Re: [PATCH] ConnOpener fixes

On 01/30/2013 08:18 PM, Amos Jeffries wrote:
> One performane optimization I can see:
>
> * if the callback_ is != NULL but has been cancelled by the receiving
> Job. Your code now calls sendAnswer() and schedules the already
> cancelled Call.
> Previously this was tested for in swanSong() to simply NULL the
> callback_ pointer instead of scheduling a dead Call.
> NP: it would probably be a good idea to test for the
> callback_->cancelled() case and debugs() report it instead of scheduling.
>
>
> +1. Other than the above performance tweak this looks fine for commit.

Added the extra check and committed to trunk as r12629.

Please let me know if you need my help with porting this to v3.2.

Thank you,

Alex.
Received on Fri Feb 01 2013 - 00:31:22 MST