Date: Sun, 16 Dec 2007 00:58:40 +0100 From: Harald Schmalzbauer <h.schmalzbauer@omnisec.de> To: freebsd-stable@freebsd.org Subject: sbp/da (ohci) write regression (da-quirk removement problem?) Message-ID: <47646A30.2060906@omnisec.de>
next in thread | raw e-mail | index | archive | help
[-- Attachment #1 --] Hello, I wanted to archive something on my external firewire drive and recognized a massive write performance degradation over 7-current from 3 months ago. I could read _and_ write about 30MB/s, reading still gives me a value like that but writing broke down to 1,4 MB/s!!! Also I see some warnings I haven't seen before: da4 at sbp0 bus 0 target 0 lun 0 da4: <NEWMOTIO 2045-11 0135> Fixed Simplified Direct Access SCSI-4 device da4: 50.000MB/s transfers da4: 39083MB (80043264 512 byte sectors: 255H 63S/T 4982C) (da4:sbp0:0:0:0): SYNCHRONIZE CACHE. CDB: 35 0 0 0 0 0 0 0 0 0 (da4:sbp0:0:0:0): ABORTED COMMAND asc:20,0 (da4:sbp0:0:0:0): Invalid command operation code (da4:sbp0:0:0:0): SYNCHRONIZE CACHE. CDB: 35 0 0 0 0 0 0 0 0 0 (da4:sbp0:0:0:0): ABORTED COMMAND csi:0,ae,47,c4 asc:20,0 (da4:sbp0:0:0:0): Invalid command operation code I remember that some da-quirks have been removed, respectivley code was written to detect umass drives more generally. Possibly that's the culprit? Any help highly appreciated. Thanks, -Harry [-- Attachment #2 --] -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.4 (FreeBSD) iD8DBQFHZGowLDqVQ9VXb8gRAoqbAJ4hsZ0TaZ94O3sYrUSZgSJBHdtq8ACfRIrU mwL6pEMlZ1Z7iQV3Rpx38Do= =QZnh -----END PGP SIGNATURE-----
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?47646A30.2060906>