Re: [PATCH v9 8/8] writeback, cgroup: release dying cgwbs by switching attached inodes

[Andrew Morton <akpm@linux-foundation.org>]

On Wed, 9 Jun 2021 00:37:10 +0000 Dennis Zhou <dennis@kernel.org> wrote:

> On Tue, Jun 08, 2021 at 05:23:34PM -0700, Roman Gushchin wrote:
> > On Tue, Jun 08, 2021 at 05:12:37PM -0700, Andrew Morton wrote:
> > > On Tue, 8 Jun 2021 16:02:25 -0700 Roman Gushchin <guro@fb.com> wrote:
> > > 
> > > > Asynchronously try to release dying cgwbs by switching attached inodes
> > > > to the nearest living ancestor wb. It helps to get rid of per-cgroup
> > > > writeback structures themselves and of pinned memory and block cgroups,
> > > > which are significantly larger structures (mostly due to large per-cpu
> > > > statistics data). This prevents memory waste and helps to avoid
> > > > different scalability problems caused by large piles of dying cgroups.
> > > > 
> > > > Reuse the existing mechanism of inode switching used for foreign inode
> > > > detection. To speed things up batch up to 115 inode switching in a
> > > > single operation (the maximum number is selected so that the resulting
> > > > struct inode_switch_wbs_context can fit into 1024 bytes). Because
> > > > every switching consists of two steps divided by an RCU grace period,
> > > > it would be too slow without batching. Please note that the whole
> > > > batch counts as a single operation (when increasing/decreasing
> > > > isw_nr_in_flight). This allows to keep umounting working (flush the
> > > > switching queue), however prevents cleanups from consuming the whole
> > > > switching quota and effectively blocking the frn switching.
> > > > 
> > > > A cgwb cleanup operation can fail due to different reasons (e.g. not
> > > > enough memory, the cgwb has an in-flight/pending io, an attached inode
> > > > in a wrong state, etc). In this case the next scheduled cleanup will
> > > > make a new attempt. An attempt is made each time a new cgwb is offlined
> > > > (in other words a memcg and/or a blkcg is deleted by a user). In the
> > > > future an additional attempt scheduled by a timer can be implemented.
> > > > 
> > > > ...
> > > >
> > > > +/*
> > > > + * Maximum inodes per isw.  A specific value has been chosen to make
> > > > + * struct inode_switch_wbs_context fit into 1024 bytes kmalloc.
> > > > + */
> > > > +#define WB_MAX_INODES_PER_ISW	115
> > > 
> > > Can't we do 1024/sizeof(struct inode_switch_wbs_context)?
> > 
> > It must be something like
> > DIV_ROUND_DOWN_ULL(1024 - sizeof(struct inode_switch_wbs_context), sizeof(struct inode *)) + 1
> 
> Sorry to keep popping in for 1 offs but maybe this instead? I think the
> above would result in > 1024 kzalloc() call.
> 
> DIV_ROUND_DOWN_ULL(max(1024 - sizeof(struct inode_switch_wbs_context), sizeof(struct inode *)),
>                    sizeof(struct inode *))
> 
> might need max_t not sure.

Unclear to me why plain old division won't work, but whatever.  Please
figure it out?  "115" is too sad to live!