On Jan 31, 2008, at 8:41 AM, Matthew Toseland wrote:

> We are still getting timeouts. [...]
> Any theories about the most likely cause?

Considering the rather common occurrence of high-ping opennet  
peernodes, my first suspect is that they are culminated pingtimes and  
coalescing delays. If this is the case, the only way I am aware of to  
solve it is to favor nodes with low ping times; I actually already  
have a patch for that, although in it's present incantation it also  
favors darknet nodes for routing (easily excised).

My only other suspect is a bug in the message/link layer that drops  
messages.

In the past while examining the throttle controls, I have suspected  
that (with priority queues) the "90-seconds at full throttle" constant  
might actually reduce to taking on too many concurrent chk transfers  
for them all to complete on time.

> Do timeouts show up in simulation?

I don't normally watch for them, I've started a new run with Accepted  
& Fatal request timeouts being logged. So far nothing.

> What can we do to debug this?


Probably:
(1) a simulated high-ping times seen in the public network at about  
the same rate,
(2) a message/link layer stress test complete with rekeying/ 
disconnects/and [busy/not-busy] spikes

--
Robert Hailey


Reply via email to