Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 27 Apr 2012 13:21:04 +0000
From:      Javier - <javier_9185@hotmail.com>
To:        <rizzo@iet.unipi.it>
Cc:        freebsd-ipfw@freebsd.org
Subject:   RE: Dummynet and bursting!
Message-ID:  <SNT136-W152D11EF4664B93A7936FB96250@phx.gbl>
In-Reply-To: <20120427130200.GA17737@onelab2.iet.unipi.it>
References:  <20120427065523.GA90180@onelab2.iet.unipi.it> <SNT136-W154D1068D52BC93BA4553D96250@phx.gbl>, <20120427130200.GA17737@onelab2.iet.unipi.it>

next in thread | previous in thread | raw e-mail | index | archive | help

I will make more testing and comment.
what=B4s the max value for burst? i did not find this in docs...

=20

=20


----------------------------------------
> Date: Fri=2C 27 Apr 2012 15:02:00 +0200
> From: rizzo@iet.unipi.it
> To: javier_9185@hotmail.com
> CC: freebsd-ipfw@freebsd.org
> Subject: Re: Dummynet and bursting!
>
> On Fri=2C Apr 27=2C 2012 at 12:40:05PM +0000=2C Javier - wrote:
> >
> > OK=2C but with increased burst to 5mbytes i have same results.
> >
>
> the issue is the bandwidth=2C not the burst.
> it is possible that the system has a bottleneck
> similar to the 125k you are configuring.
> Besides=2C the tcp window or socket buffer might be
> small (say 64Kbytes) so you won't be able to
> use the burst anyways.
>
> luigi
>
> > will try fresh install from freebsd (no pfsense)=2C and the results wil=
l be posted later.
> >
> >
> >
> > Thanks!
> >
> >
> >
> > ---------------------------------------------------------------
> >
> > Transfer estimates are completely unreliable in general=2C
> > you need time for tcp to open the window=2C plus the RTT
> > of the connection influences the throughput=2C etc.
> >
> > You can perhaps make some reasonable test by setting a low
> > bandwidth. Burst seems to work fine here (on stable/9)=2C see below
> >
> > --- no pipes=2C no nothing ---
> > > ping localhost
> > PING localhost (127.0.0.1): 56 data bytes
> > 64 bytes from 127.0.0.1: icmp_seq=3D0 ttl=3D64 time=3D0.079 ms
> > 64 bytes from 127.0.0.1: icmp_seq=3D1 ttl=3D64 time=3D0.064 ms
> > ^C
> >
> > --- one 10Kbit/s pipe=2C no burst ---
> > > sudo ipfw add 100 pipe 1 proto icmp out
> > 00100 pipe 1 ip from any to any proto icmp out
> > > sudo ipfw pipe 1 config bw 10Kbit/s burst 0
> > > sudo ipfw pipe show
> > 00001: 10.000 Kbit/s 0 ms burst 0
> > q131073 50 sl. 0 flows (1 buckets) sched 65537 weight 0 lmax 0 pri 0 dr=
optail
> > sched 65537 type FIFO flags 0x0 0 buckets 0 active
> > > ping localhost
> > PING localhost (127.0.0.1): 56 data bytes
> > 64 bytes from 127.0.0.1: icmp_seq=3D0 ttl=3D64 time=3D134.602 ms
> > 64 bytes from 127.0.0.1: icmp_seq=3D1 ttl=3D64 time=3D135.011 ms
> > 64 bytes from 127.0.0.1: icmp_seq=3D2 ttl=3D64 time=3D135.019 ms
> > ^C
> >
> > --- now increase the burst to 100Kbytes ---
> > > sudo ipfw pipe 1 config bw 10Kbit/s burst 100K
> > > sudo ipfw pipe show
> > 00001: 10.000 Kbit/s 0 ms burst 102400
> > q131073 50 sl. 0 flows (1 buckets) sched 65537 weight 0 lmax 0 pri 0 dr=
optail
> > sched 65537 type FIFO flags 0x0 0 buckets 0 active
> > > ping localhost
> > PING localhost (127.0.0.1): 56 data bytes
> > 64 bytes from 127.0.0.1: icmp_seq=3D0 ttl=3D64 time=3D0.070 ms
> > 64 bytes from 127.0.0.1: icmp_seq=3D1 ttl=3D64 time=3D0.083 ms
> > 64 bytes from 127.0.0.1: icmp_seq=3D2 ttl=3D64 time=3D0.066 ms
> > ^C
> >
> > cheers
> > luigi
> > ----------------------------------------
> > > Date: Fri=2C 27 Apr 2012 13:49:41 +0200
> > > From: rizzo@iet.unipi.it
> > > To: javier_9185@hotmail.com
> > > CC: freebsd-ipfw@freebsd.org
> > > Subject: Re: Dummynet and bursting!
> > >
> > > On Fri=2C Apr 27=2C 2012 at 10:50:17AM +0000=2C Javier - wrote:
> > > >
> > > > I want to leave at cable speed n bytes=2C after n bytes apply the q=
ueue bw limit...
> > >
> > > and what are you seeing instead ? Do you have a trace or
> > > something that shows that it does not work like this ?
> > >
> > > cheers
> > > luigi
> > >
> > > > In Linux with htb this is done with cburst parameter...
> > > >
> > > >
> > > >
> > > > Regards!
> > > >
> > > >
> > > > > Date: Fri=2C 27 Apr 2012 08:55:23 +0200
> > > > > From: rizzo@iet.unipi.it
> > > > > To: javier_9185@hotmail.com
> > > > > CC: freebsd-ipfw@freebsd.org
> > > > > Subject: Re: Dummynet and bursting!
> > > > >
> > > > > On Fri=2C Apr 27=2C 2012 at 04:57:20AM +0000=2C Javier - wrote:
> > > > > >
> > > > > >
> > > > > >
> > > > > >
> > > > > > Hello all!=2C i?m researching about bursting with dummynet?s pi=
pes. i can?t find the way in order to make the burst paramter work under pi=
pe command=3Bpipe config ........ burst 500000 (500Kbytes)->not luck pipe c=
onfig ........ burst 500000 queue 500Kbytes ->not luck These parameters see=
ms to be ok under pipe show=2C but no effect on real escenario... traffic i=
s anyway at same speed defiined by "bw". Any help/comment wll be appreciate=
d...specially from Luigi! Is he alive on the list? Regards! _______________=
________________________________
> > > > >
> > > > > can you clarify what you are expecting and what you are seeing ?
> > > > >
> > > > > cheers
> > > > > luigi 		 	   		  =



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?SNT136-W152D11EF4664B93A7936FB96250>