public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: "Richard W.M. Jones" <rjones@redhat.com>
To: Paolo Bonzini <pbonzini@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>,
	linux-scsi@vger.kernel.org, linux-kernel@vger.kernel.org,
	"Martin K. Petersen" <martin.petersen@oracle.com>
Subject: Re: Increased memory usage with scsi-mq
Date: Mon, 7 Aug 2017 13:27:02 +0100	[thread overview]
Message-ID: <20170807122701.GH20914@redhat.com> (raw)
In-Reply-To: <b133b97e-9660-ba9b-51de-39fa23fce903@redhat.com>

On Mon, Aug 07, 2017 at 02:11:39PM +0200, Paolo Bonzini wrote:
> You could also add a module parameter to the driver, and set it to 64 on
> the kernel command line (there is an example in
> drivers/scsi/vmw_pvscsi.c of how to do it).

[Proviso: I've not tested the performance of difference values, nor do
I have any particular knowledge in this area]

can_queue is documented as:

         * This determines if we will use a non-interrupt driven
         * or an interrupt driven scheme.  It is set to the maximum number
         * of simultaneous commands a given host adapter will accept.

Wouldn't it be better to make it default to k * number of CPUs for
some small integer k?

I looked at the other scsi drivers and they set it to all kinds of
values.  1, small integers, large integers, configurable values.

Also I noticed this code in virtio_scsi.c:

        cmd_per_lun = virtscsi_config_get(vdev, cmd_per_lun) ?: 1;
        shost->cmd_per_lun = min_t(u32, cmd_per_lun, shost->can_queue);

but setting cmd_per_lun (as a qemu virtio-scsi-pci parameter) didn't
seem to make any difference to memory usage.

Rich.

-- 
Richard Jones, Virtualization Group, Red Hat http://people.redhat.com/~rjones
Read my programming and virtualization blog: http://rwmj.wordpress.com
virt-df lists disk usage of guests without needing to install any
software inside the virtual machine.  Supports Linux and Windows.
http://people.redhat.com/~rjones/virt-df/

  reply	other threads:[~2017-08-07 12:27 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-08-04 21:00 Increased memory usage with scsi-mq Richard W.M. Jones
2017-08-05  8:44 ` Christoph Hellwig
2017-08-05  9:27   ` Richard W.M. Jones
2017-08-05 13:39     ` Christoph Hellwig
2017-08-05 15:51       ` Richard W.M. Jones
2017-08-07 12:11         ` Paolo Bonzini
2017-08-07 12:27           ` Richard W.M. Jones [this message]
2017-08-07 13:07             ` Paolo Bonzini
2017-08-09 16:01               ` Christoph Hellwig
2017-08-09 16:50                 ` Paolo Bonzini
2017-08-10 12:22                   ` Richard W.M. Jones
2017-08-10 12:53                     ` Paolo Bonzini
2017-08-10 14:16                       ` Richard W.M. Jones
2017-08-10 14:30                         ` Paolo Bonzini
2017-08-10 15:40                           ` Richard W.M. Jones
2017-08-10 16:04                             ` Paolo Bonzini

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=20170807122701.GH20914@redhat.com \
    --to=rjones@redhat.com \
    --cc=hch@lst.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=martin.petersen@oracle.com \
    --cc=pbonzini@redhat.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox