[RFC, PATCH 0/2] xfs: dynamic speculative preallocation for delalloc
michael.monnerie at is.it-management.at
Fri Oct 15 02:14:54 CDT 2010
On Donnerstag, 14. Oktober 2010 Ivan.Novick at emc.com wrote:
> I have seen ~50% performance improvement in read rate when changing
> from small extents to large extents with XFS. Essentially going from
> not using allocsize to setting 1gb allocsize. Also GB/s class
In case of a database, I'd say 1GB allocsize seems fine. But when you're
at /var/log/, it could be a penalty, as when you have 50 open log files
which get permanently appended, you have 50GB preallocated which almost
surely won't be needed before the log is rotated anyway.
The question is: what is a good value for preallocation?
I'd guess for a database 1GB seems reasonable, for /var/log one full
stripe (nr-data-disks * stripe size), for webserver/ftp data too, as
well as a fileserver (storing office documents) and mailserver (storing
each mail as a separate file or into one flat file).
Or, when you have an app that writes files of specific size, use the
"normal maximum" file size. We have a special server storing files of
normally 50M-1G size, there I set allocsize=1024k, so that files will be
in one junk on disk. When sometimes a file is bigger, then it will be
fragmented but at reasonable sizes so it won't matter too much.
Is that reasonable?
Are there guides to help with that? I'd like to write a FAQ entry if
there is (can ever be?) a consensus of what would be a good value.
mit freundlichen Grüssen,
Michael Monnerie, Ing. BSc
it-management Internet Services
http://proteger.at [gesprochen: Prot-e-schee]
Tel: 0660 / 415 65 31
****** Radiointerview zum Thema Spam ******
// Wir haben im Moment zwei Häuser zu verkaufen:
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Size: 198 bytes
Desc: This is a digitally signed message part.
More information about the xfs