Re: TREE_SRCU slows hotplug by factor ~16

2017-04-27 Thread Paul E. McKenney
On Thu, Apr 27, 2017 at 07:44:00AM +0200, Mike Galbraith wrote: > On Wed, 2017-04-26 at 22:32 -0700, Paul E. McKenney wrote: > > On Thu, Apr 27, 2017 at 06:15:56AM +0200, Mike Galbraith wrote: > > > On Wed, 2017-04-26 at 21:11 -0700, Paul E. McKenney wrote: > > > > > > > This is with

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-27 Thread Paul E. McKenney
On Thu, Apr 27, 2017 at 07:44:00AM +0200, Mike Galbraith wrote: > On Wed, 2017-04-26 at 22:32 -0700, Paul E. McKenney wrote: > > On Thu, Apr 27, 2017 at 06:15:56AM +0200, Mike Galbraith wrote: > > > On Wed, 2017-04-26 at 21:11 -0700, Paul E. McKenney wrote: > > > > > > > This is with

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Mike Galbraith
On Wed, 2017-04-26 at 22:32 -0700, Paul E. McKenney wrote: > On Thu, Apr 27, 2017 at 06:15:56AM +0200, Mike Galbraith wrote: > > On Wed, 2017-04-26 at 21:11 -0700, Paul E. McKenney wrote: > > > > > This is with srcutree.exp_holdoff set to 25*1000? > > > > Yup. > > And please see below for the

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Mike Galbraith
On Wed, 2017-04-26 at 22:32 -0700, Paul E. McKenney wrote: > On Thu, Apr 27, 2017 at 06:15:56AM +0200, Mike Galbraith wrote: > > On Wed, 2017-04-26 at 21:11 -0700, Paul E. McKenney wrote: > > > > > This is with srcutree.exp_holdoff set to 25*1000? > > > > Yup. > > And please see below for the

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Paul E. McKenney
On Thu, Apr 27, 2017 at 06:15:56AM +0200, Mike Galbraith wrote: > On Wed, 2017-04-26 at 21:11 -0700, Paul E. McKenney wrote: > > > This is with srcutree.exp_holdoff set to 25*1000? > > Yup. And please see below for the trivial patch, just for confirmation. May I add your Tested-by?

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Paul E. McKenney
On Thu, Apr 27, 2017 at 06:15:56AM +0200, Mike Galbraith wrote: > On Wed, 2017-04-26 at 21:11 -0700, Paul E. McKenney wrote: > > > This is with srcutree.exp_holdoff set to 25*1000? > > Yup. And please see below for the trivial patch, just for confirmation. May I add your Tested-by?

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Mike Galbraith
On Wed, 2017-04-26 at 21:11 -0700, Paul E. McKenney wrote: > This is with srcutree.exp_holdoff set to 25*1000? Yup.

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Mike Galbraith
On Wed, 2017-04-26 at 21:11 -0700, Paul E. McKenney wrote: > This is with srcutree.exp_holdoff set to 25*1000? Yup.

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Paul E. McKenney
On Thu, Apr 27, 2017 at 05:43:59AM +0200, Mike Galbraith wrote: > On Wed, 2017-04-26 at 20:12 +0200, Mike Galbraith wrote: > > On Wed, 2017-04-26 at 10:56 -0700, Paul E. McKenney wrote: > > > > > > OK, I do need to do more work. My current guess is that I should have > > > > set the default for

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Paul E. McKenney
On Thu, Apr 27, 2017 at 05:43:59AM +0200, Mike Galbraith wrote: > On Wed, 2017-04-26 at 20:12 +0200, Mike Galbraith wrote: > > On Wed, 2017-04-26 at 10:56 -0700, Paul E. McKenney wrote: > > > > > > OK, I do need to do more work. My current guess is that I should have > > > > set the default for

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Mike Galbraith
On Wed, 2017-04-26 at 20:12 +0200, Mike Galbraith wrote: > On Wed, 2017-04-26 at 10:56 -0700, Paul E. McKenney wrote: > > > > OK, I do need to do more work. My current guess is that I should have > > > set the default for srcutree.exp_holdoff to 25*1000 instead of 50*1000. > > > But I am sure

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Mike Galbraith
On Wed, 2017-04-26 at 20:12 +0200, Mike Galbraith wrote: > On Wed, 2017-04-26 at 10:56 -0700, Paul E. McKenney wrote: > > > > OK, I do need to do more work. My current guess is that I should have > > > set the default for srcutree.exp_holdoff to 25*1000 instead of 50*1000. > > > But I am sure

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Paul E. McKenney
On Wed, Apr 26, 2017 at 08:12:10PM +0200, Mike Galbraith wrote: > On Wed, 2017-04-26 at 10:56 -0700, Paul E. McKenney wrote: > > > > OK, I do need to do more work. My current guess is that I should have > > > set the default for srcutree.exp_holdoff to 25*1000 instead of 50*1000. > > > But I am

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Paul E. McKenney
On Wed, Apr 26, 2017 at 08:12:10PM +0200, Mike Galbraith wrote: > On Wed, 2017-04-26 at 10:56 -0700, Paul E. McKenney wrote: > > > > OK, I do need to do more work. My current guess is that I should have > > > set the default for srcutree.exp_holdoff to 25*1000 instead of 50*1000. > > > But I am

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Mike Galbraith
On Wed, 2017-04-26 at 10:56 -0700, Paul E. McKenney wrote: > > OK, I do need to do more work. My current guess is that I should have > > set the default for srcutree.exp_holdoff to 25*1000 instead of 50*1000. > > But I am sure that further data will show me the error of my ways. ;-) I can give

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Mike Galbraith
On Wed, 2017-04-26 at 10:56 -0700, Paul E. McKenney wrote: > > OK, I do need to do more work. My current guess is that I should have > > set the default for srcutree.exp_holdoff to 25*1000 instead of 50*1000. > > But I am sure that further data will show me the error of my ways. ;-) I can give

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Paul E. McKenney
On Wed, Apr 26, 2017 at 10:55:44AM -0700, Paul E. McKenney wrote: > On Wed, Apr 26, 2017 at 07:45:57PM +0200, Mike Galbraith wrote: > > On Wed, 2017-04-26 at 17:49 +0200, Mike Galbraith wrote: > > > On Wed, 2017-04-26 at 08:44 -0700, Paul E. McKenney wrote: > > > > > > Should I be comparing this

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Paul E. McKenney
On Wed, Apr 26, 2017 at 10:55:44AM -0700, Paul E. McKenney wrote: > On Wed, Apr 26, 2017 at 07:45:57PM +0200, Mike Galbraith wrote: > > On Wed, 2017-04-26 at 17:49 +0200, Mike Galbraith wrote: > > > On Wed, 2017-04-26 at 08:44 -0700, Paul E. McKenney wrote: > > > > > > Should I be comparing this

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Paul E. McKenney
On Wed, Apr 26, 2017 at 07:45:57PM +0200, Mike Galbraith wrote: > On Wed, 2017-04-26 at 17:49 +0200, Mike Galbraith wrote: > > On Wed, 2017-04-26 at 08:44 -0700, Paul E. McKenney wrote: > > > > Should I be comparing this with the 55s number from your initial email, > > > or to the 39s number? > >

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Paul E. McKenney
On Wed, Apr 26, 2017 at 07:45:57PM +0200, Mike Galbraith wrote: > On Wed, 2017-04-26 at 17:49 +0200, Mike Galbraith wrote: > > On Wed, 2017-04-26 at 08:44 -0700, Paul E. McKenney wrote: > > > > Should I be comparing this with the 55s number from your initial email, > > > or to the 39s number? > >

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Mike Galbraith
On Wed, 2017-04-26 at 17:49 +0200, Mike Galbraith wrote: > On Wed, 2017-04-26 at 08:44 -0700, Paul E. McKenney wrote: > > Should I be comparing this with the 55s number from your initial email, > > or to the 39s number? > > Should be the 39... And 39 it is. -Mike

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Mike Galbraith
On Wed, 2017-04-26 at 17:49 +0200, Mike Galbraith wrote: > On Wed, 2017-04-26 at 08:44 -0700, Paul E. McKenney wrote: > > Should I be comparing this with the 55s number from your initial email, > > or to the 39s number? > > Should be the 39... And 39 it is. -Mike

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Paul E. McKenney
On Wed, Apr 26, 2017 at 05:49:59PM +0200, Mike Galbraith wrote: > On Wed, 2017-04-26 at 08:44 -0700, Paul E. McKenney wrote: > > On Wed, Apr 26, 2017 at 05:26:20PM +0200, Mike Galbraith wrote: > > > On Wed, 2017-04-26 at 07:31 -0700, Paul E. McKenney wrote: > > > > > > > And a sneak preview,

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Paul E. McKenney
On Wed, Apr 26, 2017 at 05:49:59PM +0200, Mike Galbraith wrote: > On Wed, 2017-04-26 at 08:44 -0700, Paul E. McKenney wrote: > > On Wed, Apr 26, 2017 at 05:26:20PM +0200, Mike Galbraith wrote: > > > On Wed, 2017-04-26 at 07:31 -0700, Paul E. McKenney wrote: > > > > > > > And a sneak preview,

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Mike Galbraith
On Wed, 2017-04-26 at 08:44 -0700, Paul E. McKenney wrote: > On Wed, Apr 26, 2017 at 05:26:20PM +0200, Mike Galbraith wrote: > > On Wed, 2017-04-26 at 07:31 -0700, Paul E. McKenney wrote: > > > > > And a sneak preview, semi-tested. If you get a chance to run this, please > > > let me know now it

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Mike Galbraith
On Wed, 2017-04-26 at 08:44 -0700, Paul E. McKenney wrote: > On Wed, Apr 26, 2017 at 05:26:20PM +0200, Mike Galbraith wrote: > > On Wed, 2017-04-26 at 07:31 -0700, Paul E. McKenney wrote: > > > > > And a sneak preview, semi-tested. If you get a chance to run this, please > > > let me know now it

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Paul E. McKenney
On Wed, Apr 26, 2017 at 05:26:20PM +0200, Mike Galbraith wrote: > On Wed, 2017-04-26 at 07:31 -0700, Paul E. McKenney wrote: > > > And a sneak preview, semi-tested. If you get a chance to run this, please > > let me know now it goes. > > That took 'time stress-cpu-hotplug.sh' down to 48s, close

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Paul E. McKenney
On Wed, Apr 26, 2017 at 05:26:20PM +0200, Mike Galbraith wrote: > On Wed, 2017-04-26 at 07:31 -0700, Paul E. McKenney wrote: > > > And a sneak preview, semi-tested. If you get a chance to run this, please > > let me know now it goes. > > That took 'time stress-cpu-hotplug.sh' down to 48s, close

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Mike Galbraith
On Wed, 2017-04-26 at 07:31 -0700, Paul E. McKenney wrote: > And a sneak preview, semi-tested. If you get a chance to run this, please > let me know now it goes. That took 'time stress-cpu-hotplug.sh' down to 48s, close to classic. -Mike

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Mike Galbraith
On Wed, 2017-04-26 at 07:31 -0700, Paul E. McKenney wrote: > And a sneak preview, semi-tested. If you get a chance to run this, please > let me know now it goes. That took 'time stress-cpu-hotplug.sh' down to 48s, close to classic. -Mike

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Paul E. McKenney
On Tue, Apr 25, 2017 at 03:36:42PM -0700, Paul E. McKenney wrote: > On Mon, Apr 24, 2017 at 09:24:42AM -0700, Paul E. McKenney wrote: > > On Mon, Apr 24, 2017 at 09:35:03AM +0200, Mike Galbraith wrote: > > > On Sun, 2017-04-23 at 23:22 -0700, Paul E. McKenney wrote: > > > > > > > Could you please

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-26 Thread Paul E. McKenney
On Tue, Apr 25, 2017 at 03:36:42PM -0700, Paul E. McKenney wrote: > On Mon, Apr 24, 2017 at 09:24:42AM -0700, Paul E. McKenney wrote: > > On Mon, Apr 24, 2017 at 09:35:03AM +0200, Mike Galbraith wrote: > > > On Sun, 2017-04-23 at 23:22 -0700, Paul E. McKenney wrote: > > > > > > > Could you please

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-25 Thread Paul E. McKenney
On Mon, Apr 24, 2017 at 09:24:42AM -0700, Paul E. McKenney wrote: > On Mon, Apr 24, 2017 at 09:35:03AM +0200, Mike Galbraith wrote: > > On Sun, 2017-04-23 at 23:22 -0700, Paul E. McKenney wrote: > > > > > Could you please collect an ftrace (or whatever) showing the timestamp > > > sequence of

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-25 Thread Paul E. McKenney
On Mon, Apr 24, 2017 at 09:24:42AM -0700, Paul E. McKenney wrote: > On Mon, Apr 24, 2017 at 09:35:03AM +0200, Mike Galbraith wrote: > > On Sun, 2017-04-23 at 23:22 -0700, Paul E. McKenney wrote: > > > > > Could you please collect an ftrace (or whatever) showing the timestamp > > > sequence of

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-24 Thread Paul E. McKenney
On Mon, Apr 24, 2017 at 09:35:03AM +0200, Mike Galbraith wrote: > On Sun, 2017-04-23 at 23:22 -0700, Paul E. McKenney wrote: > > > Could you please collect an ftrace (or whatever) showing the timestamp > > sequence of calls to synchronize_srcu(), synchronize_srcu_expedited(), > > and call_srcu()

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-24 Thread Paul E. McKenney
On Mon, Apr 24, 2017 at 09:35:03AM +0200, Mike Galbraith wrote: > On Sun, 2017-04-23 at 23:22 -0700, Paul E. McKenney wrote: > > > Could you please collect an ftrace (or whatever) showing the timestamp > > sequence of calls to synchronize_srcu(), synchronize_srcu_expedited(), > > and call_srcu()

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-24 Thread Mike Galbraith
On Mon, 2017-04-24 at 09:35 +0200, Mike Galbraith wrote: > # tracer: nop > # > # entries-in-buffer/entries-written: 229332/229332 #P:8 > # > # _-=> irqs-off > # / _=> need-resched > #| / _---=>

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-24 Thread Mike Galbraith
On Mon, 2017-04-24 at 09:35 +0200, Mike Galbraith wrote: > # tracer: nop > # > # entries-in-buffer/entries-written: 229332/229332 #P:8 > # > # _-=> irqs-off > # / _=> need-resched > #| / _---=>

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-24 Thread Mike Galbraith
On Sun, 2017-04-23 at 23:22 -0700, Paul E. McKenney wrote: > Could you please collect an ftrace (or whatever) showing the timestamp > sequence of calls to synchronize_srcu(), synchronize_srcu_expedited(), > and call_srcu() during the execution of the stress script? If it is easy > to do, also

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-24 Thread Mike Galbraith
On Sun, 2017-04-23 at 23:22 -0700, Paul E. McKenney wrote: > Could you please collect an ftrace (or whatever) showing the timestamp > sequence of calls to synchronize_srcu(), synchronize_srcu_expedited(), > and call_srcu() during the execution of the stress script? If it is easy > to do, also

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-24 Thread Paul E. McKenney
On Mon, Apr 24, 2017 at 07:24:44AM +0200, Mike Galbraith wrote: > On Sun, 2017-04-23 at 20:32 -0700, Paul E. McKenney wrote: > > On Mon, Apr 24, 2017 at 04:48:09AM +0200, Mike Galbraith wrote: > > > Greetings, > > > > > > Running Steven's hotplug stress script in tip w. CLASSIC_SRCU takes 55s > >

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-24 Thread Paul E. McKenney
On Mon, Apr 24, 2017 at 07:24:44AM +0200, Mike Galbraith wrote: > On Sun, 2017-04-23 at 20:32 -0700, Paul E. McKenney wrote: > > On Mon, Apr 24, 2017 at 04:48:09AM +0200, Mike Galbraith wrote: > > > Greetings, > > > > > > Running Steven's hotplug stress script in tip w. CLASSIC_SRCU takes 55s > >

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-23 Thread Mike Galbraith
On Sun, 2017-04-23 at 20:32 -0700, Paul E. McKenney wrote: > On Mon, Apr 24, 2017 at 04:48:09AM +0200, Mike Galbraith wrote: > > Greetings, > > > > Running Steven's hotplug stress script in tip w. CLASSIC_SRCU takes 55s > > in my i4790 box, whereas TREE_SRCU takes over 16m. (Master with the > >

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-23 Thread Mike Galbraith
On Sun, 2017-04-23 at 20:32 -0700, Paul E. McKenney wrote: > On Mon, Apr 24, 2017 at 04:48:09AM +0200, Mike Galbraith wrote: > > Greetings, > > > > Running Steven's hotplug stress script in tip w. CLASSIC_SRCU takes 55s > > in my i4790 box, whereas TREE_SRCU takes over 16m. (Master with the > >

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-23 Thread Paul E. McKenney
On Mon, Apr 24, 2017 at 04:48:09AM +0200, Mike Galbraith wrote: > Greetings, > > Running Steven's hotplug stress script in tip w. CLASSIC_SRCU takes 55s > in my i4790 box, whereas TREE_SRCU takes over 16m. (Master with the > same config does it in 39s.. but then lockdep isn't enabled in master)

Re: TREE_SRCU slows hotplug by factor ~16

2017-04-23 Thread Paul E. McKenney
On Mon, Apr 24, 2017 at 04:48:09AM +0200, Mike Galbraith wrote: > Greetings, > > Running Steven's hotplug stress script in tip w. CLASSIC_SRCU takes 55s > in my i4790 box, whereas TREE_SRCU takes over 16m. (Master with the > same config does it in 39s.. but then lockdep isn't enabled in master)

TREE_SRCU slows hotplug by factor ~16

2017-04-23 Thread Mike Galbraith
Greetings, Running Steven's hotplug stress script in tip w. CLASSIC_SRCU takes 55s in my i4790 box, whereas TREE_SRCU takes over 16m. (Master with the same config does it in 39s.. but then lockdep isn't enabled in master) -Mike

TREE_SRCU slows hotplug by factor ~16

2017-04-23 Thread Mike Galbraith
Greetings, Running Steven's hotplug stress script in tip w. CLASSIC_SRCU takes 55s in my i4790 box, whereas TREE_SRCU takes over 16m. (Master with the same config does it in 39s.. but then lockdep isn't enabled in master) -Mike