From: Marcelo Tosatti <mtosatti@redhat.com>
To: Richard Cochran <richardcochran@gmail.com>
Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
Paolo Bonzini <pbonzini@redhat.com>,
Radim Krcmar <rkrcmar@redhat.com>,
Miroslav Lichvar <mlichvar@redhat.com>
Subject: Re: [patch 4/5] PTP: add PTP_SYS_OFFSET emulation via cross timestamps infrastructure
Date: Mon, 23 Jan 2017 21:06:20 -0200 [thread overview]
Message-ID: <20170123230617.GA14752@amt.cnet> (raw)
In-Reply-To: <20170123184415.GA2158@localhost.localdomain>
On Mon, Jan 23, 2017 at 07:44:15PM +0100, Richard Cochran wrote:
> On Mon, Jan 23, 2017 at 11:19:17AM -0200, Marcelo Tosatti wrote:
> > This is needed to generate the PTP_SYS_OFFSET data: a table with read
> > from realtime clock, read from device clock, read from realtime clock,
> > ... :
> >
> > time ->
> > device clock | |sample2| |sample4| |sample6| ...
> > -------------------------------------------------------------
> > realtime clock |sample1| |sample3| |sample5|
>
> Here "realtime clock" is CLOCK_REALTIME on the guest, and "device
> clock" is CLOCK_REALTIME on the host?
Yes.
>
> > Where sampleN is the read of the respective clock.
> >
> > From the following PTP_SYS_OFFSET_PRECISE data:
> >
> > device clock |sample1P,deviceclock| |sample2P,deviceclock|
> > -------------------------------------------------------------
> > realtime clock |sample1P,realtimeclock| |sample2P,realtimeclock|
>
> Are |sample1P,deviceclock| and |sample1P,realtimeclock| taken at the
> same instant in time?
Yes they are.
> If not, then calling that PTP_SYS_OFFSET_PRECISE is misleading.
It is.
> Still don't get what you are doing here...
What KVM provides is reading two clocks (host clock and guest clock)
at the exact same time (because both are based on TSC, so you do RDTSC
once and use that result to calculate two clocks: host and guest realtime
clocks).
So what this interface provides is the following: If a PTP driver
provides ->getcrosstimestamps callback (meaning the driver can read
the value of two clocks at the same instant), and does not provide
->gettime64 callback, then you approximate the first "diagram"
using the second "diagram" (ie: the arithmetic mean of the samples).
Can you please describe what problem exists with this scheme?
Would you prefer to get rid of the "emulation" of ->gettime64
by implementing ->gettime64 directly? Can do that as well.
Thanks.
next prev parent reply other threads:[~2017-01-23 23:09 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-01-20 12:20 [patch 0/5] KVM virtual PTP driver (v3) Marcelo Tosatti
2017-01-20 12:20 ` [patch 1/5] KVM: x86: provide realtime host clock via vsyscall notifiers Marcelo Tosatti
2017-01-20 12:20 ` [patch 2/5] KVM: x86: add KVM_HC_CLOCK_OFFSET hypercall Marcelo Tosatti
2017-01-20 12:20 ` [patch 3/5] kvmclock: export kvmclock clocksource pointer Marcelo Tosatti
2017-01-20 12:55 ` Paolo Bonzini
2017-01-20 12:20 ` [patch 4/5] PTP: add PTP_SYS_OFFSET emulation via cross timestamps infrastructure Marcelo Tosatti
2017-01-20 12:55 ` Paolo Bonzini
2017-01-20 13:07 ` Marcelo Tosatti
2017-01-20 13:36 ` Paolo Bonzini
2017-01-20 13:52 ` Marcelo Tosatti
2017-01-20 14:02 ` Radim Krcmar
2017-01-20 14:23 ` Paolo Bonzini
2017-01-20 14:31 ` Miroslav Lichvar
2017-01-20 18:30 ` Radim Krcmar
2017-01-20 20:25 ` Richard Cochran
2017-01-23 13:19 ` Marcelo Tosatti
2017-01-23 18:44 ` Richard Cochran
2017-01-23 19:44 ` Paolo Bonzini
2017-01-24 5:43 ` Richard Cochran
2017-01-24 11:23 ` Marcelo Tosatti
2017-01-24 11:35 ` Richard Cochran
2017-01-23 23:06 ` Marcelo Tosatti [this message]
2017-01-24 5:32 ` Richard Cochran
2017-01-24 8:15 ` Miroslav Lichvar
2017-01-20 12:20 ` [patch 5/5] PTP: add kvm PTP driver Marcelo Tosatti
2017-01-20 12:58 ` Paolo Bonzini
2017-01-20 13:11 ` Marcelo Tosatti
2017-01-20 14:12 ` Radim Krcmar
2017-01-20 14:20 ` Radim Krcmar
2017-01-20 15:00 ` Marcelo Tosatti
2017-01-20 17:11 ` Paolo Bonzini
2017-01-20 18:08 ` Radim Krcmar
2017-01-20 19:10 ` Marcelo Tosatti
2017-01-21 8:02 ` Paolo Bonzini
2017-01-20 13:10 ` [patch 0/5] KVM virtual PTP driver (v3) Paolo Bonzini
2017-01-20 14:51 [patch 0/5] KVM virtual PTP driver (v4) Marcelo Tosatti
2017-01-20 14:51 ` [patch 4/5] PTP: add PTP_SYS_OFFSET emulation via cross timestamps infrastructure Marcelo Tosatti
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=20170123230617.GA14752@amt.cnet \
--to=mtosatti@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mlichvar@redhat.com \
--cc=pbonzini@redhat.com \
--cc=richardcochran@gmail.com \
--cc=rkrcmar@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;
as well as URLs for NNTP newsgroup(s).