Attempting ATA TRIM on SAS devices?

Steven Hartland killing at multiplay.co.uk
Thu Jan 9 00:13:54 UTC 2014


----- Original Message ----- 
From: "Garrett Wollman" <wollman at csail.mit.edu>


> <<On Wed, 8 Jan 2014 23:57:57 -0000, "Steven Hartland" <killing at multiplay.co.uk> said:
> 
>> You could just force the delete_method to UNMAP then:
>> kern.cam.da.X.delete_method=UNMAP
> 
> I'm not sure that that works, given that the zpool is auto-imported at
> boot time and I don't know which da units will be assigned to the SSDs
> in question (no way to pin them so far as I can tell).  Does ZFS
> generate BIO_DELETE on the cache devices at any time other than pool
> import?

Yes on every delete, once a delete method has failed though it wont
be tried again so the only real side effect is that the first delete
will be attempted twice, so if you can live with that and cant
get a fixed FW for the disk then...

    Regarsd
    Steve

================================================
This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it. 

In the event of misdirection, illegible or incomplete transmission please telephone +44 845 868 1337
or return the E.mail to postmaster at multiplay.co.uk.



More information about the freebsd-scsi mailing list