bufferbloat.net
Heartbleed and CeroWrt - upgrade please! - Bufferbloat.net
https://www.bufferbloat.net/news/50
Heartbleed and CeroWrt - upgrade please! Posted on Apr 16, 2014 by Dave Täht. In response to the heartbleed (CVE-2014-0160) vulnerability, on April. 9th 2014 we updated the under-development CeroWrt release to include. The fixed version of openssl. The fix is in CeroWrt 3.10.36-3 and. We have no means of fixing the “stable” (3.7.5) release of CeroWrt,. Nor any of the innumerable development releases since then. Please do a clean, fresh upgrade to CeroWrt 3.10.36-6 or later. [1]. New firmware images conta...
blog.cerowrt.org
A bit about TCP BBR - http://blog.cerowrt.org/
http://blog.cerowrt.org/post/a_bit_about_bbr
CeroWrt notebook: On fixing the internet since 2011. A bit about TCP BBR. Knowing something like BBR must exist was maddening and motivating. Rdquo; - that person asked - and I poked deeper and saw, seemingly - that the cwnd was a bit weird, but nothing I could put a finger on. I wasn’t in a position to guess, further, that BBR. Had also been deployed there - nor am I sure it actually was, at the time - I don’t think it was, not in its present form, at least. It had a very good idea in it:. Note: The BBR...
blog.cerowrt.org
Cruzio and Meraki make my day - http://blog.cerowrt.org/
http://blog.cerowrt.org/post/meraki_and_cruzio_make_my_day
CeroWrt notebook: On fixing the internet since 2011. Cruzio and Meraki make my day. Every so often theres good news over coffee. My favorite coffee shop in Santa Cruz is the Pergolesi. Back in the early 2000s, it was one of the first ones that offered free wifi. Several people I knew then helped them set that up in exhange for free coffee - it was a heck of a deal for both parties - they got more customers - and the thirdbreak. Many of my friends use the cruzio ISP. None, presently. Sigh. Flent Network T...
blog.cerowrt.org
Posts - http://blog.cerowrt.org/
http://blog.cerowrt.org/post
CeroWrt notebook: On fixing the internet since 2011. Ive never really recovered from the loss of the lab. Posted on February 11, 2017. Posted on December 23, 2016. Not) Getting a fair share from 4 queues. Posted on December 12, 2016. Cruzio and Meraki make my day. Posted on October 20, 2016. Finally. the real net-next 4.8 fq codel/airtime-fair ath9k results. Posted on October 12, 2016. Some traceroutes from Nicaragua. Posted on October 12, 2016. Exploring wifi mcs rates with fq codel. A bit about TCP BBR.
blog.cerowrt.org
Some traceroutes from Nicaragua - http://blog.cerowrt.org/
http://blog.cerowrt.org/post/nicaragua
CeroWrt notebook: On fixing the internet since 2011. Some traceroutes from Nicaragua. It seemed like the entire country was behind one big nat. What does your internet look like? How can you figure out anything about your userbase if your users are behind 7! Layers of private network? Yes - 1143ms RTT on this test. And I at least - had no extra traffic on the link. How the heck can IPv6 ever deploy with this much nat in the way? None, presently. Sigh. Comcast Research Innovation Fund. October 12, 2016.
blog.cerowrt.org
A simple routing trick makes my tests easier - http://blog.cerowrt.org/
http://blog.cerowrt.org/post/routing_test_tricks
CeroWrt notebook: On fixing the internet since 2011. A simple routing trick makes my tests easier. Try this in your topology! The APs in the yurtlab are mostly in a routed configuration, where all the devices under test are on the same ethernet switch. To do a test of some configuration, all I do is do a ifdown lan on the devices I want to talk to wirelessly, and the babel protocol figures out which way to go. This saves hugely on renaming, and renumbering things. If you don’t have pdsh:. Dave@nemesis: /...
blog.cerowrt.org
Exploring wifi mcs rates with fq_codel - http://blog.cerowrt.org/
http://blog.cerowrt.org/post/mcs_rates
CeroWrt notebook: On fixing the internet since 2011. Exploring wifi mcs rates with fq codel. Theres always something else wrong. I don’t trust anyone else’s test tools. I make enough mistakes using flent. And I spend a maddening amount of time trying to figure out ways to test no more than two variables in isolation - or to confidently test dozens and draw a sane conclusion from large set of statistically significant results. Often, I fail. We’re winning, or so I thought last night. I’m driving thi...
