Re: [RFC][PATCH 06/13] mm/migrate: update migration order during on hotplug events

2021-02-10 Thread Oscar Salvador
On Tue, Feb 09, 2021 at 03:45:55PM -0800, Dave Hansen wrote: > On 2/2/21 3:42 AM, Oscar Salvador wrote: > >> +static int __meminit migrate_on_reclaim_callback(struct notifier_block > >> *self, > >> + unsigned long action, void > >> *arg) > >> +{ > >> + s

Re: [RFC][PATCH 06/13] mm/migrate: update migration order during on hotplug events

2021-02-09 Thread Dave Hansen
On 2/2/21 3:42 AM, Oscar Salvador wrote: >> +static int __meminit migrate_on_reclaim_callback(struct notifier_block >> *self, >> + unsigned long action, void >> *arg) >> +{ >> +switch (action) { >> +case MEM_GOING_OFFLINE: >> +/* >>

Re: [RFC][PATCH 06/13] mm/migrate: update migration order during on hotplug events

2021-02-02 Thread Oscar Salvador
On Mon, Jan 25, 2021 at 04:34:23PM -0800, Dave Hansen wrote: > > From: Dave Hansen > > Reclaim-based migration is attempting to optimize data placement in > memory based on the system topology. If the system changes, so must > the migration ordering. > > The implementation here is pretty simpl

Re: [RFC][PATCH 06/13] mm/migrate: update migration order during on hotplug events

2021-01-29 Thread Yang Shi
On Mon, Jan 25, 2021 at 4:41 PM Dave Hansen wrote: > > > From: Dave Hansen > > Reclaim-based migration is attempting to optimize data placement in > memory based on the system topology. If the system changes, so must > the migration ordering. > > The implementation here is pretty simple and enti

[RFC][PATCH 06/13] mm/migrate: update migration order during on hotplug events

2021-01-25 Thread Dave Hansen
From: Dave Hansen Reclaim-based migration is attempting to optimize data placement in memory based on the system topology. If the system changes, so must the migration ordering. The implementation here is pretty simple and entirely unoptimized. On any memory or CPU hotplug events, assume tha