Re: Ebuild/rpm/deb repo's (was Re: reiser4 can now bear with filled fs, looks stable to me...)
Am Dienstag, 1. August 2006 23:59 schrieb Sander Sweers: On Tue, 2006-08-01 at 23:12 +0200, Maciej Sołtysiak wrote: [...] Are there any on the list who know of rpm's for Suse/Redhat/Mandrake that include reiser4? Suse excluded reiser4 from 10.1 because they want to keep the kernel cleaner than in previous versions. Il ask what's the status with 10.2, but I think it's still left out. With the new build-server (http://en.opensuse.org/Build_Service) it shouldn't be too hard to build packages. Also Suse supports now special packages for kernel-modules, which can even survive a kernel-update, if the API does not change. But I see another important point: Reiser4 is very fast if you have more than one reiser4 partition. But: most home users make one or two reiser4 partitions for testing purpose. Until the whole system does not run on reiser4 the speed improvement cannot be felt 100%. So community members should make pressure at Suse, Fedora, Mandriva to get reiser4 supported by the distro. -- Üdvözlettel -- Mit freundlichen Grüssen, Marcel Hilzinger
Re: Ebuild/rpm/deb repo's (was Re: reiser4 can now bear with filled fs, looks stable to me...)
Am Donnerstag, 3. August 2006 10:55 schrieb Marcel Hilzinger: Am Dienstag, 1. August 2006 23:59 schrieb Sander Sweers: On Tue, 2006-08-01 at 23:12 +0200, Maciej Sołtysiak wrote: [...] Are there any on the list who know of rpm's for Suse/Redhat/Mandrake that include reiser4? One more idea: The next release of Ubuntu is a playground release. Hans, perhaps you should have a meeting with Mark Shuttleworth. Reiser4 inclusion in Linspire was a big step, but Linspire has not really a community. If you get Reiser4 included in the next Ubuntu release (and can make it rock stable then!), you do not have to bother about Fedora or Suse... It's quite late for inclusion in the next Ubuntu release, but who knows. -- Üdvözlettel -- Mit freundlichen Grüssen, Marcel Hilzinger
Re: Reiser4 default in Underground Dekstop distribution
Am Sonntag, 26. Februar 2006 19:34 schrieb Peter Foldiak: Marcel (Hilzinger), Did you write this Linux Magazine article? Could you give some details on what the problem was? Yes, I wrote the article. The version I tested suffered much from the fsync problem. There were timeouts approx every 10 seconds, where the system didn't respond for a very short time (_very_ disturbing when watching videos). I then asked the creator of Underground Linux if he also had this problems and I pointet him to this list. He denied then, but it seems that other users did report problems with underground 022 as well. I didn't even know, that Underground went back to ReiserFS. -- Üdvözlettel -- Mit freundlichen Grüssen, Marcel Hilzinger
Re: Reiser4 default in Underground Dekstop distribution
Am Mittwoch, 1. März 2006 23:51 schrieben Sie: Marcel Hilzinger wrote: Am Sonntag, 26. Februar 2006 19:34 schrieb Peter Foldiak: Marcel (Hilzinger), Did you write this Linux Magazine article? Could you give some details on what the problem was? Yes, I wrote the article. The version I tested suffered much from the fsync problem. There were timeouts approx every 10 seconds, where the system didn't respond for a very short time (_very_ disturbing when watching videos). I then asked the creator of Underground Linux if he also had this problems and I pointet him to this list. He denied then, but it seems that other users did report problems with underground 022 as well. I didn't even know, that Underground went back to ReiserFS. Interesting. The reason it is interesting is because I can only understand if it happened every 600 seconds due to an atom being expired. If it happens every 10 seconds, then my next guess as to the culprit would be balance_dirty_pages, and perhaps entd doing too much work at a time. I need more data, and the exact kernel version. Hmm. Maybe Vitaly can try installing it and trying to reproduce. I assume a single cpu machine? It would be interesting as a datapoint to know if the problem goes away with a 2 cpu machine. Yes, it was a single CPU machine. I observed the problem on a similar PC, too. Underground Linux 022 should still be available for download. -- Üdvözlettel -- Mit freundlichen Grüssen, Marcel Hilzinger
Re: Linux Gazette benchmark Reiser 4
Am Montag, 9. Januar 2006 19:22 schrieb Hans Reiser: Andrea Gelmini wrote: 2006/1/6, Robert Hulme [EMAIL PROTECTED] mailto:[EMAIL PROTECTED]: http://linuxgazette.net/122/TWDT.html#piszcz It seems to come off fairly badly in most of the tests. I really did not understand this kind of benchmark. I don't care which filesystem is faster creating 10.000 files (something I never have to do). I care about which filesystem fits better with my everyday use of my data. Days ago I wrote a few script trying to simulate a tipical desktop session, *my* tipical desktop session. With different filesystem I've got difference of minutes. That's a benchmark that mean something to me. Why I'm trying/looking at reiser4? Because: a) seeks are the real problem of hd (they kill performance); b) journal in a fixed position creates a lot of seeks; c) I love ext2, but my laptop crash a lot of time in a day (tests, battery and so on). Testing reiser4 is giving to me a good feeling with wondering logs. You know... less seek, less HD stress... so more responsiveness. Well, it's too early to express an opinion about R4 (I'm using it since last week), but the only way to test a FS is to use it for a long time. Sorry for my bad english, gelma reiser4 is normally very fast in creating 10,000 files. I suspect that there was simply error in how he did the test, and when the guys get back i will have someone try to reproduce his results. I made some benchmarks for the german Linux-Magazin 6 month ago. Reiser4 on Suse Linux OSS was twice as fast as the next FS when copying the uncompressed kernel-sources. Either there was a bug in the version of reiser4 he used, or he did something completely wrong. If I have some free time, I will redo the benches with kernel 2.6.15 -- Üdvözlettel -- Mit freundlichen Grüssen, Marcel Hilzinger
Re: Reiser4 Install Guide for Ubuntu 5.10
Am Dienstag, 22. November 2005 01:52 schrieb Ryan Nordman: Hi Hans, Allow me to introduce myself, I'm one of Peter (aka pvh)'s colleagues here at the University of Victoria. A while back we mentioned we'd write a practical install guide for Reiser4 with Ubuntu 5.10. Well, here it is. Let us know if you want us to make any changes to the format or add/remove any steps. [...] 8. Reboot with the new kernel, create a Reiser partition and mount it and you're good to go! Did you also try to make / with reiser4? -- Üdvözlettel -- Mit freundlichen Grüssen, Marcel Hilzinger
Re: More Slowdown
Am Donnerstag, 17. November 2005 14:47 schrieb Hesse, Christian: Vladimir V. Saveliev wrote: Please try whether the attached patch improves anything. It simplifies fsync by avoid commiting of transactions which do not modify file being fsync-ed. Did you ever think about, that this is not a reiser4 problem, but a kernel bug or a problem related to hal? Suse 10 has big problems with external USB drives using sync as mount option. They used sync already in 9.3 but with 2.6.11 there were no such problems. There has been some changes in kernel 2.6.13 and 2.6.14 concering the sync behavior, perhaps it can help investigating there first, bevor fixing reiser4 for nothing... -- Üdvözlettel -- Mit freundlichen Grüssen, Marcel Hilzinger
Re: More Slowdown
Am Dienstag, 22. November 2005 11:38 schrieb Sander: Marcel Hilzinger wrote (ao): Did you ever think about, that this is not a reiser4 problem, but a kernel bug or a problem related to hal? Suse 10 has big problems with external USB drives using sync as mount option. They used sync already in 9.3 but with 2.6.11 there were no such problems. There has been some changes in kernel 2.6.13 and 2.6.14 concering the sync behavior, perhaps it can help investigating there first, bevor fixing reiser4 for nothing... Running Debian here, and all the reports have been on Reiser4 filesystems. Also, the same system has no such problems with other filesystems. It's not about Debian or Suse. It's about kernel 2.6.13 or 2.6.14. At least it seems, that the problem does not appear on older kernels (right?) -- Üdvözlettel -- Mit freundlichen Grüssen, Marcel Hilzinger
Re: More Slowdown
Am Dienstag, 22. November 2005 15:29 schrieb David Masover: Marcel Hilzinger wrote: [...] It's not about Debian or Suse. It's about kernel 2.6.13 or 2.6.14. At least it seems, that the problem does not appear on older kernels (right?) Wrong. You are talking about the fsync issue, right? As far as I know, while there has been progress lately, fsync has always been slow on Reiser4, because until recently, it was basically a call to sync, and reiser4 syncs can be huge due to lazy writes -- stuff only ever hits disk when there's nowhere else to put it in RAM. Actual calls to sync are rare enough (shutdown/reboot) that lazy writes are a good thing, but fsync apparently needs to be faster. I disabled fsync before the FS was even stable, because I was sick of waiting 30 seconds or so for vim to save and quit. It may help to have fsync only sync the file in question (as it always has, except on Reiser4). This has been done with lazy writes, in XFS, so I see no reason it can't be done here -- there might have even been a patch recently. Personally, I'd like to see it stay as slow as it is for awhile, so we can find the people doing stupid things (evolution) and flame them into crispy obediance. fsync means flush to disk. This is something you're supposed to do with a file when the file is so important you want to guarentee you'll have the most recent, uncorrupted version after a crash. If evolution is calling fsync while resizing, this is an evolution bug, made more obvious by reiser4 -- if a computer crashes, does the user really care if their Evolution columns are still lined up _exactly_ the way they were (maybe mid-click'n'drag) when the crash occurred? Thanks a lot. I understand now. But is there any bug to hunt within reiser4 then? -- Üdvözlettel -- Mit freundlichen Grüssen, Marcel Hilzinger
Re: journal size reiserfs vs reiser4
Am Donnerstag, 1. September 2005 15:05 schrieb Thomas Kuther: On Thu, 01 Sep 2005 16:53:32 +0400 Vladimir V. Saveliev [EMAIL PROTECTED] wrote: Hello [...] reiser4 reserves 5% of disk space for its internal needs. Ah OK, that computes. So i'll go with reiserfs on that big one (11 GB for internal stuff is too much i have to admit). If I remember well, you can adjust this value in the code. -- Üdvözlettel -- Mit freundlichen Grüssen, Marcel Hilzinger
Re: journal size reiserfs vs reiser4
Am Donnerstag, 1. September 2005 18:06 schrieb Peter Staubach: Hans Reiser wrote: Research for filesystems generally says that as you get more than 85% full the performance goes down, by a lot as you get close to 100%. 5% is probably too little rather than too much. Wow. What is all that space used for? Other journalling file systems that I have seen have limited things like journals to a much smaller space, expressed in megabytes, and a much smaller number than thought originally. The bigger journals just didn't end up adding to the performance measurably and were just considered to be a waste of space that could be used more usefully. It's almost not for the journal. AND If you have a lot of small files, reiser4 manages space much better than every other filesystems. So the space you mean to loose with this 5% reiser4 gives it back with better packaging, eg: kernel 2.6.12 extracted: with reiser4 ~ 200 MB with ext3/reiserfs ~ 230 MB -- Üdvözlettel -- Mit freundlichen Grüssen, Marcel Hilzinger
Re: df -i reports '-' inodes available on reiser4
Am Donnerstag, 3. Mrz 2005 13:45 schrieb Branko F. Granar: Hello, We're evaluating reiser4 filesystem for our storage server, which will run on linux 2.6.x. However, according to our tests it performs very well. Becouse our storage server will be responsible to server very *huge* amount of small files, we need to investigate the following issue: Command df -i reports '-' as number of used and total inodes available on filesystem. Is this a bug, or a feature? Or i missed out some documentation which i should read before i formatted storage volume? There is a long thread on this, which starts with a mail from Miguel on 13.05.2004 at 09:34 (acording to my mailer). If you are interested in, I can send it to you by mail. -- dvzlettel -- Mit freundlichen Grssen, Marcel Hilzinger
Re: Atomic filesystem or not
Donnerstag 15 Juli 2004 14.54 dtummal ezt rta: On Thursday 15 July 2004 13:34, Marcel Hilzinger wrote: I tried to do a crash-test with Reiser4. I copied a 650 MB file from directory A to directory B and pressed the reset buttom at approx 300 MB (the testmachine has 256 MB RAM). After reboot the 300 MB chunk was still in B. I thougt it should be either there full or not at all? Or did I understand something wrong? Does it work only with files RAM? What's the difference You did understand something wrong ;-) I was quite sure about this :-)) A copy using the Unix cp command is not an atomic operation per se. When it is said that reiser4 is atomic what it means is that each low level operation on the filesystem either happens or not at all. That means that each block write request issued by cp either happens or not, but the entire 650MB copy itself is composed of many separate atomig requests. So what you shouldn't see on the half copied file is blocks which contain zeros or otherwise garbage data that didn't belong to the original file (as somethimes happens on other journalling filesystems, reiserfs 3.6 sometimes included). If you check the differences between the files, they should contain the same data up to the last block that hit disk surface before you pressed the reset button. OK. Everything clear now. I will then make an octal or a hexa dump of the original and the copied file and compare them. If Reiser4 is atomic, there must not be any different entry in the copied file. Thanks. Marcel -- dvzlettel -- Mit freundlichen Grssen, Marcel Hilzinger
Re: we need a slogan for our reiser4 t-shirt
2004. június 23. 21.38 dátummal Hans Reiser ezt írta: we are going to use our fastman logo from our web page plus reiser4 in letters, but we need some slogan underneath it. What about: The Living Filesystem (as there are dancing trees, wandering logs, and development is really alive :-) -- Üdvözlettel -- Mit freundlichen Grüssen, Marcel Hilzinger
Fanout of main tree?
I read, that the fanout of each node can be different, but what is the initial fanout of the main tree (approx)? Is it depending on the filesystem size? Is it done during formatting just once, or dynamic, as more leaf nodes are needed? If it is dynamic (I guess): What makes the decision, wheter to increase the fanout or to make the tree higher? Thanks. Marcel, who wants to understand Reiser4 ;-) -- Üdvözlettel -- Mit freundlichen Grüssen, Marcel Hilzinger
Re: Working Reiser4 patch for kernel 2.6.6(-mm2)?
May this be the same problem? I tried to repeat my benchmark with kernel 2.6.7, but was not able to copy a directory to reiser4. I could create files with touch, but copying gave this error message (and the cp process hangs as D+): kernel 2.6.7-rc1 + 2.6.7-rc1-mm1.bz2 + reiser4-2004.06.02-19.39-linux-2.6.7-rc1-mm1.diff.gz patching + compiling without errors Jun 3 23:28:01 linux kernel: CPU:0 Jun 3 23:28:01 linux kernel: EIP:0060:[]Not tainted VLI Jun 3 23:28:01 linux kernel: EFLAGS: 00010246 (2.6.7-rc1-mm1) Jun 3 23:28:01 linux kernel: EIP is at 0x0 Jun 3 23:28:01 linux kernel: eax: efd4bae0 ebx: efd4bae0 ecx: efd4bad4 edx: Jun 3 23:28:01 linux kernel: esi: efd4bc7c edi: c03b50e8 ebp: 0001 esp: efd4bad0 Jun 3 23:28:01 linux kernel: ds: 007b es: 007b ss: 0068 Jun 3 23:28:01 linux kernel: Process pdflush (pid: 38, threadinfo=efd4a000 task=efd6f120) Jun 3 23:28:01 linux kernel: Stack: c01ba127 dd635b40 0001 0 105 Jun 3 23:28:01 linux kernel: efd4bafc efd4bafc efd4bb04 efd4b b04 efd4bb34 Jun 3 23:28:01 linux kernel: efd4bc7c efd4bb34 efd4bcd4 c01b9f15 c01b0 70d Jun 3 23:28:01 linux kernel: Call Trace: Jun 3 23:28:01 linux kernel: [c01ba127] scan_by_coord+0xa7/0x2e0 Jun 3 23:28:01 linux kernel: [c01b9f15] scan_unformatted+0x115/0x1b0 Jun 3 23:28:01 linux kernel: [c01b070d] longterm_lock_znode+0xed/0x240 Jun 3 23:28:01 linux kernel: [c01acabd] zload_ra+0x1d/0x20 Jun 3 23:28:01 linux kernel: [c01b9dad] scan_common+0x2d/0x60 Jun 3 23:28:01 linux kernel: [c01b7dce] jnode_flush+0x2ee/0x300 Jun 3 23:28:01 linux kernel: [c01b7fae] flush_current_atom+0x1ae/0x220 Jun 3 23:28:01 linux kernel: [c01b5b91] try_commit_txnh+0x161/0x180 Jun 3 23:28:01 linux kernel: [c01b5bdf] commit_txnh+0x2f/0xa0 Jun 3 23:28:01 linux kernel: [c01b4e9e] txn_end+0x2e/0x40 Jun 3 23:28:01 linux kernel: [c01b4eb8] txn_restart+0x8/0x20 Jun 3 23:28:01 linux kernel: [c01b5588] force_commit_atom_nolock+0x18/0x20 Jun 3 23:28:01 linux kernel: [c01b565e] txnmgr_force_commit_all+0x9e/0xb0 Jun 3 23:28:01 linux kernel: [c01c2350] writeout+0x20/0xb0 Jun 3 23:28:01 linux kernel: [c01c240c] reiser4_sync_inodes+0x2c/0x50 Jun 3 23:28:01 linux kernel: [c01c23e0] reiser4_sync_inodes+0x0/0x50 Jun 3 23:28:01 linux kernel: [c0169f39] sync_sb_inodes+0x19/0x20 Jun 3 23:28:01 linux kernel: [c016a007] sync_inodes_sb+0x67/0xa0 Jun 3 23:28:01 linux kernel: [c016b197] mpage_writepages+0xf7/0x300 Jun 3 23:28:01 linux kernel: [c013a870] pdflush+0x0/0x20 Jun 3 23:28:01 linux kernel: [c016a0c9] sync_inodes+0x19/0x80 Jun 3 23:28:01 linux kernel: [c01505c1] do_sync+0x11/0x60 Jun 3 23:28:01 linux kernel: [c015061a] sys_sync+0xa/0x10 Jun 3 23:28:01 linux kernel: [c013a7c2] __pdflush+0xd2/0x180 Jun 3 23:28:01 linux kernel: [c013a88a] pdflush+0x1a/0x20 Jun 3 23:28:01 linux kernel: [c013a080] laptop_flush+0x0/0x10 Jun 3 23:28:01 linux kernel: [c013a870] pdflush+0x0/0x20 Jun 3 23:28:01 linux kernel: [c012ae9c] kthread+0x7c/0xb0 Jun 3 23:28:01 linux kernel: [c012ae20] kthread+0x0/0xb0 Jun 3 23:28:01 linux kernel: [c010424d] kernel_thread_helper+0x5/0x18 Jun 3 23:28:01 linux kernel: Jun 3 23:28:01 linux kernel: Code: Bad EIP value. -- dvzlettel -- Mit freundlichen Grssen, Marcel Hilzinger
Re: Reiser4 on SuSE 9.1
2004. jnius 4. 16.14 dtummal Mike Young ezt rta: Has anyone put Reiser4 on the latest SuSE 9.1 release? I'd like to use it there without having to patch a pristine kernel. Preferably, I'd like to be able to use their RPM build environment so I can continue to take updates from SuSE. Probably this is not, what you need, but I test Reiser4 on SuSE 9.1 with kernel 2.6.5. This is NOT a SuSE kernel, but I use the config file form the official SuSE 2.6.4 kernel and it compiled without problems. Even cryptoloop with the old SuSE twofish works. Of course kernel update will not work any more... I tried to patch the SUSE kernel with reiser4 patches, but as I'm just a stupid user, I couldn't make it work. It would be great, if the SuSE kernel developers could make a patch for the SuSE 9.1 kernels. This would also be good for namesys, as with this help much more tester could be won for testing Reiser4. As I'm a user, I know, that many users have time to do such tests, and they don't bother about data anyway :-) Marcel -- dvzlettel -- Mit freundlichen Grssen, Marcel Hilzinger
Some kind of benchmark
I tested reiser3.6, reiser4 and ext3 with the compiled kernel source 2.6.5. I made 6 5 GB partitions at the end of a 60 GB disk and formatted always two of them with above file systems: /hda6: reiser3 /hda7: ext3 /hda8: reiser4 /hda9: reiser3 /hda10: ext3 /hda11: reiser4 then I copied the compiled kernel source from one partition to another always within the same file system. The commands I used: write: time cp -a linux-2.6.5/ /$FS rewrite: time cp -a linux-2.6.5/ /$FS delete: rm -r /$FS/linux-2.6.5 In one test I made these steps 7 times without breaks. And I made several tests. Here the results (just averages) FS write rewrite delete SUSE 9.1 with SUSE kernel: ext301:25,8101:34,02 00:05,54 reiser3 01:17,5701:35,90 00:03,35 Same system with kernel 2.6.5 ext301:25,5002:10,31 00:11,56 reiser3 01:21,9101:58,18 00:06,67 reiser4 00:40,4602:10,26 00:12,83 Yes, reiser4 is fast :-) !! Question: Why may be rewriting and delete (almost 2 times) slower on 2.6.5 kernel than on SUSE 2.6.4 kernel? Marcel u.i. Tests with big files will follow :-) -- dvzlettel -- Mit freundlichen Grssen, Marcel Hilzinger
Mail archive offline
I'd like to read the contents of the Mailing list form the past 6-9 months. Could somebody send me his/her? Mail folder, where the mails of the list are stored, so that I can read the archive offline. Thank you. -- dvzlettel -- Mit freundlichen Grssen, Marcel Hilzinger
Re: Mail archive offline - I got one. Thanks
I got one. Thanks Marcel
Stupid question
What, if someone likes to create a directory called metas under reiser4? Actually this is not possible, as the system will complain about: there is already a directory metas. Marcel -- dvzlettel -- Mit freundlichen Grssen, Marcel Hilzinger
