Messages in this thread | | | Date | Mon, 7 Sep 2009 21:50:45 +0200 | From | Jens Axboe <> | Subject | Re: [PATCH 3/8] writeback: switch to per-bdi threads for flushing data v2 |
| |
On Mon, Sep 07 2009, Jan Kara wrote: > On Mon 07-09-09 20:45:18, Jens Axboe wrote: > > On Mon, Sep 07 2009, Jan Kara wrote: > > > Hi Jens, > > > > > > now I've found just two minor things (see below). Besides them the only > > > thing which is blocking my ack is a way to effectively lookup a BDI from a > > > superblock so that we can reasonably effectively fsync a superblock... > > > > Can we side step that as an inclusion criteria, please? I'd really like > > to work on adding that quick lookup, but I'd also hate to potentiall > > destabilize anything at this point. So we can probably quite easily make > > .32 as well for that, but I'd rather not risk doing a version and > > include that from the beginning. OK? > Well, for now I thought about a simple hack like a pointer to > backing_dev_info in a superblock. That should work for every filesystem > right now and shouldn't be too complex...
Oh certainly, it wont be complex. But there's still a risk with operations such as that, referencing to something new...
> But if you promise you'll fix that up before 2.6.32 is released, I'm OK > with your patch as is. I'll give your patches some testing with some less > usual benchmarks this week and if that works out fine you have my ack.
I promise :-)
Let me post a new version tomorrow, and you can base your tests off that.
-- Jens Axboe
| |