Ocfs2 users - Jul 2008 - Much higher disk usage in OCFS2 then in XFS

Hi all,

I created a OCFS2 volume with a block size of 4kB and a clustersize of 
4kB. After I mounted the volume the first time there have been already 
over 600 MB in use. Then I started to copy a directory with a overall 
size of 1784 MB(measured on an XFS with "du"). After an hour about 4 
GB(!) have been used on the OCFS2 volume so I stopped the copy.
The files I copied are mostly smaller then 12kB.

Why is there such a big difference between XFS and OCFS2? Is it 
recommended to use OCFS2 for such small files(there are over 2 TB of them)?

Regards,

	Markus Meyer

That's 175 million files. I hope they are spread out across many 
directories.

Our inodes are blocksized.
4k blocksize means 700G of metadata.
2K means 350G.
1K means 175G.

AFAIK, XFS has 256 byte inodes.

Maybe try 1K blocksize and 8K clustersize.

You would be an ideal candidate for the inlinedata feature we
will release shortly. If possible, it stores the data in the
inode itself.

Markus Meyer wrote:
> Hi all,
>
> I created a OCFS2 volume with a block size of 4kB and a clustersize of 
> 4kB. After I mounted the volume the first time there have been already 
> over 600 MB in use. Then I started to copy a directory with a overall 
> size of 1784 MB(measured on an XFS with "du"). After an hour
about 4
> GB(!) have been used on the OCFS2 volume so I stopped the copy.
> The files I copied are mostly smaller then 12kB.
>
> Why is there such a big difference between XFS and OCFS2? Is it 
> recommended to use OCFS2 for such small files(there are over 2 TB of them)?
>
> Regards,
>
> 	Markus Meyer
>
> _______________________________________________
> Ocfs2-users mailing list
> Ocfs2-users at oss.oracle.com
> http://oss.oracle.com/mailman/listinfo/ocfs2-users
>