Matt Dillon’s updated his diary page.
If you have an Athlon or Xeon processor, go into usr/src/test/sysperf, do make, and the resulting /tmp/mem1 program will probably give interesting results, which you can then post to the kernel mailing list. A caveat from Matt Dillon:
“Note however that you have to manually edit which copy tests it does since it bus fault if you try to run the XMM (SSE2) test on a machine without SSE2 :-)”
It’s been very quiet, but that’s because people are really, really busy working on DragonFly features. Here’s a roundup:
– Devon H. O’Dell and others are still working on the installer, promtped by Hiten Pandya. The code for this is available via cvsweb, including the very interesting design notes. (It has diagrams, so it must be good.)
– Hiten Pandya and Joerg Sonnenberger are updating the device subsystem to match FreeBSD 5.x. (I don’t have a lot of details on this; they’re busy!)
– Matt Dillon is writing a paper with FreeBSD’s Alan Cox detailing the performance improvements of certain pipe optimizations; he’s been doing various benchmarks for data. He’s also been working on AMD64-specific code, which he’s planning to commit soon.
– I may as well toss this in too: Jeffrey Hsu has been quietly and steadily changing the networking system. I don’t often mention his patches because he’s working at a level that’s quite beyond my ability to summarize.
Devon already noted this in comments on the last post, but a screenshot (not a prototype) of his installer work is at http://sitetronics.com/current.png.
Devon H. O’Dell has been working on an installer. This is a prototype, not a screenshot.
The libcaps interprocess communication is now functional, though not implemented. Matt Dillon wrote how this could be worked up, which I am reporting wholesale:
Continue reading “libcaps complete”
Sascha Wildner submitted a whole bunch of changes to vidcontrol(1); among other things, the colors/modes you can set in your terminal are more flexible, and it handles problems a lot better. This hasn’t been committed yet, and I usually don’t mention code until it’s in, but Sascha posted some nice photos of some of the possible modes:
There’s a new ‘known good’ installation ISO on the dragonflybsd.org download page.
Devon H. O’Dell has been creating a whole set of premade packages for DragonFly. Instead of working with ports/dfports, you can pkg_add these file directly.
Matt Dillon’s changed the UPDATING document, separating the “Upgrade from FreeBSD” and the “Upgrade DragonFly” sections into separate passages.
‘esmith’ linked to another project that handles devices, used in Linux: “User-Space System Device Enumeration” (uDSE).
Looking for things to do? Here’s Hiten Pandya’s list of possible merges from FreeBSD. There’s a lot of tasks there of varying length and difficulty, so if you feel like trying something out, go for it and post your patch to the dragonfly.submit list.
Jonathon McKitrick asked about “last known stable” tags, and the June release date for 1.0. Matt Dillon replied that a known stable tag will appear once the networking code is stable, and that a late June release is still planned
‘esmith’ asked about udev/hotplug in contrast to FreeBSD-5’s devfs, listing these links for more info.
http://www.kernel.org/pub/linux/utils/kernel/hotplug/udev-FAQ
http://kerneltrap.org/node/view/1893
http://www.gentoo.org/doc/en/udev-guide.xml
Joerg Sonnenberger is merging some FreeBSD 5.x changes to kobj, which changes the ABI. This means rebuild all modules on your next kernel build. That includes your nvidia driver, too, if you have it.
Matt Dillon found that using short-form names in /etc/fstab would cause the DNS resolver to return “host not found”, even if there was just a timeout (which should result in “try again”) when first looking up that name. This is now fixed. If you found you could not mount NFS volumes at boot, but they worked when done manually after boot, this should fix it.
Jeremy Almey alerted me to the DragonFly Wikipedia entry that he maintains – a good summary of the project, including one of the better explanations of tokens and the LWKT that I’ve seen.
Andre Nathan asked for links on SSI (Single System Image), since that’s DragonFly’s pie-in-the-sky goal. Walt gave a link to Larry McVoy’s paper (Linux-specific) on the subject.