[mdonohue]

So "page weight" isn't the issue then, contradicting the title. It's the pipeline depth of the page.

[Retric]

Dropped packets are directly related to "page weight" and get worse depending on latency.

400 round trips * 500ms latency is 3 min 20 seconds. This took 20 minutes to load 1 megabyte.

[foobarian]

In other words the bandwidth really is something like 6.6 kbps instead of the nominal rate.

(Really, did anyone ever get the nominal 56k modem rate back in the day?)

[keithpeter]

Yes as it happens, pretty close. Unfortunately British Telecom had a policy of dropping data connections after 2 hours in those days...

[masklinn]

No.

[Silhouette]

Page weight is an issue generally, but particularly for people on mobile where there are often relatively low bandwidth caps before the insane fees kick in.

Page "girth", the number of different parts of a page that need loading via separate requests, is often a more significant issue for performance, again particularly on mobile devices but this time because wireless connections tend to be less reliable and even a modest increase in dropped packets can really hit your effective page load time.