Skip navigation

Tag Archives: Dave Taht

To one day get hardware that has low latency and good queue management at gigE speeds or higher requires better hardware offloading techniques than the bulk notions like GRO and TSO that exist today. And it has long been obvious that the rate limiting +
fq_codel techniques we now use successfully at sub 200mbit speeds do not scale higher well on low end chips to handle  #bufferbloat  . So the algorithms need to move into hardware, also.

******so… a brief commercial interruption****

I think the open source design method has worked spectacularly for software, and I think the same methods can work for hardware if only we can pull together larger communities to do the work, worldwide.

There are only 24 hours left on this kickstarter – we CAN start to take back the edge of the internet – if we can only find another 5k of funding. (obviously, more would be nice)

https://www.kickstarter.com/projects/onetswitch/onetswitch-open-source-hardware-for-networking

This FPGA board´s pcie interface and switch design – and the split memory interfaces between the programmable logic and the onboard dual A9 core – and reducing the cost from 7000 to 700 bucks – are the important parts to why the open source community needs this board – in my case – so that more of htb + fq_codel can move into hardware that anyone can build and use – in other cases? who knows what could be done with it!?

One day, we could move the logic into asics, and finally have proven, open source, binary blob-free hardware to work with for any network purpose.

There are people on these lists with money, and there are those with talent and time, and it would be great if more of those people could
line up with each other. I put in all I could spare (8500 dollars) into this kickstarter.  I have one of their high end boards, already.

It´s great.

There is a “get one give one” program that I asked meshsr (the company making the board) to put in to try and enable connecting more developers up with this board. If there is anyone here that would like to help hack together the next generation of edge network hardware, after this kickstarter completes, let me know.

I return you now to your normal despair about vendors not listening,
and crappy OSes you can´t otherwise fix.

Setting up an interior gateway router (IGR) on Netgear WNDR 3800

Let’s say you want a second router upstairs in your home, where you have run an ethernet cable, what do you do? (Wireless only meshes, or failover from ethernet to wireless is also possible, in CeroWrt).

“Yesterday jg and I were working on cleaning up
http://www.bufferbloat.net/projects/cerowrt/wiki/Setting_up_an_interior_gateway_router
 and it is still pretty dense.” Dave Taht, developer, CEROwrt.

CeroWrt routes by default, not bridges. This brings in some complexity in setup but large gains in latency.

For information on bridging, rather than routing, see Setting up CeroWrt to bridge. See also Tuning your CeroWrt default gateway.

Post is an excerpt from the CEROwrt site and a quote from an email from Dave That.

Hey Dave, 
On the G. Carlin style rant. A literary masterpiece shouldn’t be altered. One of these days a tech archivist will stumble upon that piece, and say, “Oh my fucking god, that’s awesome, and so encapsulates that era.” Keep it, it’s under appreciated. 
 
I read about your struggles with your project, the time out of your life, and I’d guessed about the pull of other projects, and hard choices. It seemed to me that CERO was a best-kept-secret that everyone should hear about. Your system, which is more like an operating system, than firmware, felt right from the beginning, and ready for the next step, beyond mainline Linux and Openwrt, and on to mainline users. 
 
I see that you have a chicken and egg dilemma, in that too much of a good thing has several outcomes, so which do you choose? Sometimes funding is slow to come in the very early stages. You’ve had a rough time, funding and working at the same time. I thought that writing about it might bring publicity that would help with funding. Because routers are more important now, than before, I wondered why a tech journalist hadn’t picked up on your project. I see a few stories have begun to appear in the New York Times, and tech magazines about MESH.
 
MESH networks are socially important to places like Ferguson, MO, towns under duress. Just think what a crude but fast mesh could have meant to that community, and similar communities at risk for civil emergencies, or for that matter, survival after hurricanes or earthquakes or whatever is in our future, since our physical communication infrastructure is disappearing. Think about the Comcast merger that will determine the speed of WiFi or who is allowed to log on and who is not. I’m guessing not a profane blogger who wants to make an awesome point.
 
A MESH network, where nodes can be thrown up on demand, and healed when others go down, is the future. And, without the bloat, the CERO MESH is possibly easier and faster than other firmwares. And though it’s a bit complex for the average person, someone always knows someone who can help them with it. The Netgear router you’ve chosen is inexpensive, prevalent and usable, and that makes it easier for CERO to spread quickly after this most recent release. It’s good hardware.
 
Current router firmware is so full of holes that fixing one is like digging a deep hole in the ground, and throwing the dirt in behind us, only to have it fall right back in the hole, and fill it up again. Even after the Asus, Cisco, name it, debacle with USB and other flaws in router firmware, manufacturers don’t seem to get it. People have had enough disengagement with security, with buggy software that wasn’t well developed to protect them or speed up their connection. 
 
Your firmware is ahead of its time. That makes it difficult. We’re just learning how little manufacturers feel about customers, and how necessary it is to our everyday lives, for banking, relationships, shopping, and future lives, when  online medical consultations become ordinary, and maker communities design prosthetic limbs to print online, and a shitload of other services that we haven’t thought up, yet, happen online, but can’t do without.
 
All of this stuff, I’m sure you know, but it never hurts to say it again.  Feel free to reprint the stuff from my blog on you site or wherever it helps you. I’ll be following your progress with interest.

Email to Dave Taht, CEROwrt

One of the reasons I wrote “Flash Netgear WNDR 3800CH Router with TORONTO CEROwrt 3.10.50-1” is that the dev/user area at CEROwrt seemed to have only a few users; although, dev was very active.

CeroWrt  3.10.50-1 is ready for wider use —  if a non-coding user like me is installing it. I tinker but I don’t  hack code; I’m an end user. And, as full of errors as the story below might be it’s still one of a half-dozen stories on old blogs about Cerwrt that might familiarize people who search Google for information about this latest version of Cerowrt.

DD-WRT users are a group who might benefit from it, at this point in its development, but there are others like me who aren’t on those forums but might be encouraged to try it, with help.

I’d like to see a broad based users group come together. As a system this version of Cerowrt is pretty sweet. I’m as excited about it as i was when i first saw Linux many years ago. Users help each other. I want that help. I’m not an early adopter. I come in later when a technology is just ready to be baked in but too soon for the timid.

Could the site make a more visible area that doesn’t seem as formidable. I don’t belong w/ the devs, and other people w/ these routers don’t feel comfortable w/ the devs, we kind of feel in the way. There are a ton of these Chinese routers out there w/ buggy stock firmware but nice not-too-dated hardware. Can you refer me to anyone who might want to enlarge this User Area?

Thanks, also for the link on civil liberty, George Carlin style.