* when/why to use diffferent raid values for btrfs data & metadata?
@ 2010-01-24 4:02 mail ignored
2010-01-24 11:28 ` RK
0 siblings, 1 reply; 6+ messages in thread
From: mail ignored @ 2010-01-24 4:02 UTC (permalink / raw)
To: linux-btrfs
Hi,
Just getting started with btrfs.
I understand that btrfs stores data/metadata in two different tree
structures =96 one for file/directory names, and one for data blocks.
Reading @,
http://btrfs.wiki.kernel.org/index.php/Using_Btrfs_with_Multiple_Devic=
es
Use raid10 for both data and metadata
mkfs.btrfs -m raid10 -d raid10 /dev/sdb /dev/sdc /dev/sdd /dev/sde
and @,
"Churning Butter(FS): An Interview with Chris Mason"
http://www.linux-mag.com/id/7329
CM Today you can do this:
mkfs.btrfs -m raid1 -d raid10 /dev/sda /dev/sdb /dev/sdc /dev/sdd
And you=92ll get metadata on raid1 and data on raid10. The raid10 will
use all four drives and the raid1 will use two drives at a time. Yes,
btrfs allows you to pick different values for data or metadata.
The fact that I *can* setup data & metadata differently is clear. But
I'm not at all clear *why* I'd want to, or what the advantages are.
I'd guess it's a balance/combination of performance & resiliency.
Naively "-m raid10 -d raid10" seems to make the most sense -- if i
have it, use it.
Are there any benchmarks, guidelines or recommendations?
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" =
in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: when/why to use diffferent raid values for btrfs data & metadata?
2010-01-24 4:02 when/why to use diffferent raid values for btrfs data & metadata? mail ignored
@ 2010-01-24 11:28 ` RK
2010-01-24 16:38 ` 0bo0
0 siblings, 1 reply; 6+ messages in thread
From: RK @ 2010-01-24 11:28 UTC (permalink / raw)
Cc: linux-btrfs
try this article "Linux Don't Need No Stinkin' ZFS: BTRFS Intro &
Benchmarks"
http://www.linux-mag.com/id/7308/3/
, there is a benchmark table and speed analysis (very informative), but
all the benchmarks are done with same -m and -d mkfs.btrfs option
mail ignored wrote:
> Hi,
>
> Just getting started with btrfs.
>
> I understand that btrfs stores data/metadata in two different tree
> structures =96 one for file/directory names, and one for data blocks.
>
> Reading @,
>
> http://btrfs.wiki.kernel.org/index.php/Using_Btrfs_with_Multiple_Dev=
ices
> Use raid10 for both data and metadata
> mkfs.btrfs -m raid10 -d raid10 /dev/sdb /dev/sdc /dev/sdd /dev/sd=
e
>
> and @,
>
> "Churning Butter(FS): An Interview with Chris Mason"
> http://www.linux-mag.com/id/7329
>
> CM Today you can do this:
> mkfs.btrfs -m raid1 -d raid10 /dev/sda /dev/sdb /dev/sdc /dev/sdd
> And you=92ll get metadata on raid1 and data on raid10. The raid10 wil=
l
> use all four drives and the raid1 will use two drives at a time. Yes,
> btrfs allows you to pick different values for data or metadata.
>
> The fact that I *can* setup data & metadata differently is clear. Bu=
t
> I'm not at all clear *why* I'd want to, or what the advantages are.
> I'd guess it's a balance/combination of performance & resiliency.
>
> Naively "-m raid10 -d raid10" seems to make the most sense -- if i
> have it, use it.
>
> Are there any benchmarks, guidelines or recommendations?
> --
> To unsubscribe from this list: send the line "unsubscribe linux-btrfs=
" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> =20
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" =
in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: when/why to use diffferent raid values for btrfs data & metadata?
2010-01-24 11:28 ` RK
@ 2010-01-24 16:38 ` 0bo0
2010-02-06 0:23 ` 0bo0
0 siblings, 1 reply; 6+ messages in thread
From: 0bo0 @ 2010-01-24 16:38 UTC (permalink / raw)
To: RK; +Cc: linux-btrfs
hi
On Sun, Jan 24, 2010 at 3:28 AM, RK <rkasl@computer.org> wrote:
> try this article "Linux Don't Need No Stinkin' ZFS: BTRFS Intro &
> Benchmarks"
> http://www.linux-mag.com/id/7308/3/
> , there is a benchmark table and speed analysis (very informative), but
> all the benchmarks are done with same -m and -d mkfs.btrfs option
that's one of the articles i' read. it also does mention that you can
define data/metadata as differnt RAID, afaict, it doesn't (?) say
anything about the what/why you would ... which is what i'm unclear
about.
thanks!
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: when/why to use diffferent raid values for btrfs data & metadata?
2010-01-24 16:38 ` 0bo0
@ 2010-02-06 0:23 ` 0bo0
2010-02-06 13:16 ` Goffredo Baroncelli
0 siblings, 1 reply; 6+ messages in thread
From: 0bo0 @ 2010-02-06 0:23 UTC (permalink / raw)
To: RK; +Cc: linux-btrfs
anyone on when/why to use different RAID geometries for data & metadata=
?
On Sun, Jan 24, 2010 at 8:38 AM, 0bo0 <0.bugs.only.0@gmail.com> wrote:
> hi
>
> On Sun, Jan 24, 2010 at 3:28 AM, RK <rkasl@computer.org> wrote:
>> try this article "Linux Don't Need No Stinkin' ZFS: BTRFS Intro &
>> Benchmarks"
>> http://www.linux-mag.com/id/7308/3/
>> , there is a benchmark table and speed analysis (very informative), =
but
>> all the benchmarks are done with same -m and -d mkfs.btrfs option
>
> that's one of the articles i' read. =A0it also does mention that you =
can
> define data/metadata as differnt RAID, afaict, it doesn't (?) say
> anything about the what/why you would ... which is what i'm unclear
> about.
>
> thanks!
>
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" =
in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: when/why to use diffferent raid values for btrfs data & metadata?
2010-02-06 0:23 ` 0bo0
@ 2010-02-06 13:16 ` Goffredo Baroncelli
2010-02-06 14:57 ` 0bo0
0 siblings, 1 reply; 6+ messages in thread
From: Goffredo Baroncelli @ 2010-02-06 13:16 UTC (permalink / raw)
To: linux-btrfs
On Saturday 06 February 2010, 0bo0 wrote:
> anyone on when/why to use different RAID geometries for data & metadata?
>
I expected that the size of data and meta-data are different by several order
of magnitude. So I can choice different trade-off between
space/speed/reliability for data and/or metadata.
If I need speed I can put the meta-data in a "fast" raid (like raid10) and put
the data in a slow raid (like raid6).
Or if I can tolerate the lost of data, I can put the meta-data in raid1 and
the data in raid0. A fault of a disk, may lead to lost of data, but not to
lost of the meta-data (the file-system is fully working).
> On Sun, Jan 24, 2010 at 8:38 AM, 0bo0 <0.bugs.only.0@gmail.com> wrote:
> > hi
> >
> > On Sun, Jan 24, 2010 at 3:28 AM, RK <rkasl@computer.org> wrote:
> >> try this article "Linux Don't Need No Stinkin' ZFS: BTRFS Intro &
> >> Benchmarks"
> >> http://www.linux-mag.com/id/7308/3/
> >> , there is a benchmark table and speed analysis (very informative), but
> >> all the benchmarks are done with same -m and -d mkfs.btrfs option
> >
> > that's one of the articles i' read. it also does mention that you can
> > define data/metadata as differnt RAID, afaict, it doesn't (?) say
> > anything about the what/why you would ... which is what i'm unclear
> > about.
> >
> > thanks!
> >
> --
> To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
--
gpg key@ keyserver.linux.it: Goffredo Baroncelli (ghigo) <kreijackATinwind.it>
Key fingerprint = 4769 7E51 5293 D36C 814E C054 BF04 F161 3DC5 0512
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: when/why to use diffferent raid values for btrfs data & metadata?
2010-02-06 13:16 ` Goffredo Baroncelli
@ 2010-02-06 14:57 ` 0bo0
0 siblings, 0 replies; 6+ messages in thread
From: 0bo0 @ 2010-02-06 14:57 UTC (permalink / raw)
To: Goffredo Baroncelli; +Cc: linux-btrfs
On Sat, Feb 6, 2010 at 5:16 AM, Goffredo Baroncelli <kreijack@libero.it> wrote:
>> anyone on when/why to use different RAID geometries for data & metadata?
>>
>
> I expected that the size of data and meta-data are different by several order
> of magnitude. So I can choice different trade-off between
> space/speed/reliability for data and/or metadata.
>
> If I need speed I can put the meta-data in a "fast" raid (like raid10) and put
> the data in a slow raid (like raid6).
> Or if I can tolerate the lost of data, I can put the meta-data in raid1 and
> the data in raid0. A fault of a disk, may lead to lost of data, but not to
> lost of the meta-data (the file-system is fully working).
sounds like there's no further, subtle considerations beyond the usual
"which RAID" considerations. then, i suppose that as long as i find
RAID-10 "good enough"(as it has been in the md-case), there's no
compelling reason NOT tp place both data/metadata in RAID-10
constructs in btrfs.
thanks.
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2010-02-06 14:57 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2010-01-24 4:02 when/why to use diffferent raid values for btrfs data & metadata? mail ignored
2010-01-24 11:28 ` RK
2010-01-24 16:38 ` 0bo0
2010-02-06 0:23 ` 0bo0
2010-02-06 13:16 ` Goffredo Baroncelli
2010-02-06 14:57 ` 0bo0
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).