On Mon, 3 Nov 1997, Bill Studenmund wrote:
> No clue. What happens if you stick in a jra _ASM_LABEL(rei)?

Well, ping times are much better:
----gedd.metonymy.com PING Statistics----
23686 packets transmitted, 23686 packets received, 0% packet loss
round-trip min/avg/max = 0.612/0.641/12.373 ms
  1522.0 packets/sec sent,  1522.0 packets/sec received

And throughput is a bit better too...

Pentium 166 w/3C595 to Centris 660av:
ttcp-t: buflen=8192, nbuf=2048, align=16384/+0, port=5001  tcp  -> gedd
ttcp-t: socket
ttcp-t: connect
ttcp-t: 16777216 bytes in 16.29 real seconds = 1005.66 KB/sec +++
ttcp-t: 2048 I/O calls, msec/call = 8.15, calls/sec = 125.71
ttcp-t: 0.0user 2.2sys 0:16real 13% 0i+0d 0maxrss 0+0pf 2980+15csw

Centris 660av to P166:
ttcp-r: buflen=8192, nbuf=2048, align=16384/+0, port=5001  tcp
ttcp-r: socket
ttcp-r: accept from 10.1.1.68
ttcp-r: 16777216 bytes in 18.86 real seconds = 868.55 KB/sec +++
ttcp-r: 11587 I/O calls, msec/call = 1.67, calls/sec = 614.25
ttcp-r: 0.0user 0.6sys 0:18real 3% 0i+0d 0maxrss 0+0pf 11586+11csw

(see http://www.bga.com/~khym/netbsd/ttcp.html for numbers with the rte
instead of jra _ASM_LABEL(rei))... The quick summary is 869.69KB/s
receiving and 860.80KB/s sending.

Serial performance is perhaps slightly worse than before, but not
significantly, in my opinion. I ftp'd a file over a 57.6kbps PPP
connection (null modem, so it really is 57.6k) while flood pinging the
Mac, and got occasional ring overruns, but I was getting those before too.
I don't know what the change would do on slower machines like the Mac II
though.