[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Bacula-devel] MaximumBlockSize Problem and Question
On Thursday 06 November 2008 22:02:26 Alex Chekholko wrote:
> On Wed, 5 Nov 2008 16:12:51 +0100
> Kern Sibbald <kern@xxxxxxxxxxx> wrote:
> > For writing to tape (providing it is LTO-n) I strongly recommend a block
> > size not to exceed 256K.
> Hi Kern,
> Why do you say that?
It is my experience with my own testing, and I asked the Quantum technical
gurus about using large blocks. They think it is not a good idea at all using
values larger than 512K and prefer as I do values around 256K. The bigger it
is the more likely the tape writing will get out of phase and IMO the gain is
not worth the possible problems.
> Is this thread relevant?:
> Also, I would like to corroborate the OP's experiences; I had an almost
> identical thread about small block size and slow write speed:
> In fact, I was unable to get higher block sizes working at all with
> So I am still stuck at ~22MB/s writing to LTO-4 with the default block
There are a lot of other parameters to consider, but I cannot give such advice
any more -- no time:
- Up the block size to 128K or 256K and verify that it is being written that
- Increase the Maximum File Size to about 5GB.
- Use only *very* fast RAID disks running at 15,000 rpm. Maybe soon we can
- Get only the best disk and tape controllers.
- Get good quality, big, fast hardware -- you need hardware experts to get
lots of speed.
Then you need to do the same kinds of tuning of your network.
This SF.Net email is sponsored by the Moblin Your Move Developer's challenge
Build the coolest Linux based applications with Moblin SDK & win great prizes
Grand prize is a trip for two to an Open Source event anywhere in the world
Bacula-devel mailing list
This mailing list archive is a service of Copilot Consulting.