As part of a discussion about internationalization, Matt Dillon mentioned he plans to finish IPC this weekend as it would be a useful implementation method. He also mentioned offhand that the first release of DragonFly could be in June/July.
Benches being marked
Jean-Marc Zucconi benchmarked FreeBSD 4.9-R, 5.1-R, 5.2-R and DragonFly on a multiprocessor system, and posted the large quantity of data this generated. It’s mashed into a table here:
(updated with better results for 5.2; ACPI was generating so many interrupts it was slowing his system.)
(see end of entry for his notes)
Continue reading “Benches being marked”
645dx tricks
Bernhard Valenti found he had to put “set hw.ata.ata_dma=0” in the boot loader to get his 645DX-based motherboard ATA working. Jeroen Ketema also found that write caching had to be off: “set hw.ata.wc=0“
Make upgrade
Because of the GCC2/GCC3 work (which, incidentally, will allow other compilers like TenDRA to be used in system compilation), do a “make upgrade” after your next installworld. This will clean up now-stale compiler files, plus update files in rc.d and so on.
I C I18N
Following up on recent discussion, ibotty listed ICU as another internationalization alternative.
GCC integrated; updating abnegated
David Rhodus and Matt Dillon are getting GCC2 and GCC3 into the base system today; updating your source during the next 24 hours may bring you an unstable version.
Some links to look at
Ryan Dooley brought up The CITRUS Project as a way to assist internationalization in DragonFly.
According to this benchmark, linked to by Xin LI, there’s file descriptor allocation code in FreeBSD 5 that may be worth the effort to port.
200 posts!
This is the 200th post here – neat! I’m averaging just under 1.5 posts per day, which is good: healthy posting, healthy project.
Benchmark setups
In a discussion about benchmarks, it was noted that /etc/malloc.conf changes can help benchmarks tremendously. Rahul Siddharthan suggested ‘/etc/malloc.conf -> H' and Jeremy Messenger suggested '/etc/malloc.conf -> aj‘
Also, Matt Dillon made a number of suggestions on what to check when benchmarking DragonFly vs. FreeBSD (4 or 5)
Matt Dillon quote follows:
Continue reading “Benchmark setups”
Prelinking reported
Simon ‘corecode’ Schubert pointed out prelinking should be mentioned on the 2003 report; here’s the text that will soon show up on that report:
Prelinking
Prelinking capability was added to DragonFly by Simon ‘corecode’ Schubert, which allows faster loading of applications that use a large number of dynamic libraries while running, like Qt/KDE. It is not currently hooked into the system or any port building process.
ssh bug fixed
Matt Dillon fixed an apparently long-term problem in OpenSSH where a server can hang because it has a lot of data to send, but no immediate resources to do it with.
Reproduce it like so:
limit filesize 64k
ssh remotebox -n cat /usr/share/dict/words | cat > junkfile
Ips = ServeRAID
The IBM ServeRAID controller is now supported, thanks to TONETANI Tomokazu. That would be the “ips” device.
Jump on journaling
David Rhodus has the journaling filesystem code from Apple located in vfs_journal.c and vfs_journal.h. He estimate it’d take 2-3 (long) days of work to get it worked into the system, which would mean no more long fscks after unlcean shutdowns. Any takers? Everyone would love you for it.
Idle hands do the daemon’s work
Eirik Nygaard was looking for something to do; Max Laier pointed out removal of #if defined(__FreeBSD__) / #if __FreeBSD_version > 5 would help, and Jeffrey Hsu indicated backporting the UFS2 size extensions would also be good.
I’ll quote my own followup to say there’s plenty of non-coding tasks available, too.
Site updates
The main DragonFly website now has an additional mirror listed (bottom of page) for daily snapshots, and Matt Dillon’s put up slides from his talk at BAFUG in a new Docs section.
OpenOffice OK
Port-fixing fiend Joerg Sonnenberger has committed a dfports override for OpenOffice.
Paying off already
David Rhodus imported Hyperthreading changes from FreeBSD which allow you to automatically use Hyperthreading on supported CPUs with just the regular multiprocessor options turned on in your kernel; e.g. options SMP, options APIC_IO.
However, the DragonFly version has no idling loops in it to reduce CPU resource contention. Because of the way DragonFly schedules per-CPU/sends IPI messages, there’s no performance issue caused by multiple CPUS HLTing. Already, a benefit.
Data Size on Unix
In a discussion about a submitted firewall design, Jeroen Ruigrok listed Data Size Neutrality at unix.org.
KDE Korrected
Dave Leimbach has added changes to KDE in CVS to allow kdebase to compile on DragonFly. This is in the actual KDE source code, not a ports override.
Card testing
Joerg Sonnenberger is looking for anyone with either PCCARD or CARDBUS hardware, for testing of this patch and this patch.
He noted, “After applying both patches remove bus/pccard and link bus/pcmcia to bus/pccard.”