Skip to Content.
Sympa Menu

wg-multicast - Re: multicast stats

Subject: All things related to multicast

List archive

Re: multicast stats


Chronological Thread 
  • From: "Marshall Eubanks" <>
  • To: <>, Marshall Eubanks <>
  • Cc: Greg Shepherd <>, Jon Zeeff <>,
  • Subject: Re: multicast stats
  • Date: Thu, 04 Sep 2003 20:34:54 -0400

On Thu, 4 Sep 2003 17:57:31 -0700 (PDT)

<>
wrote:
> On Thu, 4 Sep 2003, Marshall Eubanks wrote:
>
> > On Thu, 4 Sep 2003 14:35:53 -0700 (PDT)
> > Greg Shepherd
> > <>
> > wrote:
> > >
> > > On Thu, 4 Sep 2003, Marshall Eubanks wrote:
> > >
> > > > On Thu, 04 Sep 2003 16:03:28 -0400
> > > > Jon Zeeff
> > > > <>
> > > > wrote:
> > > > >
> > > > > How can I find out what are the most popular multicast uses on the
> > > > > Internet? Or perhaps on Abilene (where netflow data is available).
> > > > >
> > > > >
> > > > > For example, I assume that some of the UofOregon traffic is popular,
> but
> > > I
> > > > > don't know for sure.
> > > > >
> > > >
> > > > Ever since ASM RTCP receiver reports withered and died, no one really
> > > knows.
> > > > I am not really sure why this happened. Many people think that having
> > > > each member of a large group send to every other member is not a good
> > > thing,
> > > > but I do not think that it was caused by complaints.
> > >
> > > I recall and early 'complaint' was during the NetAid broadcast. The
> > > issue
> > > was not the sending/recieving of the packets, but the potential
> > > explosion
> > > of state in the routers. Every sending 'receiver' would create an S,G
> > > entry in the network. We were targeting 10K's of S's for just this one
> > > G.
> > > It became clear that any large audience adoption of mcast would create
> > > an
> > > unmanagable amount of network S,G state IF ASM RTCP were the receiver
> > > reporting mechanism.
> > >
> > > > My experiments indicate that I do not get RR's for more than a tiny
> > > > fraction (<< 1/10th) of the audience, but what that fraction is
> > > > is unknown. Most times all I really know is whether or not
> > > > I have outbound state.
> > >
> > > Marshall, does your app use mcast of ucast for receiver reports?
> >
> > The MCTPlayer does send back unicast RR's here, but its use has never been
> more
> > than a small fraction of the total usage of our MP3 channels (about 1/8th
> > of reported usage, which is of course not the full usage).
> >
> > Our new video multicasts use Quicktime (and Real, as soon as we get
> > the bugs out), and those use standard RTCP.
>
> 'standard' RTCP being mcast?

Quicktime does a pretty good job with rtcp reports except that I found
recently
that, for
MPEG-4 only, the TTL was set equal to one, which does cut down on the traffic.

Real sends perfectly formatted RTCP RR's, but for some reason it sends them
_very_ infrequently - maybe once every 15 minutes or less. Again, it
keeps the traffic down - and maybe some get eaten because of the low
frequency.
RealOne rarely if ever sends "TOOL" reports; I only know this because of
in-house tests.

You might find this interesting - it's from one day of the IETF-57 multicasts.

[tme@hendrix
dump]$ more ietf57.report.full

rtcp_parse : Information From RTCP Reports

For the Period From Wed Jul 16 06:12:42 2003 to Thu Jul 17 10:53:30 2003
Total Duration = 1.20 Days

There were 47 Separate IP Addresses Encountered
There were 46 Separate Receivers Encountered
There were 8 Separate Sources Encountered
There were 19 Separate TOOLS Encountered

Overall Packet Loss Statistics

There were 58204 Loss Reports Encountered
Of these 66.49 Per Cent Had Zero Loss

Average packet loss fraction = 11.85 per cent
Maximum packet loss fraction = 99.61 per cent
RMS packet loss fraction = 19.94 per cent

Source Information :

81.160.32.10 used port 64390 : 13211 records read
81.160.32.2 used port 61010 : 23667 records read
81.160.32.4 used port 49470 : 13036 records read
81.160.32.6 used port 61030 : 4650 records read
81.160.32.7 used port 61041 : 23 records read
81.160.32.8 used port 61020 : 38621 records read
lagavulin.cc.tut.fi used port 61031 : 2 records read
drift3.uninett.no used port 61031 : 3 records read

Receiver Information :

RW-18.MIT.EDU used port 64391 : 765 records read
dhcp-64-101-64-92.cisco.com used port 49471 : 327 records read
81.160.32.10 used port 64390 : 16 records read
81.160.32.12 used port 32798 : 18725 records read
81.160.32.2 used port 61010 : 15 records read
81.160.32.4 used port 49470 : 13844 records read
81.160.32.6 used port 61030 : 1873 records read
81.160.32.7 used port 1033 : 1900 records read
81.160.32.8 used port 61020 : 6446 records read
81.160.96.41 used port 1229 : 1448 records read
adam.cs.ucl.ac.uk used port 33000 : 2 records read
D-128-208-20-224.dhcp4.washington.edu used port 61020 : 1 records read
d125-137.uoregon.edu used port 2111 : 3 records read
tesla.uoregon.edu used port 1040 : 219 records read
iceberg.uoregon.edu used port 61030 : 772 records read
icecast.uoregon.edu used port 61011 : 799 records read
c84.al.cl.cam.ac.uk used port 1107 : 19 records read
klap.utdallas.edu used port 61030 : 269 records read
telstar12.gmd.de used port 32797 : 141 records read
tikal.TechFak.Uni-Bielefeld.DE used port 39342 : 52 records read
samipelt.atm.tut.fi used port 61030 : 1 records read
kongi.atm.tut.fi used port 61030 : 1 records read
130.237.95.246 used port 61041 : 6 records read
130.237.95.69 used port 58983 : 6 records read
minotaure.ipv6.lip6.fr used port 1108 : 2 records read
churchward.erg.abdn.ac.uk used port 49979 : 19 records read
arcangel-mac.erg.abdn.ac.uk used port 49470 : 2 records read
cna4-044.cna.depaul.edu used port 61010 : 2375 records read
dhcp-peg3-vl30-144-254-7-119.cisco.com used port 61011 : 13 records read
dhcp-peg3-vl30-144-254-7-137.cisco.com used port 64391 : 2383 records read
dhcp-peg3-vl30-144-254-7-65.cisco.com used port 61011 : 655 records read
dhcp-bru-peg2-vl26-144-254-9-170.cisco.com used port 61011 : 241 records
read
mobi4.tmit.bme.hu used port 1055 : 2 records read
drift3.uninett.no used port 40604 : 1 records read
sapporo.uninett.no used port 33249 : 5 records read
sverresborg.uninett.no used port 32827 : 1 records read
laptop13.cs.utk.edu used port 61031 : 1866 records read
valley.aarnet.edu.au used port 64391 : 9840 records read
dhcp181.heanet.ie used port 4635 : 1 records read
dhcp183.heanet.ie used port 61010 : 3 records read
brage.nta.no used port 1051 : 2 records read
jazz.rap.prd.fr used port 4191 : 2 records read
dhcp124.dante.org.uk used port 1079 : 636 records read
visio2.univ-paris13.fr used port 1099 : 9 records read
prt80-cc.univ-paris13.fr used port 1669 : 6 records read
cc8.univ-paris13.fr used port 1940 : 5 records read

tool Cisco IP/TV Server (3.4.0) was used by 1 addresses
tool Illegal String was used by 2 addresses
tool IP/TV Viewer (3.2), version 3.2.24.0 was used by 2 addresses
tool IP/TV Viewer (3.4.20), version 3.4.20.0 was used by 1 addresses
tool IP/TV Viewer (3.4), version 3.4.14.0 was used by 3 addresses
tool QuickTime Streaming/4.1.1 was used by 3 addresses
tool QuickTime Streaming/5.0.2 was used by 2 addresses
tool QuickTime Streaming/6.3 was used by 2 addresses
tool vic-2.8/NetBSD-1.6U-i386 was used by 1 addresses
tool vic-2.8/SunOS-5.8-sun4u was used by 1 addresses
tool vic-2.8ucl-1.0/Windows NT-4.0-intel was used by 1 addresses
tool vic-2.8ucl-1.1.3/SunOS-5.8-sun4u was used by 1 addresses
tool vic-2.8ucl-1.1.3/Windows 95-4.10-intel was used by 1 addresses
tool vic-2.8ucl-1.1.3/Windows NT-5.1-intel was used by 3 addresses
tool vic-2.8ucl1.1.5/Linux-2.4.20-8-i686 was used by 1 addresses
tool vic-2.8ucl1.1.5/Windows 95-4.10-intel was used by 1 addresses
tool vic-2.8ucl4/Linux-2.4.7-10-i686 was used by 1 addresses
tool vic-5.2/Linux-2.4.20-18.7-i686 was used by 1 addresses
tool vic-5.2/Linux-2.4.20-18.9-i686 was used by 1 addresses

RW-18.MIT.EDU used tool
Illegal String
dhcp-64-101-64-92.cisco.com used tool QuickTime
Streaming/5.0.2
81.160.32.10 used tool IP/TV Viewer (3.4.20),
version
3.4.20.0
81.160.32.12 used tool vic-2.8ucl-1.1.3/Windows
NT-5.1-intel
81.160.32.4 used tool IP/TV Viewer (3.2),
version
3.2.24.0
81.160.32.6 used tool Cisco IP/TV
Server (3.4.0)
81.160.32.7 used tool
vic-5.2/Linux-2.4.20-18.9-i686
81.160.32.8 used tool IP/TV Viewer (3.4),
version
3.4.14.0
81.160.96.41 used tool vic-2.8ucl1.1.5/Windows
95-4.10-intel
adam.cs.ucl.ac.uk used tool
Illegal String
tesla.uoregon.edu used tool
vic-5.2/Linux-2.4.20-18.7-i686
iceberg.uoregon.edu used tool IP/TV Viewer (3.4),
version
3.4.14.0
icecast.uoregon.edu used tool vic-2.8ucl-1.0/Windows
NT-4.0-intel
c84.al.cl.cam.ac.uk used tool
vic-2.8ucl4/Linux-2.4.7-10-i686
klap.utdallas.edu used tool IP/TV Viewer (3.2),
version
3.2.24.0
telstar12.gmd.de used tool
vic-2.8ucl1.1.5/Linux-2.4.20-8-i686
tikal.TechFak.Uni-Bielefeld.DE used tool
vic-2.8/SunOS-5.8-sun4u
130.237.95.246 used tool QuickTime
Streaming/6.3
130.237.95.69 used tool
vic-2.8/NetBSD-1.6U-i386
churchward.erg.abdn.ac.uk used tool
vic-2.8ucl-1.1.3/SunOS-5.8-sun4u
cna4-044.cna.depaul.edu used tool IP/TV Viewer (3.4),
version
3.4.14.0
dhcp-peg3-vl30-144-254-7-119.cisco.com used tool QuickTime
Streaming/4.1.1
dhcp-peg3-vl30-144-254-7-137.cisco.com used tool QuickTime
Streaming/5.0.2
dhcp-peg3-vl30-144-254-7-65.cisco.com used tool QuickTime
Streaming/4.1.1
dhcp-bru-peg2-vl26-144-254-9-170.cisco.com used tool QuickTime
Streaming/4.1.1
laptop13.cs.utk.edu used tool QuickTime
Streaming/6.3
dhcp124.dante.org.uk used tool vic-2.8ucl-1.1.3/Windows
NT-5.1-intel
visio2.univ-paris13.fr used tool vic-2.8ucl-1.1.3/Windows
95-4.10-intel
cc8.univ-paris13.fr used tool vic-2.8ucl-1.1.3/Windows
NT-5.1-intel


>
> Greg
>
> > Marshall
> >
> > >
> > > Greg
> > >
> > > > Marshall
> > > >
> > > >
> > >
> >
>




Archive powered by MHonArc 2.6.16.

Top of Page