On 03/29/2012 12:54 AM, Goffredo Baroncelli wrote:
>>
>
> Could you elaborate which would be the issue ?
> "cp --reflink"-ing a file is not different than snapshotting a file. In
> any case I could mount a snapshot and not the source subvolume.
>
>
>
We already have a debate about this "cross-
Alex posted on Wed, 28 Mar 2012 22:11:01 + as excerpted:
> Phillip Susi ubuntu.com> writes:
>
>
>> So currently btrfs's concept of raid0 is "stripe across as many disks
>> as possible, with a minimum of 2 disks". Is there any reason for that
>> minimum? I don't see why it can't allow only
We convert btrfs_file_aio_write() to use new freeze check. We also add proper
freeze protection to btrfs_page_mkwrite(). Checks in cleaner_kthread() and
transaction_kthread() can be safely removed since btrfs_freeze() will lock
the mutexes and thus block the threads (and they shouldn't have anythi
Hello,
here is the fourth iteration of my patches to improve filesystem freezing.
Filesystem freezing is currently racy and thus we can end up with dirty data on
frozen filesystem (see changelog patch 06 for detailed race description). This
patch series aims at fixing this.
To be able to bloc
When mnt_want_write() starts to handle freezing it will get a full lock
semantics requiring proper lock ordering. So push mnt_want_write() call
consistently outside of i_mutex.
CC: Chris Mason
CC: linux-btrfs@vger.kernel.org
Signed-off-by: Jan Kara
---
fs/btrfs/ioctl.c | 23 +++---
Phillip Susi ubuntu.com> writes:
>
> So currently btrfs's concept of raid0 is "stripe across as many disks as
> possible, with a minimum of 2 disks". Is there any reason for that
> minimum? I don't see why it can't allow only one if that's the best it
> can manage.
>
That's called "Single"
> I'd like to see how they do that. The fact is you are still going to get
> random
> seeks since you have to binary search the blocks in an entire row since
> there is
> no way you can read a several thousand block row into memory to search it,
> so
> once your rows get pretty big you are doing j
On Wed, Mar 28, 2012 at 10:44:03PM +0200, Niels de Carpentier wrote:
>
> >
> > You are still going to have to have at least 29 levels to accomodate 1
> > billion
> > objects, though they won't all be full (sorry I missed the must be full or
> > empty
> > bit). So it looks like we'll have to actua
>
> You are still going to have to have at least 29 levels to accomodate 1
> billion
> objects, though they won't all be full (sorry I missed the must be full or
> empty
> bit). So it looks like we'll have to actually search what 13 rows right?
> So
> still more rows than a b-tree, and again you
I imagine there is, but based on what little information they've shown
I don't see how it's a hands down win against b-trees. If anything
we're talking about having to solve really complex problems in order
to get any sort of good performance out of this thing.
Oh, absolutely. Tack on COW an
On Wed, Mar 28, 2012 at 03:50:07PM -0400, Zach Brown wrote:
>
> >but lets say O(log N/2) where N is the number of elements in the row.
> >So in the situation I describe you are looking at having to do minimum
> >of 29 reads, one for each row,
>
> Hmm.
>
> Levels are powers of two and are either
but lets say O(log N/2) where N is the number of elements in the row.
So in the situation I describe you are looking at having to do minimum
of 29 reads, one for each row,
Hmm.
Levels are powers of two and are either full or empty. So the total
item count tells you which levels are full or e
On Wed, Mar 28, 2012 at 02:42:04PM -0400, Josef Bacik wrote:
> On Wed, Mar 28, 2012 at 02:25:39PM +, Danny Piccirillo wrote:
> > The case has been made on Phoronix for F-Trees: They makes use hard
> > drive speeds, not (relatively slow) access times; beat SSD's; and scale
> > perfectly across
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
On 03/28/2012 02:42 PM, Josef Bacik wrote:
> On Wed, Mar 28, 2012 at 02:25:39PM +, Danny Piccirillo wrote:
>> The case has been made on Phoronix for F-Trees: They makes use
>> hard drive speeds, not (relatively slow) access times; beat
>> SSD's; an
On Wed, Mar 28, 2012 at 02:25:39PM +, Danny Piccirillo wrote:
> The case has been made on Phoronix for F-Trees: They makes use hard
> drive speeds, not (relatively slow) access times; beat SSD's; and scale
> perfectly across multiple cores with hundreds of millions of entries.
>
> http://en.w
On 3/17/2012 8:19 AM, Hugo Mills wrote:
Where is the problem, how can I use the full space?
You can't. btrfs requires RAID-0 to be at least two devices wide
(otherwise it's not striped at all, which is the point of RAID-0). If
you want to use the full capacity of both disks and don't care a
I had a test that creates a 7gig raid1 device but it was ending up wonky
because the second device that gets added is the full size of the disk
instead of the limited size. So enforce the limited size on all disks
passed in at mkfs time, otherwise our threshold calculations end up wonky
when doing
Hello Liu
On 03/28/2012 04:18 AM, Liu Bo wrote:
On 03/28/2012 06:24 AM, Matthias G. Eckermann wrote:
# time cp -a --reflink /var/lib/lxc/installserver_tmp/rootfs
/var/lib/lxc/installserver
This is too much weird.
AFAIK, clone between different subvolumes should be forbidden.
So this wou
On Wed, Mar 28, 2012 at 9:25 AM, Danny Piccirillo
wrote:
> The case has been made on Phoronix for F-Trees: They makes use hard
> drive speeds, not (relatively slow) access times; beat SSD's; and scale
> perfectly across multiple cores with hundreds of millions of entries.
>
> http://en.wikipedia.o
The case has been made on Phoronix for F-Trees: They makes use hard
drive speeds, not (relatively slow) access times; beat SSD's; and scale
perfectly across multiple cores with hundreds of millions of entries.
http://en.wikipedia.org/wiki/TokuDB#Fractal_tree_indexes
How TokuDB Fractal Tree Datab
David Sterba jikos.cz> writes:
>
> On Tue, Mar 27, 2012 at 05:19:06PM +, Alex wrote:
> > Can I create/convert a existing (btrfs) directory into a subvolume?
>
> For the reference there's an entry at the wiki:
>
>
http://btrfs.ipv5.de/index.php?title=UseCases#Can_I_take_a_snapshot_of_a_dire
Danny Piccirillo posted on Wed, 28 Mar 2012 06:15:41 + as excerpted:
> Chris Mason oracle.com> writes:
>>
>> People have already started picking up #4, fujitsu had some patches in
>> this direction that we'll keep developing with.
>>
>> I stepped back to add some directory metadata fixups a
On Tue, Mar 27, 2012 at 05:19:06PM +, Alex wrote:
> Can I create/convert a existing (btrfs) directory into a subvolume?
For the reference there's an entry at the wiki:
http://btrfs.ipv5.de/index.php?title=UseCases#Can_I_take_a_snapshot_of_a_directory.3F
as noted in the thread, this relies on
On Wed, Mar 28, 2012 at 08:46:13AM +0700, Fajar A. Nugraha wrote:
> On Wed, Mar 28, 2012 at 5:24 AM, Matthias G. Eckermann wrote:
> > While the time measurement might be flawed due to the subvol
> > actions inbetween, caching etc.: I tried several times, and
> > "cp --reflinks" always is multiple
24 matches
Mail list logo