Skip to Content.
Sympa Menu

wg-multicast - Re: Lab imaging using multicast

Subject: All things related to multicast

List archive

Re: Lab imaging using multicast


Chronological Thread 
  • From: jf <>
  • To: Ying Zhang <>
  • Cc: wg-multicast <>
  • Subject: Re: Lab imaging using multicast
  • Date: Fri, 09 May 2008 07:24:13 -0400

Another thing to check is to make sure your multicast traffic is staying in the same transmit queues. If you are policing and remarking DSCP, you will want to make sure all traffic toward that multicast address receives the same color.

Ying Zhang wrote:
Thanks for all the replies. To answer all the questions, in case it's helpful for other people.
In the test lab, we have three clients and one server on a Nortel ERS5510 switch with all gig-uplinks. Unicast take 30 minutes and multicast takes 75 minutes. In the real environment with 30 clients, unicast takes 38 minutes while multicast take 3 hours 5 minutes. We found:
- there is no speed mismatch;
- no difference with/without IGMP ;
- very limited configuration on Novell server and client concerning mcast, like bandwidth cap, buffer size, request missed packet etc.;
- in the imaging process, 74 bytes control packets really slow things down. sniff program can't interpret it and no document found on this. We think it's the application causing the slowness.

----- Original Message -----
*From:* Ying Zhang
<mailto:>
*To:* wg-multicast
<mailto:>
*Sent:* Tuesday, May 06, 2008 10:17 AM
*Subject:* Lab imaging using multicast

Hello all,
In our university, we using Novell ZENworks preboot services to
image thousands of lab computers. We found if use unicast to do
imaging, it takes about 30 minutes for each client, while using
multicast takes hours to image a lab with 20+ machines. And the time
increases proportionally with the number of machines. What is
strange about this is it takes a lot longer to do multicast, no
matter how many clients are being imaged.
The server and clients are on the same VLAN. So no multicast routing
is involved. IGMP is enabled on the switch. It uses group address
231.164.242.170. Just wondering if any other universities have
similar experience and what could be done on the network side to
improve the performance. Any help is appreciated.
Ying
UNB



Archive powered by MHonArc 2.6.16.

Top of Page