Bakul Shah wrote:
>
> IMHO you are better off using a recent route lookup algorithm
> than messing with caches. The PATRICIA tree algorithm is
> what 33 years old now?
Not true. Any routing algorithm takes longer because they are by
definition a "fuzzy match." The fastforward algorithm is not
Ruslan Ermilov wrote:
>
> BTW, Wes, I'm still waiting for a working example of an indirect route
> with also indirect gateway.
Any indirect route via the opposite end of a point-to-point connection.
Right?
--
"Where am I, and what am I doing in this handbasket?"
Wes Peters
On Thu, Jun 28, 2001 at 10:32:50PM +0200, Dag-Erling Smorgrav wrote:
> Wes Peters <[EMAIL PROTECTED]> writes:
> > The description there isn't very forthcoming. fastforwarding caches
> > the results of a route lookup for destination addresses that are not
> > on
Dag-Erling Smorgrav wrote:
>
> Wes Peters <[EMAIL PROTECTED]> writes:
> > The description there isn't very forthcoming. fastforwarding caches
> > the results of a route lookup for destination addresses that are not
> > on the local machine, and uses th
Wes Peters <[EMAIL PROTECTED]> writes:
> The description there isn't very forthcoming. fastforwarding caches
> the results of a route lookup for destination addresses that are not
> on the local machine, and uses the cached route to short-circuit the
> normal (relati
> machdep.forward_roundrobin_enabled: 1
> >
> > What does the fastforwarding option do that the normal forwarding option
> > doesn't?
> >
> See inet(4).
The description there isn't very forthcoming. fastforwarding caches
the results of a route lookup for destin
On Mon, Jun 25, 2001 at 06:47:41PM -0400, Deepak Jain wrote:
> sysctl -A |grep forward
> net.inet.ip.forwarding: 1
> net.inet.ip.fastforwarding: 0
> machdep.forward_irq_enabled: 1
> machdep.forward_signal_enabled: 1
> machdep.forward_roundrobin_enabled: 1
>
> What does t
It kinda sounds to me like the improved speed you are getting is
from reduced latency rather then from higher available bandwidth.
You may be able to get the same result by increasing the TCP window
size on source and destination. The default is only 16K (on FreeBSD
boxes), 8
> It kinda sounds to me like the improved speed you are getting is
> from reduced latency rather then from higher available bandwidth.
right, i got the same feeling. only 550KB on a 10MBit ethernet is
kind of slow anyways.
cheers
luigi
> You may be able to get the sa
> The question is not "how fast is fast forwarding?", but
> "why is it crashing?" I can imagine small timing changes
> speeding up a session between other boxes.
yes, the original poster was concerned about crashes,
i was mainly concerned on the gains in fastforwa
> >
> > Has anyone here tried setting net.inet.ip.fastforwarding on in a high
> > traffic enviroment?
> >
> > This setting DRASTICALLY speeds up transfers between boxes talking through
> > a freebsd gateway when you are using 2 100mbit interfaces, but it seems to
> > kernel panic the system af
I will take a look and see if I can get a panic message later on,
unfortunatly the one box that I have running forwarding is a highly
important system that I cant afford downtime on, and most of the time when
it panics Im working on it remotely, but it definatly panics and the box
reboots.
I will
Luigi Rizzo wrote:
>
> > Another coupla hundred kilobytes per second?
>
> from what to what ? sounds like a 5% improvement or even less...
> > > > This setting DRASTICALLY speeds up transfers
> > > > between boxes talking through
> > > > a freebsd gateway when you are using 2 100mbit
> > > > i
Another couple of 100k/sec per connection.
When I was running as follows:
10mbit network -> pix -> freebsd gateway -> internal network (100mbit)
with 100mbit ethernet on the fbsd gateway, 10mbit up to the gateway (there
are routers inbetween the pix and the gateway), and 100mbit on the
internal
> Another coupla hundred kilobytes per second?
from what to what ? sounds like a 5% improvement or even less...
cheers
luigi
>
> Andrew
>
> On Mon, 12 Jun 2000, Luigi Rizzo wrote:
>
> > > Hi All,
> > >
> > > I posted this a coupla days ago and just thought I would ask again
Another coupla hundred kilobytes per second?
Andrew
On Mon, 12 Jun 2000, Luigi Rizzo wrote:
> > Hi All,
> >
> > I posted this a coupla days ago and just thought I would ask again in the
> > hope that someone had encounted something since then.
> >
> > Has anyone here tried setting net.inet.i
> Hi All,
>
> I posted this a coupla days ago and just thought I would ask again in the
> hope that someone had encounted something since then.
>
> Has anyone here tried setting net.inet.ip.fastforwarding on in a high
> traffic enviroment?
>
> This setting DRASTICALLY speeds up transfers betwe
Hi All,
I posted this a coupla days ago and just thought I would ask again in the
hope that someone had encounted something since then.
Has anyone here tried setting net.inet.ip.fastforwarding on in a high
traffic enviroment?
This setting DRASTICALLY speeds up transfers between boxes talking t
18 matches
Mail list logo