Hi, It''s funny, since I spent hours researching this problem yesterday, too. I kind of fixed the problem by echo ''zfs_txg_synctime/W 0t1'' | mdb -kw (Pasted from <http://echelog.matzon.dk/logs/browse/opensolaris/1210284000> ) I only say kind of, because zfs response time sometimes is still horrible some time. I think It''s a zfs flush problem.I hope it helps. wbkang -- This message posted from opensolaris.org