On Monday 03 November 2003 09:13 pm, Toad wrote:
> On Mon, Nov 03, 2003 at 09:54:52PM -0500, Ken Corson wrote:
> > Toad wrote:
> > >I added routingSuccessRatioCHK.
> > >
> > ><toad_> do people download stuff through fuqid that only succeeds after
> > >dozens of retries?
> > ><lostlogic> toad_: yes.
> > ><lostlogic> toad_: and through frost too
> > ><tessier> Heck, that's how most of my fproxy downloads go
> > ><soros> i set my retries at 25 in fproxy when downloading splitfiles
> > >lately
> > ><tessier> soros: Me too
> > ><tessier> Actually I set htl at 25 and retries at 50 (the max)
> > ><tessier> And threads at 100 (the max also)
> > >
> > ><tessier> But when that one file succeeded it really went. Quite odd.
> > ><tessier> A couple days ago. Maybe night before last.
> > >
> > >This strongly suggests that routing is not doing terribly great. The
> > >suspicion is that there is some form of network fragmentation going
> > >on. Ian refuses to admit the possibility of network fragmentation, so I
> > >am wondering how to produce extraordinary evidence to support my
> > >extraordinary claim :).
> >
> > Toad- just count the number of rejections experienced by a single
> > request as it is handled by Node. When you see numbers around 15-20
> > retries (out of maxRoutingSteps), it will be crystal-clear why
> > things are smelling rather putrid :<( If that turns out to be the
> > case. I'm angling to earn some "developer" points, without yet
> > writing any code :)
>
> So you are suggesting that the reason that routing sucks is that nodes
> constantly reject 80%+? Perhaps you are right, but from what I have seen
> the rejection is mostly because of bandwidth usage... is that the
> consensus? Why do your nodes reject, people?

No, I would say threads.

Uptime:   0 days,   6 hours,   29 minutes 
Current routingTime: 9ms. 
Pooled threads running jobs: 101     (84.2%) 
Pooled threads which are idle: 69
Current estimated load: 84.2%. 
Load due to thread limit = 84.2%
Load due to routingTime = 70.1% = 85% + 15% * (9.711 - 1000.000) / 1000.000 <= 
overloadLow (85%)
Load due to messageSendTimeRequest = 80.6% = 85% + 15% * (110.023 - 1000.000) 
/ 3000.000 <= overloadLow (85%) 

Total pooled threads    171
Available pooled threads        65
Pooled threads in use   106

Checkpoint: Connection opener                                           4
freenet.Message: DataReply                                                      2
freenet.interfaces.LocalNIOInterface$ConnectionShell            1
freenet.node.states.data.DataStateInitiator                             60
freenet.node.states.data.TrailerWriteCallbackMessage:true:true 39

I still don't get why it doesn't just use those other 65 threads.

_______________________________________________
Devl mailing list
[EMAIL PROTECTED]
http://dodo.freenetproject.org/cgi-bin/mailman/listinfo/devl

Reply via email to