From: Avihai Horon <avihaih@nvidia.com>
To: "Maciej S. Szmigiero" <mail@maciej.szmigiero.name>,
Peter Xu <peterx@redhat.com>, Fabiano Rosas <farosas@suse.de>
Cc: "Alex Williamson" <alex.williamson@redhat.com>,
"Cédric Le Goater" <clg@redhat.com>,
"Eric Blake" <eblake@redhat.com>,
"Markus Armbruster" <armbru@redhat.com>,
"Daniel P . Berrangé" <berrange@redhat.com>,
"Joao Martins" <joao.m.martins@oracle.com>,
qemu-devel@nongnu.org
Subject: Re: [PATCH v2 01/17] vfio/migration: Add save_{iterate,complete_precopy}_started trace events
Date: Thu, 5 Sep 2024 16:08:02 +0300 [thread overview]
Message-ID: <8ec6abeb-25ee-417e-9f3f-d0f27ec4f370@nvidia.com> (raw)
In-Reply-To: <3c43bf662842e579c0009dfc5135024e45166987.1724701542.git.maciej.szmigiero@oracle.com>
Hi Maciej,
On 27/08/2024 20:54, Maciej S. Szmigiero wrote:
> External email: Use caution opening links or attachments
>
>
> From: "Maciej S. Szmigiero" <maciej.szmigiero@oracle.com>
>
> This way both the start and end points of migrating a particular VFIO
> device are known.
>
> Add also a vfio_save_iterate_empty_hit trace event so it is known when
> there's no more data to send for that device.
Out of curiosity, what are these traces used for?
>
> Signed-off-by: Maciej S. Szmigiero <maciej.szmigiero@oracle.com>
> ---
> hw/vfio/migration.c | 13 +++++++++++++
> hw/vfio/trace-events | 3 +++
> include/hw/vfio/vfio-common.h | 3 +++
> 3 files changed, 19 insertions(+)
>
> diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
> index 262d42a46e58..24679d8c5034 100644
> --- a/hw/vfio/migration.c
> +++ b/hw/vfio/migration.c
> @@ -472,6 +472,9 @@ static int vfio_save_setup(QEMUFile *f, void *opaque, Error **errp)
> return -ENOMEM;
> }
>
> + migration->save_iterate_run = false;
> + migration->save_iterate_empty_hit = false;
> +
> if (vfio_precopy_supported(vbasedev)) {
> switch (migration->device_state) {
> case VFIO_DEVICE_STATE_RUNNING:
> @@ -605,9 +608,17 @@ static int vfio_save_iterate(QEMUFile *f, void *opaque)
> VFIOMigration *migration = vbasedev->migration;
> ssize_t data_size;
>
> + if (!migration->save_iterate_run) {
> + trace_vfio_save_iterate_started(vbasedev->name);
> + migration->save_iterate_run = true;
Maybe rename save_iterate_run to save_iterate_started so it's aligned
with trace_vfio_save_iterate_started and
trace_vfio_save_complete_precopy_started?
> + }
> +
> data_size = vfio_save_block(f, migration);
> if (data_size < 0) {
> return data_size;
> + } else if (data_size == 0 && !migration->save_iterate_empty_hit) {
> + trace_vfio_save_iterate_empty_hit(vbasedev->name);
> + migration->save_iterate_empty_hit = true;
During precopy we could hit empty multiple times. Any reason why only
the first time should be traced?
> }
>
> vfio_update_estimated_pending_data(migration, data_size);
> @@ -633,6 +644,8 @@ static int vfio_save_complete_precopy(QEMUFile *f, void *opaque)
> int ret;
> Error *local_err = NULL;
>
> + trace_vfio_save_complete_precopy_started(vbasedev->name);
> +
> /* We reach here with device state STOP or STOP_COPY only */
> ret = vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_STOP_COPY,
> VFIO_DEVICE_STATE_STOP, &local_err);
> diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
> index 98bd4dcceadc..013c602f30fa 100644
> --- a/hw/vfio/trace-events
> +++ b/hw/vfio/trace-events
> @@ -159,8 +159,11 @@ vfio_migration_state_notifier(const char *name, int state) " (%s) state %d"
> vfio_save_block(const char *name, int data_size) " (%s) data_size %d"
> vfio_save_cleanup(const char *name) " (%s)"
> vfio_save_complete_precopy(const char *name, int ret) " (%s) ret %d"
> +vfio_save_complete_precopy_started(const char *name) " (%s)"
> vfio_save_device_config_state(const char *name) " (%s)"
> vfio_save_iterate(const char *name, uint64_t precopy_init_size, uint64_t precopy_dirty_size) " (%s) precopy initial size 0x%"PRIx64" precopy dirty size 0x%"PRIx64
> +vfio_save_iterate_started(const char *name) " (%s)"
> +vfio_save_iterate_empty_hit(const char *name) " (%s)"
Let's keep it sorted in alphabetical order.
Thanks.
> vfio_save_setup(const char *name, uint64_t data_buffer_size) " (%s) data buffer size 0x%"PRIx64
> vfio_state_pending_estimate(const char *name, uint64_t precopy, uint64_t postcopy, uint64_t precopy_init_size, uint64_t precopy_dirty_size) " (%s) precopy 0x%"PRIx64" postcopy 0x%"PRIx64" precopy initial size 0x%"PRIx64" precopy dirty size 0x%"PRIx64
> vfio_state_pending_exact(const char *name, uint64_t precopy, uint64_t postcopy, uint64_t stopcopy_size, uint64_t precopy_init_size, uint64_t precopy_dirty_size) " (%s) precopy 0x%"PRIx64" postcopy 0x%"PRIx64" stopcopy size 0x%"PRIx64" precopy initial size 0x%"PRIx64" precopy dirty size 0x%"PRIx64
> diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
> index fed499b199f0..32d58e3e025b 100644
> --- a/include/hw/vfio/vfio-common.h
> +++ b/include/hw/vfio/vfio-common.h
> @@ -73,6 +73,9 @@ typedef struct VFIOMigration {
> uint64_t precopy_init_size;
> uint64_t precopy_dirty_size;
> bool initial_data_sent;
> +
> + bool save_iterate_run;
> + bool save_iterate_empty_hit;
> } VFIOMigration;
>
> struct VFIOGroup;
next prev parent reply other threads:[~2024-09-05 13:08 UTC|newest]
Thread overview: 128+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-08-27 17:54 [PATCH v2 00/17] Multifd 🔀 device state transfer support with VFIO consumer Maciej S. Szmigiero
2024-08-27 17:54 ` [PATCH v2 01/17] vfio/migration: Add save_{iterate, complete_precopy}_started trace events Maciej S. Szmigiero
2024-09-05 13:08 ` Avihai Horon [this message]
2024-09-09 18:04 ` [PATCH v2 01/17] vfio/migration: Add save_{iterate,complete_precopy}_started " Maciej S. Szmigiero
2024-09-11 14:50 ` Avihai Horon
2024-08-27 17:54 ` [PATCH v2 02/17] migration/ram: Add load start trace event Maciej S. Szmigiero
2024-08-28 18:44 ` Fabiano Rosas
2024-08-28 20:21 ` Maciej S. Szmigiero
2024-08-27 17:54 ` [PATCH v2 03/17] migration/multifd: Zero p->flags before starting filling a packet Maciej S. Szmigiero
2024-08-28 18:50 ` Fabiano Rosas
2024-09-09 15:41 ` Peter Xu
2024-08-27 17:54 ` [PATCH v2 04/17] thread-pool: Add a DestroyNotify parameter to thread_pool_submit{, _aio)() Maciej S. Szmigiero
2024-08-27 17:54 ` [PATCH v2 05/17] thread-pool: Implement non-AIO (generic) pool support Maciej S. Szmigiero
2024-09-02 22:07 ` Fabiano Rosas
2024-09-03 12:02 ` Maciej S. Szmigiero
2024-09-03 14:26 ` Fabiano Rosas
2024-09-03 18:14 ` Maciej S. Szmigiero
2024-09-03 13:55 ` Stefan Hajnoczi
2024-09-03 16:54 ` Maciej S. Szmigiero
2024-09-03 19:04 ` Stefan Hajnoczi
2024-09-09 16:45 ` Peter Xu
2024-09-09 18:38 ` Maciej S. Szmigiero
2024-09-09 19:12 ` Peter Xu
2024-09-09 19:16 ` Maciej S. Szmigiero
2024-09-09 19:24 ` Peter Xu
2024-08-27 17:54 ` [PATCH v2 06/17] migration: Add save_live_complete_precopy_{begin, end} handlers Maciej S. Szmigiero
2024-08-28 19:03 ` [PATCH v2 06/17] migration: Add save_live_complete_precopy_{begin,end} handlers Fabiano Rosas
2024-09-05 13:45 ` Avihai Horon
2024-09-09 17:59 ` Peter Xu
2024-09-09 18:32 ` Maciej S. Szmigiero
2024-09-09 19:08 ` Peter Xu
2024-09-09 19:32 ` Peter Xu
2024-09-19 19:48 ` Maciej S. Szmigiero
2024-09-19 19:47 ` Maciej S. Szmigiero
2024-09-19 20:54 ` Peter Xu
2024-09-20 15:22 ` Maciej S. Szmigiero
2024-09-20 16:08 ` Peter Xu
2024-09-09 18:05 ` Maciej S. Szmigiero
2024-08-27 17:54 ` [PATCH v2 07/17] migration: Add qemu_loadvm_load_state_buffer() and its handler Maciej S. Szmigiero
2024-08-30 19:05 ` Fabiano Rosas
2024-09-05 14:15 ` Avihai Horon
2024-09-09 18:05 ` Maciej S. Szmigiero
2024-08-27 17:54 ` [PATCH v2 08/17] migration: Add load_finish handler and associated functions Maciej S. Szmigiero
2024-08-30 19:28 ` Fabiano Rosas
2024-09-05 15:13 ` Avihai Horon
2024-09-09 18:05 ` Maciej S. Szmigiero
2024-09-09 20:03 ` Peter Xu
2024-09-19 19:49 ` Maciej S. Szmigiero
2024-09-19 21:11 ` Peter Xu
2024-09-20 15:23 ` Maciej S. Szmigiero
2024-09-20 16:45 ` Peter Xu
2024-09-26 22:34 ` Maciej S. Szmigiero
2024-09-27 0:53 ` Peter Xu
2024-09-30 19:25 ` Maciej S. Szmigiero
2024-09-30 21:57 ` Peter Xu
2024-10-01 20:41 ` Maciej S. Szmigiero
2024-10-01 21:30 ` Peter Xu
2024-10-02 20:11 ` Maciej S. Szmigiero
2024-10-02 21:25 ` Peter Xu
2024-10-03 20:34 ` Maciej S. Szmigiero
2024-10-03 21:17 ` Peter Xu
2024-08-27 17:54 ` [PATCH v2 09/17] migration/multifd: Device state transfer support - receive side Maciej S. Szmigiero
2024-08-30 20:22 ` Fabiano Rosas
2024-09-02 20:12 ` Maciej S. Szmigiero
2024-09-03 14:42 ` Fabiano Rosas
2024-09-03 18:41 ` Maciej S. Szmigiero
2024-09-09 19:52 ` Peter Xu
2024-09-19 19:49 ` Maciej S. Szmigiero
2024-09-05 16:47 ` Avihai Horon
2024-09-09 18:05 ` Maciej S. Szmigiero
2024-09-12 8:13 ` Avihai Horon
2024-09-12 13:52 ` Fabiano Rosas
2024-09-19 19:59 ` Maciej S. Szmigiero
2024-08-27 17:54 ` [PATCH v2 10/17] migration/multifd: Convert multifd_send()::next_channel to atomic Maciej S. Szmigiero
2024-08-30 18:13 ` Fabiano Rosas
2024-09-02 20:11 ` Maciej S. Szmigiero
2024-09-03 15:01 ` Fabiano Rosas
2024-09-03 20:04 ` Maciej S. Szmigiero
2024-09-10 14:13 ` Peter Xu
2024-08-27 17:54 ` [PATCH v2 11/17] migration/multifd: Add an explicit MultiFDSendData destructor Maciej S. Szmigiero
2024-08-30 13:12 ` Fabiano Rosas
2024-08-27 17:54 ` [PATCH v2 12/17] migration/multifd: Device state transfer support - send side Maciej S. Szmigiero
2024-08-29 0:41 ` Fabiano Rosas
2024-08-29 20:03 ` Maciej S. Szmigiero
2024-08-30 13:02 ` Fabiano Rosas
2024-09-09 19:40 ` Peter Xu
2024-09-19 19:50 ` Maciej S. Szmigiero
2024-09-10 19:48 ` Peter Xu
2024-09-12 18:43 ` Fabiano Rosas
2024-09-13 0:23 ` Peter Xu
2024-09-13 13:21 ` Fabiano Rosas
2024-09-13 14:19 ` Peter Xu
2024-09-13 15:04 ` Fabiano Rosas
2024-09-13 15:22 ` Peter Xu
2024-09-13 18:26 ` Fabiano Rosas
2024-09-17 15:39 ` Peter Xu
2024-09-17 17:07 ` Cédric Le Goater
2024-09-17 17:50 ` Peter Xu
2024-09-19 19:51 ` Maciej S. Szmigiero
2024-09-19 19:49 ` Maciej S. Szmigiero
2024-09-19 21:17 ` Peter Xu
2024-09-20 15:23 ` Maciej S. Szmigiero
2024-09-20 17:09 ` Peter Xu
2024-09-10 16:06 ` Peter Xu
2024-09-19 19:49 ` Maciej S. Szmigiero
2024-09-19 21:18 ` Peter Xu
2024-08-27 17:54 ` [PATCH v2 13/17] migration/multifd: Add migration_has_device_state_support() Maciej S. Szmigiero
2024-08-30 18:55 ` Fabiano Rosas
2024-09-02 20:11 ` Maciej S. Szmigiero
2024-09-03 15:09 ` Fabiano Rosas
2024-08-27 17:54 ` [PATCH v2 14/17] migration: Add save_live_complete_precopy_thread handler Maciej S. Szmigiero
2024-08-27 17:54 ` [PATCH v2 15/17] vfio/migration: Multifd device state transfer support - receive side Maciej S. Szmigiero
2024-09-09 8:55 ` Avihai Horon
2024-09-09 18:06 ` Maciej S. Szmigiero
2024-09-12 8:20 ` Avihai Horon
2024-09-12 8:45 ` Cédric Le Goater
2024-08-27 17:54 ` [PATCH v2 16/17] vfio/migration: Add x-migration-multifd-transfer VFIO property Maciej S. Szmigiero
2024-08-27 17:54 ` [PATCH v2 17/17] vfio/migration: Multifd device state transfer support - send side Maciej S. Szmigiero
2024-09-09 11:41 ` Avihai Horon
2024-09-09 18:07 ` Maciej S. Szmigiero
2024-09-12 8:26 ` Avihai Horon
2024-09-12 8:57 ` Cédric Le Goater
2024-08-28 20:46 ` [PATCH v2 00/17] Multifd 🔀 device state transfer support with VFIO consumer Fabiano Rosas
2024-08-28 21:58 ` Maciej S. Szmigiero
2024-08-29 0:51 ` Fabiano Rosas
2024-08-29 20:02 ` Maciej S. Szmigiero
2024-10-11 13:58 ` Cédric Le Goater
2024-10-15 21:12 ` Maciej S. Szmigiero
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=8ec6abeb-25ee-417e-9f3f-d0f27ec4f370@nvidia.com \
--to=avihaih@nvidia.com \
--cc=alex.williamson@redhat.com \
--cc=armbru@redhat.com \
--cc=berrange@redhat.com \
--cc=clg@redhat.com \
--cc=eblake@redhat.com \
--cc=farosas@suse.de \
--cc=joao.m.martins@oracle.com \
--cc=mail@maciej.szmigiero.name \
--cc=peterx@redhat.com \
--cc=qemu-devel@nongnu.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;
as well as URLs for NNTP newsgroup(s).