Re: Use of hfsprogs in Ubuntu
Hi, Morten. Sorry for the very late reply. To reach a wider audience, I'm Cc'ing the people at debian-powerpc (to which I am subscribed), debian-68k (which probably has people with HFS+ filesystems), debian-amd64 (which possibly has people with newer Apple systems) and debian-mentors (which probably has someone that would like to get started packaging something with a patch system and that involves portability issues). On May 16 2008, Morten Kjeldgaard wrote: > Rogério Brito wrote: > > I would like to ask you two things: > > > > 1 - would it be possible to upgrade the package from the Debian > > repository? > > Packages in Ubuntu are synchronized with packages from Debian/unstable at > regular intervals. At the moment, packages are getting sync'ed into > Intrepid. It seems that hfsprogs revision -4 has already been imported into the Ubuntu repository for intrepid, but the version available for hardy is completely broken (the last time I checked). Please, do update it or please remove it from the distribution. It will have ill effects on people who depends on it. > > 2 - since I plan on packaging it so that it compiles on all arches > > available on Debian, I would like to ask if any of you would like to > > help me with this task in a cooperative way (I plan on creating a > > repository on Debian's Alioth service). > > We do uploads of source code (actually: source packages) that are compiled on > a set of build-hosts without human intervention (and so does Debian). I do know about that. > It is not possible to "tweak" compilations on a particular machine and > upload binary packages. Therefore, the package should be able to handle > the different architectures automatically, and if something special needs > to be set (compiler options or such) it should be take care of in > debian/rules. This is why I am asking for some helping hand on maintaining the package: it currently consists of a huge patch taken from Gentoo, together with some patches of mine, all applied to hfsprogs with the help of quilt. The problem is the following: while my patches are designed to address just one issue and are easily disabled, the patch from Gentoo is a monolithic thing that changes things from trivial to quite essential things and this prevents the upload of a newer upstream version of the tools. > It is more difficult to handle different patches for different platforms, > and > although it can be done, it is discouraged. The closest to being acceptable > is passing different arguments to ./configure, and of course your code can > rely on #ifdefs etc. BTW, there is no "./configure" thing in this packaging of Apple's utilities. > Putting your project on alioth is a good idea, and perhaps your best bets is > to collaborate with the Debian maintainers to get the package compile & > working. Then those packages will quickly show up in Ubuntu. Perhaps I was misunderstood the first time and now my idea is clearer, but I am interested in getting feedback from Ubuntu. The way you wrote the sentences above give me (what I wouldn't like to believe) a bad impression of the MOTUs regarding just getting the job done. I hope that I am mistaken. Regards, -- Rogério Brito : [EMAIL PROTECTED],ime.usp}.br : GPG key 1024D/7C2CAEB8 http://www.ime.usp.br/~rbrito : http://meusite.mackenzie.com.br/rbrito Projects: algorithms.berlios.de : lame.sf.net : vrms.alioth.debian.org -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of "unsubscribe". Trouble? Contact [EMAIL PROTECTED]
Please, testers of hfsprogs are needed
Hi there. I am the maintainer of hfsprogs, which provides both a mkfs and (more importantly) a fsck for HFS+ filesystems (used by default on Apple's operating system). I have uploaded some revisions of the package to the unstable archive, but I actually believe that everything is alright, even for production use, but I would like to have more feedback on that. I fixed, through a less than desirable way, a problem on amd64 (actually, a problem that would affect any 64 bit architectures), but I have only enabled the build of one 64 bit arch (amd64) right now. I, therefore, would appreciate if you could send me feedback on hfsprogs so that I can improve the packaging and include other patches there, if needed. The following would be a good first test after installing the package: dd if=/dev/zero of=disk.img bs=100M count=1 mkfs.hfsplus disk.img mount -t hfsplus -o loop disk.img /some/mount/point (perform some tests) umount /some/mount/point fsck.hfsplus disk.img Feedback is appreciated in the form of bugs for it or as Cc'es to this e-mail, as I am not subscribed currently to -user nor to -amd64 (only to -powerpc). Hope you find the package useful, Rogerio Brito. -- Rogério Brito : [EMAIL PROTECTED],ime.usp}.br : GPG key 1024D/7C2CAEB8 http://www.ime.usp.br/~rbrito : http://meusite.mackenzie.com.br/rbrito Projects: algorithms.berlios.de : lame.sf.net : vrms.alioth.debian.org -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of "unsubscribe". Trouble? Contact [EMAIL PROTECTED]
Looking for help with maintainance of a package
Dear people,
I am the maintainer of hfsprogs, which is a package taken from Apple's
Darwin code that provides a mkfs.hfs{,plus} and, more importantly,
fsck.hfs{,plus}.
Unfortunately, the present version has problems not being 64-bit clean
and, as a result, I had to restrict the list of architectures to those
that are 32 bit only.
This has been reported as bug #436159 on our bug tracking system. As I
myself have all the interest to have this package available on as many
architectures as possible (since, in particular, I use an amd64 machine,
but keep some of my data/backups on external HDs formatted with HFS+),
it would be ideal to have it as arch: any.
But alas, it is not. :-( It won't compile without a number of patches
and I have already got Gentoo's patch as a starting point for the
package. But it would be better to have it divided as a series of
independent patches (as I already use quilt to manage the patches). I
have already started doing this.
Seeing that Apple has released a new version to match their Leopard
release, it would be a good thing to keep the patches separate as some
parts will apply nicely while others are obsolete now (the code has
changed a bit, but not much).
As I posted on ubuntuforums.org [*], for this goal, I would like to see
if there are interested developers so that I would create a project on
Alioth to maintain patches that are team-maintained and which would
clean up miscoding, warnings, consistency, correctness and, perhaps,
submit them upstream so that we can reduce our work in the future (and
have a more solid filesystem for exchange of data between computers).
I have already made a package yesterday that uses the 32-bit emulation
of amd64 to have a functioning fsck.hfsplus program and I plan on
uploading it to experimental, but it is based on older source code, not
on the new upstream version (let's move one step at a time).
So, that is it. If you have interest and know of more people interested
in this (like Ubuntu people), please let me know. BTW, as I am not
subscribed to any specific Debian list nowadays (besides
-devel-announce), I would appreciate CC's.
Regards, Rogério Brito.
[*] http://ubuntuforums.org/showthread.php?p=4919975
--
Rogério Brito : [EMAIL PROTECTED],ime.usp}.br : GPG key 1024D/7C2CAEB8
http://www.ime.usp.br/~rbrito : http://meusite.mackenzie.com.br/rbrito
Projects: algorithms.berlios.de : lame.sf.net : vrms.alioth.debian.org
signature.asc
Description: Digital signature
Problemas with 64 bit cleanliness (was: Re: Intel Core2Duo (T7400))
On Nov 07 2007, Bernd Petrovitsch wrote: > On Tue, 2007-11-06 at 13:35 -0500, Lennart Sorensen wrote: > > A few programs still don't compile or work on 64bit systems (not > > amd64 > > Any real-world examples? Yes, one package that I maintain does not work with 64 bit systems (hfsprogs). This is code taken directly from Apple's Darwin system and has a few silly programming mistakes (like using index -1 in a C array). For luck, fsck.hfsplus works on 32 bit systems, but that just what I said: luck. BTW, fixing it would be a major undertaking... :-( > The only which I remember rumors are "grub". But being a bootloader, > that probably doesn't hurt much. Does anybody know how about the status of grub 2? I would like to use just one booloader for the main architectures that I live with (ppc, amd64, i386). > Fact is that I run pure 64bit Linux since months on my home desktop > (though I'm not the typical desktop user;-). I consider myself a pretty typical Desktop user (working on papers for my studies and preparing classes, surfing the web, reading mail etc) and I'm using a pure 64 bit Linux system. :-) Of course, one of the reasons I like alternative ports (like PowerPC also) is that it is a very good test for pureness of Free Software: it's also got something to do with me liking Free Software to the point of maintaining the Virtual RMS (package: vrms). :-) > > I guess you could say that the fact the programs are slightly bigger > > (since all pointers become 8 bytes rather than 4) is a disadvantage, > > but on the other hand a lot of code runs slightly faster with 64bit, > > with a > > Yes, x86_64 has more registers than i386. Yes, this is a good thing for compilers, as less parameters are passed by memory and less temporary expressions are spilled to memory. I wish that x86-64 had more of them... > Some browsers (konqueror, firefox as far as I've been told) allow to run > 32bit plugins from the 64bit version. Didn't know that. > Since the flash-plugin and others is not really important for me, I > don't really care. Same thing here: I even block other things with privoxy. :-) > > problems since many are 32bit windows code only. Some people just run > > the few problem programs in a 32bit chroot and deal with it that way, > > Or install 32bit libs and run a 32bit browser/application on the x86_64 > installation. While this can be done, it would "taint" the pure 64 bit installation... Regards, -- Rogério Brito : [EMAIL PROTECTED],ime.usp}.br : GPG key 1024D/7C2CAEB8 http://www.ime.usp.br/~rbrito : http://meusite.mackenzie.com.br/rbrito Projects: algorithms.berlios.de : lame.sf.net : vrms.alioth.debian.org -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of "unsubscribe". Trouble? Contact [EMAIL PROTECTED]
Re: openoffice.org crashes testing
Please, don't top post. On Aug 26 2007, Don Montgomery wrote: > I am using oo 2.0.4 and linux 2.6.18-4-amd64. How do I upgrade open > office without pulling everything else along with it? These questions would be much more suitable for debian-user. Anyway, just to answer your question, you should look into apt pinning and the APT::Default-Release variable of apt.conf. Regards, Rogério Brito. -- Rogério Brito : [EMAIL PROTECTED],ime.usp}.br : GPG key 1024D/7C2CAEB8 http://www.ime.usp.br/~rbrito : http://meusite.mackenzie.com.br/rbrito Projects: algorithms.berlios.de : lame.sf.net : vrms.alioth.debian.org -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of "unsubscribe". Trouble? Contact [EMAIL PROTECTED]
On the complexity order of algorithms (was: Re: AMD64 X2 questions)
On Aug 24 2007, Chris Ahlstrom wrote: > I found this recent article (by a Microsoft guy!) in Dr. Dobbs to be > interesting: > >http://www.ddj.com/hpc-high-performance-computing/201202924 (...) > * Comparing O(1) and O(K) Ugh! This article just shows that the Microsoft people should take some classes in theoretical computer science, as O(1) is the very same thing for O(K), if K is a constant. Regards, Rogério Brito. -- Rogério Brito : [EMAIL PROTECTED],ime.usp}.br : GPG key 1024D/7C2CAEB8 http://www.ime.usp.br/~rbrito : http://meusite.mackenzie.com.br/rbrito Projects: algorithms.berlios.de : lame.sf.net : vrms.alioth.debian.org -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of "unsubscribe". Trouble? Contact [EMAIL PROTECTED]
