[Tech] Backoff considered harmful?

[Ian Clarke]

Excellent :-)  I can't wait to see more results.

Ian.

On 21 Nov 2006, at 16:11, Michael Rogers wrote:

> Here are some preliminary results from the simulator - I must  
> stress that they're only preliminary. I haven't simulated token  
> passing yet - these results only show throttling with backoff,  
> throttling alone, and backoff alone.
>
> The load model is a bit simplistic: one in ten nodes is a  
> publisher, and each publisher has ten randomly selected readers.  
> Each publisher occasionally inserts a key, waits for ten minutes,  
> then informs its readers of the key; the readers then request the  
> key. The publication rate (and therefore the request rate) can be  
> varied to investigate the effect of load.
>
> Each run lasted for three hours' simulation time, with the first  
> hour's logs discarded to minimise the effect of the initial  
> conditions.
>
> All three mechanisms showed an increase in throughput under  
> increasing load, ie there was no congestion collapse. Throttling  
> alone produced higher throughput than either throttling with  
> backoff or backoff alone, especially under heavy load.
>
> All three mechanisms showed a decrease in success rate with  
> increasing load, suggesting that congestion collapse might  
> eventually occur at high enough loads. Throttling alone produced a  
> higher success rate and slower degradation under load than either  
> throttling with backoff or backoff alone.
>
> This suggests that the backoff mechanism is not effective in  
> controlling load, and the request throttle would work better  
> without backoff. These conclusions are only tentative though - much  
> more remains to be done, when I can find enough disk space for the  
> logs!