Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1244994 > unrolled thread

Re: [Ksummit-discuss] [BELATED CORE TOPIC] context tracking / nohz / RCU state

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.

Contents

  Re: [Ksummit-discuss] [BELATED CORE TOPIC] context tracking / nohz /  RCU state Theodore Ts'o <tytso@mit.edu> - 2015-10-12 20:50 +0200
    Re: [Ksummit-discuss] [BELATED CORE TOPIC] context tracking / nohz  / RCU state Thomas Gleixner <tglx@linutronix.de> - 2015-10-12 22:00 +0200
    Re: [Ksummit-discuss] [BELATED CORE TOPIC] context tracking / nohz /  RCU state "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2015-10-12 22:50 +0200
      Re: [Ksummit-discuss] [BELATED CORE TOPIC] context tracking / nohz /  RCU state Frederic Weisbecker <fweisbec@gmail.com> - 2015-10-16 19:10 +0200
        Re: [Ksummit-discuss] [BELATED CORE TOPIC] context tracking / nohz /  RCU state Theodore Ts'o <tytso@mit.edu> - 2015-10-17 21:50 +0200

#1244994 — Re: [Ksummit-discuss] [BELATED CORE TOPIC] context tracking / nohz / RCU state

This thread had fairly intense discussion for two days, but then went dead.

Do folks think this is worth discussing at the kernel summit?

thanks,

						- Ted



On Tue, Aug 11, 2015 at 10:49:36AM -0700, Andy Lutomirski wrote:
> This is a bit late, but here goes anyway.
> 
> Having played with the x86 context tracking hooks for awhile, I think
> it would be nice if core code that needs to be aware of CPU context
> (kernel, user, idle, guest, etc) could come up with single,
> comprehensible, easily validated set of hooks that arch code is
> supposed to call.
> 
> Currently we have:
> 
>  - RCU hooks, which come in a wide variety to notify about IRQs, NMIs, etc.
> 
>  - Context tracking hooks.  Only used by some arches.  Calling these
> calls the RCU hooks for you in most cases.  They have weird
> interactions with interrupts and they're slow.
> 
>  - vtime.  Beats the heck out of me.
> 
>  - Whatever deferred things Christoph keeps reminding us about.
> 
> Honestly, I don't fully understand what all these hooks are supposed
> to do, nor do I care all that much.  From my perspective, the code
> code should be able to do whatever it wants and rely on appropriate
> notifications from arch code.  It would be great if we could come up
> with something straightforward that covers everything.  For example:
> 
> user_mode_to_kernel_mode()
> kernel_mode_to_user_mode()
> kernel_mode_to_guest_mode()
> in_a_periodic_tick()
> starting_nmi()
> ending_nmi()
> may_i_turn_off_ticks_right_now()
> or, better yet:
> i_am_turning_off_ticks_right_now_and_register_your_own_darned_hrtimer_if_thats_a_problem()
> 
> Some arches may need:
> 
> i_am_lame_and_forgot_my_previous_context()
> 
> x86 will soon (4.3 or 4.4, depending on how my syscall cleanup goes)
> no longer need that.
> 
> Paul says that some arches need something that goes straight from IRQ
> to user mode (?) -- sigh.
> 
> etc.
> 
> It might make sense to get enough people who understand what's going
> on behind the scenes together to hash out the requirements.
> 
> --Andy
> _______________________________________________
> Ksummit-discuss mailing list
> Ksummit-discuss@lists.linuxfoundation.org
> https://lists.linuxfoundation.org/mailman/listinfo/ksummit-discuss
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [next] | [standalone]

#1245088 — Re: [Ksummit-discuss] [BELATED CORE TOPIC] context tracking / nohz / RCU state

On Mon, 12 Oct 2015, Theodore Ts'o wrote:

> This thread had fairly intense discussion for two days, but then went dead.
> 
> Do folks think this is worth discussing at the kernel summit?

We can do it the same way as hch proposed for the irq affinity
stuff. Just a short summary of the issue and then find a hallway slot
with the involved folks.

Thanks,

	tglx
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]

#1245123

On Mon, Oct 12, 2015 at 02:40:51PM -0400, Theodore Ts'o wrote:
> This thread had fairly intense discussion for two days, but then went dead.
> 
> Do folks think this is worth discussing at the kernel summit?

I am very interested in discussing this.  Of course, part of that
interest is due to the direct involvement of RCU code.

							Thanx, Paul

> thanks,
> 
> 						- Ted
> 
> 
> 
> On Tue, Aug 11, 2015 at 10:49:36AM -0700, Andy Lutomirski wrote:
> > This is a bit late, but here goes anyway.
> > 
> > Having played with the x86 context tracking hooks for awhile, I think
> > it would be nice if core code that needs to be aware of CPU context
> > (kernel, user, idle, guest, etc) could come up with single,
> > comprehensible, easily validated set of hooks that arch code is
> > supposed to call.
> > 
> > Currently we have:
> > 
> >  - RCU hooks, which come in a wide variety to notify about IRQs, NMIs, etc.
> > 
> >  - Context tracking hooks.  Only used by some arches.  Calling these
> > calls the RCU hooks for you in most cases.  They have weird
> > interactions with interrupts and they're slow.
> > 
> >  - vtime.  Beats the heck out of me.
> > 
> >  - Whatever deferred things Christoph keeps reminding us about.
> > 
> > Honestly, I don't fully understand what all these hooks are supposed
> > to do, nor do I care all that much.  From my perspective, the code
> > code should be able to do whatever it wants and rely on appropriate
> > notifications from arch code.  It would be great if we could come up
> > with something straightforward that covers everything.  For example:
> > 
> > user_mode_to_kernel_mode()
> > kernel_mode_to_user_mode()
> > kernel_mode_to_guest_mode()
> > in_a_periodic_tick()
> > starting_nmi()
> > ending_nmi()
> > may_i_turn_off_ticks_right_now()
> > or, better yet:
> > i_am_turning_off_ticks_right_now_and_register_your_own_darned_hrtimer_if_thats_a_problem()
> > 
> > Some arches may need:
> > 
> > i_am_lame_and_forgot_my_previous_context()
> > 
> > x86 will soon (4.3 or 4.4, depending on how my syscall cleanup goes)
> > no longer need that.
> > 
> > Paul says that some arches need something that goes straight from IRQ
> > to user mode (?) -- sigh.
> > 
> > etc.
> > 
> > It might make sense to get enough people who understand what's going
> > on behind the scenes together to hash out the requirements.
> > 
> > --Andy
> > _______________________________________________
> > Ksummit-discuss mailing list
> > Ksummit-discuss@lists.linuxfoundation.org
> > https://lists.linuxfoundation.org/mailman/listinfo/ksummit-discuss
> 

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]

#1249003

On Mon, Oct 12, 2015 at 01:40:05PM -0700, Paul E. McKenney wrote:
> On Mon, Oct 12, 2015 at 02:40:51PM -0400, Theodore Ts'o wrote:
> > This thread had fairly intense discussion for two days, but then went dead.
> > 
> > Do folks think this is worth discussing at the kernel summit?
> 
> I am very interested in discussing this.  Of course, part of that
> interest is due to the direct involvement of RCU code.

Please don't talk about this without me. Context tracking is deeply involved
and I haven't been invited to kernel summit.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]

#1249438

On Fri, Oct 16, 2015 at 07:02:58PM +0200, Frederic Weisbecker wrote:
> On Mon, Oct 12, 2015 at 01:40:05PM -0700, Paul E. McKenney wrote:
> > On Mon, Oct 12, 2015 at 02:40:51PM -0400, Theodore Ts'o wrote:
> > > This thread had fairly intense discussion for two days, but then went dead.
> > > 
> > > Do folks think this is worth discussing at the kernel summit?
> > 
> > I am very interested in discussing this.  Of course, part of that
> > interest is due to the direct involvement of RCU code.
> 
> Please don't talk about this without me. Context tracking is deeply involved
> and I haven't been invited to kernel summit.

Are you going to be in Seoul for the Korea Linux Forum?  (KLF
attendees are welcome to attend the dual-track technical sessions
day.)

	      	      	 	    	       - Ted
					       
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web