tech-kern archive

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]

Re: Proposal: B_ARRIER (addresses wapbl performance?)

On Dec 9, 2008, at 3:27 PM, Manuel Bouyer wrote:

Because the ordering constraint bewteen journal and other writes are
both way, the way I understand it: some "other writes" have to happen
before some journal writes, and some "other writes" have to happen
after some journal writes. I guess this doens't leave much writes with
no ordered contraints.

Journal writes really only need to be constrained with respect to the metadata they're journaling, and themselves (i.e. entry hits oxide before the header update that makes it valid does). Doesn't matter for data writes (assuming you're not journaling data, which we don't).

Manuel Bouyer <>
    NetBSD: 26 ans d'experience feront toujours la difference

-- thorpej

Home | Main Index | Thread Index | Old Index