From: Zachary Amsden <zamsden@redhat.com>
To: Glauber Costa <glommer@redhat.com>
Cc: avi@redhat.com, mtosatti@redhat.com, kvm@vger.kernel.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH 05/17] Keep SMP VMs more in sync on unstable TSC
Date: Wed, 16 Jun 2010 11:15:46 -1000 [thread overview]
Message-ID: <4C193F02.1090406@redhat.com> (raw)
In-Reply-To: <20100616133257.GK19104@mothafucka.localdomain>
On 06/16/2010 03:32 AM, Glauber Costa wrote:
> On Mon, Jun 14, 2010 at 09:34:07PM -1000, Zachary Amsden wrote:
>
>> SMP VMs on machines with unstable TSC have their TSC offset adjusted by the
>> local offset delta from last measurement. This does not take into account how
>> long it has been since the measurement, leading to drift. Minimize the drift
>> by accounting for any time difference the kernel has observed.
>>
>> Signed-off-by: Zachary Amsden<zamsden@redhat.com>
>>
> I believe this should be done not only if we have check_tsc_unstable() == true,
> but anytime we adjust the tsc. I mean:
>
> Sure it is expected to be much more relevant in this case, but if we're testing
> generally for tsc_delta< 0 in the adjustment code, it is because we believe
> it can happen, even if tsc is stable (otherwise, we'd better take it off completely).
>
> And in that case, we should account elapsed time too.
>
If we get tsc_delta < 0 test turning true, we've got an unstable tsc to
begin with, so perhaps we should just check that and let the TSC code
deal with detecting an unstable TSC for us.
next prev parent reply other threads:[~2010-06-16 21:34 UTC|newest]
Thread overview: 70+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-06-15 7:34 TSC cleanups, fixes, documentation for KVM Zachary Amsden
2010-06-15 7:34 ` [PATCH 01/17] Eliminate duplicated timer code Zachary Amsden
2010-06-16 13:07 ` Glauber Costa
2010-06-15 7:34 ` [PATCH 02/17] Make cpu_tsc_khz updates use local CPU Zachary Amsden
2010-06-15 8:02 ` Avi Kivity
2010-06-15 7:34 ` [PATCH 03/17] Unify vendor TSC logic Zachary Amsden
2010-06-16 8:10 ` Jason Wang
2010-06-16 13:22 ` Glauber Costa
2010-06-17 8:03 ` Jason Wang
2010-06-16 18:42 ` Zachary Amsden
2010-06-17 8:15 ` Jason Wang
2010-06-17 20:30 ` Zachary Amsden
2010-06-15 7:34 ` [PATCH 04/17] Fix deep C-state TSC desynchronization Zachary Amsden
2010-06-15 8:09 ` Avi Kivity
2010-06-15 8:14 ` Zachary Amsden
2010-06-16 8:10 ` Jason Wang
2010-06-16 18:43 ` Zachary Amsden
2010-06-16 13:24 ` Glauber Costa
2010-06-16 19:20 ` Zachary Amsden
2010-06-15 7:34 ` [PATCH 05/17] Keep SMP VMs more in sync on unstable TSC Zachary Amsden
2010-06-15 8:11 ` Avi Kivity
2010-06-16 8:11 ` Jason Wang
2010-06-16 13:32 ` Glauber Costa
2010-06-16 21:15 ` Zachary Amsden [this message]
2010-06-15 7:34 ` [PATCH 06/17] Rename KVM_REQ_KVMCLOCK_UPDATE Zachary Amsden
2010-06-15 7:34 ` [PATCH 07/17] Perform hardware_enable in CPU_STARTING callback Zachary Amsden
2010-06-15 7:34 ` [PATCH 08/17] Add clock sync request to hardware enable Zachary Amsden
2010-06-15 8:24 ` Avi Kivity
2010-06-15 7:34 ` [PATCH 09/17] Move scale_delta into common header Zachary Amsden
2010-06-15 7:34 ` [PATCH 10/17] Make KVM clock computation work for other scales Zachary Amsden
2010-06-15 7:34 ` [PATCH 11/17] Fix a possible backwards warp of kvmclock Zachary Amsden
2010-06-15 8:40 ` Avi Kivity
2010-06-15 20:37 ` Zachary Amsden
2010-06-15 23:47 ` Marcelo Tosatti
2010-06-16 0:21 ` Zachary Amsden
2010-06-16 0:39 ` Marcelo Tosatti
2010-06-16 8:11 ` Jason Wang
2010-06-16 13:58 ` Glauber Costa
2010-06-16 14:13 ` Avi Kivity
2010-06-16 14:58 ` Glauber Costa
2010-06-16 22:38 ` Zachary Amsden
2010-06-16 19:36 ` Zachary Amsden
2010-06-15 7:34 ` [PATCH 12/17] Add helper function get_kernel_ns Zachary Amsden
2010-06-15 8:41 ` Avi Kivity
2010-06-15 21:03 ` Zachary Amsden
2010-06-15 21:13 ` john stultz
2010-06-16 8:12 ` Jason Wang
2010-06-16 14:03 ` Glauber Costa
2010-06-15 7:34 ` [PATCH 13/17] Add TSC offset tracking Zachary Amsden
2010-06-15 8:44 ` Avi Kivity
2010-06-15 7:34 ` [PATCH 14/17] Fix SVM VMCB reset Zachary Amsden
2010-06-15 7:34 ` [PATCH 15/17] Fix AMD C1 TSC desynchronization Zachary Amsden
2010-06-15 8:47 ` Avi Kivity
2010-06-15 9:21 ` Zachary Amsden
2010-06-15 14:46 ` Roedel, Joerg
2010-06-15 7:34 ` [PATCH 16/17] TSC reset compensation Zachary Amsden
2010-06-15 8:51 ` Avi Kivity
2010-06-15 20:32 ` Zachary Amsden
2010-06-16 0:27 ` Marcelo Tosatti
2010-06-16 0:32 ` Zachary Amsden
2010-06-16 13:52 ` Glauber Costa
2010-06-16 22:36 ` Zachary Amsden
2010-06-15 7:34 ` [PATCH 17/17] Add timekeeping documentation Zachary Amsden
2010-06-15 8:51 ` Avi Kivity
2010-06-15 20:27 ` Randy Dunlap
2010-06-16 23:59 ` Zachary Amsden
2010-06-17 8:55 ` Andi Kleen
2010-06-17 21:14 ` Zachary Amsden
2010-06-18 7:49 ` Andi Kleen
2010-06-18 16:33 ` Zachary Amsden
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4C193F02.1090406@redhat.com \
--to=zamsden@redhat.com \
--cc=avi@redhat.com \
--cc=glommer@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mtosatti@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox