On 19 Jan, Matti Saarinen wrote: > Don Lewis <truckman_at_freebsd.org> writes: > >>> (da0:ahd0:0:0:0): Retrying Command >>> (da0:ahd0:0:0:0): Queue Full >>> (da0:ahd0:0:0:0): tagged openings now 128 >>> (da0:ahd0:0:0:0): Retrying Command >> >> Try using the camcontrol modepage command to turn off write caching >> on each of the drives (set the WCE bit to 0). > > > I hope I've understood the output of the camcontrol command correctly. > The WCE bit is already set zero for all the devices connected to ahd0. > > # camcontrol modepage da0 -l > 0x01 Read-Write Error Recovery Page > 0x02 Disconnect-Reconnect Page > 0x03 Format Device Page > 0x04 Rigid Disk Drive Geometry Page > 0x07 Verify Error Recovery Page > 0x08 Caching Page > 0x0a Control Mode Page > 0x0c Notch and Partition Page > 0x19 > 0x1c > 0x21 > 0x00 Vendor-Specific > 0x34 > > # for i in {0..6} > do > echo -n "da$i: " && ( camcontrol modepage da$i -m 0x08 | grep WCE ) > done > da0: WCE: 0 > da1: WCE: 0 > da2: WCE: 0 > da3: WCE: 0 > da4: WCE: 0 > da5: WCE: 0 > da6: WCE: 0 That looks correct. You might try setting "camcontrol tags" down to 64 for each drive, since that is what it seems to be falling back to. I haven't used the IBM disks, only Seagate, and the one's that I've used seem to only support 64.Received on Mon Jan 19 2004 - 04:29:29 UTC
This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:37:38 UTC