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;
Content-Type: text/plain;
        charset=us-ascii
Mime-Version: 1.0 (Mac OS X Mail 11.3 \(3445.6.18\))
Subject: Re: bug in tag handling in blk-mq?
From:   Paolo Valente <paolo.valente@linaro.org>
In-Reply-To: <1525839089.15732.1.camel@gmx.de>
Date:   Wed, 9 May 2018 07:06:31 +0200
Cc:     Jens Axboe <axboe@kernel.dk>, Christoph Hellwig <hch@lst.de>,
        linux-block <linux-block@vger.kernel.org>,
        Ulf Hansson <ulf.hansson@linaro.org>,
        LKML <linux-kernel@vger.kernel.org>,
        Linus Walleij <linus.walleij@linaro.org>,
        Oleksandr Natalenko <oleksandr@natalenko.name>
Content-Transfer-Encoding: quoted-printable
Message-Id: <511C7624-6089-44E2-840A-E2657141AD88@linaro.org>
References: <999DF2B3-4EE8-4BDF-89C5-EB0C2D8BF69E@linaro.org>
 <7760d23b-7a4c-a645-1c7a-da7569bb44dc@kernel.dk>
 <84145CD7-B917-4B32-8A5C-310C1910DB71@linaro.org>
 <1525755090.24338.1.camel@gmx.de> <1525768632.5208.4.camel@gmx.de>
 <ffd0c030-43f8-0dbe-42b3-03bb9c410bea@kernel.dk>
 <1525797766.5204.2.camel@gmx.de>
 <3692ce7d-a767-72e6-65ae-6178b6c2e7d8@kernel.dk>
 <f04636df-3f97-6c16-f37b-d407e062b9e5@kernel.dk>
 <57952405-bdeb-f4e4-1aef-a7c0a8a68674@kernel.dk>
 <1525839089.15732.1.camel@gmx.de>
To:     Mike Galbraith <efault@gmx.de>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk


> Il giorno 09 mag 2018, alle ore 06:11, Mike Galbraith <efault@gmx.de> =
ha scritto:
>=20
> On Tue, 2018-05-08 at 19:09 -0600, Jens Axboe wrote:
>>=20
>> Alright, I managed to reproduce it. What I think is happening is that
>> BFQ is limiting the inflight case to something less than the wake
>> batch for sbitmap, which can lead to stalls. I don't have time to =
test
>> this tonight, but perhaps you can give it a go when you are back at =
it.
>> If not, I'll try tomorrow morning.
>>=20
>> If this is the issue, I can turn it into a real patch. This is just =
to
>> confirm that the issue goes away with the below.
>=20
> Confirmed.  Impressive high speed bug stomping.
>=20

Great! It's a real relief that this ghost is gone.

Thank you both,
Paolo

>> diff --git a/lib/sbitmap.c b/lib/sbitmap.c
>> index e6a9c06ec70c..94ced15b6428 100644
>> --- a/lib/sbitmap.c
>> +++ b/lib/sbitmap.c
>> @@ -272,6 +272,7 @@ EXPORT_SYMBOL_GPL(sbitmap_bitmap_show);
>>=20
>> static unsigned int sbq_calc_wake_batch(unsigned int depth)
>> {
>> +#if 0
>> 	unsigned int wake_batch;
>>=20
>> 	/*
>> @@ -284,6 +285,9 @@ static unsigned int sbq_calc_wake_batch(unsigned =
int depth)
>> 		wake_batch =3D max(1U, depth / SBQ_WAIT_QUEUES);
>>=20
>> 	return wake_batch;
>> +#else
>> +	return 1;
>> +#endif
>> }
>>=20
>> int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int =
depth,
>>=20