Hello, I see strange behaviour when qualifying disk drives for ZFS. The tests I want to run should make sure that the drives honour the cache flush command. For this I do the following:
1) Create singe disk pools (only one disk in the pool) 2) Perorm I/O on the pools This is done via SQLIte and transactions. As soon as the transaction is commited to the calling application, I record the number of the transaction (a increasing number). 3) Then I pull the disk 4) I remember the number last committed 5) I power off the server 6) I plug the disk back 7) I power on the server 8) I verify that the last commited number is on disk Here I find that this fails always by 1 transaction. One transaction is committed to the appliance but not on disk. The strange thing is that if I only wait 10 seconds after the disk pull and do the reoot then, then all transactions are on disk. For me it looks like the I/O "in flight" is commited altought it never reaches the disk. Any tipps how to investigate further ? Regards, Robert -- This message posted from opensolaris.org _______________________________________________ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
