Michael Galloway wrote: > nothing is solved yet. i rebooted everything this morning to make sure the > scsi bus was cleared and reset. then i decided to try the individual btape > tests to see if i could isolate the issue. the fill test is running all day > still running:
Does your LSI controller have hard disk RAID features? If so I suggest that you disable it in the controller BIOS. Even better make sure that you have an Initiator Target firmware installed (there appears to be one for your HBA on the LSI web site). I have an LSI SAS3442X-R. I spent quite a few days trying to get decent performance out of an IBM LTO 4 drive. I finally fixed it by removing the IR (Integrated Raid) firmware and putting IT (Initiator Target) firmware on instead. This basically removes the RAID features, and in th Before I could only get 70MB/sec (with a large block size -- something like 20MB/sec with the default bacula 64k block size). I've not seen the drive hit 200MB/sec, which is a very nice increase in performance. [EMAIL PROTECTED]:/etc/bacula# dd if=/dev/zero of=/dev/nst0 bs=262144 count=100000 100000+0 records in 100000+0 records out 26214400000 bytes (26 GB) copied, 144.685 seconds, 181 MB/s BTW I think I agree with Kern now, huge block sizes don't help (though they did help to mask the effects of dodgy LSI firmware), though switching from 64k to ~256k does help. ------------------------------------------------------------------------- This SF.net email is sponsored by: Splunk Inc. Still grepping through log files to find problems? Stop. Now Search log events and configuration files using AJAX and a browser. Download your FREE copy of Splunk now >> http://get.splunk.com/ _______________________________________________ Bacula-users mailing list Bacula-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/bacula-users
