if we don't reset the auto-converge counter,
it will continue to run with COLO running,
and eventually the system will hang due to the
CPU throttle reaching DEFAULT_MIGRATE_MAX_CPU_THROTTLE.
Signed-off-by: Lei Rao <lei.rao@intel.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Lukas Straub <lukasstraub2@web.de>
Tested-by: Lukas Straub <lukasstraub2@web.de>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
When flushing memory from ram cache to ram during every checkpoint
on secondary VM, we can copy continuous chunks of memory instead of
4096 bytes per time to reduce the time of VM stop during checkpoint.
Signed-off-by: Lei Rao <lei.rao@intel.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Lukas Straub <lukasstraub2@web.de>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Tested-by: Lukas Straub <lukasstraub2@web.de>
Signed-off-by: Juan Quintela <quintela@redhat.com>
If postcopy has finished, it frees the array.
But vhost-user unregister it at cleanup time.
fixes: c4f7538
Signed-off-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
One might set dump-guest-core=off to make coredumps smaller and
still allow to debug many qemu bugs. Extend this option to the colo
cache.
Signed-off-by: Lukas Straub <lukasstraub2@web.de>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
When we first stated the COLO, the last-mode is as follows:
{ "execute": "query-colo-status" }
{"return": {"last-mode": "primary", "mode": "primary", "reason": "none"}}
The last-mode is unreasonable. After the patch, will be changed to the
following:
{ "execute": "query-colo-status" }
{"return": {"last-mode": "none", "mode": "primary", "reason": "none"}}
Signed-off-by: Lei Rao <lei.rao@intel.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
After the live migration, the related fd will be cleanup in
migration_incoming_state_destroy(). So, the qemu_close()
in colo_process_incoming_thread is not necessary.
Signed-off-by: Lei Rao <lei.rao@intel.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
The GDB statck is as follows:
Program terminated with signal SIGSEGV, Segmentation fault.
0 object_class_dynamic_cast (class=0x55c8f5d2bf50, typename=0x55c8f2f7379e "qio-channel") at qom/object.c:832
if (type->class->interfaces &&
[Current thread is 1 (Thread 0x7f756e97eb00 (LWP 1811577))]
(gdb) bt
0 object_class_dynamic_cast (class=0x55c8f5d2bf50, typename=0x55c8f2f7379e "qio-channel") at qom/object.c:832
1 0x000055c8f2c3dd14 in object_dynamic_cast (obj=0x55c8f543ac00, typename=0x55c8f2f7379e "qio-channel") at qom/object.c:763
2 0x000055c8f2c3ddce in object_dynamic_cast_assert (obj=0x55c8f543ac00, typename=0x55c8f2f7379e "qio-channel",
file=0x55c8f2f73780 "migration/qemu-file-channel.c", line=117, func=0x55c8f2f73800 <__func__.18724> "channel_shutdown") at qom/object.c:786
3 0x000055c8f2bbc6ac in channel_shutdown (opaque=0x55c8f543ac00, rd=true, wr=true, errp=0x0) at migration/qemu-file-channel.c:117
4 0x000055c8f2bba56e in qemu_file_shutdown (f=0x7f7558070f50) at migration/qemu-file.c:67
5 0x000055c8f2ba5373 in migrate_fd_cancel (s=0x55c8f4ccf3f0) at migration/migration.c:1699
6 0x000055c8f2ba1992 in migration_shutdown () at migration/migration.c:187
7 0x000055c8f29a5b77 in main (argc=69, argv=0x7fff3e9e8c08, envp=0x7fff3e9e8e38) at vl.c:4512
The root cause is that we still want to shutdown the from_dst_file in
migrate_fd_cancel() after qemu_close in colo_process_checkpoint().
So, we should set the s->rp_state.from_dst_file = NULL after
qemu_close().
Signed-off-by: Lei Rao <lei.rao@intel.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
This patch fixed as follows:
Thread 1 (Thread 0x7f34ee738d80 (LWP 11212)):
#0 __pthread_clockjoin_ex (threadid=139847152957184, thread_return=0x7f30b1febf30, clockid=<optimized out>, abstime=<optimized out>, block=<optimized out>) at pthread_join_common.c:145
#1 0x0000563401998e36 in qemu_thread_join (thread=0x563402d66610) at util/qemu-thread-posix.c:587
#2 0x00005634017a79fa in process_incoming_migration_co (opaque=0x0) at migration/migration.c:502
#3 0x00005634019b59c9 in coroutine_trampoline (i0=63395504, i1=22068) at util/coroutine-ucontext.c:115
#4 0x00007f34ef860660 in ?? () at ../sysdeps/unix/sysv/linux/x86_64/__start_context.S:91 from /lib/x86_64-linux-gnu/libc.so.6
#5 0x00007f30b21ee730 in ?? ()
#6 0x0000000000000000 in ?? ()
Thread 13 (Thread 0x7f30b3dff700 (LWP 11747)):
#0 __lll_lock_wait (futex=futex@entry=0x56340218ffa0 <qemu_global_mutex>, private=0) at lowlevellock.c:52
#1 0x00007f34efa000a3 in _GI__pthread_mutex_lock (mutex=0x56340218ffa0 <qemu_global_mutex>) at ../nptl/pthread_mutex_lock.c:80
#2 0x0000563401997f99 in qemu_mutex_lock_impl (mutex=0x56340218ffa0 <qemu_global_mutex>, file=0x563401b7a80e "migration/colo.c", line=806) at util/qemu-thread-posix.c:78
#3 0x0000563401407144 in qemu_mutex_lock_iothread_impl (file=0x563401b7a80e "migration/colo.c", line=806) at /home/workspace/colo-qemu/cpus.c:1899
#4 0x00005634017ba8e8 in colo_process_incoming_thread (opaque=0x563402d664c0) at migration/colo.c:806
#5 0x0000563401998b72 in qemu_thread_start (args=0x5634039f8370) at util/qemu-thread-posix.c:519
#6 0x00007f34ef9fd609 in start_thread (arg=<optimized out>) at pthread_create.c:477
#7 0x00007f34ef924293 in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95
The QEMU main thread is holding the lock:
(gdb) p qemu_global_mutex
$1 = {lock = {_data = {lock = 2, __count = 0, __owner = 11212, __nusers = 9, __kind = 0, __spins = 0, __elision = 0, __list = {_prev = 0x0, __next = 0x0}},
__size = "\002\000\000\000\000\000\000\000\314+\000\000\t", '\000' <repeats 26 times>, __align = 2}, file = 0x563401c07e4b "util/main-loop.c", line = 240,
initialized = true}
>From the call trace, we can see it is a deadlock bug. and the QEMU main thread holds the global mutex to wait until the COLO thread ends. and the colo thread
wants to acquire the global mutex, which will cause a deadlock. So, we should release the qemu_global_mutex before waiting colo thread ends.
Signed-off-by: Lei Rao <lei.rao@intel.com>
Reviewed-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
This patch fixes the following:
qemu-system-x86_64: invalid runstate transition: 'shutdown' -> 'running'
Aborted (core dumped)
The gdb bt as following:
0 __GI_raise (sig=sig@entry=6) at ../sysdeps/unix/sysv/linux/raise.c:50
1 0x00007faa3d613859 in __GI_abort () at abort.c:79
2 0x000055c5a21268fd in runstate_set (new_state=RUN_STATE_RUNNING) at vl.c:723
3 0x000055c5a1f8cae4 in vm_prepare_start () at /home/workspace/colo-qemu/cpus.c:2206
4 0x000055c5a1f8cb1b in vm_start () at /home/workspace/colo-qemu/cpus.c:2213
5 0x000055c5a2332bba in migration_iteration_finish (s=0x55c5a4658810) at migration/migration.c:3376
6 0x000055c5a2332f3b in migration_thread (opaque=0x55c5a4658810) at migration/migration.c:3527
7 0x000055c5a251d68a in qemu_thread_start (args=0x55c5a5491a70) at util/qemu-thread-posix.c:519
8 0x00007faa3d7e9609 in start_thread (arg=<optimized out>) at pthread_create.c:477
9 0x00007faa3d710293 in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95
Signed-off-by: Lei Rao <lei.rao@intel.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Lei Rao <lei.rao@intel.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>
If the compression migration fails or is canceled, the query for the value of
compression_counters during the next compression migration is wrong.
Signed-off-by: yuxiating <yuxiating@huawei.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
This avoids to call migrate_get_current() in the caller function
whereas migration_cancel() already needs the pointer to the current
migration state.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
introduce dirty-bitmap mode as the third method of calc-dirty-rate.
implement dirty-bitmap dirtyrate calculation, which can be used
to measuring dirtyrate in the absence of dirty-ring.
introduce "dirty_bitmap:-b" option in hmp calc_dirty_rate to
indicate dirty bitmap method should be used for calculation.
Signed-off-by: Hyman Huang(黄勇) <huangy81@chinatelecom.cn>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
introduce global var total_dirty_pages to stat dirty pages
along with memory_global_dirty_log_sync.
Signed-off-by: Hyman Huang(黄勇) <huangy81@chinatelecom.cn>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
We already don't ever migrate memory that corresponds to discarded ranges
as managed by a RamDiscardManager responsible for the mapped memory region
of the RAMBlock.
virtio-mem uses this mechanism to logically unplug parts of a RAMBlock.
Right now, we still populate zeropages for the whole usable part of the
RAMBlock, which is undesired because:
1. Even populating the shared zeropage will result in memory getting
consumed for page tables.
2. Memory backends without a shared zeropage (like hugetlbfs and shmem)
will populate an actual, fresh page, resulting in an unintended
memory consumption.
Discarded ("logically unplugged") parts have to remain discarded. As
these pages are never part of the migration stream, there is no need to
track modifications via userfaultfd WP reliably for these parts.
Further, any writes to these ranges by the VM are invalid and the
behavior is undefined.
Note that Linux only supports userfaultfd WP on private anonymous memory
for now, which usually results in the shared zeropage getting populated.
The issue will become more relevant once userfaultfd WP supports shmem
and hugetlb.
Acked-by: Peter Xu <peterx@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Let's factor out prefaulting/populating to make further changes easier to
review and add a comment what we are actually expecting to happen. While at
it, use the actual page size of the ramblock, which defaults to
qemu_real_host_page_size for anonymous memory. Further, rename
ram_block_populate_pages() to ram_block_populate_read() as well, to make
it clearer what we are doing.
In the future, we might want to use MADV_POPULATE_READ to speed up
population.
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Let's use QEMU_ALIGN_DOWN() and friends to make the code a bit easier to
read.
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Currently, when someone (i.e., the VM) accesses discarded parts inside a
RAMBlock with a RamDiscardManager managing the corresponding mapped memory
region, postcopy will request migration of the corresponding page from the
source. The source, however, will never answer, because it refuses to
migrate such pages with undefined content ("logically unplugged"): the
pages are never dirty, and get_queued_page() will consequently skip
processing these postcopy requests.
Especially reading discarded ("logically unplugged") ranges is supposed to
work in some setups (for example with current virtio-mem), although it
barely ever happens: still, not placing a page would currently stall the
VM, as it cannot make forward progress.
Let's check the state via the RamDiscardManager (the state e.g.,
of virtio-mem is migrated during precopy) and avoid sending a request
that will never get answered. Place a fresh zero page instead to keep
the VM working. This is the same behavior that would happen
automatically without userfaultfd being active, when accessing virtual
memory regions without populated pages -- "populate on demand".
For now, there are valid cases (as documented in the virtio-mem spec) where
a VM might read discarded memory; in the future, we will disallow that.
Then, we might want to handle that case differently, e.g., warning the
user that the VM seems to be mis-behaving.
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
We don't want to migrate memory that corresponds to discarded ranges as
managed by a RamDiscardManager responsible for the mapped memory region of
the RAMBlock. The content of these pages is essentially stale and
without any guarantees for the VM ("logically unplugged").
Depending on the underlying memory type, even reading memory might populate
memory on the source, resulting in an undesired memory consumption. Of
course, on the destination, even writing a zeropage consumes memory,
which we also want to avoid (similar to free page hinting).
Currently, virtio-mem tries achieving that goal (not migrating "unplugged"
memory that was discarded) by going via qemu_guest_free_page_hint() - but
it's hackish and incomplete.
For example, background snapshots still end up reading all memory, as
they don't do bitmap syncs. Postcopy recovery code will re-add
previously cleared bits to the dirty bitmap and migrate them.
Let's consult the RamDiscardManager after setting up our dirty bitmap
initially and when postcopy recovery code reinitializes it: clear
corresponding bits in the dirty bitmaps (e.g., of the RAMBlock and inside
KVM). It's important to fixup the dirty bitmap *after* our initial bitmap
sync, such that the corresponding dirty bits in KVM are actually cleared.
As colo is incompatible with discarding of RAM and inhibits it, we don't
have to bother.
Note: if a misbehaving guest would use discarded ranges after migration
started we would still migrate that memory: however, then we already
populated that memory on the migration source.
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
An internal version that removes -only-migratable implications. It can be used
for temporary migration blockers like dump-guest-memory.
Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
save_snapshot() checks migration blocker, which looks sane. At the meantime we
should also teach the blocker add helper to fail if during a snapshot, just
like for migrations.
Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
use dirty ring feature to implement dirtyrate calculation.
introduce mode option in qmp calc_dirty_rate to specify what
method should be used when calculating dirtyrate, either
page-sampling or dirty-ring should be passed.
introduce "dirty_ring:-r" option in hmp calc_dirty_rate to
indicate dirty ring method should be used for calculation.
Signed-off-by: Hyman Huang(黄勇) <huangy81@chinatelecom.cn>
Message-Id: <7db445109bd18125ce8ec86816d14f6ab5de6a7d.1624040308.git.huangy81@chinatelecom.cn>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
since main thread may "query dirty rate" at any time, it's better
to move init step into main thead so that synchronization overhead
between "main" and "get_dirtyrate" can be reduced.
Signed-off-by: Hyman Huang(黄勇) <huangy81@chinatelecom.cn>
Message-Id: <109f8077518ed2f13068e3bfb10e625e964780f1.1624040308.git.huangy81@chinatelecom.cn>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
registering get_dirtyrate thread in advance so that both
page-sampling and dirty-ring mode can be covered.
Signed-off-by: Hyman Huang(黄勇) <huangy81@chinatelecom.cn>
Message-Id: <d7727581a8e86d4a42fc3eacf7f310419b9ebf7e.1624040308.git.huangy81@chinatelecom.cn>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
introduce "DirtyRateMeasureMode" to specify what method should be
used to calculate dirty rate, introduce "DirtyRateVcpu" to store
dirty rate for each vcpu.
use union to store stat data of specific mode
Signed-off-by: Hyman Huang(黄勇) <huangy81@chinatelecom.cn>
Message-Id: <661c98c40f40e163aa58334337af8f3ddf41316a.1624040308.git.huangy81@chinatelecom.cn>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
since dirty ring has been introduced, there are two methods
to track dirty pages of vm. it seems that "logging" has
a hint on the method, so rename the global_dirty_log to
global_dirty_tracking would make description more accurate.
dirty rate measurement may start or stop dirty tracking during
calculation. this conflict with migration because stop dirty
tracking make migration leave dirty pages out then that'll be
a problem.
make global_dirty_tracking a bitmask can let both migration and
dirty rate measurement work fine. introduce GLOBAL_DIRTY_MIGRATION
and GLOBAL_DIRTY_DIRTY_RATE to distinguish what current dirty
tracking aims for, migration or dirty rate.
Signed-off-by: Hyman Huang(黄勇) <huangy81@chinatelecom.cn>
Message-Id: <9c9388657cfa0301bd2c1cfa36e7cf6da4aeca19.1624040308.git.huangy81@chinatelecom.cn>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
destination:
../qemu/build/qemu-system-x86_64 -enable-kvm -netdev tap,id=hn0,script=/etc/qemu-ifup,downscript=/etc/qemu-ifdown -device e1000,netdev=hn0,mac=50:52:54:00:11:22 -boot c -drive if=none,file=./Fedora-rdma-server-migration.qcow2,id=drive-virtio-disk0 -device virtio-blk-pci,bus=pci.0,addr=0x4,drive=drive-virtio-disk0,id=virtio-disk0 -m 2048 -smp 2 -device piix3-usb-uhci -device usb-tablet -monitor stdio -vga qxl -spice streaming-video=filter,port=5902,disable-ticketing -incoming rdma:192.168.22.23:8888
qemu-system-x86_64: -spice streaming-video=filter,port=5902,disable-ticketing: warning: short-form boolean option 'disable-ticketing' deprecated
Please use disable-ticketing=on instead
QEMU 6.0.50 monitor - type 'help' for more information
(qemu) trace-event qemu_rdma_block_for_wrid_miss on
(qemu) dest_init RDMA Device opened: kernel name rxe_eth0 uverbs device name uverbs2, infiniband_verbs class device path /sys/class/infiniband_verbs/uverbs2, infiniband class device path /sys/class/infiniband/rxe_eth0, transport: (2) Ethernet
qemu_rdma_block_for_wrid_miss A Wanted wrid CONTROL SEND (2000) but got CONTROL RECV (4000)
source:
../qemu/build/qemu-system-x86_64 -enable-kvm -netdev tap,id=hn0,script=/etc/qemu-ifup,downscript=/etc/qemu-ifdown -device e1000,netdev=hn0,mac=50:52:54:00:11:22 -boot c -drive if=none,file=./Fedora-rdma-server.qcow2,id=drive-virtio-disk0 -device virtio-blk-pci,bus=pci.0,addr=0x4,drive=drive-virtio-disk0,id=virtio-disk0 -m 2048 -smp 2 -device piix3-usb-uhci -device usb-tablet -monitor stdio -vga qxl -spice streaming-video=filter,port=5901,disable-ticketing -S
qemu-system-x86_64: -spice streaming-video=filter,port=5901,disable-ticketing: warning: short-form boolean option 'disable-ticketing' deprecated
Please use disable-ticketing=on instead
QEMU 6.0.50 monitor - type 'help' for more information
(qemu)
(qemu) trace-event qemu_rdma_block_for_wrid_miss on
(qemu) migrate -d rdma:192.168.22.23:8888
source_resolve_host RDMA Device opened: kernel name rxe_eth0 uverbs device name uverbs2, infiniband_verbs class device path /sys/class/infiniband_verbs/uverbs2, infiniband class device path /sys/class/infiniband/rxe_eth0, transport: (2) Ethernet
(qemu) qemu_rdma_block_for_wrid_miss A Wanted wrid WRITE RDMA (1) but got CONTROL RECV (4000)
NOTE: we use soft RoCE as the rdma device.
[root@iaas-rpma images]# rdma link show rxe_eth0/1
link rxe_eth0/1 state ACTIVE physical_state LINK_UP netdev eth0
This migration could not be completed when out of order(OOO) CQ event occurs.
The send queue and receive queue shared a same completion queue, and
qemu_rdma_block_for_wrid() will drop the CQs it's not interested in. But
the dropped CQs by qemu_rdma_block_for_wrid() could be later CQs it wants.
So in this case, qemu_rdma_block_for_wrid() will block forever.
OOO cases will occur in both source side and destination side. And a
forever blocking happens on only SEND and RECV are out of order. OOO between
'WRITE RDMA' and 'RECV' doesn't matter.
below the OOO sequence:
source destination
rdma_write_one() qemu_rdma_registration_handle()
1. S1: post_recv X D1: post_recv Y
2. wait for recv CQ event X
3. D2: post_send X ---------------+
4. wait for send CQ send event X (D2) |
5. recv CQ event X reaches (D2) |
6. +-S2: post_send Y |
7. | wait for send CQ event Y |
8. | recv CQ event Y (S2) (drop it) |
9. +-send CQ event Y reaches (S2) |
10. send CQ event X reaches (D2) -----+
11. wait recv CQ event Y (dropped by (8))
Although a hardware IB works fine in my a hundred of runs, the IB specification
doesn't guaratee the CQ order in such case.
Here we introduce a independent send completion queue to distinguish
ibv_post_send completion queue from the original mixed completion queue.
It helps us to poll the specific CQE we are really interested in.
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
The responder mr registering with ODP will sent RNR NAK back to
the requester in the face of the page fault.
---------
ibv_poll_cq wc.status=13 RNR retry counter exceeded!
ibv_poll_cq wrid=WRITE RDMA!
---------
ibv_advise_mr(3) helps to make pages present before the actual IO is
conducted so that the responder does page fault as little as possible.
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Previously, for the fsdax mem-backend-file, it will register failed with
Operation not supported. In this case, we can try to register it with
On-Demand Paging[1] like what rpma_mr_reg() does on rpma[2].
[1]: https://community.mellanox.com/s/article/understanding-on-demand-paging--odp-x
[2]: http://pmem.io/rpma/manpages/v0.9.0/rpma_mr_reg.3
CC: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
To: <quintela@redhat.com>, <dgilbert@redhat.com>, <qemu-devel@nongnu.org>
CC: Li Zhijian <lizhijian@cn.fujitsu.com>
Date: Sat, 31 Jul 2021 22:05:52 +0800 (5 weeks, 4 days, 17 hours ago)
And change the default to true so that in '-incoming defer' case, user is able
to change multifd capability.
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
To: <quintela@redhat.com>, <dgilbert@redhat.com>, <qemu-devel@nongnu.org>
CC: Li Zhijian <lizhijian@cn.fujitsu.com>
Date: Sat, 31 Jul 2021 22:05:51 +0800 (5 weeks, 4 days, 17 hours ago)
multifd with unsupported protocol will cause a segment fault.
(gdb) bt
#0 0x0000563b4a93faf8 in socket_connect (addr=0x0, errp=0x7f7f02675410) at ../util/qemu-sockets.c:1190
#1 0x0000563b4a797a03 in qio_channel_socket_connect_sync
(ioc=0x563b4d16e8c0, addr=0x0, errp=0x7f7f02675410) at
../io/channel-socket.c:145
#2 0x0000563b4a797abf in qio_channel_socket_connect_worker (task=0x563b4cd86c30, opaque=0x0) at ../io/channel-socket.c:168
#3 0x0000563b4a792631 in qio_task_thread_worker (opaque=0x563b4cd86c30) at ../io/task.c:124
#4 0x0000563b4a91da69 in qemu_thread_start (args=0x563b4c44bb80) at ../util/qemu-thread-posix.c:541
#5 0x00007f7fe9b5b3f9 in ?? ()
#6 0x0000000000000000 in ?? ()
It's enough to check migrate_multifd_is_allowed() in multifd cleanup() and
multifd setup() though there are so many other places using migrate_use_multifd().
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
The parameter is unused, let's drop it.
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
To: qemu-devel <qemu-devel@nongnu.org>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>, Juan Quintela
<quintela@redhat.com>, Peter Xu <peterx@redhat.com>, Leonardo Bras Soares
Passos <lsoaresp@redhat.com>
Date: Wed, 4 Aug 2021 21:26:32 +0200 (5 weeks, 11 hours, 52 minutes ago)
[[PGP Signed Part:No public key for 35AB0B289C5DB258 created at 2021-08-04T21:26:32+0200 using RSA]]
Unconditionally unregister yank function in multifd_load_cleanup().
If it is not unregistered here, it will leak and cause a crash
in yank_unregister_instance(). Now if the ioc is still in use
afterwards, it will only lead to qemu not being able to recover
from a hang related to that ioc.
After checking the code, i am pretty sure that ref is always 1
when arriving here. So all this currently does is remove the
unneeded check.
Signed-off-by: Lukas Straub <lukasstraub2@web.de>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
To: qemu-devel <qemu-devel@nongnu.org>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>, Juan Quintela
<quintela@redhat.com>, Peter Xu <peterx@redhat.com>, Leonardo Bras Soares
Passos <lsoaresp@redhat.com>
Date: Wed, 1 Sep 2021 17:58:57 +0200 (1 week, 15 hours, 17 minutes ago)
[[PGP Signed Part:No public key for 35AB0B289C5DB258 created at 2021-09-01T17:58:57+0200 using RSA]]
When introducing yank functionality in the migration code I forgot
to cover the multifd send side.
Signed-off-by: Lukas Straub <lukasstraub2@web.de>
Tested-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
qemu_savevm_state_complete_postcopy assumes the iothread lock (BQL)
to be held, but instead it isn't.
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Message-Id: <20211005080751.3797161-3-eesposit@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
init_dirty_bitmap_migration assumes the iothread lock (BQL)
to be held, but instead it isn't.
Instead of adding the lock to qemu_savevm_state_setup(),
follow the same pattern as the other ->save_setup callbacks
and lock+unlock inside dirty_bitmap_save_setup().
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-Id: <20211005080751.3797161-2-eesposit@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Commit b673eab4e2 "multifd: Make multifd_load_setup() get an Error
parameter" changed migration_incoming_setup() to take an Error **
argument, and adjusted the callers accordingly. It neglected to
change adjust multifd_load_setup(): it still exit()s on error. Clean
that up.
The error now gets propagated up two call chains: via
migration_fd_process_incoming() to rdma_accept_incoming_migration(),
and via migration_ioc_process_incoming() to
migration_channel_process_incoming(). Both chain ends report the
error with error_report_err(), but otherwise ignore it. Behavioral
change: we no longer exit() on this error.
This is consistent with how we handle other errors here, e.g. from
multifd_recv_new_channel() via migration_ioc_process_incoming() to
migration_channel_process_incoming(). Whether it's consistently right
or consistently wrong I can't tell.
Also clean up the return value from the unusual 0 on success, 1 on
error to the more common true on success, false on error.
Cc: Juan Quintela <quintela@redhat.com>
Cc: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <20210720125408.387910-11-armbru@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta@ionos.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
We did this with scripts/coccinelle/use-error_fatal.cocci before, in
commit 50beeb6809 and 007b06578a. This commit cleans up rarer
variations that don't seem worth matching with Coccinelle.
Cc: Thomas Huth <thuth@redhat.com>
Cc: Cornelia Huck <cornelia.huck@de.ibm.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Juan Quintela <quintela@redhat.com>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Marc-André Lureau <marcandre.lureau@redhat.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <20210720125408.387910-2-armbru@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
When skipping free pages to send, their corresponding dirty bits in the
memory region dirty bitmap need to be cleared. Otherwise the skipped
pages will be sent in the next round after the migration thread syncs
dirty bits from the memory region dirty bitmap.
Cc: David Hildenbrand <david@redhat.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Reported-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Wei Wang <wei.w.wang@intel.com>
Message-Id: <20210722083055.23352-1-wei.w.wang@intel.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
It's efficient, but hackish to call yank unregister calls in channel_close(),
especially it'll be hard to debug when qemu crashed with some yank function
leaked.
Remove that hack, but instead explicitly unregister yank functions at the
places where needed, they are:
(on src)
- migrate_fd_cleanup
- postcopy_pause
(on dst)
- migration_incoming_state_destroy
- postcopy_pause_incoming
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20210722175841.938739-6-peterx@redhat.com>
Reviewed-by: Lukas Straub <lukasstraub2@web.de>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
migration uses QIOChannel typed qemufiles. In follow up patches, we'll need
the capability to identify this fact, so that we can get the backing QIOChannel
from a QEMUFile.
We can also define types for QEMUFile but so far since we only need to be able
to identify QIOChannel, introduce a boolean which is simpler.
Introduce another helper qemu_file_get_ioc() to return the ioc backend of a
qemufile if has_ioc is set.
No functional change.
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20210722175841.938739-5-peterx@redhat.com>
Reviewed-by: Lukas Straub <lukasstraub2@web.de>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
There're plenty of places in migration/* that checks against either socket or
tls typed ioc for yank operations. Provide two helpers to hide all these
information.
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20210722175841.938739-4-peterx@redhat.com>
Reviewed-by: Lukas Straub <lukasstraub2@web.de>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Accessing from_dst_file is potentially racy in current code base like below:
if (s->from_dst_file)
do_something(s->from_dst_file);
Because from_dst_file can be reset right after the check in another
thread (rp_thread). One example is migrate_fd_cancel().
Use the same qemu_file_lock to protect it too, just like to_dst_file.
When it's safe to access without lock, comment it.
There's one special reference in migration_thread() that can be replaced by
the newly introduced rp_thread_created flag.
Reported-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Lukas Straub <lukasstraub2@web.de>
Message-Id: <20210722175841.938739-3-peterx@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
with Peter's fixup
It's possible that the migration thread skip the join() of the rp_thread in
below race and crash on src right at finishing migration:
migration_thread rp_thread
---------------- ---------
migration_completion()
(before rp_thread quits)
from_dst_file=NULL
[thread got scheduled out]
s->rp_state.from_dst_file==NULL
(skip join() of rp_thread)
migrate_fd_cleanup()
qemu_fclose(s->to_dst_file)
yank_unregister_instance()
assert(yank_find_entry()) <------- crash
It could mostly happen with postcopy, but that shouldn't be required, e.g., I
think it could also trigger with MIGRATION_CAPABILITY_RETURN_PATH set.
It's suspected that above race could be the root cause of a recent (but rare)
migration-test break reported by either Dave or PMM:
https://lore.kernel.org/qemu-devel/YPamXAHwan%2FPPXLf@work-vm/
The issue is: from_dst_file is reset in the rp_thread, so if the thread reset
it to NULL fast enough then the migration thread will assume there's no
rp_thread at all.
This could potentially cause more severe issue (e.g. crash) after the yank code.
Fix it by using a boolean to keep "whether we've created rp_thread".
Cc: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20210722175841.938739-2-peterx@redhat.com>
Reviewed-by: Lukas Straub <lukasstraub2@web.de>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Taking the mutex every time for each dirty bit to clear is too slow, especially
we'll take/release even if the dirty bit is cleared. So far it's only used to
sync with special cases with qemu_guest_free_page_hint() against migration
thread, nothing really that serious yet. Let's move the lock to be upper.
There're two callers of migration_bitmap_clear_dirty().
For migration, move it into ram_save_iterate(). With the help of MAX_WAIT
logic, we'll only run ram_save_iterate() for no more than 50ms-ish time, so
taking the lock once there at the entry. It also means any call sites to
qemu_guest_free_page_hint() can be delayed; but it should be very rare, only
during migration, and I don't see a problem with it.
For COLO, move it up to colo_flush_ram_cache(). I think COLO forgot to take
that lock even when calling ramblock_sync_dirty_bitmap(), where another example
is migration_bitmap_sync() who took it right. So let the mutex cover both the
ramblock_sync_dirty_bitmap() and migration_bitmap_clear_dirty() calls.
It's even possible to drop the lock so we use atomic operations upon rb->bmap
and the variable migration_dirty_pages. I didn't do it just to still be safe,
also not predictable whether the frequent atomic ops could bring overhead too
e.g. on huge vms when it happens very often. When that really comes, we can
keep a local counter and periodically call atomic ops. Keep it simple for now.
Cc: Wei Wang <wei.w.wang@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hailiang Zhang <zhang.zhanghailiang@huawei.com>
Cc: Dr. David Alan Gilbert <dgilbert@redhat.com>
Cc: Juan Quintela <quintela@redhat.com>
Cc: Leonardo Bras Soares Passos <lsoaresp@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20210630200805.280905-1-peterx@redhat.com>
Reviewed-by: Wei Wang <wei.w.wang@intel.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
For each "migrate" command, remember to clear the s->error before going on.
For one reason, when there's a new error it'll be still remembered; see
migrate_set_error() who only sets the error if error==NULL. Meanwhile if a
failed migration completes (e.g., postcopy recovered and finished), we
shouldn't dump an error when calling migrate_fd_cleanup() at last.
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20210708190653.252961-4-peterx@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Below process could crash qemu with postcopy recovery:
1. (hmp) migrate -d ..
2. (hmp) migrate_start_postcopy
3. [network down, postcopy paused]
4. (hmp) migrate -r $WRONG_PORT
when try the recover on an invalid $WRONG_PORT, cleanup_bh will be cleared
5. (hmp) migrate -r $RIGHT_PORT
[qemu crash on assert(cleanup_bh)]
The thing is we shouldn't cleanup if it's postcopy resume; the error is set
mostly because the channel is wrong, so we return directly waiting for the user
to retry.
migrate_fd_cleanup() should only be called when migration is cancelled or
completed.
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20210708190653.252961-3-peterx@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
When postcopy pause triggered, we rely on the migration thread to cleanup the
to_dst_file handle, and the return path thread to cleanup the from_dst_file
handle (which is stored in the local variable "rp").
Within the process, from_dst_file cleanup (qemu_fclose) is postponed until it's
setup again due to a postcopy recovery.
It used to work before yank was born; after yank is introduced we rely on the
refcount of IOC to correctly unregister yank function in channel_close(). If
without the early and on-time release of from_dst_file handle the yank function
will be leftover during paused postcopy.
Without this patch, below steps (quoted from Xiaohui) could trigger qemu src
crash:
1.Boot vm on src host
2.Boot vm on dst host
3.Enable postcopy on src&dst host
4.Load stressapptest in vm and set postcopy speed to 50M
5.Start migration from src to dst host, change into postcopy mode when migration is active.
6.When postcopy is active, down the network card(do migration via this network) on dst host.
7.Wait untill postcopy is paused on src&dst host.
8.Before up network card, recover migration on dst host, will get error like following.
9.Ignore the error of step 8, go on recovering migration on src host:
After step 9, qemu on src host will core dump after some seconds:
qemu-kvm: ../util/yank.c:107: yank_unregister_instance: Assertion `QLIST_EMPTY(&entry->yankfns)' failed.
1.sh: line 38: 44662 Aborted (core dumped)
Reported-by: Li Xiaohui <xiaohli@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20210708190653.252961-2-peterx@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
When the migration fails or is canceled we wait the end of the unplug
operation to be able to plug it back. But if the unplug operation
is never finished we stop to wait and QEMU emits a warning to inform
the user.
Based-on: 20210629155007.629086-1-lvivier@redhat.com
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Message-Id: <20210701131458.112036-1-lvivier@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Rao, Lei
Juan Quintela
Lukas Straub
yuxiating
Laurent Vivier
Hyman Huang(黄勇)
David Hildenbrand
Peter Xu
Li Zhijian
Emanuele Giuseppe Esposito
Markus Armbruster
Wei Wang