on 13/05/2011 22:14 Bruce Evans said the following:
> It might happen for clock_gettime()
> in separate threads where the threads somehow know and depend on the
> order of the calls.
My simplistic world view is that those threads then should be the place to do
all the fence dances, not the generic
on 13/05/2011 19:57 Jung-uk Kim said the following:
> You guys keep saying some code derived from OpenSolaris exists to
> sync. TSCs. Can you let me see it, pretty please? I don't know what
> else to say. :-(
http://people.freebsd.org/~avg/tsc/
I think I've posted this before.
--
Andriy Gapo
On Fri, 13 May 2011, Jung-uk Kim wrote:
On Friday 13 May 2011 08:47 am, Andriy Gapon wrote:
on 12/05/2011 19:39 Jung-uk Kim said the following:
Actually, I am kinda reluctant to enable smp_tsc by default on
recent CPUs. Although they made all TSCs in sync, it is very
very tricky to make it wo
On Friday 13 May 2011 08:47 am, Andriy Gapon wrote:
> on 12/05/2011 19:39 Jung-uk Kim said the following:
> > On Thursday 12 May 2011 07:23 am, Andriy Gapon wrote:
> >> on 09/05/2011 20:34 Jung-uk Kim said the following:
> >>> Author: jkim
> >>> Date: Mon May 9 17:34:00 2011
> >>> New Revision: 22
on 12/05/2011 19:39 Jung-uk Kim said the following:
> On Thursday 12 May 2011 07:23 am, Andriy Gapon wrote:
>> on 09/05/2011 20:34 Jung-uk Kim said the following:
>>> Author: jkim
>>> Date: Mon May 9 17:34:00 2011
>>> New Revision: 221703
>>> URL: http://svn.freebsd.org/changeset/base/221703
>>
>>
On Thursday 12 May 2011 07:23 am, Andriy Gapon wrote:
> on 09/05/2011 20:34 Jung-uk Kim said the following:
> > Author: jkim
> > Date: Mon May 9 17:34:00 2011
> > New Revision: 221703
> > URL: http://svn.freebsd.org/changeset/base/221703
>
> [snip]
>
> I would to note [again] that I don't like cod
On 5/12/11 7:05 AM, Andriy Gapon wrote:
on 12/05/2011 13:55 John Baldwin said the following:
On 5/12/11 6:55 AM, Stanislav Sedov wrote:
On Thu, 12 May 2011 13:43:58 +0300
Andriy Gapon mentioned:
Theory:
- smp_rv_waiters[2] becomes equal to smp_rv_ncpus
- [at least] one slave CPU is still i
on 12/05/2011 14:40 John Baldwin said the following:
>
> Hmmm, this might be interesting. I think you want to always wait for this
> though
> even if you have a teardown function.
>
I think so too. In fact I have that change in my private tree, but was still
waiting (a few months) for someone
On 5/12/11 6:55 AM, Stanislav Sedov wrote:
On Thu, 12 May 2011 13:43:58 +0300
Andriy Gapon mentioned:
Theory:
- smp_rv_waiters[2] becomes equal to smp_rv_ncpus
- [at least] one slave CPU is still in the last call to cpu_spinwait() in
smp_rendezvous_action()
- master CPU notices that the condi
on 09/05/2011 20:34 Jung-uk Kim said the following:
> Author: jkim
> Date: Mon May 9 17:34:00 2011
> New Revision: 221703
> URL: http://svn.freebsd.org/changeset/base/221703
[snip]
I would to note [again] that I don't like code style of this change.
> Modified: head/sys/x86/x86/tsc.c
> =
on 12/05/2011 13:55 John Baldwin said the following:
> On 5/12/11 6:55 AM, Stanislav Sedov wrote:
>> On Thu, 12 May 2011 13:43:58 +0300
>> Andriy Gapon mentioned:
>>
>>>
>>> Theory:
>>> - smp_rv_waiters[2] becomes equal to smp_rv_ncpus
>>> - [at least] one slave CPU is still in the last call to cp
On Thu, 12 May 2011 13:43:58 +0300
Andriy Gapon mentioned:
>
> Theory:
> - smp_rv_waiters[2] becomes equal to smp_rv_ncpus
> - [at least] one slave CPU is still in the last call to cpu_spinwait() in
> smp_rendezvous_action()
> - master CPU notices that the condition is true, exits smp_rendezvous
on 12/05/2011 12:49 Stanislav Sedov said the following:
> On Mon, 9 May 2011 17:34:00 + (UTC)
> Jung-uk Kim mentioned:
>
>> Author: jkim
>> Date: Mon May 9 17:34:00 2011
>> New Revision: 221703
>> URL: http://svn.freebsd.org/changeset/base/221703
>>
>> Log:
>> Implement boot-time TSC synch
On Mon, 9 May 2011 17:34:00 + (UTC)
Jung-uk Kim mentioned:
> Author: jkim
> Date: Mon May 9 17:34:00 2011
> New Revision: 221703
> URL: http://svn.freebsd.org/changeset/base/221703
>
> Log:
> Implement boot-time TSC synchronization test for SMP. This test is executed
> when the user ha
On Monday 09 May 2011 01:34 pm, Jung-uk Kim wrote:
> Author: jkim
> Date: Mon May 9 17:34:00 2011
> New Revision: 221703
> URL: http://svn.freebsd.org/changeset/base/221703
>
> Log:
> Implement boot-time TSC synchronization test for SMP. This test
> is executed when the user has indicated that
Author: jkim
Date: Mon May 9 17:34:00 2011
New Revision: 221703
URL: http://svn.freebsd.org/changeset/base/221703
Log:
Implement boot-time TSC synchronization test for SMP. This test is executed
when the user has indicated that the system has synchronized TSCs or it has
P-state invariant T
16 matches
Mail list logo
