From richb.hanover at gmail.com Sun May 14 08:31:57 2017 From: richb.hanover at gmail.com (Rich Brown) Date: Sun, 14 May 2017 08:31:57 -0400 Subject: [Codel] fq_codel is *five* years old today In-Reply-To: References: <24D7CF8A-6FAE-47D8-A9EE-1C1B0734D1E6@gmail.com> Message-ID: <612E36A6-7FB8-4FBA-AC38-339DFC04AB47@gmail.com> There have been so many improvements in so many ways... - Cake is the acknowledged winner in SQM - Make Wi-Fi Fast has removed a couple orders of magnitude of latency in the Wi-Fi stack, and Airtime Fairness has eliminated the Wi-Fi Paradox. - All this is Implemented in LEDE, so it's available as a (somewhat) straightforward install on hundreds of different kinds of routers. As a side note, LEDE and OpenWrt are working toward a merger, with a unification of the development efforts. - A few commercial products - notably IQrouter and Ubiquiti - are shipping a good SQM implementation in their products. Let's all take a moment and revel in solving some of the major annoyances in networking. Best regards, Rich > On May 14, 2016, at 9:18 AM, Rich Brown wrote: > > Another year, further progress toward world domination (or at least, fixing the world's internet...) > > - The team is working furiously on Making Wi-Fi Fast. This has entailed lots of deep research into the behavior of Wi-Fi at low and high loads, airtime fairness, wireless drivers, new hardware platforms for testing. Lots more work ahead. > > - We had a huge response (260 signers) to the Save Wi-Fi from the FCC filing re: locking down OTS router firmware. > > - We have officially declared the CeroWrt project to be dead. All its interesting facilities have been subsumed into OpenWrt mainline code. > > - The OpenWrt project has a fork - LEDE (http://lede-project.org) It remains to be seen what effect this will have on our anti-Bufferbloat effort. > > - RIP: the original www.bufferbloat.net server. Hopefully someone can pick up the pieces (even for historical purposes) as we re-deploy the information to a new (non-Redmine) system. > > What else happened this year? > > Best regards, > > Rich > >> Begin forwarded message: >> >> From: Rich Brown >> Subject: fq_codel is *three* years old today >> Date: May 14, 2015 at 8:11:38 AM EDT >> To: bloat , cerowrt-devel >> Cc: Justin Beech >> >> Folks, >> >> Today is the third anniversary of the announcement of a testable fq_codel (see https://lists.bufferbloat.net/pipermail/cerowrt-devel/2014-May/002984.html et. seq.) >> >> Here's (an approximation of) the state of the world: >> >> - We didn't know it at the time, but we would be able to declare victory on CeroWrt less than three months later with the 3.10.50-1 build. Not only did that firmware reduce bufferbloat, but it showed that DNSSEC and IPv6 could be implemented in "normal" home routers without any kind of jiggery-pokery. Field reports at the end of 2014 showed that build was very stable - we had lots of reports of 80 day uptimes, and a high of ~140 days. >> >> - fq_codel is installed a large and growing of places. It's available off the shelf for OpenWrt in the SQM QoS package, the Linux kernel, IPFire, DD-WRT, and other routers. >> >> - "Bufferbloat" is entering the lexicon. People are speaking about it in blogs and open literature as a known entity, not some voodoo effect that's only a concern to crazy people. The writers don't always get the description or symptoms right, but there is an acknowledgement that something could be better in your home (and everywhere) network connection. (See for example, http://www.internetsociety.org/blog/tech-matters/2015/04/measure-your-bufferbloat-new-browser-based-tool-dslreports ) >> >> - Speaking of which, the new DSLReports Speed Test has recently stirred things up. Not only do we have an attractive tool that we can recommend to friends, but people are getting a little hot under the collar when they see the crummy performance of the router that they just paid dearly for. See, for example, http://www.dslreports.com/forum/r30051856-Connectivity-Buffer-Bloat >> >> - Now that we've shown that fq_codel conquers bufferbloat, we're finding further optimizations. There's a lot of effort on cake, which promises to bring higher speed processing, and looking into corner cases that can be improved. >> >> - And of course, Dave Täht is taking on another big project: "Making Wi-Fi Fast". >> >> What else has happened in this year? >> >> Best, >> >> Rich > From stephen at networkplumber.org Sun May 14 21:04:52 2017 From: stephen at networkplumber.org (Stephen Hemminger) Date: Sun, 14 May 2017 18:04:52 -0700 Subject: [Codel] [Bloat] fq_codel is *five* years old today In-Reply-To: <612E36A6-7FB8-4FBA-AC38-339DFC04AB47@gmail.com> References: <24D7CF8A-6FAE-47D8-A9EE-1C1B0734D1E6@gmail.com> <612E36A6-7FB8-4FBA-AC38-339DFC04AB47@gmail.com> Message-ID: <20170514180452.18907177@xeon-e3> Rich, you gave a good "glass is half full" story but my experience is currently much worse. Here is the "glass is mostly empty" story. > There have been so many improvements in so many ways... > > - Cake is the acknowledged winner in SQM But is still not upstream and requires tuning. In real world, SQM needs to be adaptive and/or require no tuning. Fq_codel is still way ahead on this. > > - Make Wi-Fi Fast has removed a couple orders of magnitude of latency in the Wi-Fi stack, and Airtime Fairness has eliminated the Wi-Fi Paradox. But still only works with one chipset, and not in consumer products. > > - All this is Implemented in LEDE, so it's available as a (somewhat) straightforward install on hundreds of different kinds of routers. As a side note, LEDE and OpenWrt are working toward a merger, with a unification of the development efforts. The merger is wonderful. But my experiments with OpenWRT/LEDE and DD-Wrt all show that the OEM firmware has more stable Wifi on Linksys ACM3200. It seems current code base is about where Cerowrt was 2 years ago. > - A few commercial products - notably IQrouter and Ubiquiti - are shipping a good SQM implementation in their products. But these are are not the consumer products people get from Comcast, Fry's or Best Buy. Don't confuse developing with deploying. The biggest challenge in the bloat world now is getting solutions deployed. I hope the world will get better, it just seems to take longer than expected.