Beta

Slashdot: News for Nerds

×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Making BitTorrent Clients Prioritize By Geography?

timothy posted more than 5 years ago | from the hey-you're-blocking-my-bandwidth dept.

Software 227

Daengbo writes "While I live in S.Korea and have virtually unlimited bandwidth in and out of the country, not all my Asian friends are so lucky. Many of the SE Asian and African countries have small international pipes. Even when a user has a high-speed local connection, downloads from abroad will trickle in. Bittorrent clients apparently don't prioritize other users on the same ISP or at least in the same country. Why is that? Is it difficult to manage? If I were to write a plug-in for, say, Deluge, what hurdles would I be likely to come across? If this functionality is available in other clients or through plug-ins, please chime in."

cancel ×

227 comments

Azereus already has a plugin for this (4, Informative)

dave562 (969951) | more than 5 years ago | (#25962271)

There is already a plugin for Azereus that does this. I downloaded it about a year ago. I'm at work right now or otherwise I would look at my installation and tell you the exact name of it.

Re:Azereus already has a plugin for this (4, Informative)

LSD-OBS (183415) | more than 5 years ago | (#25962369)

Is that the same plugin that constantly runs a barrage of pings in a hidden shell? Can't remember the name, but I ran a similar sounding plugin and didn't see much speed improvement but it sure did chew up my CPU.

Re:Azereus already has a plugin for this (2, Informative)

dave562 (969951) | more than 5 years ago | (#25962753)

It probably is the same one. I seem to remember that it was developed as part of a university project. I probably even read about it right here on /. I never checked the background activity so I can't comment on the barrage of pings. I do recall that it didn't make much of a difference in my torrent speeds. I'm on DSL at home and always get consistently good torrent performance.

Re:Azereus already has a plugin for this (5, Funny)

markov_chain (202465) | more than 5 years ago | (#25962583)

You can tell me, I work in the same place.

Re:Azereus already has a plugin for this (2, Funny)

electrosoccertux (874415) | more than 5 years ago | (#25963055)

Where do you two work, I want to come join you so I can browse /. instead of doing my job. :p

Re:Azereus already has a plugin for this (1, Funny)

revlayle (964221) | more than 5 years ago | (#25963185)

you mean like you are doing RIGHT NOW??

Re:Azereus already has a plugin for this (5, Informative)

mark_hill97 (897586) | more than 5 years ago | (#25962805)

It is called Ono and it can be found here [northwestern.edu]

Re:Azereus already has a plugin for this (0)

Anonymous Coward | more than 5 years ago | (#25963457)

There's also p4p
http://azureus.sourceforge.net/plugin_details.php?plugin=p4p

But this requires support from your ISP

Re:Azereus already has a plugin for this (1)

phillips321 (955784) | more than 5 years ago | (#25963969)

But this requires support from your ISP

Like hell is that going to happen!

Re:Azereus already has a plugin for this (4, Interesting)

Sancho (17056) | more than 5 years ago | (#25964837)

ISPs actually like P4P. It gives the customers what they want (fast P2P) and it gives the ISPs what they want (less data sent to the tubes that they don't own, and thus reduced costs and overhead.)

Re:Azereus already has a plugin for this (2, Interesting)

ElizabethGreene (1185405) | more than 5 years ago | (#25963045)

You could make a whole lot of ISP's happy by prioritizing the "closest" hosts. To do this would require computing the number of hops between the two devices. Ip packets have a ttl header that is (or should be) decremented by each router in the path. A little "magic" would be required since hosts don't universally have a consistent beginning ttl, and some firewalls play with it to obscure the host information. Discovering it shouldn't be too hard though. Another factor could be latency between hosts. This works on the assumption that a packet will have queue delays if it is on a congested link. This isn't always accurate because of high-bandwidth high-latency links. fun,fun,fun. -ellie

Re:Azereus already has a plugin for this (1)

Ex-MislTech (557759) | more than 5 years ago | (#25963559)

I wish there was a way to setup a p2p app with something
like internet radios multi cast.

basically 100 or 100,000 ppl could download because they
would "tune in" to a download that was just like a song
that played, and replayed and eventually they would have
all the song once the CRC lines up.

It would save enormous amounts of bandwidth, and if you could
get multi-seeds setup, you could tune into other parts
of the data stream and get it faster.

Ie. if 5 ppl were seeding, they'd xmit just 20% of the total
stream and the server client could negotiate which parts.

It would take less bandwidth and be faster IMHO.

Won't work (2, Insightful)

Andy Dodd (701) | more than 5 years ago | (#25964149)

There is little to no support for multicast by last-mile ISPs.

It would be nice - ISPs keep bitching about how P2P is eating their bandwidth, but they don't bother implementing multicast which would make P2P use a fraction of the bandwidth it currently does.

Admittedly, in addition to lack of support, IPv4 multicast is pretty "meh" - there aren't many multicast addresses available and I have yet to see a good way of choosing/assigning them on a global network.

Re:Won't work (2, Insightful)

bluefoxlucid (723572) | more than 5 years ago | (#25964629)

It would be nice - ISPs keep bitching about how P2P is eating their bandwidth, but they don't bother implementing multicast which would make P2P use a fraction of the bandwidth it currently does.

I believe you mean P2P uses a fraction of the bandwidth it would if we had multicast. I have a constant upstream of 200k/s, to 5 clients, each getting 40k/s down from me. With multicast, I could have a constant upstream of 200k/s, to 5 clients, each getting 200k/s from me. This means I would send 200k/s up; my router would route for about 6 hops, then send duplicate packets out to 5 different routers from that hop, which would then send 200k/s down to various points on the Internet. Instead of consuming 200k/s + 200k/s, I'd consume 200k/s + 1000k/s. Further, if 100 people want to download that file at once, I can handle 200k/s transfer to 100 people, and 3 other people can do such, and they can download the file at 600k/s, and really clog the tubes.

It'd be faster, but it'd chew a hell of a lot more bandwidth at once. The DoS potential would be massive.

ISP's are against local serving (1)

Gabrill (556503) | more than 5 years ago | (#25964991)

ISP's in America are against locals serving content. This is very obvious by the fact that your upload allowances are a significant digit smaller than your download allowances. For this reason, bit torrents are far better prioritizing a larger pipe than a shorter hop.

Remember, ISP's are NOT your friends. They are a contract partner. Their interest is not to make your experience better; it's to only make your experience slightly better than the competition.

For torrents to coexist with ISP's would require:

1. Extending a business partnership with them, and convincing them that they CAN allow users to serve content without choking their already oversold bandwidth

2. Proving to their salespeople that doing so would be an advertisable asset, thus bringing them more customers.

3. Proving to their lawyers that they would be safe from litigation, both from the media conglomerate and from Uncle Sam controlled by the media conglomerate, for encouraging the spread of unregulated data copying (or copyright infringement to the aforementioned parties).

Stop It (-1, Redundant)

sexconker (1179573) | more than 5 years ago | (#25962273)

Enough Bittorrent articles.
Fuck.

Why prioritize by geography?
Prioritize by throughput.

Oh, you meant prioritize by politics, not geography.

"None of the things in those videos were illegal... ...in the countries they were filmed.", eh?

Re:Stop It (5, Insightful)

Sparr0 (451780) | more than 5 years ago | (#25962501)

Prioritize by network topology is a better way to put it, that just happens to coincide with physical AND political geography in many cases. In the case where you can get 10Mb over a 10-hop connection, or 8Mb over a 3-hop connection, which do you pick? If you pick the latter, there is a good chance that two other users can utilize the other 70% of that 10-hop connection, making total throughput (theoretically) 24Mb.

Re:Stop It (1, Flamebait)

X0563511 (793323) | more than 5 years ago | (#25962523)

Oh, you meant prioritize by politics, not geography.

No. You can try reading the summary, asshole. Here, I'll repost it here in case you were too lazy to read it above:

"While I live in S.Korea and have virtually unlimited bandwidth [wired.com] in and out of the country, not all my Asian friends are so lucky. Many of the SE Asian and African countries have small international pipes [nationmaster.com] . Even when a user has a high-speed local connection, downloads from abroad will trickle in.
Bittorrent clients apparently don't prioritize other users on the same ISP or at least in the same country. Why is that? Is it difficult to manage? If I were to write a plug-in for, say, Deluge [deluge-torrent.org] , what hurdles would I be likely to come across? If this functionality is available in other clients or through plug-ins, please chime in."

Re:Stop It (1)

sexconker (1179573) | more than 5 years ago | (#25963921)

Yeah, I don't see talking about mountains and canyons and rivers and oceans.
I see talking about countries and borders and pipes.

Re:Stop It (1)

Ian Alexander (997430) | more than 5 years ago | (#25962573)

Actually, reading the summary, the submitter is concerned with people in countries which have small international pipes- if they can prioritize peers who aren't constrained by the international bottleneck then those people might see a speed bump with bittorrent.

Re:Stop It (1)

sexconker (1179573) | more than 5 years ago | (#25964027)

Countries. Politics.

Geography = mountains and canyons and rivers and oceans and etc.

Re:Stop It (1)

bluefoxlucid (723572) | more than 5 years ago | (#25964659)

It's called 'political geography'. You're both right. Now shut the fuck up uneducated troll.

Re:Stop It (2, Interesting)

Anonymous Coward | more than 5 years ago | (#25962585)

No. Prioritize by ASN. A smart tracker would get a BGP feed and then hook users together based on locality of network connectivity.

Any other approach is "wrong."

Re:Stop It (1)

Klaus_1250 (987230) | more than 5 years ago | (#25962885)

That approach is wrong as well. Whos says I want or only want to connect to certain pre-selected peers? I don't need or want a tracker doing that for me, I'll do that myself.

Re:Stop It (1, Interesting)

Anonymous Coward | more than 5 years ago | (#25963451)

I suppose it depends on what problem you are solving. If your goal is to get a particular piece of data as quickly as possible, then if it exists on a peer on your local network, that is where you should pull it from.

If you want a file A, broken up into parts A1, A2, A3, ... A6. Parts A1 - A4 are on computers on your local network (50 Mbps) and parts A1 - A6 are on computers across the ocean (1.5 Mbps), the quickest result will be to begin fetching A5 & A6 from the slow, distant peers and begin fetching A1 - A4 from the fast, local peers. Given the general pointlessness of providing a full BGP feed to every participant in the network, putting it at the tracker is the best location. What's more is that it would be an optimization that could be done now without making any changes at the client end.

In fact, I would not be surprised to find that ISPs would raise the cap on protocols that encouraged transfers within the ISP's network.

Basically a self configuring akamai.

Re:Stop It (1)

inasity_rules (1110095) | more than 5 years ago | (#25962895)

No. Prioritize by ASL. A smart tracker would get a BGP feed...

There fixed it for you...

Seriously though, I'm not that clued up on network acronyms. I know I'll be told to google it, but why can't we just type the whole set of words out? It's not that hard is it?

Re:Stop It (2, Insightful)

Anonymous Coward | more than 5 years ago | (#25963181)

I'm, I'll, can't, it's?

Autonomous System Number. I don't think it helps much either way. You either know what it means or you don't. Also, Border Gateway Protocol.

"Prioritizing" (5, Insightful)

zombietangelo (1394031) | more than 5 years ago | (#25962303)

IPs could, theoretically, be prioritized based on a database of known general geographies associated with certain digits. Just remember - prioritizing is one thing, but it's a slippery slope to peer exclusion.

Re:"Prioritizing" (0)

Anonymous Coward | more than 5 years ago | (#25962819)

It's called a sorted list.

Re:"Prioritizing" (4, Insightful)

evanbd (210358) | more than 5 years ago | (#25962947)

Just remember - prioritizing is one thing, but it's a slippery slope to peer exclusion.

Not really. Prioritize who you request data from, but not who you send it to. If all incoming requests are treated equally, but you only request from the optimal peers, you get all the benefits without any of the omgcensorship fud.

Re:"Prioritizing" (1)

cs02rm0 (654673) | more than 5 years ago | (#25963059)

I believe IPv6 addresses give you quite a lot of location information (lots more than IPv4).

Re:"Prioritizing" (1)

bluefoxlucid (723572) | more than 5 years ago | (#25964671)

Theoretically == libgeoip

Does it not already happen? (0)

Anonymous Coward | more than 5 years ago | (#25962307)

I was under the impression that utorrent already did this, at least to a 'country' degree.

uTorrent (5, Informative)

SpitfireSMS (1388089) | more than 5 years ago | (#25962317)

uTorrent has a feature called local peer discovery that does that exactly. It was even able to discover other people at my university sharing the files.

Re:uTorrent (1)

Fackamato (913248) | more than 5 years ago | (#25962463)

utorrent also works perfectly under wine, might give it some memory overhead though. But is there really a better torrent client?

Re:uTorrent (5, Informative)

X0563511 (793323) | more than 5 years ago | (#25962561)

rtorrent [rakshasa.no]

Re:uTorrent (1)

Fackamato (913248) | more than 5 years ago | (#25962655)

It seems rtorrent is run in a terminal? I do actually have a display adapter, so I might as well use it. No thanks, I'll stick to deluge/transmission occasionally or utorrent for hardcore stuff.

Re:uTorrent (1)

Hal_Porter (817932) | more than 5 years ago | (#25962945)

It seems rtorrent is run in a terminal? I do actually have a display adapter, so I might as well use it.

god# killit --withfire \automnt\Earth\Humans\SlashdotUsers\Fackamato

Re:uTorrent (3, Funny)

Lundse (1036754) | more than 5 years ago | (#25963639)

You must be root to do that!

Re:uTorrent (1)

3p1ph4ny (835701) | more than 5 years ago | (#25963875)

Hence the `#'.

Re:uTorrent (1)

Lundse (1036754) | more than 5 years ago | (#25964263)

Hence the `#'.

Dang it!
And here I thought I was being all gnu/linux-like with the gnu/linux crowd...
As a philosopher, though, I am not too sure god is root - but that is a semantic point, nothing wrong with the syntax but my understanding of it.

Re:uTorrent (1)

imbaczek (690596) | more than 5 years ago | (#25964297)

that's no root, that's merely a bush in the garden of eden.

Re:uTorrent (2)

Methlin (604355) | more than 5 years ago | (#25964011)

So you'd rather sacrifice performance, stability, footprint, and automation for shiny progress bars. Got it. Of course you could just use one of the several XMLRPC based GUIs for rtorrent.

Re:uTorrent (2, Interesting)

Fackamato (913248) | more than 5 years ago | (#25964233)

Performance? We're talking downloading files here, not running benchmarks or some shit like that. At 1MiB/s, wine+utorrent uses roughly 3% CPU on my machine, which is nothing. Stability? It hasn't crashed so far in the 1+ year I've used it. Shiny progress bars? No, I've disabled them. I only see "% complete", no progress bar, among my torrents. The GUI is well done, it lets me do what I want and do it fast. I don't have to look for anything, buttons (if I'd use them) are in the right places. Actually I rarely press any buttons, utorrent autoopens any torrent I click on in the webbrowser and shows me a list of files in the torrent, all preselected. Then select files if you don't want them all, and any speed caps etc, press ok. Of course you could disable the box that shows up, if you're not into that sort of thing. IMO when just browsing the web, clicking around, I'd hate to put both hands on the keyboard just to type something in, or enter a key shortcut, when I could just move the mouse pointer somewhere and click a button. Seamless. But hey, maybe you don't use a DE, maybe you use a tiling WM with 2423423 xterms up, coding stuff. Then utorrent would stand out I guess.

Re:uTorrent (1)

bluefoxlucid (723572) | more than 5 years ago | (#25964707)

ws_ftp's GUI costs it half its transfer speed, more if it updates the display a lot. Play with the scrollbar and you can slow it down from 200k/s to 20k/s; then use wget and grab yourself that same file at 600k/s from the same server. Thread vs process prioritization.

Re:uTorrent (5, Interesting)

Freultwah (739055) | more than 5 years ago | (#25964413)

I run rtorrent in a detached screen session on a headless FreeBSD machine tucked away in the closet. I add torrent files to it just by dropping them into rtorrent's watch folder, everything else (starting, stopping, throttle management for off hours) is taken care of automatically. I do not have to have my laptop on or listen to the desktop whine all the time. Plus, rtorrent is blazing fast AND platform agnostic.

It is also accessible in many ways, ssh being the most obvious, but there are also many GUIs available, with which you can manage torrents from afar. I like it how it is possible to add a torrent to the queue, then take a 3 hour train ride home and find it's all done for you. Magic. So, yes, a torrent client that is run in a terminal can be a Very Good Thing for those who can set it up and use it the way it was meant to be. (And I am pretty sure it was meant to be used that way.)

Re:uTorrent (1)

Fackamato (913248) | more than 5 years ago | (#25964695)

I only have one computer. If I had a fileserver, rtorrent would be running on it. But I don't. ;-)

Re:uTorrent (1)

Rikiji7 (1182159) | more than 5 years ago | (#25963809)

AGREE.

Re:uTorrent (2, Funny)

easyTree (1042254) | more than 5 years ago | (#25962687)

But is there really a better torrent client?

Negative.

Re:uTorrent (1)

vally_manea (911530) | more than 5 years ago | (#25962747)

using KTorrent for a long time and never had any problems.

Re:uTorrent (1)

Lord Jester (88423) | more than 5 years ago | (#25963653)

Same here...

I can enable remote admin of it as well and manage torrents while away.

Re:uTorrent (1)

phillips321 (955784) | more than 5 years ago | (#25964073)

torrentflux, my whole household can manage the file downloads to a single point (and i can admin it)

Re:uTorrent (1)

gstoddart (321705) | more than 5 years ago | (#25962807)

uTorrent has a feature called local peer discovery that does that exactly. It was even able to discover other people at my university sharing the files.

Don't tell the RIAA -- they'll get a law passed insisting the universities implement this so they can keep their funding if they turn over the list. :-P

Cheers

Re:uTorrent (1)

msormune (808119) | more than 5 years ago | (#25962861)

Is the plugin called "To-be busted by the RIAA" plugin?

Re:uTorrent (2, Interesting)

GuldKalle (1065310) | more than 5 years ago | (#25963239)

It's not a plugin, and it doesn't make you more or less likely to get busted. It simply searched the peer list from the tracker and prioritizes peers on the same subnet as you, and optionally removes your throughput limits.
A good feature, but it doesn't completely solve the problem, since it only works within your local subnet, and is therefore inherently incompatible with NAT.

Re:uTorrent (2, Interesting)

lc_overlord (563906) | more than 5 years ago | (#25963281)

Well not exactly, it does try to find local users, but that is more or less useless on anything larger than any single localized network, like a university, which is all good and well.
But i seriously doubt that it optimizes this in a way that takes the network infrastructure in consideration.
Even though the local peer your downloading from may be your neighbor you might just end up being routed trough Zimbabwe for all utorrent cares at this moment, especially if net neutrality is destroyed.
And that is not good for anyone.

Re:uTorrent (4, Informative)

Fanro (130986) | more than 5 years ago | (#25963603)

Local peer Discovery works only within a lan, the corresponding broadcast messages are not routed over the internet

Ono (5, Informative)

pythonax (769925) | more than 5 years ago | (#25962319)

There is a plugin for Vuze (formerly Azureus) called Ono which does exactly that. Not sure what the problems they ran into, but as it is a college project I am sure they would be willing to discuss some of it with you. http://www.aqualab.cs.northwestern.edu/projects/Ono.html [northwestern.edu]

Non-geo-ip (3, Interesting)

rbanffy (584143) | more than 5 years ago | (#25962335)

One would not even need to prioritize by geographic location: the client could easily give extra priority points by network class: C first, then B, then A, then the rest. The odds of having a very fat pipe to another machine in the same class C are far better than having a fat pipe to a random machine across the planet.

And that would also alleviate the load on backbone links.

Re:Non-geo-ip (2, Informative)

VGPowerlord (621254) | more than 5 years ago | (#25962567)

That doesn't work well with networks split with CIDR. For example, the 24.x.y.z block is in the Class A address range, but it's not a class A block.

Re:Non-geo-ip (1)

jeffmeden (135043) | more than 5 years ago | (#25963319)

He forgot to say: Check ARIN, RIPE, APNIC, etc for the assignment of that block, and analyze accordingly. The information is there, it just has to be asked for.

Re:Non-geo-ip (1)

QuantumRiff (120817) | more than 5 years ago | (#25963675)

you have the "windows guide to networking" definition of Class. Class != subnet mask. Classes are quite a bit different, and millions of times larger than you are thinking.

For example, the Class A network is:
1.0.0.1 - 126.255.255.254
Thats around 2Billion hosts, if i'm not mistaken

Class C is: 192.0.1.1 - 223.255.255.254

For reference:
http://www.webopedia.com/DidYouKnow/Internet/2002/IPaddressing.asp [webopedia.com]

Re:Non-geo-ip (1)

TheThiefMaster (992038) | more than 5 years ago | (#25964581)

You misread.

The "class A" networks (plural) each have a unique first octet between 0 and 127. i.e. each class A is 2^24 (~16 million) addresses, and there are 128 class A networks. IIRC 0... and 127... are both reserved, leaving 126.
"Class B" networks have a unique first two octets, between 128.0 and 191.255. Each contain 2^16 (~65 thousand) addresses, and there are 16,384 class B networks.
"Class C" networks are identified by the first 3 octets, between 192.0.0 and 223.255.255. Each has only 2^8 (256) addresses in, but there are 2 million class C networks.

There are 3 reserved address ranges for LANs, one in each class (A, B and C), but only A is a single network range from its class: 10... (A), 172.16-31.. (16xB), 192.168.. (256xC, like a B assigned from the C range).

Even better, some As and Bs have been broken up and resold, and so companies have ranges of Bs and Cs that they treat as one larger network. Some ISPs have completely discontinuous ranges that they assign IPs from to customers. Some ISPs assign IPs from the same ranges across an entire country, meaning 199.1.1.1 could be one hop from 137.2.2.2, and 1000 miles, 37 routers and 1000ms from 199.1.1.2. This makes it very difficult to work out which hosts are on the same ISP and geographically nearby by IP address alone.

Things are better under IPv6 because addresses are vaguely hierarchical, so the number of bits at the start of address that you have in common with another IP is a good measure of closeness.

The best way to tell is still to do a hop count and/or bandwidth test.

Most BitTorrent clients will prefer peers that they get a better transfer rate from, which is understandable. If you have better connectivity inside your ISP's network than to the outside, it even works as a rudimentary way of prioritising by location.

Re:Non-geo-ip (1)

imbaczek (690596) | more than 5 years ago | (#25964307)

outdated knowledge warning in 3... 2... 1...

google CIDR.

They should prioritize by altitude (4, Funny)

Anonymous Coward | more than 5 years ago | (#25962337)

That way they can take advantage of the tendency of IP packets to flow downhill.

Re:They should prioritize by altitude (1, Redundant)

megamerican (1073936) | more than 5 years ago | (#25962565)

So that's why my download speed is so much more than my upload speed!

Re:They should prioritize by altitude (-1)

Anonymous Coward | more than 5 years ago | (#25963489)

Probably not. If your in the USA almost all internet services to you house have a much larger download then upload. The idea being your average home use is going to surf the web and download email, video, etc from websites, not upload to them. The real reason however is your isp saves money buy having lower uploads.

Already Made "Ono" (4, Informative)

StarWreck (695075) | more than 5 years ago | (#25962347)

What you're looking for is an Azureus plugin called "Ono". It prioritized based on router hops. Theoretically, this would make those connected to the same ISP preffered. After that it would make ISP's with direct connections to your ISP preferred. After that, resonably close geographically, ie same country.

Re:Already Made "Ono" (2, Informative)

drchoffnes (1256396) | more than 5 years ago | (#25964663)

For the record, it's not quite based on router hops. Ono exploits CDN redirections for very efficient peer baising. You can find the technical details here: http://www.aqualab.cs.northwestern.edu/publications/DChoffnes08Sigcomm.html [northwestern.edu] Also, if you want to restrict biasing to a custom set of IP address blocks, Ono now supports "manual peer biasing" toward those blocks. A description of how to use this feature (tailored for Kiwis) is here: http://homepages.xnet.co.nz/~createcoms/ [xnet.co.nz]

Re:Already Made "Ono" (1)

asamad (658115) | more than 5 years ago | (#25964939)

that seems to contradict what they say on their site

from http://www.aqualab.cs.northwestern.edu/projects/Ono.html [northwestern.edu]

I thought Vuze was already doing network positioning. Why use Ono? Well, as Ledlie, et al have shown, Vuze network coordinates are, too put it mildly, terribly inaccurate. In our own independent measurements, we found that only 10% of the network coordinates had less than 10% error. More than 60% had errors of 100% or more! Besides, unlike traditional network positioning systems, Ono doesn't require active network path measurement to determine relative locations in the network. Only infrequent DNS lookups are needed.

Latency? Hops? (3, Interesting)

Midnight Thunder (17205) | more than 5 years ago | (#25962357)

How good is latency or hops as indicator of distance from peer? The idea is that if it takes 5 hops, as opposed to 10, then the peer taking the least hops to get to is the closest.

Re:Latency? Hops? (0)

Anonymous Coward | more than 5 years ago | (#25963965)

It depends on the algorithm used with the routers.

http://en.wikipedia.org/wiki/Routing#Comparison_of_routing_algorithms

I studied this stuff in school and it's not always the closest geographically. It's based on the cost of the network connection and algorithm used. OSPF, Bellman-Ford, etc.

Look at that article and it'll probably help alleviate some confusion.

For Vuze, there's Ono and P4P (5, Informative)

chrysrobyn (106763) | more than 5 years ago | (#25962359)

For Vuze [vuze.com] , formerly Azureus [sourceforge.net] , there are Ono [northwestern.edu] and P4P [yale.edu] , which should do what you're looking for, although for different reasons. Unfortunately, they both rely on people in your region being interested in the same torrents you are, while P4P additionally benefits from an iTracker, an ISP provided tracker that's topology aware (they did some work to prioritize based on ping latency, using that as a distance estimate, but I don't know if it's a fallback mechanism). Due to the iTracker infrastructure and possibly conflicting supporters, there are some privacy concerns [torrentfreak.com] .

Re:For Vuze, there's Ono and P4P (1)

onkelonkel (560274) | more than 5 years ago | (#25963179)

"they both rely on people in your region being interested in the same torrents you are"

No Problem. I mean, come on, who doesn't like midget llama spanking pr0n?

Re:For Vuze, there's Ono and P4P (0)

Anonymous Coward | more than 5 years ago | (#25963337)

Wait a minute. Is that midgets spanking llamas, or midget llamas being spanked by regular sized folk? If it is the former, I'm right in the swarm with you, but the latter is just sick.

Bit Torrents? (-1, Offtopic)

SQL_SAM (697455) | more than 5 years ago | (#25962417)

I havent used them in years, always thought there were better alternatives - but you might have to pay (news groups). I guess that is the whole issue isnt it? Gotta be free!!

Geolocation libraries (2, Informative)

VGPowerlord (621254) | more than 5 years ago | (#25962445)

"Bittorrent clients apparently don't prioritize other users on the same ISP or at least in the same country. Why is that? Is it difficult to manage?"
The reason BitTorrent doesn't prioritize other users on the same ISP or the same country is that it doesn't know which ones are part of the same ISP or the same country. For ISPs, since the introduction of CIDR addresses, ISPs can have multiple blocks of IPs. Can you honestly tell me what all of, say, Comcast's IP blocks are with any degree of certainty?

For countries, you either need to know which IP blocks IANA has allocated to which IP registry or use a geolocation library.

MaxMind's GeoIP [maxmind.com] seems to be the de facto geolocation library, but they charge money for the "good" version. There is a free version [maxmind.com] now, but it has some annoying requirements, such as having to include "This product includes GeoLite data created by MaxMind, available from http://maxmind.com/ [maxmind.com] " in all advertising materials and documentation. It also only has a 99.5% accuracy as claimed by its creators, which means the the accuracy is probably considerably lower than they claim. Even if it were 99.5%, that means it's wrong for 1 out of every 200 people.

Re:Geolocation libraries (3, Insightful)

yachius (1348219) | more than 5 years ago | (#25963151)

The 99.5% accuracy number is considerably greater than 1/200. The accuracy figure is not a percentage of lookups that are incorrect, but of how close to the correct physical location the query result will be. Even the .5% of wrong locations won't be on the wrong side of the planet so it still makes for a very useful resource for figuring out regions.

Re:Geolocation libraries (1)

vux984 (928602) | more than 5 years ago | (#25963311)

Even if it were 99.5%, that means it's wrong for 1 out of every 200 people.

How wrong is wrong, and is its wrongness regional?

If it gets the country/state/province right... but wrong town/city, that's not all that bad for this purpose.

Or If the wrong results / sketchy results are heavily concentrated in Africa and Eastern Europe that's not really going to impact me much, again, that's just fine... at least for me.

Re:Geolocation libraries (1)

Lennie (16154) | more than 5 years ago | (#25963745)

It probably just says something is in europe, instead of country in europe. The free database only has country-information.

Why don't the ISPs help? (4, Insightful)

PhrostyMcByte (589271) | more than 5 years ago | (#25962457)

I've always wondered why ISPs can't give higher speeds if you stay within their network. You'd get your download faster. You'd use less peering bandwidth, costing the ISP less money. Everybody wins.

Re:Why don't the ISPs help? (5, Funny)

larry bagina (561269) | more than 5 years ago | (#25962571)

Better yet, ISPs should just snail mail their customers linux cds/dvds. That would basically eliminate all torrent traffic.

Re:Why don't the ISPs help? (1)

drspliff (652992) | more than 5 years ago | (#25962991)

NTL (now virgin media or something) had a large Linux/BSD repository covering all the major distros just a few hops away from me, and yes I got maximum speed downloading from it.

Re:Why don't the ISPs help? (5, Funny)

MooseMuffin (799896) | more than 5 years ago | (#25963111)

And then they could work on snail mailing truckloads of porn. That would basically eliminate all other traffic.

Re:Why don't the ISPs help? (1)

mewsenews (251487) | more than 5 years ago | (#25962915)

newgroups

Re:Why don't the ISPs help? (1)

Xtravar (725372) | more than 5 years ago | (#25964057)

I seem to recall there once was an initiative to push ISPs to have local p2p caches or somesuch. Of course, they want nothing to do with that. Pretty sure I read it on /., but too lazy to find a link.

You Asians Have Big Pipelines (0)

Anonymous Coward | more than 5 years ago | (#25962559)

So big pipeline! We American have tiny pipeline. Not big pipeline like you!

Re:You Asians Have Big Pipelines (4, Funny)

OpenYourEyes (563714) | more than 5 years ago | (#25962685)

But we American get email all the time offering to make our pipeline bigger!

Because it's a pointless thing to do (4, Insightful)

Nick Ives (317) | more than 5 years ago | (#25962617)

If your ISPs international pipe is flooded then bittorrent will automatically prefer local peers as they'll be the only people who can send you data at a fast enough rate. If you notice local peers who you're not connected to then it's most likely just because they've already reached their connection limit.

Most bittorent clients will connect to many peers and try to saturate your downstream bandwidth. They don't care where in the world those peers are as long as they're fast. If, in your part of the world, local peers are faster then that means you should just automatically connect to more local peers.

this is a tracker problem, not a client problem (0)

Anonymous Coward | more than 5 years ago | (#25962653)

This should be solved in the tracker, it should know about Internet topology (full BGP table) and send 2/3 of answers with clients in the same AS-number or max one AS-hop away from you.

Unfortunately tracker programmers I have spoken to so far have seen this as a performance problem and a complication of their software, and been little interested in this. I am sure the ISP business would be able to save substantial amount of money with this enhancement, and at the same time end users would see improved download times. This is only true to larger torrents though, as torrents with 50-100 peers are less likely to be closer to you.

Re:this is a tracker problem, not a client problem (1)

Intron (870560) | more than 5 years ago | (#25963023)

Since ISPs pay for inter-ISP data and get intra-ISP data "free" you would think they would be willing to spend money on developing the tracker software. Downloads are a significant fraction of their traffic.

Re:this is a tracker problem, not a client problem (1)

Klaus_1250 (987230) | more than 5 years ago | (#25963201)

Since ISPs pay for inter-ISP data and get intra-ISP data "free"

Inter-ISP data can be free as well. Google Peering.

No ISP could afforrd the legal risk (1)

Savage650 (654684) | more than 5 years ago | (#25964801)

The problem is not "getting the software developed" but getting its deployment okayed by the legal department. The risk of being seen as "helping the pirates" will keep ISPs away from this kind of "optimisation".

why not just seek out the higest bandwidth peers? (0)

Anonymous Coward | more than 5 years ago | (#25962703)

All of this would go away if (and maybe some do already) bittorrent clients just seeked out (and always continued to seek out) the highest bandwidth peers they can find.

That would even give ISPs the opportunity to promote "in-network" sharing by allowing in-network clients huge amounts of (what is essentially free for the ISP -- when compared to peering bandwidth costs) bandwidth while limiting out-of-network bandwidth.

Napster's Old Peer Selection (5, Interesting)

Aloisius (1294796) | more than 5 years ago | (#25962717)

At Napster I wrote a system to weight peers that were closer to the person searching by using network distance.

It was mostly because universities were complaining and so we weighted everyone on Internet 2 towards each other, but it also worked quite well for service providers like @Home and AOL. Since ISPs don't seem to care as much when their own bandwidth is used, a lot of complaints about our bandwidth consumption disappeared overnight. Indiana state university and someone else helped out if I remember correctly.

It was a rather simple system that used BGP routing tables from a number of routers to build a graph of network connectivity. It wasn't perfect, but it didn't have to be.

That said, with IPv6 weighting is *much* easier because of how the IP space is divided up. You can do a super naive implementation just by prefix.

An Azureus plugin Ono does something similar, though I believe they just look up the IP address for a CDN and weight people that look up the same IP towards each other. It is a decent solution, but it only works for between people who are running the plugin.

Silly question. (1)

pluto replies (1421495) | more than 5 years ago | (#25962875)

If people are able to get suped up downloads from their peers based on their location, could this ever lead to extra implications with copyright infringment?

Tune your TCP Receive Window first (5, Informative)

WinDev (1422301) | more than 5 years ago | (#25963079)

The biggest speed issue facing Asia/Australia is the latency of traffic to the rest of the planet. The (Windows) TCP Receive Window is tuned too small for the distances required. If you change the receive window to the maximum, you can get 4x more data in the same period using any client (P2P, browsers, etc...).

Refer to:
http://cable-dsl.navasgroup.com/index.htm#IncreasingWindow [navasgroup.com]

download bandwith in South Korea (-1, Offtopic)

Anonymous Coward | more than 5 years ago | (#25963649)

A little bit off topic, but I thought I'd add a little bit about download speeds. It's not too bad here in Canada, I can get 200-300 KB/sec on a good torrent. When they talk about virtually unlimited bandwith in South Korea, they aren't joking - I have a friend living there and if I remember correctly he can get 1.5-2 MB/sec - that means a 700 MB movie can be downloaded in under 10 minutes. That's pretty amazing when you think about it!

They're MY bits, not YOURS (3, Interesting)

PJ The Womble (963477) | more than 5 years ago | (#25963829)

When I was in my first year at college, we were asked to produce a questionnaire about using ATMs, including the question: "If you could change one thing about your bank's ATMs, what would it be?"

The most popular answer I managed to get was "if the machine's running out of money, they should restrict the cash withdrawal function to customers of this branch".

Does anyone see a parallel here?

Re:They're MY bits, not YOURS (1)

PingSpike (947548) | more than 5 years ago | (#25964443)

Odd. I would have thought "Make it give me free money" would have been the most popular answer.

Load More Comments
Slashdot Account

Need an Account?

Forgot your password?

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>
Create a Slashdot Account

Loading...