Are most of the nodes on dev-network overloaded or is this a client side
bug giving me mostly high search died probability?
I have 11 nodes with open connections, two with ~0.5 SDP, other close to 1.
I have got a reasonable number of Successful Transfers compared with stable.
__
On July 22, 2003 12:09 am, Tom Kaitchuck wrote:
> On Monday 21 July 2003 10:24 pm, pineapple wrote:
> > Ack! What's happening? My poor, pathetic little node
> > is running on default config yet my local load is
> > +40K, +280 connections transmitting to! I'm guessing
> > that each connection is
On Monday 21 July 2003 10:24 pm, pineapple wrote:
> Ack! What's happening? My poor, pathetic little node
> is running on default config yet my local load is
> +40K, +280 connections transmitting to! I'm guessing
> that each connection is getting ~80 byts/sec. Even
> with NIO, my node is still a
Ack! What's happening? My poor, pathetic little node
is running on default config yet my local load is
+40K, +280 connections transmitting to! I'm guessing
that each connection is getting ~80 byts/sec. Even
with NIO, my node is still at over 100% load (although
it occassionally drop to the mid
After talking to Oskar on IRC, I turned off overload triaging in CVS. The
node will now query reject once the load hits the maximum load limit.
Oskar's concern was that the triaging is detrimental to routing because busy
nodes triage all the time and so don't every allow non-specialized reques
Matthew Toseland <[EMAIL PROTECTED]> writes:
> Interesting. What about the other category of requests, announcement
> stuff? Currently they are counted by requestDistribution (I think...), and
> so I have added them to successDistribution.
It's really bad for announcement requests to fail RNF.
> 3) I think you need to distinguish between successful DataRequests and
> InsertRequests. When the network is performance is bad there will be a
> disproportiate number of successful InsertRequests as compared to the number
> of successful DataRequests. InsertRequests just mean that data wa
> 3) I think you need to distinguish between successful DataRequests and
> InsertRequests. When the network is performance is bad there will be a
> disproportiate number of successful InsertRequests as compared to the number
> of successful DataRequests. InsertRequests just mean that data wa
On Tue, Jun 25, 2002 at 01:18:37AM -0400, Gianni Johansson wrote:
> On Monday 24 June 2002 23:19, Matthew wrote:
>
> > > On Tue, Jun 25, 2002 at 04:16:49AM +0100, Matthew Toseland wrote:
> > > Patch committed, changes overload handling to:
I hoped it might get your attention :)
> > > always accep
On Monday 24 June 2002 23:19, Matthew wrote:
> > On Tue, Jun 25, 2002 at 04:16:49AM +0100, Matthew Toseland wrote:
> > Patch committed, changes overload handling to:
> > always accept if in failure table (as now)
> > 60%-70% load:
> > accept HTL=1, HTL=0 (this is after we have decremented it)
> >
On Tue, Jun 25, 2002 at 04:16:49AM +0100, Matthew Toseland wrote:
> Patch committed, changes overload handling to:
> always accept if in failure table (as now)
> 60%-70% load:
> accept HTL=1, HTL=0 (this is after we have decremented it)
> accept if in most successful 1/256th of the keyspace (by %
Patch committed, changes overload handling to:
always accept if in failure table (as now)
60%-70% load:
accept HTL=1, HTL=0 (this is after we have decremented it)
accept if in most successful 1/256th of the keyspace (by % requests
fulfilled successfully)
accept if in datastore
70-80% load:
accept
12 matches
Mail list logo
