On Sun, Nov 2, 2014 at 6:15 AM, Johannes Weiner wrote:
> Memory cgroups used to have 5 per-page pointers. To allow users to
> disable that amount of overhead during runtime, those pointers were
> allocated in a separate array, with a translation layer between them
> and struct page.
>
> There is
On Tue, Nov 04, 2014 at 04:00:39PM +0100, Michal Hocko wrote:
> On Tue 04-11-14 09:09:37, Johannes Weiner wrote:
> > On Tue, Nov 04, 2014 at 02:41:10PM +0100, Michal Hocko wrote:
> > > On Tue 04-11-14 08:27:01, Johannes Weiner wrote:
> > > > From: Johannes Weiner
> > > > Subject: [patch] mm: move
From: Johannes Weiner
Date: Tue, 4 Nov 2014 09:09:37 -0500
> You either need cgroup memory accounting and limiting or not. There
> is no possible trade-off to be had.
I couldn't have said it better myself, +1.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the bod
On Tue 04-11-14 09:09:37, Johannes Weiner wrote:
> On Tue, Nov 04, 2014 at 02:41:10PM +0100, Michal Hocko wrote:
> > On Tue 04-11-14 08:27:01, Johannes Weiner wrote:
> > > From: Johannes Weiner
> > > Subject: [patch] mm: move page->mem_cgroup bad page handling into generic
> > > code fix
> > >
>
On Tue 04-11-14 08:48:41, Johannes Weiner wrote:
> On Tue, Nov 04, 2014 at 02:06:52PM +0100, Michal Hocko wrote:
> > The code size grows (~1.5k) most probably due to struct page pointer
> > arithmetic (but I haven't checked that) but the data section shrinks
> > for SLAB. So we have additional 1.6k
On Tue, Nov 04, 2014 at 02:41:10PM +0100, Michal Hocko wrote:
> On Tue 04-11-14 08:27:01, Johannes Weiner wrote:
> > From: Johannes Weiner
> > Subject: [patch] mm: move page->mem_cgroup bad page handling into generic
> > code fix
> >
> > Remove obsolete memory saving recommendations from the MEM
On Tue, Nov 04, 2014 at 02:06:52PM +0100, Michal Hocko wrote:
> The code size grows (~1.5k) most probably due to struct page pointer
> arithmetic (but I haven't checked that) but the data section shrinks
> for SLAB. So we have additional 1.6k for SLUB. I guess this is
> acceptable.
>
>text
On Tue 04-11-14 08:27:01, Johannes Weiner wrote:
> From: Johannes Weiner
> Subject: [patch] mm: move page->mem_cgroup bad page handling into generic
> code fix
>
> Remove obsolete memory saving recommendations from the MEMCG Kconfig
> help text.
The memory overhead is still there. So I do not t
On Tue, Nov 04, 2014 at 05:36:39PM +0900, Kamezawa Hiroyuki wrote:
> (2014/11/02 12:15), Johannes Weiner wrote:
> > Memory cgroups used to have 5 per-page pointers. To allow users to
> > disable that amount of overhead during runtime, those pointers were
> > allocated in a separate array, with a t
On Mon 03-11-14 17:36:26, Johannes Weiner wrote:
[...]
> Also, nobody is using that space currently, and I can save memory by
> moving the pointer in there. Should we later add another pointer to
> struct page we are only back to the status quo - with the difference
> that booting with cgroup_disa
(2014/11/02 12:15), Johannes Weiner wrote:
> Memory cgroups used to have 5 per-page pointers. To allow users to
> disable that amount of overhead during runtime, those pointers were
> allocated in a separate array, with a translation layer between them
> and struct page.
>
> There is now only one
On Mon, Nov 03, 2014 at 10:09:42AM -0500, Johannes Weiner wrote:
> Hi Joonsoo,
>
> On Mon, Nov 03, 2014 at 05:02:08PM +0900, Joonsoo Kim wrote:
> > On Sat, Nov 01, 2014 at 11:15:54PM -0400, Johannes Weiner wrote:
> > > Memory cgroups used to have 5 per-page pointers. To allow users to
> > > disab
On Mon, Nov 03, 2014 at 04:58:07PM -0500, David Miller wrote:
> From: "Kirill A. Shutemov"
> Date: Mon, 3 Nov 2014 23:52:06 +0200
>
> > On Mon, Nov 03, 2014 at 04:36:28PM -0500, Johannes Weiner wrote:
> >> On Mon, Nov 03, 2014 at 11:06:07PM +0200, Kirill A. Shutemov wrote:
> >> > On Sat, Nov 01,
From: "Kirill A. Shutemov"
Date: Mon, 3 Nov 2014 23:52:06 +0200
> On Mon, Nov 03, 2014 at 04:36:28PM -0500, Johannes Weiner wrote:
>> On Mon, Nov 03, 2014 at 11:06:07PM +0200, Kirill A. Shutemov wrote:
>> > On Sat, Nov 01, 2014 at 11:15:54PM -0400, Johannes Weiner wrote:
>> > > Memory cgroups use
On Mon, Nov 03, 2014 at 04:36:28PM -0500, Johannes Weiner wrote:
> On Mon, Nov 03, 2014 at 11:06:07PM +0200, Kirill A. Shutemov wrote:
> > On Sat, Nov 01, 2014 at 11:15:54PM -0400, Johannes Weiner wrote:
> > > Memory cgroups used to have 5 per-page pointers. To allow users to
> > > disable that am
On Mon, Nov 03, 2014 at 11:06:07PM +0200, Kirill A. Shutemov wrote:
> On Sat, Nov 01, 2014 at 11:15:54PM -0400, Johannes Weiner wrote:
> > Memory cgroups used to have 5 per-page pointers. To allow users to
> > disable that amount of overhead during runtime, those pointers were
> > allocated in a s
On Sat, Nov 01, 2014 at 11:15:54PM -0400, Johannes Weiner wrote:
> Memory cgroups used to have 5 per-page pointers. To allow users to
> disable that amount of overhead during runtime, those pointers were
> allocated in a separate array, with a translation layer between them
> and struct page.
>
>
On Sat, Nov 01, 2014 at 11:15:54PM -0400, Johannes Weiner wrote:
> Memory cgroups used to have 5 per-page pointers. To allow users to
> disable that amount of overhead during runtime, those pointers were
> allocated in a separate array, with a translation layer between them
> and struct page.
>
>
Documentation/cgroups/memory.txt is outdate even more hopelessly than
before. It deserves a complete rewrite but I guess something like the
following should be added in the meantime to prepare potential readers
about the trap.
---
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroup
On Mon 03-11-14 10:09:42, Johannes Weiner wrote:
> Hi Joonsoo,
>
> On Mon, Nov 03, 2014 at 05:02:08PM +0900, Joonsoo Kim wrote:
> > On Sat, Nov 01, 2014 at 11:15:54PM -0400, Johannes Weiner wrote:
> > > Memory cgroups used to have 5 per-page pointers. To allow users to
> > > disable that amount o
On Sat 01-11-14 23:15:54, Johannes Weiner wrote:
> Memory cgroups used to have 5 per-page pointers. To allow users to
> disable that amount of overhead during runtime, those pointers were
> allocated in a separate array, with a translation layer between them
> and struct page.
>
> There is now on
From: Johannes Weiner
Date: Mon, 3 Nov 2014 10:09:42 -0500
> Please re-introduce this code when your new usecase is ready to be
> upstreamed. There is little reason to burden an unrelated feature
> with a sizable chunk of dead code for a vague future user.
+1
--
To unsubscribe from this list: s
Hi Joonsoo,
On Mon, Nov 03, 2014 at 05:02:08PM +0900, Joonsoo Kim wrote:
> On Sat, Nov 01, 2014 at 11:15:54PM -0400, Johannes Weiner wrote:
> > Memory cgroups used to have 5 per-page pointers. To allow users to
> > disable that amount of overhead during runtime, those pointers were
> > allocated
On Sat, Nov 01, 2014 at 11:15:54PM -0400, Johannes Weiner wrote:
> Memory cgroups used to have 5 per-page pointers. To allow users to
> disable that amount of overhead during runtime, those pointers were
> allocated in a separate array, with a translation layer between them
> and struct page.
Hel
From: Johannes Weiner
Date: Sat, 1 Nov 2014 23:15:54 -0400
> Memory cgroups used to have 5 per-page pointers. To allow users to
> disable that amount of overhead during runtime, those pointers were
> allocated in a separate array, with a translation layer between them
> and struct page.
>
> Th
Memory cgroups used to have 5 per-page pointers. To allow users to
disable that amount of overhead during runtime, those pointers were
allocated in a separate array, with a translation layer between them
and struct page.
There is now only one page pointer remaining: the memcg pointer, that
indica
26 matches
Mail list logo