xfs
[Top] [All Lists]

Re: ST alloc failures

To: linux-xfs@xxxxxxxxxxx
Subject: Re: ST alloc failures
From: Tim Shimmin <tes@xxxxxxx>
Date: Thu, 8 Apr 2004 12:56:20 +1000
Cc: Kai.Makisara@xxxxxxxx
Sender: linux-xfs-bounce@xxxxxxxxxxx
User-agent: Mutt/1.2.5.1i
Hi,

Kai Makisara wrote:
> The other problem is that you probably would like to use direct transfers 
> between the xfsdump/xfsrestore buffer and the drive instead of using the 
> "bounce" buffer in the driver. This is not possible unless the tape 
> requests are small enough for the SCSI adapter. In your case the limit is 
> 96 pages. You can try to increase this limit but it is not a general 
> solution.
> 
> I would recommend xfsdump/xfsrestore to use smaller requests if possible. 
> 64 pages of 4 kB would make 256 kB. Using this request size should not 
> limit throughput even with the fastest tape drives.
>
Okay.
Thanks for the advice, Kai.
Would have been nice to realise this at the outset of the port...nevermind,
I should have asked you then ;-)

xfsdump/restore on Linux use a default blocksize of 1Mb for local tapes.
(xfsdump/restore on IRIX uses 2MB).
One can specify the blocksize to use for xfsdump/xfsrestore using the
-b option (given in bytes, so for 256K, one would use "-b 262144").
One must remember to use the same option for the restore.

Cheers,
Tim.


<Prev in Thread] Current Thread [Next in Thread>