[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <549f1b24-b333-da7a-b598-bab7a070b52e@huawei.com>
Date: Mon, 6 Dec 2021 20:10:22 +0000
From: John Garry <john.garry@...wei.com>
To: <axboe@...nel.dk>
CC: <linux-block@...r.kernel.org>, <linux-kernel@...r.kernel.org>,
<ming.lei@...hat.com>, <kashyap.desai@...adcom.com>, <hare@...e.de>
Subject: Re: [PATCH v2 3/3] blk-mq: Optimise blk_mq_queue_tag_busy_iter() for
shared tags
On 06/12/2021 12:49, John Garry wrote:
> Kashyap reports high CPU usage in blk_mq_queue_tag_busy_iter() and callees
> using megaraid SAS RAID card since moving to shared tags [0].
>
> Previously, when shared tags was shared sbitmap, this function was less
> than optimum since we would iter through all tags for all hctx's,
> yet only ever match upto tagset depth number of rqs.
>
> Since the change to shared tags, things are even less efficient if we have
> parallel callers of blk_mq_queue_tag_busy_iter(). This is because in
> bt_iter() -> blk_mq_find_and_get_req() there would be more contention on
> accessing each request ref and tags->lock since they are now shared among
> all HW queues.
>
> Optimise by having separate calls to bt_for_each() for when we're using
> shared tags. In this case no longer pass a hctx, as it is no longer
> relevant, and teach bt_iter() about this.
>
> Ming suggested something along the lines of this change, apart from a
> different implementation.
>
> [0]https://lore.kernel.org/linux-block/e4e92abbe9d52bcba6b8cc6c91c442cc@mail.gmail.com/
>
Fixes: e155b0c238b2 ("blk-mq: Use shared tags for shared sbitmap support")
> Signed-off-by: John Garry<john.garry@...wei.com>
> Reviewed-by: Hannes Reinecke<hare@...e.de>
> Reviewed-by: Ming Lei<ming.lei@...hat.com>
> Reported-and-tested-by: Kashyap Desai<kashyap.desai@...adcom.com>
Powered by blists - more mailing lists