[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]

Re: [rhelv6-list] You suggestion for 'big' filesystem management Best Practice?

On Fri, Oct 28, 2011 at 12:32, Peter Ruprecht <peter ruprecht jila colorado edu> wrote:
Greg Swift wrote:

On Fri, Oct 28, 2011 at 11:30, Masopust, Christian <christian masopust siemens com <mailto:christian.masopust@siemens.com>> wrote:

    > Götz Reinicke wrote:
    > > Hi,
    > >
    > > we plan to set up a big file storage for media files like
    > uncompressed
    > > movies from student film projects, dvd images etc.
    > >
    > > It should be some sort of archive and will not bee accessed
    > by more than
    > > may be 5 people at the same time.
    > >
    > > The iSCSI RAID we have is about 26TB netto and I'm again
    > faced with the
    > > question: How many partitions, which filesystem, which
    > mount options etc.
    > >
    > > For the User it would be the most simpel thing, to have one big
    > > filesystem she/he could fill with all the data and dont has
    > to search
    > > e.g. on multiple volumes.
    > >
    > > On the other hand, if one big filesystem crashes or has do
    > be checked it
    > > will destroy a lot of data or the check will take hours ...
    > >
    > >
    > > Any suggestions pro or cons are welcome! :-)
    > >
    > > My favourite for now is 3 to 4 filesystems with the default ext4
    > > settings. (Redhat EL 5.7, may be soon 6.1)
    > >
    > > Thanks and best regards. Götz
    > If you decide to go with RHEL6, xfs is a good bet for making one big
    > filesystem.  We have a setup similar to what you're
    > describing and have
    > had very solid stability and performance using xfs (default
    > filesystem
    > and mount settings.)  As far as I can see (and knocking on
    > wood), xfs is
    > now a lot less flaky than it seemed to be in the past.
    >   -Peter

   I can approve what Peter mentioned. I've been using xfs on my
   CentOS 5 system with 2 16TB arrays (each holding one single filesystem)
   for several years with absolutely no issues!

So in his intial request he mentioned concern about fsck times.  How has this been for you guys (Christian and Peter) ?

fwiw, I'm actually mixing both xfs with 30+TB total file system and gluster in a different use case...  I just haven't had to fsck a system yet so I am very curious about how that is performing for others.


In testing, I purposely crashed the system while under light-moderate I/O load, and the xfs fs didn't need any recovery when it was remounted.  I don't have any real-world experience with how long it would take to xfs_check and xfs_repair a fs of that size that had gotten corrupted, sorry.  Though I will not be disappointed if I manage to avoid gaining that experience!

thats good to hear.  now that I think about it we've actually survived several system crashes (bug in firm on cpu hardware) and I don't think any of them have had to fsck.  hmm... maybe we'll force a check one of these days to experiment.

[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]