Efficient methods
in [Embedded]
|
From: Grant Edwards on 26 Jan 2010 14:08 On 2010-01-26, Paul E. Bennett <Paul_E.Bennett(a)topmail.co.uk> wrote: > Jim Stewart wrote: >> The most efficient way to send data >> is a 747 cargo plane full of DVD ROMS. > > There was a story about a data file being sent by memory stick > (encrypted) attached to the leg of a carrier pigeon. The > entire file made it to the receivers end by this means before > 30% of the same data file had been transmitted over the > internet connections. I gather that the file was some > 4Gbytes. It was done in South Africa as a stunt to publicize the slow ADSL service provided by Telkom: http://news.bbc.co.uk/2/hi/africa/8248056.stm The pigeon transported 4GB of data 60 miles between two datacenters in 1 hour 8 minutes. The transfer ADSL was 4% complete 4% in the same amount of time. Protocols requiring more interaction don't fare so well when using a Pigeon as a physical layer: http://news.cnet.com/2100-1001-257064.html -- Grant Edwards grante Yow! I threw up on my at window! visi.com
From: Oscar Almer on 26 Jan 2010 14:13 On Tue, 26 Jan 2010 10:19:48 -0800 Jim Stewart <jstewart(a)jkmicro.com> wrote: > karthikbalaguru wrote: > > Hi, > > > > Need to know some efficient > > methods for reception, > > processing and transmission > > of the high speed messages. > > > > Should i need to go in for > > a method of having a > > transmitter thread, queue > > and receiver thread concept ? > > > > Are there alternative efficient > > methods for processing of > > High Speed Messages ? > > The most efficient way to send data > is a 747 cargo plane full of DVD ROMS. Allow me to contend that nowadays it would be SDHC cards (somewhere in the region of 32GB per gram) over trains. A quick google calculator with some assumptions (100 km distance, 50 metric tons effective load / train car, 100Km/h average train speed) gives the bandwidth as (32 gigabytes * 1000 * 1000 * 50) / 1 hour = 434 Terabyte / s. //Oscar
From: FreeRTOS info on 26 Jan 2010 14:30 Oscar Almer wrote: > On Tue, 26 Jan 2010 10:19:48 -0800 > Jim Stewart <jstewart(a)jkmicro.com> wrote: > >> karthikbalaguru wrote: >>> Hi, >>> >>> Need to know some efficient >>> methods for reception, >>> processing and transmission >>> of the high speed messages. >>> >>> Should i need to go in for >>> a method of having a >>> transmitter thread, queue >>> and receiver thread concept ? >>> >>> Are there alternative efficient >>> methods for processing of >>> High Speed Messages ? >> The most efficient way to send data >> is a 747 cargo plane full of DVD ROMS. > > Allow me to contend that nowadays it would be SDHC cards (somewhere > in the region of 32GB per gram) over trains. > > A quick google calculator with some assumptions (100 km distance, 50 > metric tons effective load / train car, 100Km/h average train speed) > gives the bandwidth as > > (32 gigabytes * 1000 * 1000 * 50) / 1 hour = 434 Terabyte / s. > > > > //Oscar ...but how long would it take you to copy the data onto the cards then off the cards again at the other end? Or am I taking this too seriously :o) -- Regards, Richard. + http://www.FreeRTOS.org Designed for Microcontrollers. More than 7000 downloads per month. + http://www.SafeRTOS.com Certified by TÜV as meeting the requirements for safety related systems.
From: D Yuniskis on 26 Jan 2010 14:54 Hi Oscar, Oscar Almer wrote: > On Tue, 26 Jan 2010 10:19:48 -0800 > Jim Stewart <jstewart(a)jkmicro.com> wrote: > >> The most efficient way to send data >> is a 747 cargo plane full of DVD ROMS. > > Allow me to contend that nowadays it would be SDHC cards (somewhere > in the region of 32GB per gram) over trains. > > A quick google calculator with some assumptions (100 km distance, 50 > metric tons effective load / train car, 100Km/h average train speed) > gives the bandwidth as > > (32 gigabytes * 1000 * 1000 * 50) / 1 hour = 434 Terabyte / s. The problem with trains is you can't easily handle the redundancy required to ensure *reliable* delivery. Sure, you can send three different trains with different encodings of the data... but, for most places, there is only one track in or out. So, a wreck of "your" train *on* that track not only results in a loss of the data but, also, the means for getting *other* data to the destination. With planes, this is less of a problem owing to the nature of "plane failures" being self-clearing events -- they intrinsically "fall" out of the way of other planes which might be behind them!
From: Oscar Almer on 27 Jan 2010 05:03
On Tue, 26 Jan 2010 19:30:32 +0000 FreeRTOS info <noemail(a)given.com> wrote: > >> The most efficient way to send data > >> is a 747 cargo plane full of DVD ROMS. > > > > Allow me to contend that nowadays it would be SDHC cards (somewhere > > in the region of 32GB per gram) over trains. > > > > A quick google calculator with some assumptions (100 km distance, 50 > > metric tons effective load / train car, 100Km/h average train speed) > > gives the bandwidth as > > > > (32 gigabytes * 1000 * 1000 * 50) / 1 hour = 434 Terabyte / s. > > > > > > > > //Oscar > > > ...but how long would it take you to copy the data onto the cards then > off the cards again at the other end? Or am I taking this too > seriously :o) > Depends, d'you have something that'll dread them in parallel? I was actually looking for a wee something (of the integrated variety) that could talk to several of them at once a short while ago, and came up emptyhanded. Even so, shouldn't be too hard to gang up a pile of (insert bus type here) readers in parallel though, if you already have something to transfer 1.5 exabytes of data _to_. A physical implementation and speed measurements is left as an exercise for the hobbyists. //Oscar (good typomonster!) |