motorhead/qemu
1
0
Fork 0
mirror of https://github.com/Motorhead1991/qemu.git synced 2025-08-02 15:23:53 -06:00
Code Issues Projects Releases Packages Wiki Activity Actions

block: Use a single global AioWait

Browse source 
When draining a block node, we recurse to its parent and for subtree
drains also to its children. A single AIO_WAIT_WHILE() is then used to
wait for bdrv_drain_poll() to become true, which depends on all of the
nodes we recursed to. However, if the respective child or parent becomes
quiescent and calls bdrv_wakeup(), only the AioWait of the child/parent
is checked, while AIO_WAIT_WHILE() depends on the AioWait of the
original node.

Fix this by using a single AioWait for all callers of AIO_WAIT_WHILE().

This may mean that the draining thread gets a few more unnecessary
wakeups because an unrelated operation got completed, but we already
wake it up when something _could_ have changed rather than only if it
has certainly changed.

Apart from that, drain is a slow path anyway. In theory it would be
possible to use wakeups more selectively and still correctly, but the
gains are likely not worth the additional complexity. In fact, this
patch is a nice simplification for some places in the code.

Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
This commit is contained in:
Kevin Wolf 2018-09-18 17:09:16 +02:00
parent 5599c162c3
commit cfe29d8294
10 changed files with 26 additions and 65 deletions
Download patch file Download diff file Expand all files Collapse all files

11
block/block-backend.c
View file

@ -88,7 +88,6 @@ struct BlockBackend {
* Accessed with atomic ops.
*/
unsigned int in_flight;
AioWait wait;
};
typedef struct BlockBackendAIOCB {
@ -1298,7 +1297,7 @@ static void blk_inc_in_flight(BlockBackend *blk)
static void blk_dec_in_flight(BlockBackend *blk)
{
atomic_dec(&blk->in_flight);
aio_wait_kick(&blk->wait);
aio_wait_kick();
}
static void error_callback_bh(void *opaque)
@ -1599,9 +1598,8 @@ void blk_drain(BlockBackend *blk)
}
/* We may have -ENOMEDIUM completions in flight */
AIO_WAIT_WHILE(&blk->wait,
blk_get_aio_context(blk),
atomic_mb_read(&blk->in_flight) > 0);
AIO_WAIT_WHILE(blk_get_aio_context(blk),
atomic_mb_read(&blk->in_flight) > 0);
if (bs) {
bdrv_drained_end(bs);
@ -1620,8 +1618,7 @@ void blk_drain_all(void)
aio_context_acquire(ctx);
/* We may have -ENOMEDIUM completions in flight */
AIO_WAIT_WHILE(&blk->wait, ctx,
atomic_mb_read(&blk->in_flight) > 0);
AIO_WAIT_WHILE(ctx, atomic_mb_read(&blk->in_flight) > 0);
aio_context_release(ctx);
}