Linux block layer
 help / color / mirror / Atom feed
From: Keith Busch <kbusch@kernel.org>
To: Coly Li <colyli@kernel.org>
Cc: hch@lst.de, linux-block@vger.kernel.org
Subject: Re: Improper io_opt setting for md raid5
Date: Tue, 15 Jul 2025 11:28:22 -0600	[thread overview]
Message-ID: <aHaPtuTYTGXyd77c@kbusch-mbp> (raw)
In-Reply-To: <aHaHLKp7-RrYUeJW@kbusch-mbp>

On Tue, Jul 15, 2025 at 10:51:56AM -0600, Keith Busch wrote:
> > Then in drivers/scsi/sd.c, inside sd_revalidate_disk() from the following coce,
> > 3785         /*
> > 3786          * Limit default to SCSI host optimal sector limit if set. There may be
> > 3787          * an impact on performance for when the size of a request exceeds this
> > 3788          * host limit.
> > 3789          */
> > 3790         lim.io_opt = sdp->host->opt_sectors << SECTOR_SHIFT;
> 
> Checking where "opt_sectors" was introduced, 608128d391fa5c9 says it was
> to provide the host optimal sectors, but the io_opt limit is supposed to
> be the device's. Seems to be a mistmatch in usage here, as "opt_sectors"
> should only be the upper limit for "io_opt" rather than the starting
> value.

Oh, 'opt_sectors' does turn into an upper limit if sdkp->opt_xfer_blocks
is valid, so I guess either that value is either unusable or a larger
value than you're expecting.

  reply	other threads:[~2025-07-15 17:28 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-07-15 15:56 Improper io_opt setting for md raid5 Coly Li
2025-07-15 16:51 ` Keith Busch
2025-07-15 17:28   ` Keith Busch [this message]
2025-07-16  7:26 ` Yu Kuai
2025-07-16 12:34   ` Coly Li
2025-07-27 10:50 ` Csordás Hunor
2025-07-28  0:39   ` Damien Le Moal
2025-07-28  0:55     ` Yu Kuai
2025-07-28  2:41       ` Damien Le Moal
2025-07-28  3:08         ` Yu Kuai
2025-07-28  3:49           ` Damien Le Moal
2025-07-28  7:14             ` Yu Kuai
2025-07-28  7:44               ` Damien Le Moal
2025-07-28  9:02                 ` Yu Kuai
2025-07-29  4:23                   ` Martin K. Petersen
2025-07-29  6:25                     ` Yu Kuai
2025-07-29 22:02                     ` Tony Battersby
2025-07-29  6:13                   ` Hannes Reinecke
2025-07-29  6:29                     ` Yu Kuai
2025-07-29 22:24                     ` Keith Busch
2025-07-28 10:56                 ` Csordás Hunor
2025-07-29  4:08                 ` Martin K. Petersen
2025-07-29  3:53               ` Martin K. Petersen
2025-07-29  3:49             ` Martin K. Petersen
2025-07-29  4:44   ` Martin K. Petersen

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=aHaPtuTYTGXyd77c@kbusch-mbp \
    --to=kbusch@kernel.org \
    --cc=colyli@kernel.org \
    --cc=hch@lst.de \
    --cc=linux-block@vger.kernel.org \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox