Earlier this week I posted the results of a 10-way Linux distribution battle on the same Intel Xeon system and using all of the popular and latest Linux distribution releases. Taking things further, the article today has those results complemented by results on the Xeon system for several BSD operating systems. For seeing how the BSD performance stacks up to Linux, DragonFlyBSD, OpenBSD, and the FreeBSD-based PC-BSD were benchmarked.
If you’re in the packet delivery business, and you’ve never tired OpenBSD, then you’re really missing out. Pretty much everything you care about as a network guy on production networks is configured via a virtual interface. This includes CARP, IPSEC, and all manner of encapsulation and tunneling protocols. This is awesome because all the tools designed to work on interfaces, like tcpdump, work on these virtual interfaces too. So if I want to get a look at my VPN traffic, I can tcpdump enc0.
Which brings up another great point, with OpenBSD, your packet inspection and general network troubleshooting toolbox is way better. Nmap, Argus, sflow, tcpdump, snort, daemonlogger, and etc.. all the best tools are right there on your router if you want them. No need to use a packet tap, because your router is the packet tap.
OpenBSD has myriad built-in daemons for OSPF, BGP, and every other router protocol, as well as application-layer protocol proxies. OpenBSD is by far the fastest, easiest way to setup an ftp proxy that I know of. It also has a kernel-space packet filter called PF, which is crazy feature-rich and and easy to use. If you can console configure an ASA, or are an iptables user, you’ll pick up PF’s syntax in about 15 minutes. All the normal stuff like NAT, redirection, and forwarding are there. Further, PF can do things like policy routing, where you tag packets based on criteria you choose, and then make routing decisions later based on those tags. PF has packet queuing and prioritization built-in, so you can make some classes of traffic more important than others.
First things first: Were I to give an award for Best Presentation Title for SCALE 14X, it would clearly go to iX Systems’ Community Manager (and all-around BSD documentation queen) Dru Lavigne for “Doc Like an Egyptian” — she wins hands down, without question. Dru speaks at SCALE on Saturday, Jan. 23, at 3 p.m.
Also: openbsd laptops
Months after Axel Davy originally posted his patch-set for the SI machine scheduler to enhance the performance of AMD GCN GPUs on the open-source driver, it looks like the code will soon land in the AMDGPU LLVM back-end.
Axel posted his work on this Southern Islands machine scheduler months ago for AMD's LLVM GPU back-end. As tests showed back in August, this scheduler helps significantly boost the performance for certain workloads. One of the Phoronix readers that tested out this scheduler at the time exclaimed, "The si scheduler is such a huge performance boost! Not only it is faster, but now radeonsi is faster than Catalyst in *all* tests, sometimes by a wide margin!"
LLVM Clang 3.8 has been branched from trunk, thus making LLVM Clang 3.9 the new version under development.
LLVM developers were right on time for branching LLVM 3.8.0 and they are now preparing for the LLVM 3.8 release candidate. A LLVM 3.8 RC2 release is planned meanwhile for 27 January while the official release of LLVM 3.8.0 is expected around mid-February.
First things first: I’m the new kid on the BSD block. While in the process of still figuring things out on PC-BSD — dang that Synaptics! — and finding a place to contribute in the community, I have no real handle on the nuances of the inner workings of the wider BSD community. To my self-promoting credit, I am a quick study and the learning curve is not as difficult as I imagined. On the whole, I like what I see in those contributing to BSD, especially in the way of eagerness to help new users.
However, when Randi Harper decided to bail on participation in FreeBSD as she outlined in her blog, it raises the question, “Where have we seen this before?” Taking a step back, it raises the question, “Why does this keep happening in FOSS communities?”
Before we begin to answer those questions — and answers to those questions extend far beyond this commentary — I’m less interested in the “he said, she said” of the past than in finding workable solutions to permanently removing the 500-pound gorilla in the room — the quarter-ton simian of harassment and lack of proper channels to adequately address it.
I’m still sad I had to leave. That is a heartbreak that will probably never go away. I’ll miss the conferences and hanging out with so many incredibly talented people to discuss an operating system and open source project that I loved. This project helped me get to where I am today. I’m not advocating that minorities don’t join FreeBSD, but I hope those in charge of the project read this and understand that they’ve got to do better. I hope someone else helps them find their way.
If a volunteer project has a volunteer who is honestly so dysfunctional that he doesn’t understand why he is offensive, the project does not need him. And the volunteer needs to get help until he’s capable of behaving in a civilized manner.
Some years ago, I contributed $1000 to be one of the seed funders of the Ada Initiative, which worked to assist women in participating in Open Source projects. That worked out for several years, and the organization had sort of an ugly meltdown in their last year that is best forgotten. There was something really admirable about the Ada Initiative in its good days, which is that it stuck to one message, stuck to the positive in helping women enter and continue in communities in which they were under-represented, and wasn’t anti-male. That’s the way we should do it.
Sorry, I’m no expert, but have you ever, like, just noticed that women inject many kind of undermining phrases in their day-to-day speech?
This is the time of year when we look back and go, “Wow. How did this all ever happen?” Or something to that effect. And after about a month of PC-BSD daily use, the verdict so far (subject to appeal) is overwhelmingly positive with a couple of bumps (e.g., someday I will turn off tap-to-click on my touchpad).
Of course when I look back on the year, I can only look back as far as the time I have been using BSD. It wouldn’t be fair to go all the way back — one time back in the aughts, by some miracle, I got NetBSD to run on a PowerBook G3 until I updated the system and then poof — so this retrospective goes as far back as the month I’ve been using PC-BSD.
It took two decades, but BSD -- the operating system that dominated the Unix world during the 1980s and 1990s before being supplanted by the open source Linux kernel -- is now ready for embedded computing. That's according to the RetroBSD project, which has announced success running BSD on modern embedded hardware.
DragonFlyBSD's Francois Tigeot has done some more great work in allowing their open-source Intel graphics driver to be more featureful and comparable to the Linux i915 kernel DRM driver for which it is based.
While DragonFly's i915 DRM driver started out as woefully outdated compared to the upstream Linux kernel code, the work done by Tigeot and others is quite close to re-basing against the latest mainline code. With patches published recently, the DragonFlyBSD driver would now be comparable to what's in the Linux 4.0 kernel.