Re: [RFC PATCH 0/9] Introduce housekeeping subsystem

2017-08-11 Thread Luiz Capitulino
On Fri, 11 Aug 2017 17:01:30 +0200 Frederic Weisbecker wrote: > > Personally, I think NOHZ_FULL_ALL should just die. > > Yeah, although it's still useful for automatic boot testing to detect issues > with nohz_full on. Maybe we could rename/modify it to be a boot-time

Re: [RFC PATCH 0/9] Introduce housekeeping subsystem

2017-08-11 Thread Luiz Capitulino
On Fri, 11 Aug 2017 17:01:30 +0200 Frederic Weisbecker wrote: > > Personally, I think NOHZ_FULL_ALL should just die. > > Yeah, although it's still useful for automatic boot testing to detect issues > with nohz_full on. Maybe we could rename/modify it to be a boot-time testing option for

Re: [RFC PATCH 0/9] Introduce housekeeping subsystem

2017-08-11 Thread Chris Metcalf
On 8/11/2017 11:35 AM, Christopher Lameter wrote: Ah, Chris since you are here: What is happening with the dataplane patches? Work has been crazy and I keep expecting to have a chunk of time to work on it and it doesn't happen. September is looking relatively good though for my having time to

Re: [RFC PATCH 0/9] Introduce housekeeping subsystem

2017-08-11 Thread Chris Metcalf
On 8/11/2017 11:35 AM, Christopher Lameter wrote: Ah, Chris since you are here: What is happening with the dataplane patches? Work has been crazy and I keep expecting to have a chunk of time to work on it and it doesn't happen. September is looking relatively good though for my having time to

Re: [RFC PATCH 0/9] Introduce housekeeping subsystem

2017-08-11 Thread Christopher Lameter
On Fri, 11 Aug 2017, Chris Metcalf wrote: > > > Maybe a CONFIG_HOUSEKEEPING_BOOT_ONLY as a way to restrict housekeeping > > > by default to just the boot cpu. In conjunction with NOHZ_FULL_ALL you > > > would > > > then get the expected semantics. > > A big box with only the boot cpu for

Re: [RFC PATCH 0/9] Introduce housekeeping subsystem

2017-08-11 Thread Christopher Lameter
On Fri, 11 Aug 2017, Chris Metcalf wrote: > > > Maybe a CONFIG_HOUSEKEEPING_BOOT_ONLY as a way to restrict housekeeping > > > by default to just the boot cpu. In conjunction with NOHZ_FULL_ALL you > > > would > > > then get the expected semantics. > > A big box with only the boot cpu for

Re: [RFC PATCH 0/9] Introduce housekeeping subsystem

2017-08-11 Thread Chris Metcalf
On 8/11/2017 2:36 AM, Mike Galbraith wrote: On Thu, 2017-08-10 at 09:57 -0400, Chris Metcalf wrote: On 8/10/2017 8:54 AM, Frederic Weisbecker wrote: But perhaps I should add a new NO_HZ_FULL_BUT_HOUSEKEEPING option. Otherwise we'll change the meaning of NO_HZ_FULL_ALL way too much, to the

Re: [RFC PATCH 0/9] Introduce housekeeping subsystem

2017-08-11 Thread Chris Metcalf
On 8/11/2017 2:36 AM, Mike Galbraith wrote: On Thu, 2017-08-10 at 09:57 -0400, Chris Metcalf wrote: On 8/10/2017 8:54 AM, Frederic Weisbecker wrote: But perhaps I should add a new NO_HZ_FULL_BUT_HOUSEKEEPING option. Otherwise we'll change the meaning of NO_HZ_FULL_ALL way too much, to the

Re: [RFC PATCH 0/9] Introduce housekeeping subsystem

2017-08-11 Thread Frederic Weisbecker
On Fri, Aug 11, 2017 at 08:36:28AM +0200, Mike Galbraith wrote: > On Thu, 2017-08-10 at 09:57 -0400, Chris Metcalf wrote: > > On 8/10/2017 8:54 AM, Frederic Weisbecker wrote: > > > But perhaps I should add a new NO_HZ_FULL_BUT_HOUSEKEEPING option. > > > Otherwise we'll change the meaning of

Re: [RFC PATCH 0/9] Introduce housekeeping subsystem

2017-08-11 Thread Frederic Weisbecker
On Fri, Aug 11, 2017 at 08:36:28AM +0200, Mike Galbraith wrote: > On Thu, 2017-08-10 at 09:57 -0400, Chris Metcalf wrote: > > On 8/10/2017 8:54 AM, Frederic Weisbecker wrote: > > > But perhaps I should add a new NO_HZ_FULL_BUT_HOUSEKEEPING option. > > > Otherwise we'll change the meaning of

Re: [RFC PATCH 0/9] Introduce housekeeping subsystem

2017-08-11 Thread Mike Galbraith
On Thu, 2017-08-10 at 09:57 -0400, Chris Metcalf wrote: > On 8/10/2017 8:54 AM, Frederic Weisbecker wrote: > > But perhaps I should add a new NO_HZ_FULL_BUT_HOUSEKEEPING option. > > Otherwise we'll change the meaning of NO_HZ_FULL_ALL way too much, to the > > point > > that its default behaviour

Re: [RFC PATCH 0/9] Introduce housekeeping subsystem

2017-08-11 Thread Mike Galbraith
On Thu, 2017-08-10 at 09:57 -0400, Chris Metcalf wrote: > On 8/10/2017 8:54 AM, Frederic Weisbecker wrote: > > But perhaps I should add a new NO_HZ_FULL_BUT_HOUSEKEEPING option. > > Otherwise we'll change the meaning of NO_HZ_FULL_ALL way too much, to the > > point > > that its default behaviour

Re: [RFC PATCH 0/9] Introduce housekeeping subsystem

2017-08-10 Thread Chris Metcalf
On 8/10/2017 8:54 AM, Frederic Weisbecker wrote: But perhaps I should add a new NO_HZ_FULL_BUT_HOUSEKEEPING option. Otherwise we'll change the meaning of NO_HZ_FULL_ALL way too much, to the point that its default behaviour will be the exact opposite of the current one: by default every CPU is

Re: [RFC PATCH 0/9] Introduce housekeeping subsystem

2017-08-10 Thread Chris Metcalf
On 8/10/2017 8:54 AM, Frederic Weisbecker wrote: But perhaps I should add a new NO_HZ_FULL_BUT_HOUSEKEEPING option. Otherwise we'll change the meaning of NO_HZ_FULL_ALL way too much, to the point that its default behaviour will be the exact opposite of the current one: by default every CPU is

Re: [RFC PATCH 0/9] Introduce housekeeping subsystem

2017-08-10 Thread Frederic Weisbecker
On Fri, Jul 21, 2017 at 03:48:16PM -0400, Chris Metcalf wrote: > On 7/21/2017 9:21 AM, Frederic Weisbecker wrote: > >I'm leaving for two weeks so this is food for thoughts in the meantime :) > > > >We have a design issue with nohz_full: it drives the isolation features > >through the

Re: [RFC PATCH 0/9] Introduce housekeeping subsystem

2017-08-10 Thread Frederic Weisbecker
On Fri, Jul 21, 2017 at 03:48:16PM -0400, Chris Metcalf wrote: > On 7/21/2017 9:21 AM, Frederic Weisbecker wrote: > >I'm leaving for two weeks so this is food for thoughts in the meantime :) > > > >We have a design issue with nohz_full: it drives the isolation features > >through the

Re: [RFC PATCH 0/9] Introduce housekeeping subsystem

2017-07-21 Thread Chris Metcalf
On 7/21/2017 9:21 AM, Frederic Weisbecker wrote: I'm leaving for two weeks so this is food for thoughts in the meantime :) We have a design issue with nohz_full: it drives the isolation features through the *housekeeping*() functions: kthreads, unpinned timers, watchdog, ... But things should

Re: [RFC PATCH 0/9] Introduce housekeeping subsystem

2017-07-21 Thread Chris Metcalf
On 7/21/2017 9:21 AM, Frederic Weisbecker wrote: I'm leaving for two weeks so this is food for thoughts in the meantime :) We have a design issue with nohz_full: it drives the isolation features through the *housekeeping*() functions: kthreads, unpinned timers, watchdog, ... But things should

[RFC PATCH 0/9] Introduce housekeeping subsystem

2017-07-21 Thread Frederic Weisbecker
I'm leaving for two weeks so this is food for thoughts in the meantime :) We have a design issue with nohz_full: it drives the isolation features through the *housekeeping*() functions: kthreads, unpinned timers, watchdog, ... But things should work the other way around because the tick is just

[RFC PATCH 0/9] Introduce housekeeping subsystem

2017-07-21 Thread Frederic Weisbecker
I'm leaving for two weeks so this is food for thoughts in the meantime :) We have a design issue with nohz_full: it drives the isolation features through the *housekeeping*() functions: kthreads, unpinned timers, watchdog, ... But things should work the other way around because the tick is just