Re: [Qemu-devel] [PATCH 3/3] block: Let bdrv_drain_all() to call aio_poll() for each AioContext

Stefan Hajnoczi writes: > On Wed, Jun 10, 2015 at 02:38:17PM +0300, Alexander Yarygin wrote: >> After the commit 9b536adc ("block: acquire AioContext in >> bdrv_drain_all()") the aio_poll() function got called for every >> BlockDriverState, in assumption that every device may have its own >> AioC

Re: [Qemu-devel] [PATCH 3/3] block: Let bdrv_drain_all() to call aio_poll() for each AioContext

On Wed, Jun 10, 2015 at 02:38:17PM +0300, Alexander Yarygin wrote: > After the commit 9b536adc ("block: acquire AioContext in > bdrv_drain_all()") the aio_poll() function got called for every > BlockDriverState, in assumption that every device may have its own > AioContext. If we have thousands of

Re: [Qemu-devel] [PATCH 3/3] block: Let bdrv_drain_all() to call aio_poll() for each AioContext

Am 10.06.2015 um 13:38 schrieb Alexander Yarygin: > After the commit 9b536adc ("block: acquire AioContext in > bdrv_drain_all()") the aio_poll() function got called for every > BlockDriverState, in assumption that every device may have its own > AioContext. If we have thousands of disks attached, t

[Qemu-devel] [PATCH 3/3] block: Let bdrv_drain_all() to call aio_poll() for each AioContext

After the commit 9b536adc ("block: acquire AioContext in bdrv_drain_all()") the aio_poll() function got called for every BlockDriverState, in assumption that every device may have its own AioContext. If we have thousands of disks attached, there are a lot of BlockDriverStates but only a few AioCont