From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Message-ID: <1525672597.5064.3.camel@gmx.de> Subject: Re: [PATCH BUGFIX] block, bfq: postpone rq preparation to insert or merge From: Mike Galbraith To: Paolo Valente Cc: Jens Axboe , linux-block , LKML , Ulf Hansson , Mark Brown , linus.walleij@linaro.org, bfq-iosched@googlegroups.com, oleksandr@natalenko.name Date: Mon, 07 May 2018 07:56:37 +0200 In-Reply-To: <223CABEA-71E0-426F-A4AB-17BA8437C978@linaro.org> References: <20180504171701.6876-1-paolo.valente@linaro.org> <1525463210.622.1.camel@gmx.de> <1525508378.5406.6.camel@gmx.de> <9F155F9F-F6B2-465A-BA4D-A86FF6825071@linaro.org> <1525532191.5406.15.camel@gmx.de> <223CABEA-71E0-426F-A4AB-17BA8437C978@linaro.org> Content-Type: text/plain; charset="ISO-8859-15" Mime-Version: 1.0 List-ID: On Sun, 2018-05-06 at 09:42 +0200, Paolo Valente wrote: >=20 > diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c > index 118f319af7c0..6662efe29b69 100644 > --- a/block/bfq-mq-iosched.c > +++ b/block/bfq-mq-iosched.c > @@ -525,8 +525,13 @@ static void bfq_limit_depth(unsigned int op, struct = blk_mq_alloc_data *data) > if (unlikely(bfqd->sb_shift !=3D bt->sb.shift)) > bfq_update_depths(bfqd, bt); > =20 > +#if 0 > data->shallow_depth =3D > bfqd->word_depths[!!bfqd->wr_busy_queues][op_is_sync(op)]= ; ^^^^^^^^^^^^^ Q: why doesn't the top of this function look like so? --- block/bfq-iosched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -539,7 +539,7 @@ static void bfq_limit_depth(unsigned int struct bfq_data *bfqd =3D data->q->elevator->elevator_data; struct sbitmap_queue *bt; =20 - if (op_is_sync(op) && !op_is_write(op)) + if (!op_is_write(op)) return; =20 if (data->flags & BLK_MQ_REQ_RESERVED) { It looks a bit odd that these elements exist... + =A0=A0=A0=A0=A0=A0/* + =A0=A0=A0=A0=A0=A0=A0* no more than 75% of tags for sync writes (25% extr= a tags + =A0=A0=A0=A0=A0=A0=A0* w.r.t. async I/O, to prevent async I/O from starvi= ng sync + =A0=A0=A0=A0=A0=A0=A0* writes) + =A0=A0=A0=A0=A0=A0=A0*/ + =A0=A0=A0=A0=A0=A0bfqd->word_depths[0][1] =3D max(((1U<sb_shift) *= 3)>>2, 1U); + =A0=A0=A0=A0=A0=A0/* no more than ~37% of tags for sync writes (~20% extr= a tags) */ + =A0=A0=A0=A0=A0=A0bfqd->word_depths[1][1] =3D max(((1U<sb_shift) *= 6)>>4, 1U); ...yet we index via and log a guaranteed zero. -Mike