Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 26 Feb 2009 18:31:38 +0200
From:      Andriy Gapon <avg@icyb.net.ua>
To:        "Paul B. Mahol" <onemda@gmail.com>
Cc:        freebsd-stable@freebsd.org
Subject:   Re: qemu+aio vs C2
Message-ID:  <49A6C3EA.6060605@icyb.net.ua>
In-Reply-To: <3a142e750902260827w722f110eve23a7bdb07cfbe42@mail.gmail.com>
References:  <49A6BFD1.6090601@icyb.net.ua> <3a142e750902260827w722f110eve23a7bdb07cfbe42@mail.gmail.com>

next in thread | previous in thread | raw e-mail | index | archive | help
on 26/02/2009 18:27 Paul B. Mahol said the following:
> On 2/26/09, Andriy Gapon <avg@icyb.net.ua> wrote:
>> I see something unusual and surprising for me: if I kldload aio for qemu's
>> sake
>> and then actually start qemu, I see that share of C2 in cx_usage is
>> constantly
>> dropping and then finally there is "too many short sleeps, backing off to
>> C1".
>>
>> This is on i386 with stable/7 as of r188116.
>>
>> I am out of ideas.
> 
> And qemu guest is?
> 
> Perhaps you should try changing guest kern.hz sysctl setting.
> I dont think related comitt got MFC-ed to STABLE.
> 

For what I've been doing the guest was our boot code and loader. Nothing beyond that.
And, pardon me, how guest software could affect host's hardware in this way?
As i understand only a hardware even of some sort could interrupt C2.

-- 
Andriy Gapon



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?49A6C3EA.6060605>