On Fri, Mar 05, 2021 at 08:42:00AM -0800, Shakeel Butt wrote:
> On Fri, Mar 5, 2021 at 8:25 AM Johannes Weiner wrote:
> >
> [...]
> > I'd also rename cgroup_memory_noswap to cgroup_swapaccount - to match
> > the commandline and (hopefully) make a bit clearer what it effects.
>
> Do we really need
On Fri, Mar 5, 2021 at 8:25 AM Johannes Weiner wrote:
>
> On Fri, Mar 05, 2021 at 12:06:31AM -0800, Hugh Dickins wrote:
> > On Wed, 3 Mar 2021, Shakeel Butt wrote:
> >
> > > Currently the kernel adds the page, allocated for swapin, to the
> > > swapcache before charging the page. This is fine but
On Fri, Mar 5, 2021 at 8:25 AM Johannes Weiner wrote:
>
[...]
> I'd also rename cgroup_memory_noswap to cgroup_swapaccount - to match
> the commandline and (hopefully) make a bit clearer what it effects.
Do we really need to keep supporting "swapaccount=0"? Is swap
page_counter really a performan
On Fri, Mar 05, 2021 at 12:06:31AM -0800, Hugh Dickins wrote:
> On Wed, 3 Mar 2021, Shakeel Butt wrote:
>
> > Currently the kernel adds the page, allocated for swapin, to the
> > swapcache before charging the page. This is fine but now we want a
> > per-memcg swapcache stat which is essential for
On Wed, 3 Mar 2021, Shakeel Butt wrote:
> Currently the kernel adds the page, allocated for swapin, to the
> swapcache before charging the page. This is fine but now we want a
> per-memcg swapcache stat which is essential for folks who wants to
> transparently migrate from cgroup v1's memsw to cgr
On Thu, Mar 4, 2021 at 7:48 AM Johannes Weiner wrote:
>
> On Wed, Mar 03, 2021 at 05:42:29PM -0800, Shakeel Butt wrote:
> > Currently the kernel adds the page, allocated for swapin, to the
> > swapcache before charging the page. This is fine but now we want a
> > per-memcg swapcache stat which is
On Wed, Mar 03, 2021 at 05:42:29PM -0800, Shakeel Butt wrote:
> Currently the kernel adds the page, allocated for swapin, to the
> swapcache before charging the page. This is fine but now we want a
> per-memcg swapcache stat which is essential for folks who wants to
> transparently migrate from cgr
Currently the kernel adds the page, allocated for swapin, to the
swapcache before charging the page. This is fine but now we want a
per-memcg swapcache stat which is essential for folks who wants to
transparently migrate from cgroup v1's memsw to cgroup v2's memory and
swap counters. In addition ch
8 matches
Mail list logo