[Top][All Lists]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Qemu-devel] [PATCH 4/7] qemu_flush_work for remote vcpu execution

From: Avi Kivity
Subject: Re: [Qemu-devel] [PATCH 4/7] qemu_flush_work for remote vcpu execution
Date: Mon, 30 Nov 2009 14:06:23 +0200
User-agent: Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv: Gecko/20090922 Fedora/3.0-3.9.b4.fc12 Thunderbird/3.0b4

On 11/30/2009 01:44 PM, Glauber Costa wrote:
I really dislike this.  In general vcpu ioctls are used as components of
some work to be done, for example RMW of some state.  In this case it is
meaningless to execute the ioctls remotely, you need to execute the entire
RMW remotely instead.

Why? The "M" part of RMW is executed in shared memory.
Only the R and W parts have any restrictions on where to be executed.

If the guest continues to run during the RMW, you will get inconsistent results.

This may be prevented by qemu_mutex, but I'd rather not rely on it.

Also, I'd like remote operations to be visible.

error compiling committee.c: too many arguments to function

reply via email to

[Prev in Thread] Current Thread [Next in Thread]