This new parameter controls where the zero page checking is running.
1. If this parameter is set to 'legacy', zero page checking is
done in the migration main thread.
2. If this parameter is set to 'none', zero page checking is disabled.
Signed-off-by: Hao Xiang <hao.xiang@bytedance.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Acked-by: Markus Armbruster <armbru@redhat.com>
Link: https://lore.kernel.org/r/20240311180015.3359271-4-hao.xiang@linux.dev
Signed-off-by: Peter Xu <peterx@redhat.com>
The new mapped-ram stream format uses a file transport and puts ram
pages in the migration file at their respective offsets and can be
done in parallel by using the pwritev system call which takes iovecs
and an offset.
Add support to enabling the new format along with multifd to make use
of the threading and page handling already in place.
This requires multifd to stop sending headers and leaving the stream
format to the mapped-ram code. When it comes time to write the data, we
need to call a version of qio_channel_write that can take an offset.
Usage on HMP is:
(qemu) stop
(qemu) migrate_set_capability multifd on
(qemu) migrate_set_capability mapped-ram on
(qemu) migrate_set_parameter max-bandwidth 0
(qemu) migrate_set_parameter multifd-channels 8
(qemu) migrate file:migfile
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Fabiano Rosas <farosas@suse.de>
Link: https://lore.kernel.org/r/20240229153017.2221-21-farosas@suse.de
Signed-off-by: Peter Xu <peterx@redhat.com>
Add a new migration capability 'mapped-ram'.
The core of the feature is to ensure that RAM pages are mapped
directly to offsets in the resulting migration file instead of being
streamed at arbitrary points.
The reasons why we'd want such behavior are:
- The resulting file will have a bounded size, since pages which are
dirtied multiple times will always go to a fixed location in the
file, rather than constantly being added to a sequential
stream. This eliminates cases where a VM with, say, 1G of RAM can
result in a migration file that's 10s of GBs, provided that the
workload constantly redirties memory.
- It paves the way to implement O_DIRECT-enabled save/restore of the
migration stream as the pages are ensured to be written at aligned
offsets.
- It allows the usage of multifd so we can write RAM pages to the
migration file in parallel.
For now, enabling the capability has no effect. The next couple of
patches implement the core functionality.
Acked-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Fabiano Rosas <farosas@suse.de>
Link: https://lore.kernel.org/r/20240229153017.2221-8-farosas@suse.de
Signed-off-by: Peter Xu <peterx@redhat.com>
Some glue code was missing, so that using `qmp_migrate_set_parameters`
to set `multifd-zstd-level` or `multifd-zlib-level` did not work. This
commit adds the glue code to fix that.
Signed-off-by: Bryan Zhang <bryan.zhang@bytedance.com>
Link: https://lore.kernel.org/r/20240301035901.4006936-2-bryan.zhang@bytedance.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Coverity diagnoses a possible out-of-range array index here ...
static GSList *migration_blockers[MIG_MODE__MAX];
fill_source_migration_info() {
GSList *cur_blocker = migration_blockers[migrate_mode()];
... because it does not know that MIG_MODE__MAX will never be returned as
a migration mode. To fix, assert so in migrate_mode().
Fixes: fa3673e497 ("migration: per-mode blockers")
Reported-by: Peter Maydell <peter.maydell@linaro.org>
Suggested-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Fabiano Rosas <farosas@suse.de>
Link: https://lore.kernel.org/r/1699907025-215450-1-git-send-email-steven.sistare@oracle.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Create a mode migration parameter that can be used to select alternate
migration algorithms. The default mode is normal, representing the
current migration algorithm, and does not need to be explicitly set.
No functional change until a new mode is added, except that the mode is
shown by the 'info migrate' command.
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Message-ID: <1698263069-406971-2-git-send-email-steven.sistare@oracle.com>
Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
Acked-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Message-ID: <20231018115513.2163-6-quintela@redhat.com>
It is obsolete. It is better to use driver-mirror with NBD instead.
CC: Kevin Wolf <kwolf@redhat.com>
CC: Eric Blake <eblake@redhat.com>
CC: Stefan Hajnoczi <stefanha@redhat.com>
CC: Hanna Czenczek <hreitz@redhat.com>
Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Message-ID: <20231018115513.2163-5-quintela@redhat.com>
Helper to say if we are doing a migration over rdma.
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Li Zhijian <lizhijian@fujitsu.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Message-ID: <20231011203527.9061-2-quintela@redhat.com>
Migration bandwidth is a very important value to live migration. It's
because it's one of the major factors that we'll make decision on when to
switchover to destination in a precopy process.
This value is currently estimated by QEMU during the whole live migration
process by monitoring how fast we were sending the data. This can be the
most accurate bandwidth if in the ideal world, where we're always feeding
unlimited data to the migration channel, and then it'll be limited to the
bandwidth that is available.
However in reality it may be very different, e.g., over a 10Gbps network we
can see query-migrate showing migration bandwidth of only a few tens of
MB/s just because there are plenty of other things the migration thread
might be doing. For example, the migration thread can be busy scanning
zero pages, or it can be fetching dirty bitmap from other external dirty
sources (like vhost or KVM). It means we may not be pushing data as much
as possible to migration channel, so the bandwidth estimated from "how many
data we sent in the channel" can be dramatically inaccurate sometimes.
With that, the decision to switchover will be affected, by assuming that we
may not be able to switchover at all with such a low bandwidth, but in
reality we can.
The migration may not even converge at all with the downtime specified,
with that wrong estimation of bandwidth, keeping iterations forever with a
low estimation of bandwidth.
The issue is QEMU itself may not be able to avoid those uncertainties on
measuing the real "available migration bandwidth". At least not something
I can think of so far.
One way to fix this is when the user is fully aware of the available
bandwidth, then we can allow the user to help providing an accurate value.
For example, if the user has a dedicated channel of 10Gbps for migration
for this specific VM, the user can specify this bandwidth so QEMU can
always do the calculation based on this fact, trusting the user as long as
specified. It may not be the exact bandwidth when switching over (in which
case qemu will push migration data as fast as possible), but much better
than QEMU trying to wildly guess, especially when very wrong.
A new parameter "avail-switchover-bandwidth" is introduced just for this.
So when the user specified this parameter, instead of trusting the
estimated value from QEMU itself (based on the QEMUFile send speed), it
trusts the user more by using this value to decide when to switchover,
assuming that we'll have such bandwidth available then.
Note that specifying this value will not throttle the bandwidth for
switchover yet, so QEMU will always use the full bandwidth possible for
sending switchover data, assuming that should always be the most important
way to use the network at that time.
This can resolve issues like "unconvergence migration" which is caused by
hilarious low "migration bandwidth" detected for whatever reason.
Reported-by: Zhiyi Guo <zhguo@redhat.com>
Reviewed-by: Joao Martins <joao.m.martins@oracle.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Message-ID: <20231010221922.40638-1-peterx@redhat.com>
QEMU will crash if anyone tries to set tls-authz (which is a type
StrOrNull) with 'null' value. Fix it in the easy way by converting it to
qstring just like the other two tls parameters.
Cc: qemu-stable@nongnu.org # v4.0+
Fixes: d2f1d29b95 ("migration: add support for a "tls-authz" migration parameter")
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Fabiano Rosas <farosas@suse.de>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Message-ID: <20230905162335.235619-2-peterx@redhat.com>
qemu_start_incoming_migration needs to check the number of multifd
channels or postcopy ram channels to configure the backlog parameter (i.e.
the maximum length to which the queue of pending connections for sockfd
may grow) of listen(). So enforce the usage of postcopy-preempt and
multifd as below:
- need to use "-incoming defer" on the destination; and
- set_capability and set_parameter need to be done before migrate_incoming
Otherwise, disable the use of the features and report error messages to
remind users to adjust the commands.
Signed-off-by: Wei Wang <wei.w.wang@intel.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Message-ID: <20230606101910.20456-2-wei.w.wang@intel.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Acked-by: Juan Quintela <quintela@redhat.com>
Introduce migration dirty-limit capability, which can
be turned on before live migration and limit dirty
page rate durty live migration.
Introduce migrate_dirty_limit function to help check
if dirty-limit capability enabled during live migration.
Meanwhile, refactor vcpu_dirty_rate_stat_collect
so that period can be configured instead of hardcoded.
dirty-limit capability is kind of like auto-converge
but using dirty limit instead of traditional cpu-throttle
to throttle guest down. To enable this feature, turn on
the dirty-limit capability before live migration using
migrate-set-capabilities, and set the parameters
"x-vcpu-dirty-limit-period", "vcpu-dirty-limit" suitably
to speed up convergence.
Signed-off-by: Hyman Huang(黄勇) <yong.huang@smartx.com>
Acked-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Message-Id: <168618975839.6361.17407633874747688653-4@git.sr.ht>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Introduce "vcpu-dirty-limit" migration parameter used
to limit dirty page rate during live migration.
"vcpu-dirty-limit" and "x-vcpu-dirty-limit-period" are
two dirty-limit-related migration parameters, which can
be set before and during live migration by qmp
migrate-set-parameters.
This two parameters are used to help implement the dirty
page rate limit algo of migration.
Signed-off-by: Hyman Huang(黄勇) <yong.huang@smartx.com>
Acked-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Message-Id: <168618975839.6361.17407633874747688653-3@git.sr.ht>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Introduce "x-vcpu-dirty-limit-period" migration experimental
parameter, which is in the range of 1 to 1000ms and used to
make dirtyrate calculation period configurable.
Currently with the "x-vcpu-dirty-limit-period" varies, the
total time of live migration changes, test results show the
optimal value of "x-vcpu-dirty-limit-period" ranges from
500ms to 1000 ms. "x-vcpu-dirty-limit-period" should be made
stable once it proves best value can not be determined with
developer's experiments.
Signed-off-by: Hyman Huang(黄勇) <yong.huang@smartx.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Message-Id: <168618975839.6361.17407633874747688653-2@git.sr.ht>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Now that switchover ack logic has been implemented, enable the
capability.
Signed-off-by: Avihai Horon <avihaih@nvidia.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Tested-by: YangHang Liu <yanghliu@redhat.com>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Cédric Le Goater <clg@redhat.com>
Migration downtime estimation is calculated based on bandwidth and
remaining migration data. This assumes that loading of migration data in
the destination takes a negligible amount of time and that downtime
depends only on network speed.
While this may be true for RAM, it's not necessarily true for other
migrated devices. For example, loading the data of a VFIO device in the
destination might require from the device to allocate resources, prepare
internal data structures and so on. These operations can take a
significant amount of time which can increase migration downtime.
This patch adds a new capability "switchover ack" that prevents the
source from stopping the VM and completing the migration until an ACK
is received from the destination that it's OK to do so.
This can be used by migrated devices in various ways to reduce downtime.
For example, a device can send initial precopy metadata to pre-allocate
resources in the destination and use this capability to make sure that
the pre-allocation is completed before the source VM is stopped, so it
will have full effect.
This new capability relies on the return path capability to communicate
from the destination back to the source.
The actual implementation of the capability will be added in the
following patches.
Signed-off-by: Avihai Horon <avihaih@nvidia.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Acked-by: Markus Armbruster <armbru@redhat.com>
Tested-by: YangHang Liu <yanghliu@redhat.com>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Cédric Le Goater <clg@redhat.com>
These way we can make them atomic and use this functions from any
place. I also moved all functions that use rate_limit to
migration-stats.
Functions got renamed, they are not qemu_file anymore.
qemu_file_rate_limit -> migration_rate_exceeded
qemu_file_set_rate_limit -> migration_rate_set
qemu_file_get_rate_limit -> migration_rate_get
qemu_file_reset_rate_limit -> migration_rate_reset
qemu_file_acct_rate_limit -> migration_rate_account.
Reviewed-by: Harsh Prateek Bora <harshpb@linux.ibm.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Message-Id: <20230515195709.63843-6-quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
That the implementation does the check every 100 milliseconds is an
implementation detail that shouldn't be seen on the interfaz.
Notice that all callers of qemu_file_set_rate_limit() used the
division or pass 0, so this change is a NOP.
Signed-off-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Cédric Le Goater <clg@kaod.org>
Message-Id: <20230508130909.65420-4-quintela@redhat.com>
COLO is not listed as running state in migrate_is_running(), so, it's
theoretically possible to disable colo capability in COLO state and the
unexpected error in migration_iteration_finish() is reachable.
Let's disallow that in qmp_migrate_set_capabilities. Than the error
becomes absolutely unreachable: we can get into COLO state only with
enabled capability and can't disable it while we are in COLO state. So
substitute the error by simple assertion.
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Message-Id: <20230428194928.1426370-10-vsementsov@yandex-team.ru>
Signed-off-by: Juan Quintela <quintela@redhat.com>
colo_checkpoint_notify() is mostly used in colo.c. Outside we use it
once when x-checkpoint-delay migration parameter is set. So, let's
simplify the external API to only that function - notify COLO that
parameter was set. This make external API more robust and hides
implementation details from external callers. Also this helps us to
make COLO module optional in further patch (i.e. we are going to add
possibility not build the COLO module).
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Zhang Chen <chen.zhang@intel.com>
Message-Id: <20230428194928.1426370-3-vsementsov@yandex-team.ru>
Signed-off-by: Juan Quintela <quintela@redhat.com>
So make everything that uses it uint64_t no int64_t.
Signed-off-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-Id: <20230504113841.23130-2-quintela@redhat.com>
It is valid that params->has_block_bitmap_mapping is true and
params->block_bitmap_mapping is NULL. So we can't use the trick of
having a single function.
Move to two functions one for each value and the tests are fixed.
Fixes: b804b35b1c
migration: Create migrate_block_bitmap_mapping() function
Reported-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Message-Id: <20230503181036.14890-1-quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
We need to add a new flag to mean to flush at that point.
Notice that we still flush at the end of setup and at the end of
complete stages.
Signed-off-by: Juan Quintela <quintela@redhat.com>
Acked-by: Peter Xu <peterx@redhat.com>
---
Add missing qemu_fflush(), now it passes all tests always.
In the previous version, the check that changes the default value to
false got lost in some rebase. Get it back.
We used to flush all channels at the end of each RAM section
sent. That is not needed, so preparing to only flush after a full
iteration through all the RAM.
Default value of the property is false. But we return "true" in
migrate_multifd_flush_after_each_section() until we implement the code
in following patches.
Signed-off-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Acked-by: Peter Xu <peterx@redhat.com>
---
Rename each-iteration to after-each-section
Rename multifd-sync-after-each-section to
multifd-flush-after-each-section
Move to machine-8.0 (peter)
Notice that we changed the test of ->has_block_bitmap_mapping
for the test that block_bitmap_mapping is not NULL.
Signed-off-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
---
Make it return const (vladimir)
Signed-off-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
---
Moved the type to const char * (vladimir)
Signed-off-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
---
Moved the type to const char * (vladimir)
Signed-off-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
---
Moved the type to const char * (vladimir)
This makes the function more regular with everything else.
Signed-off-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Once there, make it more regular and remove the need for
MigrationState parameter.
Signed-off-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Instead of print it to STDERR, bring the error upwards so that it can be
reported via QMP responses.
E.g.:
{ "execute": "migrate-set-capabilities" ,
"arguments": { "capabilities":
[ { "capability": "postcopy-ram", "state": true } ] } }
{ "error":
{ "class": "GenericError",
"desc": "Postcopy is not supported: Host backend files need to be TMPFS
or HUGETLBFS only" } }
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Once there, rename it to migrate_tls() and make it return bool for
consistency.
Signed-off-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
---
Fix typos found by fabiano
Since the introduction of multifd, it's possible to perform a multifd
migration and finish it using postcopy.
A bug introduced by yank (fixed on cfc3bcf373) was previously preventing
a successful use of this migration scenario, and now thing should be
working on most scenarios.
But since there is not enough testing/support nor any reported users for
this scenario, we should disable this combination before it may cause any
problems for users.
Suggested-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Acked-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
