Re: [Question] atomic_fetch_andnot() in nohz_idle_balance()

2018-11-27 Thread Andrea Parri
On Tue, Nov 27, 2018 at 10:01:24AM +0100, Vincent Guittot wrote: > On Mon, 26 Nov 2018 at 21:44, Andrea Parri > wrote: > > > > On Mon, Nov 26, 2018 at 12:37:00PM +0100, Vincent Guittot wrote: > > > On Mon, 26 Nov 2018 at 10:30, Peter Zijlstra wrote: > > > > > > > > On Wed, Nov 21, 2018 at 11:34:5

Re: [Question] atomic_fetch_andnot() in nohz_idle_balance()

2018-11-27 Thread Vincent Guittot
On Mon, 26 Nov 2018 at 21:44, Andrea Parri wrote: > > On Mon, Nov 26, 2018 at 12:37:00PM +0100, Vincent Guittot wrote: > > On Mon, 26 Nov 2018 at 10:30, Peter Zijlstra wrote: > > > > > > On Wed, Nov 21, 2018 at 11:34:53PM +0100, Andrea Parri wrote: > > > > Hi, > > > > > > > > The comment for the

Re: [Question] atomic_fetch_andnot() in nohz_idle_balance()

2018-11-26 Thread Andrea Parri
On Mon, Nov 26, 2018 at 12:37:00PM +0100, Vincent Guittot wrote: > On Mon, 26 Nov 2018 at 10:30, Peter Zijlstra wrote: > > > > On Wed, Nov 21, 2018 at 11:34:53PM +0100, Andrea Parri wrote: > > > Hi, > > > > > > The comment for the atomic_fetch_andnot() in nohz_idle_balance() says: > > > > > > "b

Re: [Question] atomic_fetch_andnot() in nohz_idle_balance()

2018-11-26 Thread Vincent Guittot
On Mon, 26 Nov 2018 at 10:30, Peter Zijlstra wrote: > > On Wed, Nov 21, 2018 at 11:34:53PM +0100, Andrea Parri wrote: > > Hi, > > > > The comment for the atomic_fetch_andnot() in nohz_idle_balance() says: > > > > "barrier, pairs with nohz_balance_enter_idle(), ensures ..." > > > > which, well, d

Re: [Question] atomic_fetch_andnot() in nohz_idle_balance()

2018-11-26 Thread Peter Zijlstra
On Wed, Nov 21, 2018 at 11:34:53PM +0100, Andrea Parri wrote: > Hi, > > The comment for the atomic_fetch_andnot() in nohz_idle_balance() says: > > "barrier, pairs with nohz_balance_enter_idle(), ensures ..." > > which, well, does sound a note of warning... ;-) > > I see that nohz_balance_ente

[Question] atomic_fetch_andnot() in nohz_idle_balance()

2018-11-21 Thread Andrea Parri
Hi, The comment for the atomic_fetch_andnot() in nohz_idle_balance() says: "barrier, pairs with nohz_balance_enter_idle(), ensures ..." which, well, does sound a note of warning... ;-) I see that nohz_balance_enter_idle() has an smp_mb__after_atomic() but the comment for the latter suggests t