IP packet size distribution (970780293 total packets): 1-32 64 96 128 160 192 224 256 288 320 352 384 416 448 480 .000 .497 .094 .013 .009 .006 .007 .010 .010 .014 .004 .005 .002 .002 .002 ^^^^ 512 544 576 1024 1536 2048 2560 3072 3584 4096 4608 .004 .002 .189 .000 .069 .053 .000 .000 .000 .000 .000
Collected at a private interconnect between CICNet, OARnet and OSU. over a period of a week or so.
This is not surprising if you think of it. Short packets are pure ACKs, telnet keystrokes and SYNs. What is worrying is the peak at 576. It means TCP unable to grasp that path MTU is really 1.5K. --vadim
On Wed, 19 Jun 1996, Vadim Antonov wrote:
512 544 576 1024 1536 2048 2560 3072 3584 4096 4608 .004 .002 .189 .000 .069 .053 .000 .000 .000 .000 .000
Collected at a private interconnect between CICNet, OARnet and OSU. over a period of a week or so.
This is not surprising if you think of it. Short packets are pure ACKs, telnet keystrokes and SYNs. What is worrying is the peak at 576. It means TCP unable to grasp that path MTU is really 1.5K.
Agreed. There's alot of bad/old implementations out there, and that's something that should cause some worry.. -dorian
participants (2)
-
avg@postman.ncube.com
-
Dorian Kim