* Chris Hoogendyk <hoogendyk AT bio.umass DOT edu> [20090612 11:46]:
>
> Jean-Francois Malouin wrote:
>> Hi,
>>
>> Not really an Amanda question but I'll try anyway...
>>
>> I can't get better than ~60MiBs to LTO4 tape when using amtapetype. I
>> tried 32k 1024k and 2048k, with and without hw compression enabled.
>> Any hints? I've added some info below. I can provide more upon request.
>>
>> Note that tapeinfo reports hw compression off but amtapetype says it
>> on. The changer web interface also tells me that the drive has
>> hardware compression off too. Puzzling.
>>
>
> Just an off-hand note, and I am not 100% sure it applies specifically to
> LTO4, but ...
>
> There was a detailed discussion on the Bacula list last year which
> concluded that a tape drive will respect the status of a particular tape
> regardless of what your settings are that you have configured the drive
> with. So, if you use a tape that was once written with hardware
> compression, it will continue to run that way.
>
> Try a brand new tape and see if it behaves any differently.
I'll give that a try.
>
> I'm assuming, of course, that you have also assessed all your hardware
> and software and concluded that it ought to be able to support a higher
> throughput to the tape.
Yes I did assume that. As I wrote to Dustin this host used to do
better than that with LTO3s, in fact I could have 2 tapers running at
the same time and get more than 60MiBs on *both* drives. But I want to
rule that out and will try with a box that I know gets ~100MiBs with
LTO4s.
regards!
jf
>
>
>> ***
>>
>> ArcVault-48 with LTO4 Ultrium HP. HBA is a LSI U320 in a PCI-X 133Mhz
>> slot. Host is a quad core Xeon running Debian/2.6.29.3-i686-64-smp
>> with amanda-2.6.1p1.
>>
>>
>> #> tapeinfo -f /dev/sg5
>> Product Type: Tape Drive
>> Vendor ID: 'HP '
>> Product ID: 'Ultrium 4-SCSI '
>> Revision: 'W23H'
>> Attached Changer: No
>> SerialNumber: 'HU18443UTY'
>> MinBlock:1
>> MaxBlock:16777215
>> SCSI ID: 5
>> SCSI LUN: 0
>> Ready: yes
>> BufferedMode: yes
>> Medium Type: Not Loaded
>> Density Code: 0x46
>> BlockSize: 0
>> DataCompEnabled: no
>> DataCompCapable: yes
>> DataDeCompEnabled: yes
>> CompType: 0x1
>> DeCompType: 0x1
>> BOP: yes
>> Block Position: 0
>>
>> #> ~amanda/sbin/amtapetype -f -b 1024k /dev/nst1
>> Applying heuristic check for compression.
>> Wrote random (uncompressible) data at 60250145.5737705 bytes/sec
>> Wrote fixed (compressible) data at 73505177.6 bytes/sec
>> Compression: enabled
>> Writing one file to fill the volume.
>> Wrote 813618429952 bytes at 62054 kb/sec
>> Writing smaller files (8135901184 bytes) to determine filemark.
>> define tapetype unknown-tapetype {
>> comment "Created by amtapetype; compression enabled"
>> length 794549248 kbytes
>> filemark 1996 kbytes
>> speed 62054 kps
>> blocksize 1024 kbytes
>> }
>>
>> regards,
>> jf
>>
>>
>
> --
> ---------------
>
> Chris Hoogendyk
>
> -
> O__ ---- Systems Administrator
> c/ /'_ --- Biology & Geology Departments
> (*) \(*) -- 140 Morrill Science Center
> ~~~~~~~~~~ - University of Massachusetts, Amherst
>
> <hoogendyk AT bio.umass DOT edu>
>
> ---------------
>
> Erdös 4
>
--
<° >< Jean-François Malouin McConnell Brain Imaging Centre
Systems/Network Administrator Montréal Neurological Institute
3801 Rue University, Suite WB219, Montréal, Québec, H3A 2B4, Canada
|
