All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jens Axboe <axboe@kernel.dk>
To: Vincent Fu <vincentfu@gmail.com>,
	anuj1072538@gmail.com, hch@infradead.org, joshi.k@samsung.com,
	anuj20.g@samsung.com, fio@vger.kernel.org
Cc: Vincent Fu <vincent.fu@samsung.com>
Subject: Re: [PATCH 1/2] engines/io_uring: support r/w with metadata
Date: Wed, 23 Jul 2025 11:37:05 -0600	[thread overview]
Message-ID: <e548d5f8-9ebe-46cf-9f43-79be601d2057@kernel.dk> (raw)
In-Reply-To: <15cb4581-7067-40fa-9a1b-8883c9993d2c@kernel.dk>

>> +	if (!strcmp(td->io_ops->name, "io_uring") && o->md_per_io_size) {
>> +		struct nvme_data *data = FILE_ENG_DATA(io_u->file);
>> +		struct nvme_cmd_ext_io_opts ext_opts = {0};
>> +
>> +		if (data->pi_type) {
>> +			if (o->pi_act)
>> +				ext_opts.io_flags |= NVME_IO_PRINFO_PRACT;
>> +
>> +			ext_opts.io_flags |= o->prchk;
>> +			ext_opts.apptag = o->apptag;
>> +			ext_opts.apptag_mask = o->apptag_mask;
>> +		}
>> +		fio_nvme_generate_guard(io_u, &ext_opts);
>> +	}
> 
> Ehh a strcmp() in the hot path?! First of all, that's a big no-no.
> Secondly, if this really was required, you'd add something to put that
> strcmp() in the slow path and flag it. Lastly, thankfully this should be
> much better as:
> 
> 	if (td->io_ops == &ioengine_uring ...)
> 
> instead.

Eh I guess dynamically loaded engines would need special treatment. I'll
take a look. In any case, strcmp() is just too ugly to live, actually
quite a few in there and the io_uring engine is the only one that thinks
this is necessary.

-- 
Jens Axboe

  reply	other threads:[~2025-07-23 17:37 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-07-23 17:04 [PATCH 0/2] io_uring r/w with metadata Vincent Fu
2025-07-23 17:04 ` [PATCH 1/2] engines/io_uring: support " Vincent Fu
2025-07-23 17:23   ` Jens Axboe
2025-07-23 17:37     ` Jens Axboe [this message]
2025-07-23 18:28       ` Vincent Fu
2025-07-23 19:23         ` Jens Axboe
2025-07-23 17:04 ` [PATCH 2/2] t/io_uring_pi: test script for io_uring PI Vincent Fu

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=e548d5f8-9ebe-46cf-9f43-79be601d2057@kernel.dk \
    --to=axboe@kernel.dk \
    --cc=anuj1072538@gmail.com \
    --cc=anuj20.g@samsung.com \
    --cc=fio@vger.kernel.org \
    --cc=hch@infradead.org \
    --cc=joshi.k@samsung.com \
    --cc=vincent.fu@samsung.com \
    --cc=vincentfu@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.