Michael W. Lucas will be showing up tomorrow with physical copies of his books at the Grosse Pointe Library. (I’m assuming it will be both his fiction and non-fiction BSD books.) If you are near, I bet you can get a signed copy.
Even though the hosts are currently off to AsiaBSDCon, BSDNow is once again a bit early with lots of BSD news, plus an interview of Konrad Witaszczyk, apparently about encrypted crash dumps.
In what can be described as perfect timing, Sepherosa Ziehau has produced a document comparing FreeBSD, several different Linux kernels, and DragonFly, for networking. He’s presenting it in the afternoon track of Day 3 for AsiaBSDCon 2017, starting later this week.
He’s published a snippet as a PDF (via), which includes some graphs. The one place Linux outperforms DragonFly seems to be linked to the Linux version of the network card driver being able to access more hardware – so DragonFly should be comparable or better there too, once the powers-of-2 problem is solved. (This already came up in comments to a post last week.)
Those graphs are available standalone, too, which means it’s easier to see the fantastic performance for latency – see the thin blue line – that seems exclusive to DragonFly. That, if anything, is the real takeaway; that DragonFly’s model has benefits not just to plain speed but to the system’s responsiveness under load. “My CPU is maxed out cause I’m doing a lot of work but I hardly notice” is a common comment over the past few years – and now we can see that for network performance, too.
A little meta, this week.
- Why Nothing Works Anymore. Occam’s Razor applies; most people undervalue design vs. cost. (via)
- I miss Delphi
- There’s more than one way to kill a Unix process
- Sniffing out Unix processes using pgrep
- cloudbleed hero graphics. You know what Cloudbleed is, correct? It’s hard to illustrate, is what it is.
- 1000 links later. The Digest is generally a links site, and my experience matches what he’s saying.
- The PDP-10 group on GitHub. (via, via)
- Doing Presentations. I have an employee who can’t stop reading text verbatim off his slides, facing the screen… which means I can’t stop falling asleep at about slide 20 or so. (via)
- An annotated digest of the top “Hacker” “News” posts. Accurate. (via)
- ./code –poetry. (via)
- Learning from Terminals to Design the Future of User Interfaces. (via)
- comment free codex. Comment quantity is starting to matter even more than quality.
- There’s no IPv4 ranges left to allocate, but there’s some ranges that aren’t being used by their owners, and are given back. Here’s where the remaining scraps of recovered IPv4 space are tracked. It at least delays the inevitable. (via)
- Eli5: What is POSIX?
- A time-proven zsh prompt.
- About the Newton MessagePad 2xxx ROM card. (via)
Your unrelated tea link of the week: In Sri Lanka’s Tea Paradise, A Social Enterprise Is Brewing. I actually heard about the quality of the tea (very good) before I heard about the way the company was formed. Consider where your next tea purchase comes from, in light of this.
Slightly short this week, maybe because people are prepping for AsiaBSDCon? I have plenty of links for tomorrow’s Lazy Reading.
- iXsystems Attends Container World 2017. I know what it’s really about, but it sounds like a convention where everyone talks about cardboard boxes.
- NetBSD will be in Google’s Summer of Code 2017.
- FreeBSD will be in Google’s Summer of Code 2017.
- Can you run BSD packages on OSX
- Java development on BSD?
- Upcoming SemiBUG presentations. (March 21st, April 18th)
- TrueOS Stable update released 2/22/17. (via)
- Switch and FreeBSD. Only a rumor at this point, cause the license could be most any component. (via)
The longstanding practice is to load kernel modules in loader.conf, as early as possible. That’s good, for anything that needs them.
However, that also can be bad. Your machine can be unbootable if there’s a problem with a module or loader.conf is messed up, since that file is read long before the startup process finishes. Enter the new alternative: modules can be loaded in rc.conf, and the only loader.conf modules needed are those required by / to mount.
Matthew Dillon has been doing a significant amount of work on cache lines, and I haven’t been linking to it because it’s hard to point at single commits with such a technical subject. However, he’s summarized it all, along with news on NUMA handling and vkernel improvements.