🚀 go-pugleaf

Hi Frank,

it's nice to see ISP employees or prinicipals such as yourself
participating in online discussion...

In article <01bcad60$702e9d20$921bf8ce@frankisdn.ott.igs.net>,
  "Frank Kahle" <frank@igs.net> wrote:
>
> The only part I do not like is you base your PING tests, which are highly
> useless from a single source.

I agree that the single source for my current tests is a major
limitation. I hope I've made that clear on my pages. It would be more
useful to perform testing from many locations and networks and I hope to
get involved in such distributed testing. A cross-network system of
communicating monitor programs might help achieve this goal, albeit at
the price of increasing Internet traffic.

> Pings are NOT designed to test performance in any way shape or form.

I contend that they help to determine the latencies experienced by
packets travelling from one site to another. They also help to determine
the internet availability of hosts. Latency and availability to various
sites are both important (but not the only) performance factors to
consider when choosing an ISP or backcone network provider. If ping
performance numbers meant nothing, I would think that more ping utilities
would report success or failure only, rather than ping times in
milliseconds.


>Also it just adds to already congested backbone structures.

I was concerned about this issue in my testing and made some observations
and calculations. I had Pinger pinging about 70 systems, with two pings
of about 64 bytes every 10 minutes at one point.

Including DNS lookups this was sending about 29 KBytes in 282 packets
every 10 minutes, including traffic to my DNS server on Rogers Wave. (I'm
currently running my own cacheing DNS server which reduces my own load on
Rogers network, at least.)

Data received was about 91 KBytes and 300-340 packets every 10 minutes.
The total both ways was about 1 Million bits (120 KBytes) and 600 packets
every 600 seconds. On average this is equivalent to a constant flow of
about 1.8 Kbits/second and 1 packet/second for all of the sites I've been
pinging.


If the Internet can't handle this flow in 1997 from my Rogers Wave
connection then it is in a sorry state and unready for the future. Each
ISP was taking only about 1.5 % of this minimal load. Furthermore, I
beleive that by making the information I collect publicly available and
in a "live" fashion, that I am offering a valuable public service easily
justifying the minimal extra load. We're not talking here about the
Gigabytes of copyright violations, pornography and spam currently
clogging the Internet.


I AM more concerned about the HTTP tests I was running and which I intend
to run again at some point, with my own code. These were causing 5-10
times as much traffic in byte terms. I'm quite concerned about causing
any undue load. I'm open to further comments or suggestions about how to
minimize this load and provide the most useful performance data...


Regards,
Mike Reid.

-------------------==== Posted via Deja News ====-----------------------
      http://www.dejanews.com/     Search, Read, Post to Usenet