Author: Justin Sherrill

Joshua Coombs has an extensive writeup of his ideas for routing, located at http://www.outofspec.com/routing/

While talking about something else, Hiten Pandya mentioned the steps necessary to turn on profiling, to help catch bugs. I’ve saved the steps here, in case they are useful…
Continue reading “How to profile”

Emiel Kollof noted that it would be nice if the splash screen loaders could read gzipped files, so that any splash screens could be stored in a compressed format and still used. Hiten Pandya pointed at kern/imgact_gzip.c and boot/i386/kgzldr/boot.c for examples, if anyone wants to tackle this project.

David Leimbach noted that Ron Minnich was porting Plan 9 namespaces to FreeBSD, which duplicates some of the security features to be covered by VFS. Ron Minnich’s web page has more data on this and other technologies.

usr/share/examples/splash has been committed. This is the logo screen Emiel Kollof made from the DragonFly logo.

Emiel Kollof’s also got the NVIDIA binary video driver working; it should show up in dfports.

Hiten Pandya (hmp@backplane.com) is looking for anyone using a AMI MegaRAID card, who is willing to test a patch for FreeBSD-4/DragonFly.

dfports/emulators/vmware2 is in, though Matt Dillon warns that it is not yet functional.

David Rhodus has fixed the problems reported by Richard Sharpe where Linux NFS clients couldn’t achieve above 5 MBps throughput.

I wrote down the explicit steps I used to get a DragonFly machine running and up-to-date; I’m including them here for the benefit of others. This was working as of mid-September.

** Updated December 2003; silly typos.

** Update February 2004: This guide was written using FreeBSD 4.8 as a guide; it may break. There is a guide page on dragonflybsd.org that talks about upgrading from FreeBSD 4.9.
Continue reading “Installing from source”

The Slashdot interview with Matt Dillon from last night is up, in text and HTML format.

For the heck of it, there’s a pre-DragonFly interview here on KernelTrap, too.

Kip Macy listed a number of tasks left for his checkpoint/restart work, not all of which he will be covering. If this sounds interesting to you, jump in!
Continue reading “Remaining Checkpoint work”

In part of a conversation about checkpoint work, Matt Dillon described the preferred process for code changes. I’m pasting it in, wholesale.
Continue reading “How to do a diff”

Kip Macy’s very spiffy checkpoint work, allowing freezing/thawing of running applications, has resulted in a kernel module. It’s not yet in, but the most recent version he mentioned is available.

Paul Jarc brought up “>Slashpackage as a possible solution to the ports system on DragonFly; Mike Porter pointed out that it covers most everything except shared library handling.

Emiel Kollof is working on the NVIDIA binary video driver; so far it loads correctly, but doesn’t work in X11.

In other discussion about a microkernel, Gary Thorpe noted these historical links about softupdates:

http://www.netbsd.org/Documentation/tune/5.html#a3
http://www.netbsd.org/Documentation/misc/#softdeps
http://www.mckusick.com/softdep/index.html
http://www.usenix.org/publications/library/proceedings/usenix99/mckusick.html

And Pedro Guffuni followed up with this:

http://www.ece.cmu.edu/~ganger/smallfiles.html

Joshua Coombs noted he would like to work on a new firewall strategy for DragonFly, and pasted in some of his notes. They are complex enough that it’s better to paste than to sum up. (I sure could use the multiple routes he talks about.)

Pasted material follows:
Continue reading “Firewall Fun”

It looks like the PC Card problems mentioned earlier are really a problem with the DHCP client. David Rhodus is looking for someone to try a new import of the ISC DHCP code. (Updated – an import from FreeBSD-5 is happening instead, since that fixes some problems with the most recent ISC code.)

Galen Sampson found that using NFS without -maproot will cause file truncation; Matt Dillon has a temporary hack that will fix it, which will be committed by the end of the week if it works without trouble.

Matt Dillon disabled background bitmap writes, as it can apparently cause certain race conditions. He notes: “Eventually the problem background bitmap writes solved will be solved more generally by implementing page COWing durign [sic] device I/O to avoid stalls on pages undergoing write I/O.”