TCP-brutal: TCP congestion control algorithm operates on a fixed rate model

Re:TCP-brutal: TCP congestion control algorithm operates on ... by don-code on Monday November 06, 2023 @12:53PM (#38166007)

Norton Ghost could do something similar, but with UDP multicast. You'd boot a room full of machines to Ghost, have them join a multicast group, multicast an OS image to them, and then have the host machine just send the image out once (from its perspective), saving a ton of bandwidth in the process. The individual machines would then rerequest any chunks that they missed.

[ Parent | on HN ]

Re:TCP-brutal: TCP congestion control algorithm operates on ... by phyzome on Monday November 06, 2023 @12:58PM (#38166091)

Sounds very torrent-y.

[ Parent | on HN ]

Re:TCP-brutal: TCP congestion control algorithm operates on ... by ale42 on Monday November 06, 2023 @05:19PM (#38169905)

Except that Ghost was using (or still uses? I switched to udpcast since ages) ACKs from the destination hosts to adapt the bandwidth dynamically. So you didn't have to give/impose the bandwidth. The funny part was when a machine in a room with 45 PCs was misbehaving (read: failing HD), basically bringing the transfer rate close to zero for the whole deployment... and good luck finding out which machine it was.

[ Parent | on HN ]

Re:TCP-brutal: TCP congestion control algorithm operates on ... by EvanAnderson on Monday November 06, 2023 @06:43PM (#38170944)

Exactly my experience w/ Ghost, too. I moved over to udpcast as well. (The last time I did this kind of work I simply ended up blasting the output of "ntfsclone" via udpcast. I was very happy w/ how it worked.)

[ Parent | on HN ]

Re:TCP-brutal: TCP congestion control algorithm operates on ... by ale42 on Tuesday November 07, 2023 @03:38AM (#38174563)

Am almost doing the same, basically udpcasting a file that was created with partclone.ntfs -c, and piping that to partclone.ntfs -r :)

[ Parent | on HN ]