Hello Brad,
Monday, March 30, 2009, 7:57:31 PM, you wrote:
BP> I've run into this too... I believe the issue is that the block
BP> size/allocation unit size in ZFS is much larger than the default size
BP> on older filesystems (ufs, ext2, ext3).
BP> The result is that if you have lots of small files smaller than the
BP> block size, they take up more total space on the filesystem because
BP> they occupy at least the block size amount.
BP> See the 'recordsize' ZFS filesystem property, though re-reading the
BP> man pages, I'm not 100% sure that tuning this property will have the
BP> intended effect.
regardless of file size and recordsize zfs will use smaller block size
for files smaller than recordsize. The only issue here I'm aware about
is the last block in a large file which currently will be fixed in
size instead of being dynamically adjusted (there is a bug to cover
it).
Then is block doesn't compress better than 12.5% it won't be
compressed at all. Then in zfs you need extra space for checksums, etc.
How did the OP came up with how much data is being used?
--
Best regards,
Robert Milkowski
http://milek.blogspot.com
_______________________________________________
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
