Maximum block dev size / filesystem size

From: Aaron Peterson (aaron_at_alpete.com)
Date: 10/07/04

  • Next message: Alan Cox: "Re: [Patch] new serial flow control" 
    To: linux-kernel@vger.kernel.org
Date:	Thu, 07 Oct 2004 16:19:21 -0400

    I work for a company with a 15 TB SAN. All opinions about the
    disadvantages of creating really large filesystems aside, I'm trying to
    find out what is the maximum filesystem size we can allocate on our SAN
    that a linux box (x86) can really use.

    I seem to be finding (from various posts on newsgroups and the kernel
    source itself) that block devices with 2.4 kernels cannot exceed 2 TB,
    so no matter what the filesystem can theoretically handle, 2 TB is the
    practical limit.

    I've read that XFS filesystems can theoretically be created up to 18
    million TB in size.

    What I can't seem to find anywhere is whether the 2 TB block device
    limit has improved/grown with 2.6 kernels (on x86 hardware). Perhaps
    I've looked in the wrong places, but I haven't found anything.

    If you have any helpful information, or can point me towards a better
    place to look I would be very appreciative.

    I am not joined to this list, so if you can CC: me in the reply I would
    also be grateful.

    Aaron

    -
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

  • Next message: Alan Cox: "Re: [Patch] new serial flow control"

    Relevant Pages