Google Chrome web protocol seeks 2x download speeds
HTTP gets SPDY
Customer Success Testimonial: Recovery is Everything
Updated Google is developing a new application layer protocol designed to speed the movement of stuff across the web. It's called SPDY, pronounced, yes, speedy.
Unveiled Thursday with a post to the Google Research blog, this "early-stage" research project is specifically designed to reduce latency via things like multiplexed streams, request prioritization, and HTTP header compression.
The blog post is entitled A 2x faster web.
The company's research arm has already developed a prototype web server and, yes, Google Chrome client that make use of the protocol. In the lab, Google says it sees "up to" a 55 per cent improvement when downloading the web's top 25 sites over simulated home connections.
"There is still a lot of work we need to do to evaluate the performance of SPDY in real-world conditions. However, we believe that we have reached the stage where our small team could benefit from the active participation, feedback and assistance of the web community," the company says.
In its post, Google implied that good ol' http needs an update: "HTTP is an elegantly simple protocol that emerged as a web standard in 1996 after a series of experiments. HTTP has served the web incredibly well. We want to continue building on the web's tradition of experimentation and optimization, to further support the evolution of websites and browsers."
But Google's documentation explains that SPDY is not a means of replacing http. It will create a session between the HTTP application layer and the TCP transport layer. That said, this session uses an HTTP-like request-response setup.
"SPDY replaces some parts of HTTP, but mostly augments it," reads a Google FAQ. "At the highest level of the application layer, the request-response protocol remains the same. SPDY still uses HTTP methods, headers, and other semantics. But SPDY overrides other parts of the protocol, such as connection management and data transfer formats."
As it rolls out all sorts of web-based applications, Google is intent on juicing web speeds. That's why it launched its very own browser, Chrome, with its very own JavaScript engine, and that's why Chrome will soon drive Google's very own operating system.
Presumably, Google's aim it to make this a web-wide standard. It has, after all, opened up documentation and code to world+dog. " the goal is to make SPDY work in all browsers to further test our research and to help make the web faster for all users," the company tells us. But a prototype is already in place with Chrome. One wonders how its competitors will take to the idea. ®
Update: This story has been updated with comment from Google.
COMMENTS
@What about IETF and RFC process
The trouble with IETF, RFC, W3C, ECMA etc is that they really know how to bodge a standard - and in the process take years to do it. Look at the shitty "ratified" standards out there for POP3, SMTP, HTTP, HTML, Javascript etc - they are all pants. What is the use of all these committees to check standards, allow all sorts of proprietary rubbish to seep in and then keep coming up with the rubbish that they have.
I actually have sympathy with Microsoft, Google and Sun (Java) because the standards processes are just an excuse for company retards to have a few meetings to discuss politics and get an expenses paid vacation, elongating the process to ensure that next years vacation is sorted. By the time the "community" finish with this protocol it will be ruined. Sometimes you need a big company to come in and just produce a protocol - then things will start to happen.
Google here are doing the right thing and it is in everybodies interest if there are no patent issues - and hopefully it will be adopted because HTTP is a bit old fashioned now and there is scope for improvement, especially now that HTTP is being used for Web 2 communication. If, like AC mentioned, Apache and Mozilla adopt it then it will become standard.
apache?
get support added to apache and it'll become a standard protocol supported everywhere (as sites gradually update they will get support, then browsers will add support, so then other web servers will add support)... don't get it added to standard apache enabled by default, well it's probably not going to make it very far
so apache guys, question for you: will this protocol become standard or will it fail? the decision is yours...
Re: This is good - for Google, not for us
“The price is shoving everything every time down to the client…”
Definitely not good for us. That would eat into download allocation and would appear to make local caches & proxies pointless (at least where this protocol is supported).

IT infrastructure monitoring strategies
Agentless Backup is Not a Myth
Top 10 SIEM implementer’s checklist
Steps to Take Before Choosing a Business Continuity Partner
Enabling efficient data center monitoring