Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
MIME-Version: 1.0
References: <20210726060855.108250-1-pankaj.gupta.linux@gmail.com>
 <20210726060855.108250-2-pankaj.gupta.linux@gmail.com> <CAPcyv4inCFFXmg0r5+h0O6cADpt9HdboVDEL00XX-wGroy-7LQ@mail.gmail.com>
 <CAM9Jb+hqPBFUh9X4sKb9TUGXX1P0mC1xcuCNQx1BYvAvoP9uQg@mail.gmail.com>
 <CAPcyv4gUG1-y1u0ZyUkSGXg0eER_oTdexb8n-CYgb_rURvr8LA@mail.gmail.com>
 <CALzYo32AnNzENe414GDVivaF5wXQ7azaysBYkN9wHVYEW27NPw@mail.gmail.com> <CAPcyv4idY7GDYjXsvjduQ4rjfKo-qDgQoj5r6=Rr9poXqHEzeg@mail.gmail.com>
In-Reply-To: <CAPcyv4idY7GDYjXsvjduQ4rjfKo-qDgQoj5r6=Rr9poXqHEzeg@mail.gmail.com>
From:   Pankaj Gupta <pankaj.gupta@ionos.com>
Date:   Fri, 27 Aug 2021 14:39:28 +0200
Message-ID: <CALzYo315CXhcO2Dph010WazWBYkaAeEuGdjUFDnJcsVBDa5LNQ@mail.gmail.com>
Subject: Re: [RFC v2 1/2] virtio-pmem: Async virtio-pmem flush
To:     Dan Williams <dan.j.williams@intel.com>
Cc:     Pankaj Gupta <pankaj.gupta.linux@gmail.com>,
        Linux NVDIMM <nvdimm@lists.linux.dev>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        jmoyer <jmoyer@redhat.com>, David Hildenbrand <david@redhat.com>,
        "Michael S. Tsirkin" <mst@redhat.com>,
        Cornelia Huck <cohuck@redhat.com>,
        Vishal L Verma <vishal.l.verma@intel.com>,
        Dave Jiang <dave.jiang@intel.com>,
        "Weiny, Ira" <ira.weiny@intel.com>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

> > > > > > Implement asynchronous flush for virtio pmem using work queue
> > > > > > to solve the preflush ordering issue. Also, coalesce the flush
> > > > > > requests when a flush is already in process.
> > > > > >
> > > > > > Signed-off-by: Pankaj Gupta <pankaj.gupta@ionos.com>
> > > > > > ---
> > > > > >  drivers/nvdimm/nd_virtio.c   | 72 ++++++++++++++++++++++++++++--------
> > > > > >  drivers/nvdimm/virtio_pmem.c | 10 ++++-
> > > > > >  drivers/nvdimm/virtio_pmem.h | 14 +++++++
> > > > > >  3 files changed, 79 insertions(+), 17 deletions(-)
> > > > > >
> > > > > > diff --git a/drivers/nvdimm/nd_virtio.c b/drivers/nvdimm/nd_virtio.c
> > > > > > index 10351d5b49fa..61b655b583be 100644
> > > > > > --- a/drivers/nvdimm/nd_virtio.c
> > > > > > +++ b/drivers/nvdimm/nd_virtio.c
> > > > > > @@ -97,29 +97,69 @@ static int virtio_pmem_flush(struct nd_region *nd_region)
> > > > > >         return err;
> > > > > >  };
> > > > > >
> > > > > > +static void submit_async_flush(struct work_struct *ws);
> > > > > > +
> > > > > >  /* The asynchronous flush callback function */
> > > > > >  int async_pmem_flush(struct nd_region *nd_region, struct bio *bio)
> > > > > >  {
> > > > > > -       /*
> > > > > > -        * Create child bio for asynchronous flush and chain with
> > > > > > -        * parent bio. Otherwise directly call nd_region flush.
> > > > > > +       /* queue asynchronous flush and coalesce the flush requests */
> > > > > > +       struct virtio_device *vdev = nd_region->provider_data;
> > > > > > +       struct virtio_pmem *vpmem  = vdev->priv;
> > > > > > +       ktime_t req_start = ktime_get_boottime();
> > > > > > +
> > > > > > +       spin_lock_irq(&vpmem->lock);
> > > > > > +       /* flush requests wait until ongoing flush completes,
> > > > > > +        * hence coalescing all the pending requests.
> > > > > >          */
> > > > > > -       if (bio && bio->bi_iter.bi_sector != -1) {
> > > > > > -               struct bio *child = bio_alloc(GFP_ATOMIC, 0);
> > > > > > -
> > > > > > -               if (!child)
> > > > > > -                       return -ENOMEM;
> > > > > > -               bio_copy_dev(child, bio);
> > > > > > -               child->bi_opf = REQ_PREFLUSH;
> > > > > > -               child->bi_iter.bi_sector = -1;
> > > > > > -               bio_chain(child, bio);
> > > > > > -               submit_bio(child);
> > > > > > -               return 0;
> > > > > > +       wait_event_lock_irq(vpmem->sb_wait,
> > > > > > +                           !vpmem->flush_bio ||
> > > > > > +                           ktime_before(req_start, vpmem->prev_flush_start),
> > > > > > +                           vpmem->lock);
> > > > > > +       /* new request after previous flush is completed */
> > > > > > +       if (ktime_after(req_start, vpmem->prev_flush_start)) {
> > > > > > +               WARN_ON(vpmem->flush_bio);
> > > > > > +               vpmem->flush_bio = bio;
> > > > > > +               bio = NULL;
> > > > > > +       }
> > > > >
> > > > > Why the dance with ->prev_flush_start vs just calling queue_work()
> > > > > again. queue_work() is naturally coalescing in that if the last work
> > > > > request has not started execution another queue attempt will be
> > > > > dropped.
> > > >
> > > > How parent flush request will know when corresponding flush is completed?
> > >
> > > The eventual bio_endio() is what signals upper layers that the flush
> > > completed...
> > >
> > >
> > > Hold on... it's been so long that I forgot that you are copying
> > > md_flush_request() here. It would help immensely if that was mentioned
> > > in the changelog and at a minimum have a comment in the code that this
> > > was copied from md. In fact it would be extra helpful if you
> >
> > My bad. I only mentioned this in the cover letter.
>
> Yeah, sorry about that. Having come back to this after so long I just
> decided to jump straight into the patches, but even if I had read that
> cover I still would have given the feedback that md_flush_request()
> heritage should also be noted with a comment in the code.

Sure.

Thanks,
Pankaj