[Btrfs-devel] btrfs stability

[Tuncer Ayaz]

On Sat, Mar 8, 2008 at 7:50 PM, Rekrutacja119 <rekrutacja119 at gmail.com> wrote:
> running postmark with numbers set to 20 000, transactions to 10 000 and
> subdirectories to 20 000 i have following results with btrfs:
>      24 seconds total
>      11 seconds of transactions (909 per second)
>  Data:
>      26.48 megabytes read (1.10 megabytes per second)
>      136.18 megabytes written (5.67 megabytes per second)
>
>  same for xfs is:
>  Time:
>      70 seconds total
>      52 seconds of transactions (192 per second)
>  Data:
>      26.48 megabytes read (387.33 kilobytes per second)
>      136.18 megabytes written (1.95 megabytes per second)
>
>  it looks MUCH worse with more realistic setup, of 100 000 subdirs, 100 000
> files and 20 000 transactions. xfs slowed to 65KB/s !! on 4 drive RAID5 (new
> drives, just bought, seagete 500GB ones)
>  btrfs was stable
>
>  ext3 tests not possible because it would take like a day. (it is creating
> subdirs very very slow)
>  ext4 is the same as ext3
>  reiserfs is comparable speed to xfs
>  reiser4 is comparable speed to btrfs
>
>  i only tested with postmark, as this is going to be users file array, with
> files up to 3MB, and mostly in 5-50KB range
>  so no need to test how many MB/s it can copy with large files

Am I right to assume that your issue is the creation
speed and not accessing the created 100.000 entries?
I have to admit that I didn't look at what postmark
effectively measures.

>  also - how can i turn on dir_index on xfs? i think it's mkfs.ext3 option
> (and it is default on in /etc/mke2fs.conf)
>

AFAIK xfs like ReiserFS uses a B+ tree.