[Tech] Backoff considered harmful?

[Ed Tomlinson]

On Sunday 26 November 2006 09:44, Michael Rogers wrote:
> toad wrote:
> > Did you compare mandatory with advisory backoff?
> 
> Advisory backoff works much better - please see the attached graphs. The 
> results without throttling or backoff look good, but for higher loads 
> the success rate collapses spectacularly - I haven't been able to get 
> any precise figures because the message queues get so long I run out of 
> RAM. :-)

Throtting alone seems to work better though.  I wonder if we should disable the
backoff logic and see what happens.  If we trust your simulations, we should not
see much of a difference at all.

Ed