These are the prototypes and implementation of new hooks that
RDMA takes advantage of to perform dynamic page registration.
An optional hook is also introduced for a custom function
to be able to override the default save_page function.
Also included are the prototypes and accessor methods used by
arch_init.c which invoke funtions inside savevm.c to call out
to the hooks that may or may not have been overridden
inside of QEMUFileOps.
Reviewed-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Chegu Vinod <chegu_vinod@hp.com>
Tested-by: Chegu Vinod <chegu_vinod@hp.com>
Tested-by: Michael R. Hines <mrhines@us.ibm.com>
Signed-off-by: Michael R. Hines <mrhines@us.ibm.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
RDMA uses this to flush the control channel before sending its
own message to handle page registrations.
Reviewed-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Chegu Vinod <chegu_vinod@hp.com>
Tested-by: Chegu Vinod <chegu_vinod@hp.com>
Tested-by: Michael R. Hines <mrhines@us.ibm.com>
Signed-off-by: Michael R. Hines <mrhines@us.ibm.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
QEMUFileRDMA also has read and write modes. This function is now
shared to reduce code duplication.
Reviewed-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Chegu Vinod <chegu_vinod@hp.com>
Tested-by: Chegu Vinod <chegu_vinod@hp.com>
Tested-by: Michael R. Hines <mrhines@us.ibm.com>
Signed-off-by: Michael R. Hines <mrhines@us.ibm.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
The RDMA event channel can be made non-blocking just like a TCP
socket. Exporting this function allows us to yield so that the
QEMU monitor remains available.
Reviewed-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Chegu Vinod <chegu_vinod@hp.com>
Tested-by: Chegu Vinod <chegu_vinod@hp.com>
Tested-by: Michael R. Hines <mrhines@us.ibm.com>
Signed-off-by: Michael R. Hines <mrhines@us.ibm.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
RDMA writes happen asynchronously, and thus the performance accounting
also needs to be able to occur asynchronously. This allows anybody
to call into savevm.c to update both f->pos as well as into arch_init.c
to update the acct_info structure with up-to-date values when
the RDMA transfer actually completes.
Reviewed-by: Juan Quintela <quintela@redhat.com>
Tested-by: Chegu Vinod <chegu_vinod@hp.com>
Tested-by: Michael R. Hines <mrhines@us.ibm.com>
Signed-off-by: Michael R. Hines <mrhines@us.ibm.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
The leak was reported by cppcheck. Fix it by moving the g_malloc0 after
the argument validity check.
Signed-off-by: Stefan Weil <sw@weilnetz.de>
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
bdrv_snapshot_dump() and bdrv_image_info_dump() do not dump to a buffer now,
some internal buffers are still used for format control, which have no
chance to be truncated. As a result, these two functions have no more issue
of truncation, and they can be used by both qemu and qemu-img with correct
parameter specified.
Signed-off-by: Wenchao Xia <xiawenc@linux.vnet.ibm.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
This patch is a pure code move patch, except following modification:
1 get_human_readable_size() is changed to static function.
2 dump_human_image_info() is renamed to bdrv_image_info_dump().
3 in qmp_query_block() and qmp_query_blockstats, use bdrv_next(bs)
instead of direct traverse of global array 'bdrv_states'.
4 collect_snapshots() and collect_image_info() are renamed, unused parameter
*fmt in collect_image_info() is removed.
5 code style fix.
To avoid conflict and tip better, macro in header file is BLOCK_QAPI_H
instead of QAPI_H. Now block.h and snapshot.h are at the same level in
include path, block_int.h and qapi.h will both include them.
Signed-off-by: Wenchao Xia <xiawenc@linux.vnet.ibm.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
All snapshot related code, except bdrv_snapshot_dump() and
bdrv_is_snapshot(), is moved to block/snapshot.c. bdrv_snapshot_dump()
will be moved to another file later. bdrv_is_snapshot() is not related
with internal snapshot. It also fixes small code style errors reported
by check script.
Signed-off-by: Wenchao Xia <xiawenc@linux.vnet.ibm.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
The bs_snapshots global variable points to the BlockDriverState which
will be used to save vmstate. This is really a savevm.c concept but was
moved into block.c:bdrv_snapshots() when it became clear that hotplug
could result in a dangling pointer.
While auditing the block layer's global state I came upon bs_snapshots
and realized that a variable is not necessary here. Simply find the
first BlockDriverState capable of internal snapshots each time this is
needed.
The behavior of bdrv_snapshots() is preserved across hotplug because new
drives are always appended to the bdrv_states list. This means that
calling the new find_vmstate_bs() function is idempotent - it returns
the same BlockDriverState unless it was hot-unplugged.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Wenchao Xia <xiawenc@linux.vnet.ibm.com>
Signed-off-by: Wenchao Xia <xiawenc@linux.vnet.ibm.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Two instances, both spotted by Coverity. In one, two blocks were
swapped. In the other, the check is not needed anymore.
Cc: qemu-stable@nongnu.org
Cc: qemu-trivial@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
This uses system calls directly for Unix file descriptors, so that the
efficient writev_buffer can be used. Pay attention to the possibility
of partial writes in writev.
Reviewed-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Orit Wassermann <owasserm@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
It is enough to implement one of socket_writev_buffer and
socket_put_buffer.
Reviewed-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Orit Wassermann <owasserm@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
* stefanha/block:
rbd: add an asynchronous flush
iotests: Add 'check -ssh' option to test Secure Shell block device.
block: ssh: Use libssh2_sftp_fsync (if supported by libssh2) to flush to disk.
block: Add support for Secure Shell (ssh) block device.
ide: refuse WIN_READ_NATIVE_MAX on empty device
qemu-iotests: filter QEMU_PROG in 051.out
qemu-iotests: Add test for -drive options
qemu-iotests: A few more bdrv_pread/pwrite tests
block: Introduce bdrv_pwritev() for qcow2_save_vmstate
savevm: Implement block_writev_buffer()
block: Introduce bdrv_writev_vmstate
Conflicts:
savevm.c
aliguori: add f->pos parameter to writev_buffer().
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Instead of breaking up RAM state into many small chunks, pass the iovec
to the block layer for better performance.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Check f->iovcnt in add_to_iovec, f->buf_index in qemu_put_buffer/byte.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
The same QEMUFile is never used for both read and write. Simplify
the logic to simply look for presence or absence of the right ops.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
The recent patches to use vectored I/O for RAM migration caused a
regression in savevm speed. To restore previous performance,
add data to the buffer in qemu_put_buffer_async whenever writev_buffer
is not available in the QEMUFile.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
The fcntl(fd, F_SETFL, O_NONBLOCK) flag is not specific to sockets.
Rename to qemu_set_nonblock() just like qemu_set_cloexec().
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com>
This allows us to add a buffer to the iovec to send without copying it
into the static buffer, the buffer will be sent later when qemu_fflush is called.
Signed-off-by: Orit Wasserman <owasserm@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Update qemu_fflush and stdio_close to use writev ops if they are available
Use the buffers stored in the iovec.
Signed-off-by: Orit Wasserman <owasserm@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
All data is still copied into the static buffer.
Adjacent iovecs are coalesced so we send one big buffer
instead of many small buffers.
Signed-off-by: Orit Wasserman <owasserm@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
The current savevm code includes VMSTATE helpers for a number of commonly
used data types, but not for the float64 type used by the internal floating
point emulation code. This patch fixes the deficiency.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Juan Quintela <quintela@redhat.com>
The savevm code already includes a number of *_EQUAL helpers which act as
sanity checks verifying that the configuration of the saved state matches
that of the machine we're loading into to work. Variants already exist
for 8 bit 16 bit and 32 bit integers, but not 64 bit integers. This patch
fills that hole, adding a UINT64 version.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Juan Quintela <quintela@redhat.com>
This avoids adding a duplicate stub for CONFIG_USER_ONLY.
Suggested-by: Eduardo Habkost <ehabkost@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Andreas Färber <afaerber@suse.de>
Rate limiting is now simply a byte counter; client call
qemu_file_rate_limit() manually to determine if they have to exit.
So it is possible and simple to move the functionality to QEMUFile.
This makes the remaining functionality of s->file redundant;
in the next patch we can remove it and write directly to s->migration_file.
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
As a start, use QEMUFile to store the destination and close it.
qemu_get_fd gets a file descriptor that will be used by the write
callbacks.
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Force a flush when qemu_ftell is called. This simplifies the buffer magic
(it also breaks qemu_ftell for input QEMUFiles, but we never use it).
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
This is what exec_close does. Move this to the underlying QEMUFile.
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
This is what fd_close does. Prepare for switching to a QEMUFile.
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
There is no reason for outgoing exec migration to do popen manually
anymore (the reason used to be that we needed the FILE* to make it
non-blocking). Use qemu_popen_cmd.
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Buffering was needed because blocking writes could take a long time
and starve other threads seeking to grab the big QEMU mutex.
Now that all writes (except within _complete callbacks) are done
outside the big QEMU mutex, we do not need buffering at all.
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Only the migration_bitmap_sync() call needs the iothread lock.
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Right now, migration cannot entirely rely on QEMUFile's automatic
drop of I/O after an error, because it does its "real" I/O outside
the put_buffer callback. To fix this until buffering is gone, expose
qemu_file_set_error which we will use in buffered_flush.
Similarly, buffered_flush is not a complete flush because some data may
still reside in the QEMUFile's own buffer. This somewhat complicates the
process of closing the migration thread. Again, when buffering is gone
buffered_flush will disappear and calling qemu_fflush will not be needed;
in the meanwhile, we expose the function for use in migration.c.
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
This is done by almost all callers of qemu_fflush, move the code
directly to qemu_fflush.
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
This is useful, because it lets us keep the cancellation callbacks
inside the big lock while pushing the others out.
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Migration .save_live_iterate() functions return the number of bytes
transferred. The easiest way of doing this is by calling qemu_ftell(f)
at the beginning and end of the function to calculate the difference.
Make qemu_ftell() public so that block-migration will be able to use it.
Also adjust the ftell calculation for writable files where buf_offset
does not include buf_size.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Message-id: 1360661835-28663-2-git-send-email-stefanha@redhat.com
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
The incoming migration is processed in a coroutine and uses an fd read
handler to enter the yielded coroutine when data becomes available.
The read handler was set too broadly, so that spurious coroutine entries
were be triggered if other coroutine users yielded (like the block
layer's bdrv_write() function).
Install the fd read only only when yielding for more data to become
available. This prevents spurious coroutine entries which break code
that assumes only a specific set of places can re-enter the coroutine.
This patch fixes crashes in block/raw-posix.c that are triggered with
"migrate -b" when qiov becomes a dangling pointer due to a spurious
coroutine entry that frees qiov early.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 1360598505-5512-1-git-send-email-stefanha@redhat.com
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
To support multiqueue, the patch introduce a helper qemu_get_queue()
which is used to get the NetClientState of a device. The following patches would
refactor this helper to support multiqueue.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
# By Juan Quintela (7) and Paolo Bonzini (6)
# Via Juan Quintela
* quintela/thread.next:
migration: remove argument to qemu_savevm_state_cancel
migration: Only go to the iterate stage if there is anything to send
migration: unfold rest of migrate_fd_put_ready() into thread
migration: move exit condition to migration thread
migration: Add buffered_flush error handling
migration: move beginning stage to the migration thread
qemu-file: Only set last_error if it is not already set
migration: fix off-by-one in buffered_rate_limit
migration: remove double call to migrate_fd_close
migration: make function static
use XFER_LIMIT_RATIO consistently
Protect migration_bitmap_sync() with the ramlist lock
Unlock ramlist lock also in error case
Signed-off-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
