Comment don't... (Score 1) 2
don't ask on slashdot.
don't ask on slashdot.
Ok, so you get all the browsers and web servers to change the
way to do things, overnight and by magic, %100 compliance.
You don't make "the Internet faster" because HTTP headers make
up WAY less than %0.01 of the Internet traffic as a whole. If you
want to "make web pages display to the user faster" (there is
more to the Internet than port 80, 81, 443, 3128, 8000, and 8080)
make stupid graphics more cache friendly , place more/better
caches in an ISP's infrastructure, eliminate dynamically
generated static content, and have browsers support
SRV (RFC 2782 http://www.faqs.org/rfcs/rfc2782.html ) .
You also break packet sniffers,proxies, filter rules, and heaps of
other things that count on things that follow RFC standards.
Oh wait, I forgot about magic bit... my bad...
SRV record support would give you a MUCH better web page
viewing experience than rewriting a whole protocol. Its only
been about 10 years since SRV was thought up, and its more
doable than having a one letter substitution on standard replies.
If you point is to reduce number of packets sent across the
net why not put a 4 alpha/num code (a-z A-Z 0-9)for all the tags, that
will give you over 1,300,000 "tags" vs verbose stuff like
__ DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "blah://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.duh
that saves boatloads of space right there. WAY more than the
HTTP headers take up, and since the main HTML page crosses
packet boundaries, you will be reducing the packets transmitted
across the Internet. Those space savings WILL (mostly) cross the
packet boundaries, unlike the HTTP header.
While I applaud your desire to "make the Internet faster" please be
clear that web servers are a small subset of the total Internet traffic,
and HTTP headers are a MUCH smaller bit than that.
Lets travel back in time, pre torrent, around 10 years ago, when the
HTTP was the "biggest clog in the tubes", it made up around %70-%75
of the traffic as a whole.
http://www.isoc.org/inet98/proceedings/6g/6g_3.htm
Your talking about shaving 1 packet off of EACH transaction
AT THE MOST. Each "normal" packet ranges in size from
a few hundred bytes, to 1500, anything in that range is one packet.
Your scheme only "saves packets" when multiple packets are sent
out in the HTTP response, AND when your "savings" crosses
the packet boundary, a rare case.
The web page that you wrote
http://infinity-infinity.com/2009/06/making-the-internet-faster-in-5-minutes/
is over 100k, smaller than the average web page,
http://interface.missouri.edu/2008/05/average-web-page-size-triples.php
and at MOST you are talking about getting a 1k reduction in web
traffic.
If you bothered to run a simple HTML cleaner (tidy) on the web page,
http://infinity-infinity.com/2009/06/making-the-internet-faster-in-5-minutes/
you would save over 7,000 characters , over 10x more than
if everybody adopted your new and magical standard.
Lets take a look at a well written compact web page, www.lois.org ,
it is under 6,000 bytes, yours is over 140,000 bytes. Your raw
HTML is sloppy and verbose. I find it disparaging that, if you
cleaned up your own web pages you would save more packets
than if "every one did things my new and improved way".
I think it would be most ironic if you scrunched up your output,
and then added all the compliance thumbnails, making the result
larger than the uncleaned original.
Google will have some of the same issues as that "other startup",
and lots that are different. A floating oil platform
(to me) works better than a ship based datacenter.
_IF_ Google was to do a floating datacenter, I'd love to see
them take one of the old nuke flat-tops, and use that...
The big E as a datacenter would be killer, better than a pile of scrap.
http://www.defensetech.org/archives/003578.html
http://en.wikipedia.org/wiki/USS_Enterprise_(CVN-65)
http://www.nvr.navy.mil/nvrships/details/CV64.htm
EACH of the A2W power plants can deliver over 26,000 kw
(over 200,000 kw total) , and if you combine the reactor
hot water output, with an amonia based cooling system,
http://en.wikipedia.org/wiki/Einstein_refrigerator
http://www.nh3tech.org/absorption.html
can give low cost cooling.
Here is a letter that I sent to one of the VARS for the "other startup",
strangely enough, I never got an answer back. Perhaps it just got spam filtered out.
The questions remain unanswered....
*********** Mon Feb 4 11:23:17 2008
Received: from [****************.yahoo.com via HTTP; Mon, 04 Feb 2008 11:23:17 PST
Date: Mon, 4 Feb 2008 11:23:17 -0800 (PST)
**********************
Subject: Floating Data Centers?!?
To: ken@teamsilverback.com
MIME-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
Content-Transfer-Encoding: 8bit
Content-Length: 8789
I saw your article about floating datacenters, and since you asked for
input, I thought I would chime in. Let me start off by saying I like the idea,
I know that there is great room for delivering a good product, at a good price point.
Now before I put my racks in a floating data center, here are some of my
concerns and references to real world issues. (I have a lot more, but
that depends on the ship and configuration.),
1) ""using sea water for their chill water"". Having seawater around is
a good heat sink, and since the ships are at dock most of the time, a long
pipe can be run to the cooler water zones to draw in water that is
close to freezing.
http://en.wikipedia.org/wiki/Deep_lake_water_cooling
Using colder sea water (after a standard air heat exchanger) can result in
good economies, if the heat exchangers can stand up to the corrosive environment.
2) ""All generators will have access to the ships fuel storage during disaster scenarios, which
allows them to operate for nearly a month without the need to refuel.""
Traditional fuel for gen sets and large ship engines are very different. An
onboard gen set is like a modern rail road locomotive engine
(http://en.wikipedia.org/wiki/Image:3000hp_curve_ver2.jpg ), and it runs on diesel,
a main power plant for a ship (also a diesel) traditionally runs on Heavy Fuel Oil
(HFO). Without modifications to either the main power plant, or the gen sets, both
engines can not share the same fuel source. Please note the differences between #2
(the traditional fuel for ship board gen sets) , and #6 (Heavy Fuel Oil (HFO), AKA
Bunker C, the traditional fuel for ships manufactured in the 1980's). #6 is almost
a jelly at cold temperatures, and must be heated (to around 100c ) for efficient
movement, and burning. The main engine on a large cargo vessel is also much more
efficient (up to %50) in its use of fuel, making them more economical than the
smaller generators. Gen sets use a small amount of diesel per day, (compared
to the main engine) a 3100 kw gen set will use 4253 gallons of fuel per day
(http://www.antarctica.ac.uk/living_and_working/diaries/rrs_james_clark_ross/antarctic2000_2001/jrupdate86.php
) VS the very large ship engines at 1,660 gph of HFO ( http://people.bath.ac.uk/ccsshb/12cyl/ ).
3) ""able to quickly provide large scale real estate in some of the most real estate impacted
areas of the country."" Dock fees in some of those sections of the country can be
excessive, or what looks like good space can be unsuitable (silt, decaying Warf/dock ,
reserved space), and those spaces can be in some high crime zones. And while the
square footage is impressive, what matters is the gigawatts and gigabits that the
datacenter can throw around, these are dependent on the land based connections.
And now some of my own concerns.
Corrosion, poor ship building and maintenance
A report on the different kinds of corrosion how they occur, and how to detect them
http://www.ocimf.com/view_document.cfm?id=332
"of 29 fatal accidents involving bulk carriers between 1990 and 1994, 55% were due to plate
failure."
"According to Lloyd's September 1995 Shipping Economist, HTS (high-tensile (HT) steel) built ships
are also prone to a phenomenon known as "springing": because the ships are flexible and tend to
vibrate with short sea waves."
http://www.oceansatlas.com/unatlas/issues/safety/transport_telecomm/bulk_carrier/bulk99_una_2.htm
"In the early 1990s three carriers went down after their bows literally fell off. In other
instances, holes suddenly developed in carriers' hulls and some ships vanished without trace. One
bulk carrier that narrowly avoided this fate was the 24-year-old Gallant Dragon. In 1991 the ship
limped into port with a crack 50 metres long in its hull. It was scuttled shortly afterwards and
went down in 7 seconds."
"Last year the 139 000-tonne Diamond Sea, carrying a cargo of iron ore, was forced to put in for
repairs in Portugal with a 20-metre hole in its side. Another bulk carrier, the Protoklitos, was
scuttled, together with its cargo of iron ore, 400 kilometres off the coast of Brazil after it
became too badly damaged even to make the nearest port. And last November, at Ponta da Madeira in
northern Brazil, the Trade Daring broke its back while being loaded with iron ore."
"The best known of the bulk carrier losses is probably the Derbyshire, which went down in the
Pacific in 1980. But it was not a typical loss. The Derbyshire was only four years old, while most
bulk carriers that are lost are older. According to Intercargo, the average age of the carriers
lost between 1990 and 1994 was 18 years. And an investigation by the Australian parliament,
published in 1973, found that iron ore carriers over 15 years old were at the greatest risk of
sinking."
http://space.newscientist.com/article/mg14619752.200-clampdown-on-the-rust-buckets.html
"first-class ship maintenance has become increasingly rare in recent decades. Since the 1970s -
when the Erika, Nakhodka, and Castor were built - profit margins in the tanker business have
fallen steadily. Today, tankers change hands two or three times before they're taken out of
service. Temporary owners of second- or third-hand ships tend to be less interested in maintaining
their vessels than maximizing the return on their investments."
http://www.wired.com/wired/archive/10.06/superrust.html
"The plating of the oil tanker Castor corroded up to seven times faster than normal, causing
massive cracks across its deck that put the ship at risk of explosion or a hull rupture, the
American Bureau of Shipping has determined."
http://www.professionalmariner.com/ME2/SiteMaps/Sites/Document.asp?DocPath=4DEC050EBBB8412E8B2C27A67F745978%7C%7C%7CPublications%3A%3AArticle%7C%7C%7CMain%2BSite%7C%7C%7C
"The tanker being built today is flimsy, highly unreliable, unmaneuverable,
and nearly impossible to maintain. And the situation is becoming
progressively worse."
"Ship managers know that looks are
important. So they do enough chipping and painting to induce the
casual inspector to conclude that the ship is well-maintained. This
also allows them to send pretty pictures back to the owners showing
what a good job they are doing. But real maintenance, especially on
stuff that is not easily visible, is almost non-existent."
"If steel is found to be more than 25% wasted, then it must be replaced.41 Most
tanker owners let their steel deteriorate between Special Surveys and then
negotiate with the surveyor as to how much steel has to be replaced.
25% thickness loss is horribly wasted steel. Steel corrodes very
unevenly."
"The maritime press immediately announced that ABS had discovered a new
phenomenon which it dubbed "super-rust". There is no such thing. What
there is is the same old combination of poor maintenance, and understanding/
forgiving survey standards which eventually leads to a major hull failure."
"As soon as you tell an owner that a ship will be
worthless after age X, where X is any number less than 50, he will rightly
try and build a ship that is designed only to survive to age X. And if you
design a ship that can only survive to age X, you automatically have a ship
that will be a problem at age 0. An age restriction is an open invitation to
shoddy design. In order for a ship to be a good ship, it must be designed
to last forever."
http://www.c4tx.org/ctx/pub/tromedy2.pdf
Why use "end of life" commercial ships of unknown history, when stronger hulls ,
better overall constructed ships, and power plants that are converted to run on
light weight oils, are available for a low cost? (the mothball fleet).
http://hamptonroads.com/2008/01/dont-pay-us-well-pay-you-say-scrappers-ghost-fleet-ships
To me, a better option would be to refurbish the USS Constellation CV-64
(http://www.nvr.navy.mil/nvrships/details/CV64.htm ) , Ranger CV 61 (best choice) ,
or Independence CV 62 (to be sunk as a target because of poor construction practices) ,
these aircraft carriers have large long flat open spaces such as the sheltered
hangar deck and rooms below for lots of storage.
Tidal heaving, and wave action?
Storm damage?
Gen set loads, and load shedding.
Getting gigabit connections to a ship.
Getting enough electric power to a ship.
What happens when a ship must enter dry dock?
How will the hull be maintained?
Dock fires?
http://www.canada.com/victoriatimescolonist/story.html?id=e9b46da6-9af2-4178-a7c2-ebaa6129024c&k=85472
A failure will not appear until a unit has passed final inspection.