[Btrfs-devel] btrfs stability

[Rekrutacja119]

no, i measure creation, read time and deletion, and i mainly look at read
time as creation/deletion is not so common in real life.
i also used bonnie++ and it showed even more tragic results for xfs, btrfs
without any options:

                    ------Sequential Create------ --------Random
Create--------
                    -Create-- --Read--- -Delete-- -Create-- --Read---
-Delete--
files:max:min        /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec
%CP
DO 20:10000:1/10000  3289  87 17424 100  3594  96  4393  85 33271  98
2888   7

xfs, tweaked to the max (mkfs with lazy-count=1, size=128m, and mount
options noatime,nodiratime,logbufs=8,logbsize=256k (also tried nobarier):
                    ------Sequential Create------ --------Random
Create--------
                    -Create-- --Read--- -Delete-- -Create-- --Read---
-Delete--
files:max:min        /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec
%CP
DO 10:20000:1/10000   650   3 11524  28   382   4   693   4  8242  14
552   5

xfs was half of what i posted above when created default, or even 1/3.

if it's hard to read, i will just compare one , probably most important
thing, number of read random created files: 33271 on btrfs, 8242 on xfs
(something like 3000 without optimizations on xfs i think)


2008/3/8, Tuncer Ayaz <tuncer.ayaz at gmail.com>:
>
> 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.ext3option
> > (and it is default on in /etc/mke2fs.conf)
> >
>
>
> AFAIK xfs like ReiserFS uses a B+ tree.
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://oss.oracle.com/pipermail/btrfs-devel/attachments/20080308/4cfb8759/attachment.html