* Re: [Qemu-devel] about I/O
[not found] <tencent_188DEB20579AFDDF2C219C1E@qq.com>
@ 2016-01-07 5:05 ` Stefan Hajnoczi
0 siblings, 0 replies; only message in thread
From: Stefan Hajnoczi @ 2016-01-07 5:05 UTC (permalink / raw)
To: 浩樊啊; +Cc: qemu-devel
[-- Attachment #1: Type: text/plain, Size: 750 bytes --]
On Tue, Dec 29, 2015 at 03:36:07PM +0800, 浩樊啊 wrote:
> qemu use paio or libaio finish I/O reqeusts,does that mean that when a sync request comes from a vm becomes async request in the host?
Yes, although storage controllers (virtio-blk, SCSI, SATA, and even IDE
in DMA mode) are asynchronous at the hardware interface level. That
means the guest OS submits an I/O request to the device and the guest
CPU continues running until the I/O completion interrupt occurs.
The exceptions are old hardware interfaces like some of the SD Card
controllers or maybe floppy where a single hardware register read/write
actually involves synchronous I/O (the guest cannot execute CPU
instructions while the I/O request is happening).
Stefan
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 473 bytes --]
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2016-01-07 5:05 UTC | newest]
Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
[not found] <tencent_188DEB20579AFDDF2C219C1E@qq.com>
2016-01-07 5:05 ` [Qemu-devel] about I/O Stefan Hajnoczi
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.