The mailing list archives for DragonFly (lists.dragonflybsd.org) have been moved to new hardware. (Yay!) The patch that actually shows date in the listings needs to reapplied, cause Mailman is somewhat stale. (Boo!) I applied the patch and I’m regenerating all the archives now. (Yay!) There’s some garbled messages in the archives that cause a bunch of “no subject” partial messages to be dumped at the end. (Boo!) I’ll manually fix them if I can, someday. (Yay?)
Several parts of dragonflybsd.org are moving to a new blade server, so there may be some service interruptions during the transition.
Francois Tigeot has ported TTM to DragonFly from FreeBSD and I think a bit from OpenBSD. All this work has led to an update in the driver porting notes.
Everyone passed their Summer of Code midterms! Not that this was a surprise; all the students have been consistently working and overcoming problems, but a 100% pass rate makes me happy.
Here’s the status reports:
- Daniel Flores: HAMMER2 compression feature
- Larisa Grigore: System V IPC in userspace
- Pawel Dziepak: Make vkernels checkpointable
- Joris GIOVANNANGELI: Capsicum
- Mihai Carabas: hardware nested page table support for vkernels
Joris Giovannangeli, one of the Summer of Code students for DragonFly, posted his thoughts on credential descriptors – have a read. He is working on capsicum and DragonFly, so this is a natural thought process.
If you have a computer with one of the very-very-new Haswell processors from Intel, Matthew Dillon has made some changes that will interest you. They shave off (in the example given) about 20% of CPU power usage without much effect on performance.
killall -T will now kill all processes associated with the current tty, except parents of the killall process itself. It’s a shortcut to “kill all these runaway items I started by accident”.
Thanks to the effort of a number of people, DragonFly (-current) now supports KMS and accelerated video on Intel 915 chipsets. It’s 2D and x86_64 only for now, but it’s much, much better than just using the vesa driver.
Please welcome our newest DragonFly committer: Johannes Hofmann. He earned this by coming up with a significant chunk of DragonFly’s upcoming KMS/915 support, and it’s now easier to just have him work directly than to be constantly committing for him.
It’s week 6, I think, and the midterms are coming up. Here’s the status reports:
- Daniel Flores: HAMMER2 compression feature
- Larisa Grigore: System V IPC in userspace
- Pawel Dziepak: Make vkernels checkpointable
- Joris GIOVANNANGELI: Capsicum
- Mihai Carabas: hardware nested page table support for vkernels
Michael W. Lucas wrote a blog post about pkgng and Ansible on FreeBSD. Will it work on DragonFly? We already have pkgng on DragonFly in the form of dports, and Ansible… might work? Please, someone try.
In part of a long thread about dports packages on the users@ list, Matthew Dillon notes that a new set of packages for i386 and x86_64, for 3.4 and for “3.6” (meaning bleeding-edge DragonFly, even though that’s numbered 3.5) is mostly uploaded. He also notes that a Haswell-processor-based blade server for DragonFly is in the works, so much of the dragonflybsd.org infrastructure is going to move from his house to a datacenter, with the benefits that provides. It’ll also help automate binary package building.
Sepherosa Ziehau added SO_REUSEPORT to DragonFly. I don’t know how the mechanism works, because he didn’t include a description, but he did include a explanation of just how much it reduces CPU usage during as-high-as-physically-possible network load. He even wrote tools to test it more heavily.
I’m late for this, even though the students weren’t. Mea culpa! There’s been a lot of discussion on IRC, in EFNet #dragonflybsd, between the students and various DragonFly developers.
- Daniel Flores: HAMMER2 compression feature
- Larisa Grigore: System V IPC in userspace
- Pawel Dziepak: Make vkernels checkpointable
- Joris GIOVANNANGELI: Capsicum
- Mihai Carabas: hardware nested page table support for vkernels
Thanks to the efforts of a large number of people, KMS support is showing up in DragonFly. This supports accelerated video on the new Intel graphics chipsets that seem to show up on many recent laptops.
Do you have a Emulex OneConnect 10Gb NIC? Well good news! Sascha Wildner brought in updated the oce(4) driver from FreeBSD to support Skyhawk models in DragonFly.
(My bad; looked at the wrong oce(4) commit originally and re-reported the import instead of the update.)
We’ve never had a group of student post progress this regularly. It’s great!
- Daniel Flores: HAMMER2 compression feature
- Larisa Grigore: System V IPC in userspace
- Pawel Dziepak: Make vkernels checkpointable
- Joris GIOVANNANGELI: Capsicum
- Mihai Carabas: hardware nested page table support for vkernels
Something new and odd: A port of the Hammer (1) filesystem into Go, for go-fuse. As the author has said, it’s more for the practice of learning Go and Hammer than for producing anything useful. Still, an interesting way to learn.
Apparently Sepherosa Ziehau has been improving DragonFly’s route table performance under extremely heavy load. (e.g. run efficiently; don’t die) I don’t have a definitive commit message to point at, but looking at his recent commits are a good start.
Encryption seems to be the accidental theme tonight. A question about Hammer 2 and encryption prompted this list of possible solutions from Matthew Dillon. Hammer 2 is still months out, so these features both require time and someone interesting in doing them – though they sound quite possible.
Still not sure if I should be writing Hammer or HAMMER.