RFC 415

RFC 415: TENEX BANDWIDTH 💖

okay bestie, the title block first 🎀 this one is from H. Murray at Stanford Research Institute, it's NIC 392, and it's dated 29 November 1972 🦋 nothing in the header says it obsoletes or updates anything, so it's just its own little thing 🌸

Starting point 🧚

okay so NIC 11584 (RFC 392) by G. Hicks and B. Wessler at Utah was talking about how much it costs to use the network 💸 this author wanted to look at the same kinds of numbers from a different angle, no cost math, just how far the hosts can actually go 🔥 they wrote a little TENEX program that sent strings to itself over the net 💅 it used BIN/BOUT and buffered send mode, and it only counted stuff, it didn't actually process the string 🙈 they ran samples of a million bits and got these results 👑

BYTES/SIZE      REAL BAUD       CPU BAUD      CPU NEEDED

  50/36          48.8K           291K          16%
 100/36          46.5K           309K          15%
 200/36          52.7K           322K          16%
 400/36          59.3K           267K          22%
 800/36          61.1K           279K          21%

  50/8           22.0K           70K           31%
 100/8           26.7K           76K           35%
 200/8           29.0K           79K           36%
 400/8           30.0K           81K           37%
 800/8           31.9K           78K           40%
1600/8           38.1K           64K           59%
3200/8           41.8K           59K           70%

next up, they did it with SIN/SOUT and NO buffered mode 🥺 the results are below 🍓

BYTES/SIZE      REAL BAUD       CPU BAUD      CPU NEEDED
  50/36          36K             95K           38%
 100/36          44K             95K           45%
 200/36          49K             92K           53%
 400/36          54K             90K           60%

  50/8           12K             22K           57%
 100/8           16K             21K           75%
 200/8           18K             20K           92%
 400/8           20K             20K           99%

RFC 415 TENEX BANDWIDTH November 1972

the tests ran with NO other load on their system, which was an early version of 1.29 🧚 the input and output halves got averaged together, so the baud rates above were worked out using 2 million bits, since the strings went out AND came back in 💜

Other pieces of data ✨

their TTYs and LPT have ultimate CPU bandwidths around 15-20 KB 🖨️ at 2400 baud, a TTY eats 15% of the CPU 😭 and telnets nested three deep are almost compute limited just from typing stuff out on a 2400 baud terminal 💀

rough math time 🎀 the bandwidth of the TIP tape transmission feature, using Steve Butterfield's (of BBN) NETMAG program, is about 7 kilobits/sec 🦋 one tape of about 6,000 TENEX pages took about 4 hours to send 🌈 it was a full tape from ETAC to CCA late one night with nothing else running on their system 🌙 about 30% of the CPU is needed to keep up this bandwidth 🔥 and again, that's only about 20KB per CPU sec 👑

[This RFC was put into machine readable form for entry] [into the online RFC archives by Helene Morin, Via Genie 12/99]