Re: [PATCH] fs/super: skip non-memcg-aware nr_cached_objects in memcg slab shrink
Usama Arif <[email protected]>
| Newsgroups | org.kernel.vger.linux-btrfs,org.kernel.vger.linux-fsdevel,org.kernel.vger.linux-kernel,org.kernel.vger.linux-xfs,org.kvack.linux-mm |
|---|---|
| Message-ID | <[email protected]> |
On Tue, 14 Jul 2026 10:09:26 +0800 Qi Zheng <[email protected]> wrote: > Hi Usama, > > On 7/13/26 11:34 PM, Usama Arif wrote: > > > > > > On 13/07/2026 14:12, Qi Zheng wrote: > >> Hi Usama, > >> > >> On 6/9/26 8:30 PM, Usama Arif wrote: > >>> The super_block shrinker is registered with SHRINKER_MEMCG_AWARE because its > >>> dentry and inode LRUs are memcg-aware (via list_lru). But the optional > >>> ->nr_cached_objects() hooks that the shrinker also drives are not memcg-aware: > >>> btrfs extent maps and xfs inode reclaim operate on filesystem-global > >>> state, and shmem's unused-huge shrinker walks a per-superblock shrinklist. > >>> None of them filter by sc->memcg. > >> > >> This makes sense for now, but how should we handle this if these > >> shrinkers are made memcg-aware in the future? > >> > >> I've recently been working on making the shmem huge shrinker > >> memcg-aware, but noticed my changes broke after rebasing onto the latest > >> tree, which led me to this patch. > >> > >> As for the shmem huge shrinker, I can work around this limitation by > >> making it a separate shrinker. But this feels more like an overall > >> design decision, effectively meaning that all nr_cached_objects are > >> precluded from being memcg-aware. > >> > >> Thanks, > >> Qi > >> > > > > > > Hi Qi, > > > > Thanks for raising this. I think the alternative is what I mentioned in > > https://lore.kernel.org/all/[email protected]/ > > move this down to the fs own callbacks instead of here. Would that > > be better? > > Yes, I think this is a better approach. > > Later on, shrinkers that are converted to be memcg-aware can lift this > restriction themselves. > > Thanks, > Qi Thanks Qi, I have sent a patch to push it down to filesystems in [1]. No functional change inteneded in there. You would have to rebase your patch on top of that one and remove my code in shmem specifically. [1] https://lore.kernel.org/all/[email protected]/ > > > > > Thanks, > > Usama > >