magreenblatt wrote:magreenblatt wrote:Czarek wrote:Is it a good idea to disable it on Linux? Is performance going to suffer much because of it? Or should users
be informed that the CEF library must loaded the very first?
I don't currently have an answer to these questions. Perhaps you can tell us after you're done experimenting.
How did this experiment turn out for you? I'm thinking of disabling tcmalloc by default in 2171+ to avoid problems like https://code.google.com/p/javachromiume ... ail?id=137.
In CEF Python tcmalloc is now disabled by default since 31.0 release. To answer my original questions:
- Yes, it's a good idea to disable it. CEF is only one of many libraries in an application and shouldn't do tcmalloc hook implicitly. It may cause memory issues in a random manner.
- Real world test suite at http://peacekeeper.futuremark.com/ resulted in 2.3% better performance with tcmalloc disabled. However I don't understand why "cefclient > tests > other tests > js perf test" (V8 bindings/interop/marshalling) gave 30-40% better performance with tcmalloc enabled. See this topic and the docs.google links with comparison tables: viewtopic.php?f=10&t=11462
