From: "Cédric Le Goater" <clg@redhat.com>
To: Avihai Horon <avihaih@nvidia.com>, qemu-devel@nongnu.org
Cc: Alex Williamson <alex.williamson@redhat.com>,
Juan Quintela <quintela@redhat.com>, Peter Xu <peterx@redhat.com>,
Leonardo Bras <leobras@redhat.com>,
Zhenzhong Duan <zhenzhong.duan@intel.com>,
Yishai Hadas <yishaih@nvidia.com>,
Jason Gunthorpe <jgg@nvidia.com>,
Maor Gottlieb <maorg@nvidia.com>,
Kirti Wankhede <kwankhede@nvidia.com>,
Tarun Gupta <targupta@nvidia.com>,
Joao Martins <joao.m.martins@oracle.com>
Subject: Re: [PATCH 1/3] vfio/migration: Move from STOP_COPY to STOP in vfio_save_cleanup()
Date: Mon, 26 Jun 2023 11:56:49 +0200 [thread overview]
Message-ID: <3b6a527f-351c-8979-c15b-0dc0a8fdea11@redhat.com> (raw)
In-Reply-To: <20230626082353.18535-2-avihaih@nvidia.com>
On 6/26/23 10:23, Avihai Horon wrote:
> Changing the device state from STOP_COPY to STOP can take time as the
> device may need to free resources and do other operations as part of the
> transition. Currently, this is done in vfio_save_complete_precopy() and
> therefore it is counted in the migration downtime.
>
> To avoid this, change the device state from STOP_COPY to STOP in
> vfio_save_cleanup(), which is called after migration has completed and
> thus is not part of migration downtime.
That's optimization and
> Signed-off-by: Avihai Horon <avihaih@nvidia.com>
> ---
> hw/vfio/migration.c | 19 +++++++++++++------
> 1 file changed, 13 insertions(+), 6 deletions(-)
>
> diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
> index acbf0bb7ab..a8bfbe4b89 100644
> --- a/hw/vfio/migration.c
> +++ b/hw/vfio/migration.c
> @@ -383,6 +383,19 @@ static void vfio_save_cleanup(void *opaque)
> VFIODevice *vbasedev = opaque;
> VFIOMigration *migration = vbasedev->migration;
>
> + /*
> + * Changing device state from STOP_COPY to STOP can take time. Do it here,
> + * after migration has completed, so it won't increase downtime.
> + */
> + if (migration->device_state == VFIO_DEVICE_STATE_STOP_COPY) {
> + /*
> + * If setting the device in STOP state fails, the device should be
> + * reset. To do so, use ERROR state as a recover state.
> + */
> + vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_STOP,
> + VFIO_DEVICE_STATE_ERROR);
> + }
> +
> g_free(migration->data_buffer);
> migration->data_buffer = NULL;
> migration->precopy_init_size = 0;
> @@ -508,12 +521,6 @@ static int vfio_save_complete_precopy(QEMUFile *f, void *opaque)
> return ret;
> }
>
> - /*
> - * If setting the device in STOP state fails, the device should be reset.
> - * To do so, use ERROR state as a recover state.
> - */
> - ret = vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_STOP,
> - VFIO_DEVICE_STATE_ERROR);
we loose the possible returned error. Let's keep that change for later.
Thanks,
C.
> trace_vfio_save_complete_precopy(vbasedev->name, ret);
>
> return ret;
next prev parent reply other threads:[~2023-06-26 9:57 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-06-26 8:23 [PATCH 0/3] vfio/migration: Make VFIO migration non-experimental Avihai Horon
2023-06-26 8:23 ` [PATCH 1/3] vfio/migration: Move from STOP_COPY to STOP in vfio_save_cleanup() Avihai Horon
2023-06-26 9:56 ` Cédric Le Goater [this message]
2023-06-26 11:31 ` Avihai Horon
2023-06-26 8:23 ` [PATCH 2/3] vfio/migration: Reset bytes_transferred properly Avihai Horon
2023-06-26 9:52 ` Cédric Le Goater
2023-06-26 11:46 ` Avihai Horon
2023-06-26 12:01 ` Cédric Le Goater
2023-06-26 12:08 ` Avihai Horon
2023-06-26 8:23 ` [PATCH 3/3] vfio/migration: Make VFIO migration non-experimental Avihai Horon
2023-06-26 13:20 ` Cédric Le Goater
2023-06-26 13:40 ` Joao Martins
2023-06-26 15:26 ` Cédric Le Goater
2023-06-26 16:19 ` Jason Gunthorpe
2023-06-26 16:39 ` Cédric Le Goater
2023-06-26 16:36 ` Joao Martins
2023-06-26 17:27 ` Alex Williamson
2023-06-27 8:00 ` Avihai Horon
2023-06-27 12:21 ` Cédric Le Goater
2023-06-27 12:30 ` Jason Gunthorpe
2023-06-28 3:09 ` Shameerali Kolothum Thodi via
2023-06-27 14:20 ` Alex Williamson
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=3b6a527f-351c-8979-c15b-0dc0a8fdea11@redhat.com \
--to=clg@redhat.com \
--cc=alex.williamson@redhat.com \
--cc=avihaih@nvidia.com \
--cc=jgg@nvidia.com \
--cc=joao.m.martins@oracle.com \
--cc=kwankhede@nvidia.com \
--cc=leobras@redhat.com \
--cc=maorg@nvidia.com \
--cc=peterx@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=quintela@redhat.com \
--cc=targupta@nvidia.com \
--cc=yishaih@nvidia.com \
--cc=zhenzhong.duan@intel.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;
as well as URLs for NNTP newsgroup(s).