gaming experience.
The results of the latency test can be seen in figure
\begin_inset CommandInset ref
LatexCommand ref
reference "fig:latency-graph"
\end_inset
.
\end_layout
\begin_layout Standard
\begin_inset Note Note
status open
\begin_layout Plain Layout
There was also a testing session where the number of clients were measured,
however this was not a good measurement of performance and therefore these
numbers will not be included in the report.
The hardware that the GGS was running on was a Thinkpad T410, with a Intel
\begin_inset Note Note
status open
\begin_layout Plain Layout
Since we donät include this..
should we mention it?
\end_layout
\end_inset
\end_layout
\end_inset
The hardware that the GGS was running on was a Thinkpad T410, with a Intel
i5 processor and 4GB of RAM.
\end_layout
\begin_layout Standard
In the first test, where mnesia was used, the server had a peak value of
In the first test, where Mnesia was used, the server had a peak value of
nearly 6000 messages per second.
When this number was reached mnesia warned that it was overloaded and shortly
after that mnesia crashed.
When this number was reached Mnesia warned that it was overloaded and shortly
after that Mnesia failed to serve requests.
This result was not unexpected as this test put the database under heavy
load.
In the next testing session, the test was conducted with another client
that did not use mnesia.
that did not use Mnesia.
Without mnesia the server peaked at 60000 messages per second, however
this was only for a very short time.
The average throughput was around 25000 messages per second, five times
more than what the server was able to process with mnesia.
more than what the server was able to process with Mnesia in place.
\end_layout
@ -7576,7 +7654,15 @@ end{centering}
\begin_inset Caption
\begin_layout Plain Layout
\begin_inset CommandInset label
LatexCommand label
name "fig:msg-per-sec-MNESIA"
\end_inset
The graph shows messages per second for intervals of clients connected.
Each client performs 3 asynchronous writes to the Mnesia database each
second.
\end_layout
\end_inset
@ -7593,7 +7679,7 @@ end{centering}
\begin_inset Float figure
wide false
sideways false
status collapsed
status open
\begin_layout Plain Layout
\begin_inset ERT
@ -7640,7 +7726,15 @@ end{centering}
\begin_inset Caption
\begin_layout Plain Layout
\begin_inset CommandInset label
LatexCommand label
name "fig:latency-graph"
\end_inset
This graph shows the latency in a low-demand application.
The ping is measured in milliseconds for a message to make a round-trip
between client and server.
\end_layout
\end_inset
@ -7657,7 +7751,7 @@ end{centering}
\begin_inset Float figure
wide false
sideways false
status collapsed
status open
\begin_layout Plain Layout
\begin_inset ERT
@ -7704,7 +7798,8 @@ end{centering}
\begin_inset Caption
\begin_layout Plain Layout
The graph shows messages per second for intervals of clients connected.
No database is connected.
\end_layout
\end_inset