xfs
[Top] [All Lists]

xfs over linux raid5 perffered blocksize

To: xfs@xxxxxxxxxxx
Subject: xfs over linux raid5 perffered blocksize
From: "Raz Ben-Jehuda(caro)" <raziebe@xxxxxxxxx>
Date: Wed, 13 Dec 2006 16:40:03 +0200
Domainkey-signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:mime-version:content-type:content-transfer-encoding:content-disposition; b=LmPJo/JfkjeDQp3SO0wPlHpTZ/aR5i9lQDiUHggMELRbdRSTSC/+RDPmXQg7HjmuUb3Gictfony0JhugxYas2BTYOUnf/RsiE/BtaFuLJoewWkAWPKmYmeVuuoZAjJtf/hYmGSNL6BzpMY6NBD2ggrnT0j6s1FafdjD2NZ02oXI=
Sender: xfs-bounce@xxxxxxxxxxx
Hello

I need to create a writer which creates files over linux software raid5.
the files must be aligned by the stripe unit and so as the extents.

If an extent SIZE is not a factor of the stripe unit it is as if i have
done nothing.

I have learned by reading the documentatiom that the preffered io size
is the stripe width. that seems to work. I am reserving space and writing
3MB size buffers to raid5 with 1MB stripe unit over 4 disks.

my question:
Can I rely on it ?
Can I enforce this behaviour ?

thank you
--
Raz


<Prev in Thread] Current Thread [Next in Thread>
  • xfs over linux raid5 perffered blocksize, Raz Ben-Jehuda(caro) <=