Skip to contentSkip to conversation

when/why to use diffferent raid values for btrfs data & metadata?

DISCUSSION mail ignored 3 participants 6 messages Jan 24, 2010 – Feb 6, 2010 Btrfs file system

lore
Share & tools
lore
#0 lore raw

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 [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html

#1 lore raw

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

Quoted 10 lines · mail ignored

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

Quoted 2 lines

Use raid10 for both data and metadata
mkfs.btrfs -m raid10 -d raid10 /dev/sdb /dev/sdc /dev/sdd /dev/sd=

e

Quoted 9 lines

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

Quoted 4 lines

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

Quoted 9 lines

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

Quoted 3 lines

the body of a message to [email protected]
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 [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html

author
#2 lore raw

hi

Quoted 5 lines · RK

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!

author
#3 lore raw

anyone on when/why to use different RAID geometries for data & metadata= ?

Quoted 7 lines · On Sun, Jan 24, 2010 at 8:38 AM, 0bo0 <[email protected]> wrote:

hi

Quoted 4 lines · RK

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

Quoted 3 lines
Quoted 1 line

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

Quoted 6 lines

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 [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html

#4 lore raw
Quoted 2 lines · 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).

Quoted 22 lines · On Sun, Jan 24, 2010 at 8:38 AM, 0bo0 <[email protected]> wrote:
Quoted 9 lines

hi

Quoted 5 lines · RK

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

Quoted 7 lines

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 [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html

Signature · 2 lines
gpg key@ keyserver.linux.it: Goffredo Baroncelli (ghigo) <kreijackATinwind.it>
Key fingerprint = 4769 7E51 5293 D36C 814E  C054 BF04 F161 3DC5 0512
author
#5 lore raw
Quoted 7 lines · Goffredo Baroncelli
Quoted 2 lines

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.

Quoted 5 lines

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.