osm at petschge.de
Sun Mar 28 11:03:10 BST 2010
> In the end it comes to trying to equally load the clients more instead
> of the spiky cpu usage, and to equally load the server.
> I would see 2 solutions/optimizations - let the prio2 rerender
> stuff run much more often - like depend on the minutely replication
> diffs. So we sprinkel prio2 into the queue much more often so that
> halve of the clients render prio2 and half of them render the oldtile
> stuff all the time.
> Another would be to make it not a prio1 then prio2 then
> prio3 4 ... but rather a kind of "weighted fair queue". So once we have
> a bunch of prio1/2 in the queue we not start swamping the clients with them
> but rather try to feed some clients prio4 which come back fast (typically)
> and let the incoming not drain.
I totally agree that it would be nice to do such things. serge even
mentions "more intelligence within the process of distributing jobs to
clients." in this TODO list.
Uploading without caring for the state of the server is just not helping
here. "Server load too high, unlikely we can upload after rendering,
waiting 30s.." is a symptom of the uneven load distribution, not a bug
in the server (or client for that matter) which could fixed by removing
the check which generates this message.
Patrick "Petschge" Kilian
More information about the Tilesathome