John Marino has made it possible to build world and kernel on DragonFly using GCC 4.6.  (We’re currently on version 4.4)  Note that version 4.6 isn’t included with DragonFly, so you would need to download and compile GCC 4.6, and set CCVER=gcc46 before building world and kernel to try this out.

ISDN support has been removed from DragonFly.  It was not useful at this point, because it’s rarely used any more.  It does make me feel a little sad; this was the technology everyone said was the future before cable modems and DSL were figured out.

Peter Avalos updated libpcap and tcpdump.  This is on master, not the 3.0 branch.

A bit of symmetry in that title, there.  Old ATA, which was replaced years ago, is finally gone.  This should affect nobody…

John Marino has added support for RELRO in DragonFly, which makes it the first BSD to have it.  That’s great news!  What is it?  Apparently a guard against memory corruption or overflow in the linker.  His commit message gives better details.

What happens when you break enough things in DragonFly that you become a source of test cases?  As Antonio Huete Jimenez (AKA “tuxillo” on IRC) found out, you get a stress test named after you.

Nuno Antunes has committed a large quantity of work on updating netgraph to version 7.  His goal is to be able to run mpd5, though it’s not there yet.  If you want to look at it, go to the monthly page and look around the 10th; there’s too much to link to individually.

Peter Avalos has updated OpenSSL to 1.0.0f; this is to fix 6 security issues identified in the OpenSSL changelog.

You may want to update for this – a lockup bug with the re(4) (RealTek 8xxx series) driver has been fixed.

dma, which originated on DragonFly, is now at version 0.7, and so is the version in DragonFly.

John Marino updated libm, bringing a large quantity of functions.  This may be a stopgap measure for now.  As a positive side effect, buffer overflow attacks are a bit harder now.

The recently discovered telnetd vulnerability has been fixed in DragonFly, thanks to Peter Avalos.  Apparently it’s been around everywhere forever.  (last link via xhr)  Hopefully there aren’t that many people that still need a telnet daemon; SSH has run it out of town for the most part.

There’s been a rare segfault present in DragonFly for quite some time.  It’s been difficult to reproduce, and the 2.12 release due some months ago was held up specifically to fix it.  Matthew Dillon was, after many days (months?) of work, able to replicate it reliably and eventually find a way around what appears to be a new AMD-specific bug.  Read his very detailed explanation of what he did to get to this point.

Francois Tigeot benchmarked his accounting work with blogbench, and posted a PDF with the results.  Dmitrij D. Czarkoff made a simpler graph, which can be used to draw the conclusion: blogbench didn’t work well for estimating the impact of VFS accounting. If you want to try accounting yourself, put vfs.accounting_enabled="1" in your /boot/loader.conf.

(The normal DragonFly mailarchive isn’t updating because it feeds from DragonFly NNTP, and that’s not updating, so I’m using Gmane for post links.)

I’ve had a bunch of posts like this so far, but that’s not a bad thing.  Sepherosa Ziehau has a pair of optimizations that appear to make performance with big pipes (1G) and tiny packets (18b, if I read correctly) reach near the physical maximum for 1000-base-T Ethernet.

Francois Tigeot has been working for quite a while on a VFS accounting system.  It doesn’t restrict to a quota (yet), but it will give you byte totals for each mounted filesystem.  It has been committed, so it looks like a good way to tell which PFS is eating your disk.

Update: Francois pointed out he’s still adding parts for this.  So it’s not quite done yet, but soon.

Buildworlds are now much faster, because they can run themselves in parallel.  Invoke it using the -j option to make.  Matthew Dillon saw a 25% reduction in time when using ‘make -j 12 buildworld’ on a 4-core system.  You may need to manually update xinstall and mkdir:

        cd /usr/src/usr.bin/xinstall
        make clean; make obj; make all install
        cd /usr/src/bin/mkdir
        make clean; make obj; make all install

It’ll also use more memory than a non-parallel build, but heck, that’s cheap these days.

Venkatesh Srinivas made a minor change to a ddb backtrace – it now prints the raw instruction pointers.  On x86_64, a backtrace would not print the correct objects out, so this is better.  It’s a minor change, but I’m pointing it out because it totally helped solve a problem for me on a package-building machine.

Jan Lentfer has updated ldns in DragonFly to version 1.6.11.  This brings in a bunch of bugfixes, which can be viewed at the ldns site’s changelog.

The general rule of thumb is that if you have a function written in an interpreted language (Perl, Python, etc.), it’ll be faster in C.  If you need it faster than that, you go to assembly.  Prepare to have your world rocked: Venkatesh Srinivas found that strlen() in libc was actually slower written in assembly than in C.  His commit message has numbers to back that up.

It’s another throughput tweak from Sepherosa Ziehau: soaccept is run differently when pulling in network data from a socket.  The commit message once again shows the results of the change using httperf.

Binutils in DragonFly is now up to version 2.22 – the commit linked is one of several.

Sepherosa Ziehau has implemented another networking speedup.  Read the commit message for details on what he changed, since it’s rather in-depth.  He shows an 18% improvement in netperf results.

Sepherosa Ziehau has implemented an asynchronous pru_send in sendfile.  The results are a 70-90% increase in performance, as shown in his netperf localhost test.

The man page for dfregress has been put together, and you can read it and find out how to contribute, right now.

(That man page should be up by the time this is posted…)

If you’re tracking DragonFly current, you will need to do a full buildworld on your next update.  Sepherosa Ziehau made some changes in route(8) that a quickworld will not catch.

Alex Hornung has created ‘dfregress’, a test framework designed to be as simple as possible for adding tests to DragonFly.  This would make it easier to verify an upcoming release is correct, for instance.  See his commit note for extensive details, and add a trivial test for anything you value.

This is another one of those features that I bet goes away, and nobody would notice because nobody uses it any more.  Sascha Wildner has removed AppleTalk from DragonFly.

DragonFly has a new memory allocator, called (not surprisingly) “dmalloc“.  It’s only present on x86_64, not i386, because it could eat up more VSZ (virtual memory) than an i386 kernel may  have available.

You can now have, in theory, up to 32 terabytes of RAM on your 64-bit DragonFly system, from a change made by Matthew Dillon.  I’m curious to see if anyone has even 1 terabyte, as that’s at least feasible.

John Marino has updated two libraries needed for gcc 4.4: GMP and MPFR.  They are, as far as I can tell, both designed for mathematical functions.