Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
MIME-Version: 1.0
References: <20200213082643.GB9144@ming.t460p> <d2c77921-fdcd-4667-d21a-60700e6a2fa5@acm.org>
 <CAKUOC8U1H8qJ+95pcF-fjeu9hag3P3Wm6XiOh26uXOkvpNngZg@mail.gmail.com>
 <de7b841c-a195-1b1e-eb60-02cbd6ba4e0a@acm.org> <CACVXFVP114+QBhw1bXqwgKRw_s4tBM_ZkuvjdXEU7nwkbJuH1Q@mail.gmail.com>
 <CAKUOC8Xss0YPefhKfwBiBar-7QQ=QrVh3d_8NBfidCCxUuxcgg@mail.gmail.com>
 <20200215034652.GA19867@ming.t460p> <CAJmaN=miqzhnZUTqaTOPp+OWY8+QYhXoE=h5apSucMkEU4nvtA@mail.gmail.com>
 <20200219025456.GD31488@ming.t460p> <CAKUOC8UceQ_cDQC8ckvUio0AZHhasi7Np-PQ09e-dQ3fechKoA@mail.gmail.com>
 <20200219222255.GB24522@ming.t460p>
In-Reply-To: <20200219222255.GB24522@ming.t460p>
From:   Salman Qazi <sqazi@google.com>
Date:   Wed, 19 Feb 2020 14:26:26 -0800
Message-ID: <CAKUOC8VGMYM1w15G-2KKZ=SEU_T_Xv9fR2Kp3JUupogBxy5x8g@mail.gmail.com>
Subject: Re: BLKSECDISCARD ioctl and hung tasks
To:     Ming Lei <ming.lei@redhat.com>
Cc:     Jesse Barnes <jsbarnes@google.com>,
        Ming Lei <tom.leiming@gmail.com>,
        Bart Van Assche <bvanassche@acm.org>,
        Jens Axboe <axboe@kernel.dk>, Christoph Hellwig <hch@lst.de>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        linux-block <linux-block@vger.kernel.org>,
        Gwendal Grignou <gwendal@google.com>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Wed, Feb 19, 2020 at 2:23 PM Ming Lei <ming.lei@redhat.com> wrote:
>
> On Wed, Feb 19, 2020 at 09:54:31AM -0800, Salman Qazi wrote:
> > On Tue, Feb 18, 2020 at 6:55 PM Ming Lei <ming.lei@redhat.com> wrote:
> > >
> > > On Tue, Feb 18, 2020 at 08:11:53AM -0800, Jesse Barnes wrote:
> > > > On Fri, Feb 14, 2020 at 7:47 PM Ming Lei <ming.lei@redhat.com> wrote:
> > > > > What are the 'other operations'? Are they block IOs?
> > > > >
> > > > > If yes, that is why I suggest to fix submit_bio_wait(), which should cover
> > > > > most of sync bio submission.
> > > > >
> > > > > Anyway, the fix is simple & generic enough, I'd plan to post a formal
> > > > > patch if no one figures out better doable approaches.
> > > >
> > > > Yeah I think any block I/O operation that occurs after the
> > > > BLKSECDISCARD is submitted will also potentially be affected by the
> > > > hung task timeouts, and I think your patch will address that.  My only
> > > > concern with it is that it might hide some other I/O "hangs" that are
> > > > due to device misbehavior instead.  Yes driver and device timeouts
> > > > should generally catch those, but with this in place we might miss a
> > > > few bugs.
> > > >
> > > > Given the nature of these types of storage devices though, I think
> > > > that's a minor issue and not worth blocking the patch on, given that
> > > > it should prevent a lot of false positive hang reports as Salman
> > > > demonstrated.
> > >
> > > Hello Jesse and Salman,
> > >
> > > One more question about this issue, do you enable BLK_WBT on your test
> > > kernel?
> >
> > It doesn't exist on the original 4.4-based kernel where we reproduced
> > this bug.  I am curious how this interacts with this bug.
>
> blk-wbt can throttle discard request and keep discard queue not too
> deep.
>
> However, given block erase is involved in BLKSECDISCARD, I guess blk-wbt
> may not avoid this task hung issue completely.

Thanks for the explanation.

As I said, it takes one 4K BLKSECDISCARD to get to 100 second delay
where the entire device is unusable for that time.  So, the
queue doesn't have to be deep at all.  It's a single tiny IOCTL.

>
>
> Thanks,
> Ming
>