<html><head></head><body>Hi Michael,<br>
<br>
Those are very good links. I read them and they're 70% above my head, but very good. Here are some others which may be of interest:<br>
<br>
<a href="http://www.google.com/url?q=http://www.youtube.com/watch%3Fv%3DqbIozKVz73g&sa=U&ei=Qqf7T6eoIYTk9ATi1tGABw&ved=0CBQQtwIwAA&usg=AFQjCNFsdTBGktprWvDlX4kCJE4ngelAuQ">http://www.google.com/url?q=http://www.youtube.com/watch%3Fv%3DqbIozKVz73g&sa=U&ei=Qqf7T6eoIYTk9ATi1tGABw&ved=0CBQQtwIwAA&usg=AFQjCNFsdTBGktprWvDlX4kCJE4ngelAuQ</a><br>
Jim Gettys<br>
<br>
<a href="http://www.bufferbloat.net/projects/codel">http://www.bufferbloat.net/projects/codel</a><br>
<br>
<a href="http://www.bufferbloat.net/projects/codel/news">http://www.bufferbloat.net/projects/codel/news</a><br>
<br>
<a href="https://plus.google.com/101384639386588513837/posts/Cgvfn8m9XuC">https://plus.google.com/101384639386588513837/posts/Cgvfn8m9XuC</a><br>
<br>
Also, this last one mentions a #bufferbloat IRC chat channel.<br>
<br>
Sincerely,<br>
<br>
Ron<br>
<br>
<br>
<br>
--<br>
<br>
Sent from my Android Acer A500 tablet with bluetooth keyboard and K-9 Mail.<br>
Please excuse my potential brevity.<br>
<br>
(To whom it may concern. My email address has changed. Replying to former<br>
messages prior to 03/31/12 with my personal address will go to the wrong<br>
address. Please send all personal correspondence to the new address.)<br>
<br>
(PS - If you email me and don't get a quick response, you might want to<br>
call on the phone. I get about 300 emails per day from alternate energy<br>
mailing lists and such. I don't always see new email messages very quickly.)<br>
<br>
Ron Frazier<br>
770-205-9422 (O) Leave a message.<br>
linuxdude AT <a href="http://techstarship.com">techstarship.com</a><br>
<br><br><div class="gmail_quote">Michael Still <stillwaxin@gmail.com> wrote:<blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;">
<pre style="white-space: pre-wrap; word-wrap:break-word; font-family: sans-serif">Kinda late on this thread but this may be handy to check out:<br /><a href="http://queue.acm.org/detail.cfm?id=2071893">http://queue.acm.org/detail.cfm?id=2071893</a><br /><br />and<br /><br /><a href="http://queue.acm.org/detail.cfm?id=2209336">http://queue.acm.org/detail.cfm?id=2209336</a><br /><br />Not sure if these are linked to in the other articles mentioned.<br /><br />On Fri, Jul 6, 2012 at 5:13 PM, Ron Frazier (ALE)<br /><atllinuxenthinfo@techstarship.com> wrote:<br />> Hi all,<br />><br />> I want to share some information about a phenomenon which can dramatically<br />> slow down your internet connection, or connections within a LAN some times.<br />> It's called buffer bloat. I first heard about it over on the NTP questions<br />> list. I don't remember why that came up, probably related to network<br />> latencies for NTP servers. Then, later, Steve Gibson discussed it on the<br />> Security Now podcast. I've provided several links below for those who wish<br />> to research it.<br />><br />> For those not familiar, buffer refers to a memory queue in a router or other<br />> networking gear. The problem occurs when you go from a large bandwidth pipe<br />> to a smaller bandwidth pipe, such as the transition from your LAN to the<br />> internet WAN. At this point, you might go from 100 Mbps or 1 Gbps bandwidth<br />> to something like 3 Mbps or 20 Mbps or 50 Mbps or whatever. The point is,<br />> that it is a dramatic reduction in bandwidth.<br />><br />> So, if you're trying to transmit to the internet at 100 Mbps and it can only<br />> take 20 Mbps, the link will become saturated. Without buffers or queues,<br />> about 4/5 of the packets will be dropped. The system will rapidly recognize<br />> that it cannot go that fast and it will scale down to something which the<br />> link can support.<br />><br />> However, with large buffers, which many routers have, the problem becomes<br />> much worse. Let's say the router has a 4 M Byte or approximately 40 M bit<br />> ram buffer on it's outbound transmission channel. Your computer fills that<br />> buffer in about 4/10 sec, but, that buffer is going to take 2 sec to empty<br />> out sending the data to the internet. While I don't understand all the<br />> technical magic that happens, I do understand that the normal automatic<br />> throttling systems no longer work. So, your computer might be seeing a 2 sec<br />> delay to get packets out on the internet while they meander through the<br />> buffer on a first in first out basis.<br />><br />> There is a new intelligent packet dropping algorithm called CODEL that may<br />> be the solution. The bufferbloat site mentions it, and Steve did a podcast<br />> talking about it. It shows great promise, however, most routers don't<br />> implement the algorithm, and many probably never will get upgraded,<br />> including many home routers.<br />><br />> So, here, as I understand it, is a way you can work around the problem.<br />><br />> My wife works from home sometimes and uses a VPN back to work. Sometimes,<br />> here system locks up and says the connection is lost. I have as many as 7<br />> devices sharing the same internet connection, so her system may be<br />> experiencing congestion. I suspect that many times, the problem is on the<br />> other end at her office, but just in case, I decided to tweak the router. I<br />> turned on a QOS (quality of service) setting and told it to prioritize her<br />> data traffic over mine. I also made some changes to avoid any possible<br />> buffer bloat problem.<br />><br />> The buffer bloat problem only shows up when the buffer fills. By the way, a<br />> clogged upstream buffer can shut down downloads too, since, during<br />> downloads, all tcp packets have to be acknowledged, and those<br />> acknowledgements must go upstream. A clogged buffer can essentially make<br />> your Internet connection almost unusable. I think this is what happens at<br />> many coffee shops. If you can't run CODEL or something like it, one way to<br />> prevent the problem is to make sure the buffer never fills up. One way to do<br />> that is to limit your upstream bandwidth to something less than what it's<br />> possible to do. In my case, the QOS menu of the router allows me to limit<br />> upstream bandwidth. I used <a href="http://speedtest.net">speedtest.net</a> to test the system. I was able to<br />> get a peak upstream bandwidth of 5.6 Mbps. So, I set the QOS controls on the<br />> router to limit the upstream bandwidth to 5 Mbps. Theoretically, this should<br />> mean that the outbound buffer on my router never will fill up because it's<br />> always emptying out faster than I'm putting data in. Theoretically, that<br />> should prevent the buffer bloat problem on my LAN. This, combined with<br />> prioritization of my wife's data, will hopefully solve her data problems.<br />><br />> If you've had experience with this problem, please share what you learned<br />> and what you did about it.<br />><br />> If you need info on the down and dirty operation of TCP/IP, ask some of the<br />> other wizards on the list.<br />><br />> Hope this is helpful.<br />><br />> Sincerely,<br />><br />> Ron<br />><br />> links below<br />><br />> ----------------------<br />><br />><br />> <a href="http://en.wikipedia.org/wiki/Buffer_bloat">http://en.wikipedia.org/wiki/Buffer_bloat</a><br />><br />> <a href="http://www.bufferbloat.net">http://www.bufferbloat.net</a>/<br />><br />> Steve Gibson discusses buffer bloat on the Security Now podcast episode 345.<br />> He introduces a potential solution, CODEL, developed by industry<br />> researchers, in episode 359.<br />><br />> <a href="http://www.grc.com/securitynow.htm">http://www.grc.com/securitynow.htm</a> - Reference episodes 345 and 359.<br />><br />> <a href="http://twit.tv/show/security-now/345">http://twit.tv/show/security-now/345</a><br />> <a href="http://media.grc.com/sn/sn-345.mp3">http://media.grc.com/sn/sn-345.mp3</a><br />><br />> <a href="http://twit.tv/show/security-now/359">http://twit.tv/show/security-now/359</a><br />> <a href="http://media.grc.com/sn/sn-359.mp3">http://media.grc.com/sn/sn-359.mp3</a><br />><br />><br />><br />> --<br />><br />> Sent from my Android Acer A500 tablet with bluetooth keyboard and K-9 Mail.<br />> Please excuse my potential brevity.<br />><br />> (To whom it may concern. My email address has changed. Replying to former<br />> messages prior to 03/31/12 with my personal address will go to the wrong<br />> address. Please send all personal correspondence to the new address.)<br />><br />> (PS - If you email me and don't get a quick response, you might want to<br />> call on the phone. I get about 300 emails per day from alternate energy<br />> mailing lists and such. I don't always see new email messages very quickly.)<br />><br />> Ron Frazier<br />> 770-205-9422 (O) Leave a message.<br />> linuxdude AT <a href="http://techstarship.com">techstarship.com</a><br />><br />><hr /><br />> Ale mailing list<br />> Ale@ale.org<br />> <a href="http://mail.ale.org/mailman/listinfo/ale">http://mail.ale.org/mailman/listinfo/ale</a><br />> See JOBS, ANNOUNCE and SCHOOLS lists at<br />> <a href="http://mail.ale.org/mailman/listinfo">http://mail.ale.org/mailman/listinfo</a><br />><br /><br /><br /><br />-- <br />[stillwaxin@gmail.com ~]$ cat .signature<br />cat: .signature: No such file or directory<br />[stillwaxin@gmail.com ~]$<br /><hr /><br />Ale mailing list<br />Ale@ale.org<br /><a href="http://mail.ale.org/mailman/listinfo/ale">http://mail.ale.org/mailman/listinfo/ale</a><br />See JOBS, ANNOUNCE and SCHOOLS lists at<br /><a href="http://mail.ale.org/mailman/listinfo">http://mail.ale.org/mailman/listinfo</a><br /></pre></blockquote></div></body></html>