All of lore.kernel.org
 help / color / mirror / Atom feed
From: Wang Yugui <wangyugui@e16-tech.com>
To: Wang Yugui <wangyugui@e16-tech.com>
Cc: linux-block@vger.kernel.org
Subject: Re: scsi optimal_io_size changed from 0 on kernel 6.6, to 16773120(32760*512, 4095*4096) on kernel 6.12/6.16
Date: Wed, 25 Jun 2025 07:00:20 +0800	[thread overview]
Message-ID: <20250625070020.B0D8.409509F4@e16-tech.com> (raw)
In-Reply-To: <20250624091020.071E.409509F4@e16-tech.com>

Hi,

> scsi optimal_io_size changed
> from 0 on kernel 6.6, 
> to 16773120(32760*512, 4095*4096) on kernel 6.12/6.16
> 
> I tested in on same device and same os dist, but different kernel version.
> both ssd/sas and ssd/sata connected to same hba(mpi3sas driver).
> 
> Is there some feature that changed the default value?

we walked around this problem with a local dirty fix.

diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
index 351b028ef893..638dbafd695d 100644
--- a/drivers/scsi/scsi_transport_sas.c
+++ b/drivers/scsi/scsi_transport_sas.c
@@ -240,6 +240,9 @@ static int sas_host_setup(struct transport_container *tc, struct device *dev,
 	if (dma_dev->dma_mask) {
 		shost->opt_sectors = min_t(unsigned int, shost->max_sectors,
 				dma_opt_mapping_size(dma_dev) >> SECTOR_SHIFT);
+		/* /sys/block/sda/queue/optimal_io_size 16773120(32760*512, 4095*4096) @T7610 @kernel 6.12+ */
+		shost->opt_sectors = min_t(unsigned int, shost->opt_sectors,
+				SZ_1M >> SECTOR_SHIFT);
 	}
 
 	return 0;

Best Regards
Wang Yugui (wangyugui@e16-tech.com)
2025/06/25


  reply	other threads:[~2025-06-24 23:16 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-06-24  1:10 scsi optimal_io_size changed from 0 on kernel 6.6, to 16773120(32760*512, 4095*4096) on kernel 6.12/6.16 Wang Yugui
2025-06-24 23:00 ` Wang Yugui [this message]
2025-06-25  1:42 ` Martin K. Petersen
2025-06-25  2:10   ` Wang Yugui

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=20250625070020.B0D8.409509F4@e16-tech.com \
    --to=wangyugui@e16-tech.com \
    --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 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.