[Tech] LIFO simulations

[toad]

On Wed, Dec 13, 2006 at 01:53:38AM +0100, Jano wrote:
> Michael Rogers wrote:
> 
> >> * I'm dropping messages at the tail when queues reach 50.000 messages
> >> queued (for search and transfer queues). I implemented this in the hope
> >> of getting rid of OOMs. I'm getting them anyway, so I've screwed
> >> something in the process.
> > 
> > Not necessarily - 500 peers * 2 queues * 50,000 messages could easily
> > eat a gig or two of memory.
> 
> My Sim.NODES is 100? In any case the queues getting larger are the
> transfers, and with your below 17KB mean reply size that's clearly a lot
> more than 2G. By large.

The transfers? I suggest you impose an arbitrary limit on total number
of simultaneous requests per node, and reject requests with overload if
they exceed it. Transfers at 0.00001 bytes per second are no use to
anyone, and we do implement such a mechanism - more sophisticated things
too such as bandwidth pre-allocation.
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: Digital signature
Url : http://emu.freenetproject.org/pipermail/tech/attachments/20061213/9547165b/attachment-0001.pgp