Misplaced Pages

HTTP pipelining

Article snapshot taken from Wikipedia with creative commons attribution-sharealike license. Give it a read and then ask your questions in the chat. We can research this topic together.

This is an old revision of this page, as edited by Jmax- (talk | contribs) at 13:36, 2 July 2007 (I don't see how that report is "by Yahoo". The domain is owned by Mark Nottingham, and the content is his personal blog. He may work for Yahoo, but he doesn't speak for Yahoo through that means.). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

Revision as of 13:36, 2 July 2007 by Jmax- (talk | contribs) (I don't see how that report is "by Yahoo". The domain is owned by Mark Nottingham, and the content is his personal blog. He may work for Yahoo, but he doesn't speak for Yahoo through that means.)(diff) ← Previous revision | Latest revision (diff) | Newer revision → (diff)
Schema of non-pipelined vs. pipelined connection.

HTTP pipelining is a technique in which multiple HTTP requests are written out to a single socket without waiting for the corresponding responses. Pipelining is only supported in HTTP/1.1, not in 1.0.

The pipelining of requests results in a dramatic improvement in page loading times, especially over high latency connections (such as satellite Internet connections).

Since it is usually possible to fit several HTTP requests in the same TCP packet, HTTP pipelining allows fewer TCP packets to be sent over the network, reducing network load.

Only idempotent requests should be pipelined, such as GET and HEAD requests. POST requests should not be pipelined. Requests on a new connection shouldn't be pipelined either, since it has not yet been determined if the origin server (or proxy server) supports HTTP/1.1. Hence, pipelining can only be done when reusing an existing (keepalive) persistent connection.

HTTP pipelining requires both the client and the server to support it. HTTP/1.1 conforming servers are required to support pipelining. This does not mean that servers are required to pipeline responses, but that they are required not to fail if a client chooses to pipeline requests.

Implementation status

Implementation in web servers

Implementing pipelining in web servers is easy: it is enough to make sure that network buffers are not discarded between requests. For that reason, most modern web servers handle pipelining just fine.

Exceptions include IIS 4 and reportedly 5.

Implementation in web browsers

Internet Explorer as of version 7 doesn't support pipelining.

Mozilla Firefox 2.0 supports pipelining, but it's disabled by default. It uses some heuristics, especially to turn pipelining off for IIS servers. Instructions for enabling pipelining can be found here Firefox Help: Tips & Tricks.

Konqueror 2.0 supports pipelining, but it's disabled by default. Instructions for enabling it can be found here Konqueror: Tips & Tricks.

Opera has pipelining enabled by default. It uses heuristics to control the level of pipelining employed depending on the connected server.

Implementation in web proxies

Most HTTP proxies do not pipeline outgoing requests, as demonstrated by this report.

Some versions of the Squid web proxy will pipeline up to two outgoing requests. This functionality has been disabled in the latest versions.

The Polipo proxy pipelines outgoing requests.

Other implementations

Some other applications currently exploiting pipelining are phttpget from FreeBSD (a minimalist pipelined HTTP client) and portsnap (a FreeBSD ports tree distribution system).

External links

Category: