> I decided to measure this number to see what I'd get between
> my home and a machine at the office.
>
> My home machine is connected to a 100 Mb/s hub.
> The hub is connected to the home end of an ADSL modem pair.
> That modem is connected to the other end of the pair at the
> office (uplink/downlink of 256kb and 1.5Mb, I believe).
> The office modem is connected to the DSL switch, which is
> connected to the backbone switch, which is then connected
> to the office switch, all of which are switched fast ethernet.
> The link to my office is 10 Mb/sec, and then there's another
> 100 Mb/sec hub to which my desktop machine is connected.
>
> Ping reports the average round-trip time to be < 7ms on this
> "unaggressively designed network".
>
> 64 packets transmitted, 64 packets received, 0% packet loss
> round-trip min/avg/max/stddev = 6.555/6.775/12.308/0.710 ms
Nicely configured home network, there!
The hopcount does nicely model my "not-so-perfect" internal network.
In fact, its tinygram latency is 1-2 ms worse than what I expect
from that 'unaggressive internal network'.
And I like the numbers.
> That's not bad for 7 intermediate devices between two machines,
> and is hardly a death knell for centralized caching within an
> office.
There is just one thing your measurement fails to capture: waiting for
the bytes to transit over the 10Mbps link. Do a
ping -s 12000
(the mean Web object size that Squids seem to see is a tad over 12k)
...and THEN report back.
-- Jon Kay pushcache.com jkay@pushcache.com http://www.pushcache.com/ (512) 420-9025 Squid installation, maintenance, and coding 'push done right.'Received on Tue Dec 25 2001 - 01:27:48 MST
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 17:05:29 MST