Re: [PATCH 1/2]block: optimize non-queueable flush request drive

[Shaohua Li <shaohua.li@intel.com>]

On Tue, 2011-05-03 at 16:23 +0800, Tejun Heo wrote:
> Hello,
> 
> On Tue, May 03, 2011 at 02:44:31PM +0800, Shaohua Li wrote:
> > > As I've said several times already, I really don't like this magic
> > > being done in the completion path.  Can't you detect the condition on
> > > issue of the second/following flush and append it to the running list?
> >
> > hmm, don't understand it. blk_flush_complete_seq is called when the
> > second flush is issued. or do you mean do this when the second flush is
> > issued to disk? but when the second flush is issued the first flush is
> > already finished.
> 
> Ah, okay, my bad.  That's the next sequence logic, so the right place.
> Still, please do the followings.
> 
> * Put it in a separate patch.
> 
> * Preferably, detect the actual condition (back to back flush) rather
>   than the queueability test unless it's too complicated.
> 
> * Please make pending/running paths look more symmetrical.
I retested, and appears just holding queue is already good enough. After
holding queue, merging back to back flush hasn't too much benefit. So
I'll not pursue do the back-to-back merge. I'll post my latest patches
out soon.

> > > If you already have tried that but this way still seems better, can
> > > you please explain why?
> > > 
> > > Also, this is a separate logic.  Please put it in a separate patch.
> > > The first patch should implement queue holding while flushing, which
> > > should remove the regression, right?
> >
> > ok. holding queue has no performance gain in my test, but it reduced a
> > lot of request requeue.
> 
> No, holding the queue should remove the regression completely.  Please
> read on.
> 
> > > Hmmm... why do you need separate ->flush_exclusive_running?  Doesn't
> > > pending_idx != running_idx already have the same information?
> >
> > when pending_idx != running_idx, flush request is added into queue tail,
> > but this doesn't mean flush request is dispatched to disk. there might
> > be other requests in the queue head, which we should dispatch. And flush
> > request might be reqeueud. Just checking pending_idx != running_idx will
> > cause queue hang because we thought flush is dispatched and then hold
> > the queue, but actually flush isn't dispatched yet, the queue should
> > dispatch other normal requests.
> 
> Don't hold elv_next_request().  Hold ->elevator_dispatch_fn().
ok, this works.

Thanks,
Shaohua