[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <45f8532e-5aa2-4b32-ae53-bdf588133a3e@kernel.org>
Date: Thu, 9 Oct 2025 07:41:22 +0900
From: Damien Le Moal <dlemoal@...nel.org>
To: Johannes Thumshirn <Johannes.Thumshirn@....com>,
Jens Axboe <axboe@...nel.dk>
Cc: Steven Rostedt <rostedt@...dmis.org>,
Masami Hiramatsu <mhiramat@...nel.org>,
Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
"linux-block@...r.kernel.org" <linux-block@...r.kernel.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"linux-trace-kernel@...r.kernel.org" <linux-trace-kernel@...r.kernel.org>,
"linux-btrace@...r.kernel.org" <linux-btrace@...r.kernel.org>,
John Garry <john.g.garry@...cle.com>, Hannes Reinecke <hare@...e.de>,
hch <hch@....de>, Naohiro Aota <Naohiro.Aota@....com>,
Shinichiro Kawasaki <shinichiro.kawasaki@....com>,
Chaitanya Kulkarni <chaitanyak@...dia.com>,
"Martin K . Petersen" <martin.petersen@...cle.com>
Subject: Re: [PATCH v2 13/15] blktrace: trace zone management operations
On 10/8/25 22:29, Johannes Thumshirn wrote:
> I'm not sure if it makes sense to do completion tracing here. At least
> we cannot do it in the endio handler as usual.
>
> One thing to get the error and the duration would be the following:
>
> int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
> sector_t sector, sector_t nr_sectors)
> {
>
> /* [...] */
>
> trace_blkdev_zone_mgmt(bio, nr_sectors);
> ret = submit_bio_wait(bio);
>
> + trace_blkdev_zone_mgmt_completion(bio, nr_sectors, bio->bi_error);
> bio_put(bio);
That does seem OK to me. Maybe try and see how it looks ?
Though the request alloc, insert, dispatch and completion for this BIO will
still be traced, right ? If these events show correctly that this is a zone
management command (and which one it is), then we should not need the above.
--
Damien Le Moal
Western Digital Research
Powered by blists - more mailing lists