At 9:09 AM -0000 11/28/96, Eric Thomas wrote:
>socket. I wouldn't be surprised to hear that you can get these 300k/hour
>using sendmail on the same hardware, if you configured and tuned it for
The number that seems to be getting popular for "high performance"
MTAs is 100K messages per hour. As you point out in your note, metrics
need to be considerably more sophisticated than a simple 'deliveries per
second' number. That, of course, leads to a question about the right set
of measures for list processing software. Given that this is now a product
market segment, it would be helpful to develop ListStones, or somesuch.
If there is interested in separate discussion of this (i.e., if it
is deemed inappropriate to pursue as an extended discussion on this listed)
the IMC would be glad to support a separate list, e.g., imc-listproducts or
imc-listperformance or somesuch.)
>You aren't seriously suggesting that the figures will improve as the
>number of users and hosts in your workload increases? :-) 3000 people
Actually, that's not such a silly possibility, since it allows for
much better aggregation behavior. The difference between the cost of a
single message and address, processed singly, versus the average for a
large number of messages and addresses, can be huge, depending upon the
design for scaling.
d/
ps. I doubt that vanilla sendmail can get even artificial high numbers,
due to its tendency to do single message per connection and even per
process, though perhaps the recent round of enhancements has improved
things.
--------------------
Dave Crocker, Director +1 408 246 8253
Internet Mail Consortium (f) +1 408 249 6205
127 Segré Place dcrocker@imc.org
Santa Cruz, CA 95060 USA http://www.imc.org
Internet Mail Consortium http://www.imc.org, info@imc.org
Follow-Ups:
|
|
