This is especially relevant to satellite IP networks where the
latency affects each TCP connection by limiting the maximum
throughput to an un-modified TCP stack on a client.
Opening multiple parallel TCP connections is a way "pull" more
bandwidth on "one session".
You're right though, it probably wouldnt improve things over low
latency 56k or T1 lines.
jm
>?Some download managers such as NetAnts claim to be designed to maximize
>throughput by making multiple HTTP connections, each of which downloads
>a separate part of a single big file.
>
>I wonder why doing this is helpful.
>
>Suppose a user connects to the Internet via a 56kbps line. His first
>HTTP connection should consume all the bandwidth of his line, how can
>the multiple simultanous connections help?
>
>Assume the Web server haven't limited the transfer rate for the requests
>to it. If the user had a 1.5Mbps line now, then his first HTTP
>connection could still transfer the file at 1.5Mbps (assume the network
>is not the bottleneck), how can the multiple connections help?
>
>Now suppose the network is the performance bottleneck (maybe network
>congestion), then no matter how many simultanous connections are used,
>the overall transfer speed is limited by the network. How can the
>multiple connections help?
>
>However, by real experience, this kind of download manager is helpful
>and reduce the overall respond time. Why? Is it related to the HTTP 1.1?
>
>Thank you for your attention.
>
>Angus Wong
This archive was generated by hypermail 2b29 : Thu May 31 2001 - 12:56:26 EDT