Re: Dar architecture questions

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1


[...]
> 
>> Performance is the same with or without the patch.  Just for kicks I defined
>> CRITICAL_START and CRITICAL_END in special_alloc.cpp to be just '//' and the performance is only slightly better than using just special-alloc.  This pretty much removes the sigprocmask and mutex locks from the picture.  

OK, thanks for this feedback.

By the way --disable-thread-safe option given to the configure script
does the same thing among other code simplification (special_alloc,
thread_cancellation, etc.)

OK, so what I understand is that the best way to have better
performances in your situation is to reduce the number/use of critical
section.

I may have some ideas of improvement for the 2.5.x

Best Regards,
Denis.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.10 (GNU/Linux)
Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/
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=bIuP
-----END PGP SIGNATURE-----

------------------------------------------------------------------------------
Everyone hates slow websites. So do we.
Make your web apps faster with AppDynamics
Download AppDynamics Lite for free today:
http://p.sf.net/sfu/appdyn_sfd2d_oct