From: Neil Brown <neilb@suse.de> To: Larry Bates <lbates@syscononline.com> Cc: linux-kernel@vger.kernel.org, linux-raid@vger.kernel.org Subject: Re: newbie - mdadm create raid1 mirrors on large drives Date: Mon, 5 Dec 2005 09:13:26 +1100 [thread overview] Message-ID: <17299.27142.901162.564588@cse.unsw.edu.au> (raw) In-Reply-To: message from Larry Bates on Saturday December 3 On Saturday December 3, lbates@syscononline.com wrote: > I hope this is the correct list for this question. linux-raid@vger.kernel.org is possibly better, but linux-kernel is probably a suitable catch-all. > > I've just recently begun using mdadm to set up some > arrays using large drives (300-400Gb). One of the > things I don't understand is this: when you first > create a raid1 (mirrored) array from two drives > mdadm insists on mirroring the contents of the first > drive to the second even though the drives are > entirely blank (e.g. new drives don't have anything > on them). Well... they do have something one them - lots of zeros and ones, or maybe just zeros, or maybe just ones. Sure, you may not be interested in that data, but it is there. > In one configuration I have, this takes > about 16 hours on a 400Gb drive. When I do 5 of them > simultaneously this takes 2+ days to complete. Is > there some way to tell mdadm that you want to create > a mirrored set but skip this rather long initial > mirroring process? I don't really see that it actually > accomplishes anything. No, there is no way to tell mdadm to skip the initial copying process. It is not clear to me that you really want to do this(*) (though on the "enough rope" principle I'm probably going to extend the "--assume-clean" option to work in --create mode). I suggest you simply ignore the fact that it is doing the copy. Just keep using the array as though it wasn't. If this seems to be impacting over-all system performance, tune /proc/sys/dev/raid/speed_* to slow it down even more. If you reboot, it should remember where it was up to and restart from the same place (providing you are using a 2.6 kernel). If you have 5 of these 400Gb raid1's, then I suspect you really want to avoid the slow resync that happens after a crash. You should look into adding a bitmap write-intent log. This requires 2.6.14, and mdadm 2.1, and is as easy as mdadm --grow --bitmap=internal /dev/md3 while the array is running. This should dramatically reduce resync time, at a possible small cost in write throughput. Some limited measurements I have done suggest up-to 10% slowdown, though usually less. Possibly some tuning can make it much better. (*) A raid array can suffer from sleeping bad blocks. i.e. blocks that you cannot read, but normally you never do (because they haven't been allocated to a file yet). When a drive fails, and you are recovering the data onto a spare, hitting that sleeper can kill your array. For this reason it is good to regularly (daily, or weekly, maybe monthly) read through the entire array making sure everything is OK. In 2.6.16 (with complete functionality in 2.6.17) you will be able to trigger a background read-test of the whole array: echo check > /sys/block/mdX/md/sync_action If you were to create an array with --assume-clean, then whenever you run this it will report lots of errors, though you can fix them with echo repair > /sys/block/mdX/md/sync_action If you are going to be doing that (and I would recommend it) then you may as well allow the initial sync, especially as you can quite happily ignore the fact that it is happening. NeilBrown
WARNING: multiple messages have this Message-ID (diff)
From: Neil Brown <neilb@suse.de> To: "Larry Bates" <lbates@syscononline.com> Cc: <linux-kernel@vger.kernel.org>, linux-raid@vger.kernel.org Subject: Re: newbie - mdadm create raid1 mirrors on large drives Date: Mon, 5 Dec 2005 09:13:26 +1100 [thread overview] Message-ID: <17299.27142.901162.564588@cse.unsw.edu.au> (raw) In-Reply-To: message from Larry Bates on Saturday December 3 On Saturday December 3, lbates@syscononline.com wrote: > I hope this is the correct list for this question. linux-raid@vger.kernel.org is possibly better, but linux-kernel is probably a suitable catch-all. > > I've just recently begun using mdadm to set up some > arrays using large drives (300-400Gb). One of the > things I don't understand is this: when you first > create a raid1 (mirrored) array from two drives > mdadm insists on mirroring the contents of the first > drive to the second even though the drives are > entirely blank (e.g. new drives don't have anything > on them). Well... they do have something one them - lots of zeros and ones, or maybe just zeros, or maybe just ones. Sure, you may not be interested in that data, but it is there. > In one configuration I have, this takes > about 16 hours on a 400Gb drive. When I do 5 of them > simultaneously this takes 2+ days to complete. Is > there some way to tell mdadm that you want to create > a mirrored set but skip this rather long initial > mirroring process? I don't really see that it actually > accomplishes anything. No, there is no way to tell mdadm to skip the initial copying process. It is not clear to me that you really want to do this(*) (though on the "enough rope" principle I'm probably going to extend the "--assume-clean" option to work in --create mode). I suggest you simply ignore the fact that it is doing the copy. Just keep using the array as though it wasn't. If this seems to be impacting over-all system performance, tune /proc/sys/dev/raid/speed_* to slow it down even more. If you reboot, it should remember where it was up to and restart from the same place (providing you are using a 2.6 kernel). If you have 5 of these 400Gb raid1's, then I suspect you really want to avoid the slow resync that happens after a crash. You should look into adding a bitmap write-intent log. This requires 2.6.14, and mdadm 2.1, and is as easy as mdadm --grow --bitmap=internal /dev/md3 while the array is running. This should dramatically reduce resync time, at a possible small cost in write throughput. Some limited measurements I have done suggest up-to 10% slowdown, though usually less. Possibly some tuning can make it much better. (*) A raid array can suffer from sleeping bad blocks. i.e. blocks that you cannot read, but normally you never do (because they haven't been allocated to a file yet). When a drive fails, and you are recovering the data onto a spare, hitting that sleeper can kill your array. For this reason it is good to regularly (daily, or weekly, maybe monthly) read through the entire array making sure everything is OK. In 2.6.16 (with complete functionality in 2.6.17) you will be able to trigger a background read-test of the whole array: echo check > /sys/block/mdX/md/sync_action If you were to create an array with --assume-clean, then whenever you run this it will report lots of errors, though you can fix them with echo repair > /sys/block/mdX/md/sync_action If you are going to be doing that (and I would recommend it) then you may as well allow the initial sync, especially as you can quite happily ignore the fact that it is happening. NeilBrown
next prev parent reply other threads:[~2005-12-04 22:13 UTC|newest] Thread overview: 639+ messages / expand[flat|nested] mbox.gz Atom feed top 2005-12-03 13:56 RFC: Starting a stable kernel series off the 2.6 kernel Adrian Bunk 2005-12-03 14:29 ` Jesper Juhl 2005-12-03 20:19 ` Greg KH 2005-12-03 21:04 ` M. 2005-12-03 21:37 ` James Courtier-Dutton [not found] ` <f0cc38560512031254j3b28d579s539be721c247c10a@mail.gmail.com> 2005-12-03 21:12 ` Greg KH 2005-12-03 21:31 ` M. 2005-12-03 21:38 ` Arjan van de Ven 2005-12-03 21:53 ` M. 2005-12-03 22:26 ` Greg KH 2005-12-04 7:56 ` Arjan van de Ven [not found] ` <f0cc38560512040657i58cc08efqa8596c357fcea82e@mail.gmail.com> 2005-12-04 15:10 ` Arjan van de Ven 2005-12-04 16:11 ` Matthias Andree 2005-12-04 16:41 ` Arjan van de Ven 2005-12-04 20:08 ` Paul Jackson [not found] ` <f0cc38560512040724re5114c2y76bb34d63c9c5ae0@mail.gmail.com> 2005-12-04 22:47 ` Greg KH [not found] ` <f0cc38560512041503y7abd1f12rbce8bdac0ebdf30d@mail.gmail.com> 2005-12-04 23:12 ` Greg KH 2005-12-05 1:03 ` Horst von Brand 2005-12-05 19:35 ` Bill Davidsen 2005-12-03 21:54 ` Greg KH 2005-12-06 1:19 ` Florian Weimer 2005-12-06 17:55 ` Greg KH 2005-12-03 22:51 ` Adrian Bunk 2005-12-03 23:28 ` Greg KH 2005-12-03 23:35 ` Chris Wright 2005-12-06 0:37 ` Rob Landley 2005-12-07 21:38 ` Nix 2005-12-04 8:07 ` Arjan van de Ven 2005-12-05 20:33 ` Florian Weimer 2005-12-06 1:10 ` Horst von Brand 2005-12-06 10:46 ` Matthias Andree 2005-12-06 14:01 ` Florian Weimer 2005-12-06 16:52 ` Gene Heskett 2005-12-04 3:48 ` Jesper Juhl 2005-12-04 11:56 ` Matthias Andree 2005-12-04 23:24 ` Greg KH 2005-12-05 6:26 ` Willy Tarreau 2005-12-05 10:00 ` Matthias Andree 2005-12-05 10:55 ` Lars Marowsky-Bree 2005-12-05 11:34 ` Willy Tarreau 2005-12-05 11:40 ` Lars Marowsky-Bree 2005-12-05 12:01 ` Willy Tarreau 2005-12-05 12:24 ` Bernd Eckenfels 2005-12-05 12:26 ` Arjan van de Ven 2005-12-06 17:54 ` Greg KH 2005-12-06 18:57 ` John Kelly 2005-12-06 21:55 ` Adrian Bunk 2005-12-06 22:40 ` John Kelly 2005-12-05 18:51 ` Adrian Bunk 2005-12-06 17:50 ` Greg KH 2005-12-06 22:50 ` Policy for reverting user ABI breaking patches was " Andi Kleen 2005-12-06 18:42 ` Dmitry Torokhov 2005-12-06 14:32 ` Florian Weimer [not found] ` <6f6293f10512060855p79fb5e91ke6fca33f96cb1750@mail.gmail.com> 2005-12-06 17:47 ` Greg KH 2005-12-06 23:27 ` David S. Miller 2005-12-06 19:01 ` Lee Revell 2005-12-04 17:00 ` Jakob Oestergaard 2005-12-04 22:39 ` Greg KH 2005-12-05 15:17 ` Jakob Oestergaard 2005-12-05 15:44 ` Pekka Enberg 2005-12-05 17:17 ` Jakob Oestergaard 2005-12-06 17:44 ` Greg KH 2005-12-06 21:16 ` Bill Davidsen 2005-12-07 14:38 ` Massimiliano Hofer 2005-12-07 16:05 ` Horst von Brand 2005-12-07 16:29 ` Massimiliano Hofer 2005-12-05 14:48 ` Florian Weimer 2005-12-06 17:46 ` Greg KH 2005-12-03 14:31 ` Ben Collins 2005-12-03 19:35 ` Adrian Bunk 2005-12-03 19:57 ` Lee Revell 2005-12-03 21:04 ` M. 2005-12-03 22:58 ` Matthias Andree 2005-12-03 23:49 ` Lee Revell 2005-12-05 21:05 ` Florian Weimer 2005-12-05 21:41 ` Lee Revell 2005-12-05 23:00 ` Florian Weimer 2005-12-05 23:06 ` Bernd Petrovitsch 2005-12-06 0:08 ` Florian Weimer 2005-12-05 21:00 ` Florian Weimer 2005-12-05 21:06 ` Arjan van de Ven 2005-12-06 0:43 ` Florian Weimer 2005-12-06 11:21 ` Matthias Andree 2005-12-06 15:10 ` Florian Weimer 2005-12-06 16:45 ` Dmitry Torokhov 2005-12-07 11:29 ` Matthias Andree 2005-12-07 13:54 ` Horst von Brand 2005-12-08 3:29 ` Dmitry Torokhov 2005-12-08 8:29 ` Matthias Andree 2005-12-10 0:22 ` Rob Landley 2005-12-06 20:35 ` Alan Cox 2005-12-05 23:03 ` Bill Davidsen 2005-12-06 1:48 ` Jeff Garzik 2005-12-06 11:23 ` Matthias Andree 2005-12-06 19:48 ` Bill Davidsen 2005-12-06 1:56 ` Horst von Brand 2005-12-03 14:36 ` Arjan van de Ven 2005-12-03 15:23 ` Adrian Bunk 2005-12-03 15:39 ` Arjan van de Ven 2005-12-04 13:53 ` Denis Vlasenko 2005-12-05 9:47 ` Michael Frank 2005-12-06 0:54 ` Horst von Brand 2005-12-06 17:08 ` Michael Frank 2005-12-03 16:27 ` Matthias Andree 2005-12-03 16:40 ` Otavio Salvador 2005-12-03 16:58 ` David Ranson 2005-12-03 17:13 ` Steven Rostedt 2005-12-03 17:17 ` David Ranson 2005-12-03 17:53 ` Adrian Bunk 2005-12-03 18:17 ` newbie - mdadm create raid1 mirrors on large drives Larry Bates 2005-12-03 22:23 ` Matthias Andree 2005-12-04 22:13 ` Neil Brown [this message] 2005-12-04 22:13 ` Neil Brown 2005-12-03 18:34 ` RFC: Starting a stable kernel series off the 2.6 kernel David Ranson 2005-12-03 22:27 ` Matthias Andree 2005-12-03 22:34 ` Lee Revell 2005-12-03 22:50 ` Matthias Andree 2005-12-04 0:20 ` Greg KH 2005-12-04 4:46 ` Luke-Jr 2005-12-04 15:06 ` Michael Frank 2005-12-04 23:22 ` Greg KH 2005-12-05 5:59 ` Luke-Jr 2005-12-06 0:34 ` Rob Landley 2005-12-06 10:34 ` Luke-Jr 2005-12-06 19:17 ` Rob Landley 2005-12-06 17:38 ` Greg KH 2005-12-06 14:58 ` Bill Davidsen 2005-12-06 17:59 ` Greg KH 2005-12-06 21:10 ` Bill Davidsen 2005-12-06 21:51 ` Kay Sievers 2005-12-10 2:16 ` Rob Landley 2005-12-10 4:04 ` Greg KH 2005-12-05 22:47 ` Rob Landley 2005-12-05 23:05 ` Benjamin LaHaise 2005-12-06 3:19 ` Rob Landley 2005-12-06 3:32 ` Benjamin LaHaise 2005-12-06 5:49 ` Rob Landley 2005-12-06 10:51 ` Matthias Andree 2005-12-06 3:15 ` Greg KH 2005-12-06 3:23 ` Rob Landley 2005-12-03 22:36 ` David Ranson 2005-12-03 22:50 ` Matthias Andree 2005-12-06 14:59 ` Bill Davidsen 2005-12-04 1:04 ` Horst von Brand 2005-12-04 12:07 ` Matthias Andree 2005-12-04 19:29 ` Horst von Brand 2005-12-06 20:01 ` Bill Davidsen 2005-12-05 20:43 ` Bill Davidsen 2005-12-05 3:31 ` Rob Landley 2005-12-05 16:17 ` Mark Lord 2005-12-05 16:28 ` Lee Revell 2005-12-05 16:44 ` Matthias Andree 2005-12-05 17:17 ` Lee Revell 2005-12-05 17:55 ` Matthias Andree 2005-12-05 20:52 ` Florian Weimer 2005-12-05 21:21 ` Steven Rostedt 2005-12-05 23:09 ` Rob Landley 2005-12-06 0:54 ` Steven Rostedt 2005-12-06 1:10 ` Florian Weimer 2005-12-06 1:26 ` Steven Rostedt 2005-12-06 18:06 ` Horst von Brand 2005-12-06 3:22 ` Rob Landley 2005-12-06 1:06 ` Florian Weimer 2005-12-06 11:09 ` Matthias Andree 2005-12-05 17:58 ` Rob Landley 2005-12-06 18:51 ` Bill Davidsen 2005-12-07 15:48 ` Arjan van de Ven 2005-12-07 18:40 ` Horst von Brand 2005-12-07 18:14 ` Rob Landley 2005-12-10 8:35 ` ipw2200 [was Re: RFC: Starting a stable kernel series off the 2.6 kernel] Pavel Machek 2005-12-11 5:30 ` Rob Landley 2005-12-11 8:37 ` Pavel Machek 2005-12-11 9:12 ` Rob Landley 2005-12-12 11:49 ` Pavel Machek 2005-12-14 12:26 ` Rob Landley 2004-12-14 16:01 ` Pavel Machek 2005-12-11 16:26 ` Horst von Brand 2005-12-12 17:34 ` Ben Slusky 2005-12-12 20:02 ` Rob Landley [not found] ` <439DE10E.4080901@tmr.com> 2005-12-12 21:52 ` Ben Slusky 2005-12-15 2:38 ` ipw2200 Miles Bader 2005-12-10 13:41 ` RFC: Starting a stable kernel series off the 2.6 kernel Bill Davidsen 2005-12-10 17:05 ` Douglas McNaught 2005-12-11 5:52 ` Rob Landley 2005-12-12 3:25 ` Bill Davidsen 2005-12-11 5:33 ` Rob Landley 2005-12-05 21:22 ` Bill Davidsen 2005-12-06 14:59 ` Bill Davidsen 2005-12-05 18:44 ` Adrian Bunk 2005-12-03 18:21 ` Mark Lord 2005-12-03 19:22 ` Linus Torvalds 2005-12-04 3:32 ` Mark Lord 2005-12-03 22:21 ` Matthias Andree 2005-12-03 22:29 ` Greg KH 2005-12-03 22:41 ` Matthias Andree 2005-12-03 22:48 ` Steven Rostedt 2005-12-03 17:22 ` Arjan van de Ven 2005-12-03 17:35 ` M. 2005-12-03 23:05 ` Matthias Andree 2005-12-03 23:37 ` Greg KH 2005-12-04 0:52 ` Jeff V. Merkey 2005-12-04 12:12 ` Matthias Andree 2005-12-04 12:32 ` Arjan van de Ven 2005-12-04 13:28 ` Matthias Andree 2005-12-04 13:35 ` Arjan van de Ven 2005-12-04 14:25 ` Matthias Andree 2005-12-04 14:50 ` Arjan van de Ven 2005-12-04 15:08 ` Matthias Andree 2005-12-04 15:11 ` Arjan van de Ven 2005-12-04 15:36 ` Andreas Schwab 2005-12-04 16:17 ` Matthias Andree 2005-12-05 3:09 ` Joel Becker 2005-12-06 20:13 ` Alan Cox 2005-12-04 15:20 ` Arjan van de Ven 2005-12-04 16:23 ` Matthias Andree 2005-12-04 15:25 ` Richard Knutsson 2005-12-04 15:23 ` Arjan van de Ven 2005-12-05 23:51 ` Rob Landley 2005-12-06 20:40 ` Matan Peled 2005-12-04 19:57 ` Horst von Brand 2005-12-04 21:35 ` Bernd Petrovitsch 2005-12-05 0:43 ` Jeff V. Merkey 2005-12-05 9:06 ` Bernd Petrovitsch 2005-12-06 0:41 ` Horst von Brand 2005-12-06 9:38 ` Bernd Petrovitsch 2005-12-03 18:43 ` Golden rule: don't break userland (was Re: RFC: Starting a stable kernel series off the 2.6 kernel) Jeff Garzik 2005-12-03 20:34 ` Greg KH 2005-12-04 1:40 ` Dmitry Torokhov 2005-12-04 23:29 ` Greg KH 2005-12-05 21:41 ` Dmitry Torokhov 2005-12-03 22:35 ` Matthias Andree 2005-12-04 15:37 ` Michael Frank 2005-12-05 3:23 ` RFC: Starting a stable kernel series off the 2.6 kernel Rob Landley 2005-12-10 19:48 ` Ryan Anderson 2005-12-03 18:39 ` Dr. David Alan Gilbert 2005-12-03 20:59 ` Lars Marowsky-Bree 2005-12-03 21:13 ` Dave Jones 2005-12-03 21:18 ` Lars Marowsky-Bree 2005-12-03 21:42 ` [OT] " Michael Buesch 2005-12-03 22:40 ` Adrian Bunk 2005-12-03 23:02 ` Matthias Andree 2005-12-03 23:09 ` Dave Jones 2005-12-06 0:14 ` Florian Weimer 2005-12-06 13:20 ` Lars Marowsky-Bree 2005-12-06 13:37 ` Florian Weimer 2005-12-04 12:56 ` Indrek Kruusa 2005-12-04 13:05 ` Arjan van de Ven 2005-12-04 15:26 ` Indrek Kruusa 2005-12-05 23:43 ` Rob Landley 2005-12-05 19:30 ` Bill Davidsen 2005-12-05 23:25 ` Adrian Bunk 2005-12-06 11:28 ` Matthias Andree 2005-12-06 13:25 ` Lars Marowsky-Bree 2005-12-06 20:46 ` Bill Davidsen 2005-12-12 14:45 ` Felix Oxley 2005-12-12 17:17 ` Horst von Brand 2005-12-12 18:53 ` Felix Oxley 2005-12-13 13:17 ` Horst von Brand 2005-12-14 0:09 ` Felix Oxley -- strict thread matches above, loose matches on Subject: below -- 2006-07-21 19:46 the " 'official' point of view" expressed by kernelnewbies.org regarding reiser4 inclusion Hans Reiser 2006-07-22 0:11 ` Losing Technologists [was: the " 'official' point of view" expressed by kernelnewbies.org regarding reiser4 inclusion] Neil Brown 2006-07-22 0:18 ` the " 'official' point of view" expressed by kernelnewbies.org regarding reiser4 inclusion Adrian Bunk 2006-07-22 19:19 ` Diego Calleja 2006-07-22 13:02 ` Theodore Tso 2006-07-22 14:30 ` Eric Sandeen 2006-07-22 18:33 ` Hans Reiser 2006-07-22 20:29 ` Jeff Garzik 2006-07-23 7:20 ` Hans Reiser 2006-07-23 9:12 ` Matt Heler 2006-07-24 4:01 ` Hans Reiser 2006-07-24 8:54 ` Matthias Andree 2006-07-24 8:13 ` Hans Reiser 2006-07-24 10:25 ` Matthias Andree 2006-07-24 11:34 ` Christian Iversen 2006-07-24 12:37 ` Erik Mouw 2006-07-24 12:37 ` Erik Mouw 2006-07-24 16:57 ` Mike Benoit 2006-07-24 17:35 ` Matthias Andree 2006-07-24 18:28 ` Valdis.Kletnieks 2006-07-24 18:06 ` Horst H. von Brand 2006-07-24 20:37 ` Mike Benoit 2006-07-24 21:22 ` Jan-Benedict Glaw 2006-07-24 21:51 ` Horst H. von Brand 2006-07-24 22:51 ` Mike Benoit 2006-07-25 15:08 ` Denis Vlasenko 2006-07-25 20:49 ` Matthias Andree 2006-07-25 23:04 ` David Masover 2006-07-26 11:20 ` Matthias Andree 2006-07-26 11:26 ` Matthias Andree 2006-07-26 13:02 ` Bernd Eckenfels 2006-07-26 18:54 ` Buddy Lucas 2006-07-27 1:29 ` David Masover 2006-07-26 0:29 ` David Masover 2006-07-26 0:36 ` David Lang 2006-07-26 0:47 ` David Masover 2006-07-31 10:58 ` Adrian Ulrich 2006-07-31 14:47 ` Matthias Andree 2006-07-31 15:59 ` Adrian Ulrich 2006-07-31 15:59 ` Adrian Ulrich 2006-07-31 16:22 ` Jan-Benedict Glaw 2006-07-31 16:44 ` David Masover 2006-07-31 17:34 ` Bernd Eckenfels 2006-07-31 18:36 ` Jan-Benedict Glaw 2006-07-31 16:44 ` Rudy Zijlstra 2006-07-31 17:20 ` Jan-Benedict Glaw 2006-07-31 17:32 ` Jan-Benedict Glaw 2006-07-31 17:46 ` Dan Oglesby 2006-07-31 18:11 ` Matthias Andree 2006-07-31 18:43 ` Jan-Benedict Glaw 2006-07-31 19:17 ` Clay Barnes 2006-07-31 19:29 ` Jan-Benedict Glaw 2006-07-31 20:00 ` David Masover 2006-07-31 20:53 ` the " 'official' point of view" expressed by kernelnewbies.orgregarding " David Lang 2006-07-31 21:16 ` David Masover 2006-07-31 21:14 ` the " 'official' point of view" expressed by kernelnewbies.org regarding " Bernd Schubert 2006-08-01 14:28 ` Horst H. von Brand 2006-08-01 14:52 ` Adrian Ulrich 2006-08-01 14:52 ` Adrian Ulrich 2006-08-01 15:29 ` Alan Cox 2006-08-01 16:44 ` David Masover 2006-08-01 17:04 ` Gregory Maxwell 2006-08-01 12:01 ` Hans Reiser 2006-08-01 17:41 ` David Masover 2006-08-01 18:14 ` Adrian Ulrich 2006-08-01 17:19 ` Alan Cox 2006-08-01 11:36 ` Hans Reiser 2006-08-01 17:40 ` David Masover 2006-08-01 19:27 ` Krzysztof Halasa 2006-08-03 13:58 ` Matthias Andree 2006-08-03 18:48 ` Gregory Maxwell 2006-08-03 23:25 ` Checksumming blocks? [was Re: the " 'official' point of view" expressed by kernelnewbies.org regarding reiser4 inclusion] Russell Leighton 2006-08-03 23:35 ` Matthias Andree 2006-08-04 0:01 ` Russell Leighton 2006-08-04 7:56 ` Toby Thain 2006-08-04 11:55 ` Russell Leighton 2006-08-04 11:41 ` Tomasz Torcz 2006-08-04 20:42 ` Horst H. von Brand 2006-08-04 20:51 ` David Masover 2006-08-01 18:11 ` the " 'official' point of view" expressed by kernelnewbies.org regarding reiser4 inclusion Adrian Ulrich 2006-08-01 18:21 ` Ric Wheeler 2006-08-01 11:41 ` Hans Reiser 2006-08-03 14:03 ` Matthias Andree 2006-08-03 15:44 ` Edward Shishkin 2006-08-03 17:26 ` Hans Reiser 2006-08-04 17:04 ` Edward Shishkin 2006-08-04 18:57 ` Antonio Vargas 2006-08-05 1:02 ` Hans Reiser 2006-08-05 0:56 ` Hans Reiser 2006-08-06 22:19 ` Edward Shishkin 2006-08-09 8:40 ` Hans Reiser 2006-08-09 11:53 ` Jan Engelhardt 2006-08-09 15:48 ` David Masover 2006-08-07 7:57 ` Matthias Andree 2006-08-08 11:06 ` Edward Shishkin 2006-08-01 19:11 ` David Masover 2006-08-03 14:03 ` Matthias Andree 2006-08-03 16:50 ` Theodore Tso 2006-08-01 16:57 ` David Masover 2006-08-06 22:59 ` Pavel Machek 2006-08-06 23:36 ` David Masover 2006-08-09 8:37 ` Hans Reiser 2006-08-09 9:48 ` Pavel Machek 2006-08-09 9:15 ` Hans Reiser 2006-08-09 15:52 ` David Masover 2006-07-31 19:42 ` Alan Cox 2006-07-31 19:34 ` Clay Barnes 2006-07-31 21:00 ` Gregory Maxwell 2006-07-31 21:40 ` Alan Cox 2006-07-31 21:43 ` David Masover 2006-07-31 21:54 ` Jeff V. Merkey 2006-07-31 22:02 ` Jeff V. Merkey 2006-07-31 22:21 ` Jeff V. Merkey 2006-07-31 22:56 ` Nate Diller 2006-07-31 23:52 ` Jeff V. Merkey 2006-07-31 23:43 ` Nate Diller 2006-08-01 0:15 ` Jeffrey V. Merkey 2006-08-01 6:28 ` Toby Thain 2006-07-31 22:17 ` Matthias Andree 2006-07-31 21:21 ` Łukasz Mierzwa 2006-07-31 21:21 ` Łukasz Mierzwa 2006-07-31 16:47 ` Dan Oglesby 2006-07-31 17:16 ` Jan-Benedict Glaw 2006-07-31 17:34 ` Matthias Andree 2006-07-31 17:44 ` Dan Oglesby 2006-07-31 16:54 ` Matthias Andree 2006-07-31 17:56 ` Adrian Ulrich 2006-07-31 20:07 ` Matthias Andree 2006-07-31 20:32 ` Adrian Ulrich 2006-07-31 20:32 ` Adrian Ulrich 2006-07-31 19:41 ` Theodore Tso 2006-07-31 22:53 ` Matthias Andree 2006-08-01 2:33 ` Hans Reiser 2006-07-31 19:18 ` Solaris ZFS on Linux [Was: Re: the " 'official' point of view" expressed by kernelnewbies.org regarding reiser4 inclusion] Horst H. von Brand 2006-07-31 20:31 ` Toby Thain 2006-07-31 20:57 ` Adrian Ulrich 2006-07-31 20:57 ` Adrian Ulrich 2006-07-31 21:54 ` Matthias Andree 2006-07-31 23:21 ` Nate Diller 2006-07-31 23:27 ` David Lang 2006-07-31 23:50 ` Nate Diller 2006-07-31 23:55 ` David Lang 2006-08-01 0:05 ` Nate Diller 2006-08-01 1:02 ` Matthias Andree 2006-08-01 1:25 ` Nate Diller 2006-08-01 1:31 ` David Masover 2006-08-01 3:00 ` Theodore Tso 2006-08-01 3:38 ` David Masover 2006-08-01 3:47 ` Timothy Webster 2006-08-01 4:24 ` David Masover 2006-08-01 4:41 ` Solaris ZFS on Linux [Was: Re: the " 'official' point of view"expressed " David Lang 2006-08-01 4:57 ` David Masover 2006-08-01 6:48 ` Theodore Tso 2006-08-01 2:40 ` Hans Reiser 2006-08-01 10:59 ` Jan Engelhardt 2006-08-01 10:56 ` Hans Reiser 2006-08-01 7:24 ` Avi Kivity 2006-08-01 9:25 ` Matthias Andree 2006-08-01 9:38 ` Avi Kivity 2006-08-01 17:03 ` David Masover 2006-08-01 4:38 ` Solaris ZFS on Linux [Was: Re: the " 'official' point of view" expressed " Mike Benoit 2006-08-01 4:21 ` Solaris ZFS on Linux [Was: Re: the " 'official' point of view"expressed " David Lang 2006-08-01 4:32 ` David Masover 2006-08-01 4:53 ` Solaris ZFS on Linux [Was: Re: the " 'official' point of view"expressedby " David Lang 2006-08-01 5:59 ` David Masover 2006-08-01 23:50 ` Solaris ZFS on Linux [Was: Re: the " 'official' point of view"expressed by " Ian Stirling 2006-08-02 2:29 ` Kyle Moffett 2006-08-02 14:28 ` Solaris ZFS on Linux Krzysztof Halasa 2006-08-02 18:12 ` Ian Stirling 2006-08-03 2:20 ` Wil Reichert 2006-08-03 9:32 ` Helge Hafting 2006-08-02 3:52 ` Solaris ZFS on Linux [Was: Re: the " 'official' point of view"expressed by kernelnewbies.org regarding reiser4 inclusion] David Masover 2006-08-01 7:51 ` Solaris ZFS on Linux [Was: Re: the " 'official' point of view" expressed " Adrian Ulrich 2006-08-01 7:51 ` Adrian Ulrich 2006-08-01 9:09 ` Matthias Andree 2006-08-01 9:57 ` Avi Kivity 2006-08-01 10:57 ` Jan Engelhardt 2006-08-01 13:15 ` Matthias Andree 2006-08-01 13:40 ` Jan Engelhardt 2006-07-31 22:08 ` Horst H. von Brand 2006-07-31 23:25 ` Nate Diller 2006-08-01 7:47 ` Adrian Ulrich 2006-08-01 7:47 ` Adrian Ulrich 2006-08-01 10:40 ` the " 'official' point of view" expressed by kernelnewbies.org regarding reiser4 inclusion Helge Hafting 2006-08-01 10:59 ` venom 2006-07-31 16:52 ` David Masover 2006-08-01 6:22 ` Jan Engelhardt 2006-07-24 20:28 ` Lex Lyamin 2006-07-26 13:17 ` Pavel Machek 2006-07-27 15:39 ` Grzegorz Kulewski 2006-07-27 17:28 ` Matthias Andree 2006-07-28 2:40 ` Hans Reiser 2006-07-27 17:56 ` Jeff Garzik 2006-07-27 19:06 ` David Masover 2006-07-28 2:26 ` Hans Reiser 2006-07-28 11:15 ` metadata plugins (was Re: the " 'official' point of view" expressed by kernelnewbies.org regarding reiser4 inclusion) Jeff Garzik 2006-07-28 14:02 ` Horst H. von Brand 2006-07-28 15:48 ` David Masover 2006-07-28 16:33 ` Linus Torvalds 2006-07-28 11:57 ` Hans Reiser 2006-07-28 19:44 ` David Masover 2006-07-28 13:34 ` Hans Reiser 2006-07-28 20:58 ` Łukasz Mierzwa 2006-07-28 21:32 ` Mike Benoit 2006-07-29 3:21 ` Hans Reiser 2006-07-28 21:53 ` David Masover 2006-07-29 1:36 ` Hans Reiser 2006-07-29 9:12 ` Arjan van de Ven 2006-07-29 18:11 ` David Masover 2006-07-29 20:02 ` Sarath Menon 2006-07-29 20:30 ` David Masover 2006-07-30 11:55 ` Christian Trefzer 2006-07-30 21:10 ` Wil Reichert 2006-07-30 21:39 ` Christian Trefzer 2006-07-30 21:42 ` Christian Trefzer 2006-07-30 22:38 ` David Masover 2006-07-31 15:21 ` Wil Reichert 2006-07-31 15:57 ` David Masover 2006-07-31 16:05 ` Łukasz Mierzwa 2006-07-31 22:05 ` Sarath Menon 2006-08-01 12:27 ` Christian Trefzer 2006-08-01 8:50 ` Christian Trefzer 2006-08-01 16:59 ` David Masover 2006-07-30 0:45 ` Maciej Sołtysiak 2006-07-30 1:08 ` Hans Reiser 2006-07-30 10:30 ` Łukasz Mierzwa 2006-07-30 10:30 ` Łukasz Mierzwa 2006-08-07 22:00 ` Pavel Machek 2006-07-29 12:28 ` Nikita Danilov 2006-07-29 18:31 ` David Masover 2006-07-29 18:57 ` Nikita Danilov 2006-07-29 23:01 ` Hans Reiser 2006-07-30 10:13 ` Łukasz Mierzwa 2006-07-30 10:13 ` Łukasz Mierzwa 2006-07-30 15:33 ` David Masover 2006-07-30 15:33 ` David Masover 2006-07-29 22:58 ` Hans Reiser 2006-07-31 11:58 ` Nikita Danilov 2006-07-29 18:25 ` David Masover 2006-07-31 13:28 ` Horst H. von Brand 2006-07-28 23:08 ` Jeff Garzik 2006-07-29 3:20 ` Hans Reiser 2006-08-07 21:56 ` ext3 vs reiserfs speed (was Re: metadata plugins (was Re: the " 'official' point of view" expressed by kernelnewbies.org regarding reiser4 inclusion)) Pavel Machek 2006-07-29 10:30 ` metadata plugins (was Re: the " 'official' point of view" expressed by kernelnewbies.org regarding reiser4 inclusion) Łukasz Mierzwa 2006-07-29 10:31 ` Łukasz Mierzwa 2006-07-30 18:41 ` Horst H. von Brand 2006-07-30 21:15 ` Toby Thain 2006-07-28 20:14 ` Hua Zhong 2006-07-28 13:40 ` Hans Reiser 2006-08-01 15:32 ` Łukasz Mierzwa 2006-08-01 15:32 ` Łukasz Mierzwa 2006-08-01 16:43 ` Vladimir V. Saveliev 2006-08-01 16:43 ` Vladimir V. Saveliev 2006-08-02 18:45 ` Horst H. von Brand 2006-08-02 17:07 ` Łukasz Mierzwa 2006-08-02 17:07 ` Łukasz Mierzwa 2006-08-05 1:01 ` David Masover 2006-07-23 11:48 ` the " 'official' point of view" expressed by kernelnewbies.org regarding reiser4 inclusion Jan-Benedict Glaw 2006-07-23 17:43 ` Toby Thain 2006-07-23 17:43 ` Toby Thain 2006-07-23 20:46 ` Jeff Mahoney 2006-07-23 21:15 ` Hans Reiser 2006-07-23 23:22 ` Jeff Mahoney 2006-07-23 22:35 ` Hans Reiser 2006-07-25 19:13 ` Russell Cattelan 2006-07-25 23:51 ` David Masover 2006-07-26 14:26 ` Hans Reiser 2006-07-26 18:16 ` Russell Cattelan 2006-07-27 1:19 ` David Masover 2006-07-27 20:11 ` Maciej Sołtysiak 2006-07-27 20:23 ` David Masover 2006-07-26 0:44 ` David Masover 2006-07-26 7:59 ` the ' 'official' point of view' " Luigi Genoni 2006-07-26 14:33 ` the " 'official' point of view" " Hans Reiser 2006-07-26 10:38 ` David Weinehall 2006-07-24 8:41 ` Matthias Andree 2006-07-24 8:09 ` Hans Reiser 2006-07-24 10:32 ` Matthias Andree 2006-07-24 13:49 ` Horst H. von Brand 2006-07-23 7:20 ` Rene Rebe 2006-07-24 7:49 ` Nikita Danilov 2006-07-25 12:35 ` Andrea Arcangeli 2006-07-25 12:51 ` Rene Rebe 2006-07-25 17:47 ` Hans Reiser 2006-07-25 19:20 ` Francesco Biscani 2006-07-25 21:17 ` Horst H. von Brand 2006-07-25 22:48 ` Jim Crilly 2006-07-25 23:48 ` andrea 2006-07-25 23:45 ` Luigi Genoni 2006-07-26 12:45 ` Adrian Bunk 2006-07-26 13:29 ` andrea 2006-07-26 13:43 ` Adrian Bunk 2006-07-26 14:28 ` andrea 2006-07-26 14:50 ` Adrian Bunk 2006-07-26 16:06 ` andrea 2006-07-26 16:53 ` Adrian Bunk 2006-07-26 17:02 ` J. Bruce Fields 2006-07-26 17:20 ` andrea 2006-07-26 19:01 ` Jerome Pinot 2006-07-26 20:50 ` andrea 2006-07-26 20:50 ` Adrian Bunk 2006-07-26 21:17 ` andrea 2006-07-26 21:37 ` J. Bruce Fields 2006-07-26 22:17 ` andrea 2006-07-27 6:56 ` Adrian Bunk 2006-07-27 8:33 ` the ' 'official' point of view' " Luigi Genoni 2006-07-27 10:04 ` Adrian Bunk 2006-07-27 11:07 ` Luigi Genoni 2006-07-27 11:35 ` Adrian Bunk 2006-07-27 11:43 ` Luigi Genoni 2006-07-27 11:56 ` Adrian Bunk 2006-07-27 13:30 ` Horst H. von Brand 2006-07-27 13:42 ` gmu 2k6 2006-07-27 13:50 ` andrea 2006-07-27 14:31 ` Luigi Genoni 2006-07-27 18:37 ` Jim Crilly 2006-07-27 19:34 ` andrea 2006-07-27 18:43 ` Horst H. von Brand 2006-07-27 20:11 ` andrea 2006-07-27 12:21 ` CaT 2006-07-28 2:25 ` Hans Reiser 2006-07-28 10:01 ` Adrian Bunk 2006-07-28 14:05 ` Horst H. von Brand 2006-07-27 11:52 ` the " 'official' point of view" " andrea 2006-07-27 12:18 ` Adrian Bunk 2006-07-27 13:10 ` andrea 2006-07-27 13:58 ` Adrian Bunk 2006-07-27 14:45 ` andrea 2006-07-27 15:05 ` Adrian Bunk 2006-07-27 16:11 ` andrea 2006-07-28 2:25 ` Hans Reiser 2006-07-28 14:31 ` andrea 2006-07-28 1:47 ` Hans Reiser 2006-07-27 4:35 ` Hans Reiser 2006-07-27 13:26 ` Horst H. von Brand 2006-07-24 2:08 ` Steve Lord 2006-07-24 7:53 ` Nikita Danilov 2006-07-24 10:30 ` Theodore Tso 2006-07-24 11:35 ` Olivier Galibert 2006-07-24 13:39 ` Theodore Tso 2006-07-24 15:38 ` Olivier Galibert 2006-07-24 16:17 ` Theodore Tso 2006-07-24 17:50 ` Olivier Galibert 2006-07-24 18:29 ` Jeff Garzik 2006-07-26 13:08 ` Pavel Machek 2006-07-27 15:52 ` Olivier Galibert 2006-07-27 21:42 ` suspend2 merge history [was Re: the " 'official' point of view" expressed by kernelnewbies.org regarding reiser4 inclusion] Pavel Machek 2006-07-27 23:22 ` Olivier Galibert 2006-07-28 14:01 ` Pavel Machek 2006-07-29 19:23 ` Bill Davidsen 2006-07-29 21:19 ` Rafael J. Wysocki 2006-07-29 21:56 ` Hua Zhong 2006-07-29 22:54 ` Rafael J. Wysocki 2006-07-30 22:25 ` Hua Zhong 2006-07-30 23:07 ` Pavel Machek 2006-07-31 14:28 ` Bill Davidsen 2006-07-31 16:23 ` Pavel Machek 2006-07-31 18:55 ` Hua Zhong 2006-07-31 23:08 ` Rafael J. Wysocki 2006-08-01 1:09 ` Pavel Machek 2006-07-29 23:19 ` Bill Davidsen 2006-07-29 23:28 ` Pavel Machek 2006-07-29 23:47 ` Pavel Machek 2006-07-30 12:57 ` Bill Davidsen 2006-07-30 14:34 ` Rafael J. Wysocki 2006-07-29 23:31 ` Pavel Machek 2006-07-27 16:43 ` the " 'official' point of view" expressed by kernelnewbies.org regarding reiser4 inclusion Alan Cox 2006-07-25 21:44 ` Valdis.Kletnieks 2006-07-24 22:17 ` Paul Jackson 2006-07-25 8:05 ` Hans Reiser [not found] <matthias.andree@gmx.de> 2002-12-04 11:34 ` #! incompatible -- binfmt_script.c broken? Matthias Andree 2002-12-04 14:26 ` Alex Riesen 2002-12-04 15:23 ` Matthew Garrett 2002-12-04 18:37 ` Matthias Andree 2002-12-04 20:37 ` Matthew Garrett 2002-12-04 22:28 ` H. Peter Anvin 2002-12-05 11:55 ` Matthias Andree 2002-12-05 0:42 ` Horst von Brand 2002-12-05 11:38 ` Matthias Andree 2002-12-04 22:25 ` Andries Brouwer 2002-12-05 0:10 ` Horst von Brand
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=17299.27142.901162.564588@cse.unsw.edu.au \ --to=neilb@suse.de \ --cc=lbates@syscononline.com \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-raid@vger.kernel.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.