Re: [RFC PATCH 2/2] PM: hibernate: introduce opportunistic memory reclaim

2020-09-21 Thread Andrea Righi
On Mon, Sep 21, 2020 at 05:36:30PM +0200, Rafael J. Wysocki wrote: ... > > > 3. It is not clear how much mm_reclaim/release is going to help. If > > > the preloading of the swapped-out pages uses some kind of LIFO order, > > > and can batch multiple pages, then it might help. Otherwise demand >

Re: [RFC PATCH 2/2] PM: hibernate: introduce opportunistic memory reclaim

2020-09-21 Thread Rafael J. Wysocki
Hi Andrea, On Tue, Jun 9, 2020 at 8:19 AM Andrea Righi wrote: > > On Mon, Jun 08, 2020 at 03:23:22PM -0700, Luigi Semenzato wrote: > > Hi Andrea, > > > > 1. This mechanism is quite general. It is possible that, although > > hibernation may be an important use, there will be other uses for it. >

Re: [RFC PATCH 2/2] PM: hibernate: introduce opportunistic memory reclaim

2020-06-09 Thread Andrea Righi
On Mon, Jun 08, 2020 at 03:23:22PM -0700, Luigi Semenzato wrote: > Hi Andrea, > > 1. This mechanism is quite general. It is possible that, although > hibernation may be an important use, there will be other uses for it. > I suggest leaving the hibernation example and performance analysis, > but

Re: [RFC PATCH 2/2] PM: hibernate: introduce opportunistic memory reclaim

2020-06-08 Thread Luigi Semenzato
Hi Andrea, 1. This mechanism is quite general. It is possible that, although hibernation may be an important use, there will be other uses for it. I suggest leaving the hibernation example and performance analysis, but not mentioning PM or hibernation in the patch subject. 2. It may be useful

[RFC PATCH 2/2] PM: hibernate: introduce opportunistic memory reclaim

2020-06-01 Thread Andrea Righi
== Overview == When a system is going to be hibernated, the kernel needs to allocate and dump the content of the entire memory to the resume device (swap) by creating a "hibernation image". To make sure this image fits in the available free memory, the kernel can induce an artificial memory