Ejabberd resource tests/try 5: Difference between revisions

From OLPC
Jump to navigation Jump to search
(Ejabberd test results, attempt 5)
mNo edit summary
Line 31: Line 31:
[[Image:try5-load_avg_5_min_per_conn-load_avg_5_max_per_conn-load_avg_5_median_per_conn.png]]
[[Image:try5-load_avg_5_min_per_conn-load_avg_5_max_per_conn-load_avg_5_median_per_conn.png]]


[[Image:load_avg_1-load_avg_5-load_avg_15.png]]
[[Image:try5-load_avg_1-load_avg_5-load_avg_15.png]]





Revision as of 03:01, 4 November 2008

Try 5: a few hundred users, interacting properly

It turns out that in the hyperactivity agents were not interacting in Ejabberd resource tests/try 4.

For this test several hyperactivity instances were used, each running 50 clients. 4 XO laptops were also connected, so the total number of clients was at most stages 50n + 4.

Memory use

Here you can see the memory use is slightly over 1 MB per user, and growth is perhaps slightly more than linear.

Try5-users active vs resident mem.png

Try5-psmem-resident mem-virtual mem.png

Memory use vs connections

This shows max-median-min values for stable points along the way.

Try5-resident mem min per conn-resident mem max per conn-resident mem median per conn.png


CPU usage

Cumulative CPU use by the ejabberd process:

Try5-users active vs cputime.png

Load averages, by connections and by time:

Try5-load avg 5 min per conn-load avg 5 max per conn-load avg 5 median per conn.png

Try5-load avg 1-load avg 5-load avg 15.png


The laptops

Note that they all see a different number of clients.

Try5-hyperactivity-3-800.jpg