I think that sending a 32 byte ping packet is a little less
strenous on the machine than the mud process. And most machines reply
to pings on the highest priority, and dependening on the machines useage,
the mud may not be #1 on priority.
This is evident when one flood pings a machine that is hooked up
with a 1.5 mbit or faster link to a t1 or greater (ie this will crash the
machine, or lag it to a stop if done right)
=)
At 12:35 PM 8/23/96 -0500, you wrote:
>I am puzzled by the lag behavior of muds.
>They run and then lag (sometimes badly),
>the telnet connections to them time out but
>the host they are on replies to ping immediately
>without errors.
>
>May this be caused by priority aging (specifically
>I think about Sun's), as MUD's usually run on user
>level, not as normal daemons which run in su mode.
>
>Is there any tuning one can do to the source to
>reduce lag? Of course optimize code, but how?
>One can optimize s.t. pageing is minnimized
>(link with the info from the profiler: gmon.out)
>Best tuning: nice --10 ;)
>
>Of course the biggest foe for muds is WWW as it sucks
>up all of the bandwidth of the internet with its pictures
>and ad's.
>
>Another possibility would be to put parts of the MUD
>in special threads, but its impossible whith this
>shared buffer design of circle. Circle is virtually
>free of reentrant code.
>
>Cat.
+-----------------------------------------------------------+
| Ensure that you have read the CircleMUD Mailing List FAQ: |
| http://cspo.queensu.ca/~fletcher/Circle/list_faq.html |
+-----------------------------------------------------------+
This archive was generated by hypermail 2b30 : 12/07/00 PST