zfs discuss - Jul 2006 - raidz and 512 byte files

Hello,

When files are created that are <= 512 bytes using a raidz pool, how are 
full stripe writes performed ?

-thanks,
-Dave

In RAID-Z, the width of the stripe can vary. For a small block (such as would
hold 512 bytes or less of file data), the stripe will be 1 data block and either
1 or 2 parity blocks. So a full-stripe write will simply look like either
mirroring (RAIDZ1) or mirror plus one additional ECC block (RAIDZ2). In either
case, there aren''t any "unused" blocks written to disk.

See
<http://cvs.opensolaris.org/source/xref/on/usr/src/uts/common/fs/zfs/vdev_raidz.c>.
You can see this logic in vdev_raidz_map_alloc().
 
 
This message posted from opensolaris.org