Changes between Version 2 and Version 3 of Profiling

Timestamp:

01/07/13 11:38:27 (8 years ago)

Author:

Antoine Martin

Comment:

--

Profiling

@@ -30 +30 @@
 
 [http://pycallgraph.slowchop.com/ pycallgraph] can generate pretty diagrams.
+We now ship a wrapper which takes care of simplifying the calls to {{{pycallgraph}}}:
+{{{
+./tests/scripts/xpra/pycallgraph
+}}}
+This command includes a number of working examples and lists the groups and threads available for profiling.
+
+=== Using pycallgraph to identify bottlenecks ==
+General guidelines:
+* start with a small delay (ie: {{{-d 2}}}) to skip the initial setup, potentially longer if you start a server and then also need to connect the client before profiling
+* when comparing versions/changes/settings: use the runtime parameter to ensure that each run will last for exactly the same amount of time - this makes it easier to compare the labels using absolute values, and script the whole thing so the client connects at exactly the same time if profiling the server
+* focus on one thread at a time - there is not much overlap/impact between different threads
+* choose an application to test which will stress the desired portion of the code (ie: if testing the network or encoding thread, an application that generates a high frames-per-second is more appropriate than what may ultimately be the target application for the system)
+* choose an application whose behaviour is predictable: preferably not using the network or relying on any external resources
+* start with most groups enabled
+* most groups can usually be disabled early - unless they are being profiled specifically
+* some [./Debugging Debugging] environment variables may be useful