| Message ID | 20230331070818.2792558-3-yosryahmed@google.com (mailing list archive) |
|---|---|
| State | Mainlined, archived |
| Headers | show |
| Series | Ignore non-LRU-based reclaim in memcg reclaim | expand |
On Fri, Mar 31, 2023 at 07:08:17AM +0000, Yosry Ahmed wrote: > During reclaim, we keep track of pages reclaimed from other means than > LRU-based reclaim through scan_control->reclaim_state->reclaimed_slab, > which we stash a pointer to in current task_struct. > > However, we keep track of more than just reclaimed slab pages through > this. We also use it for clean file pages dropped through pruned inodes, > and xfs buffer pages freed. Rename reclaimed_slab to reclaimed, and add > a helper function that wraps updating it through current, so that future > changes to this logic are contained within mm/vmscan.c. > > Signed-off-by: Yosry Ahmed <yosryahmed@google.com> ..... > diff --git a/mm/vmscan.c b/mm/vmscan.c > index fef7d1c0f82b2..a3e38851b34ac 100644 > --- a/mm/vmscan.c > +++ b/mm/vmscan.c > @@ -511,6 +511,34 @@ static void set_task_reclaim_state(struct task_struct *task, > task->reclaim_state = rs; > } > > +/* > + * mm_account_reclaimed_pages(): account reclaimed pages outside of LRU-based > + * reclaim > + * @pages: number of pages reclaimed > + * > + * If the current process is undergoing a reclaim operation, increment the > + * number of reclaimed pages by @pages. > + */ > +void mm_account_reclaimed_pages(unsigned long pages) > +{ > + if (current->reclaim_state) > + current->reclaim_state->reclaimed += pages; > +} > +EXPORT_SYMBOL(mm_account_reclaimed_pages); Shouldn't this be a static inline in a header file? Then you don't need an EXPORT_SYMBOL() - which should really be EXPORT_SYMBOL_GPL() - and callers don't add the overhead of a function call for two lines of code.... -Dave.
On Fri, Mar 31, 2023 at 1:51 PM Dave Chinner <david@fromorbit.com> wrote: > > On Fri, Mar 31, 2023 at 07:08:17AM +0000, Yosry Ahmed wrote: > > During reclaim, we keep track of pages reclaimed from other means than > > LRU-based reclaim through scan_control->reclaim_state->reclaimed_slab, > > which we stash a pointer to in current task_struct. > > > > However, we keep track of more than just reclaimed slab pages through > > this. We also use it for clean file pages dropped through pruned inodes, > > and xfs buffer pages freed. Rename reclaimed_slab to reclaimed, and add > > a helper function that wraps updating it through current, so that future > > changes to this logic are contained within mm/vmscan.c. > > > > Signed-off-by: Yosry Ahmed <yosryahmed@google.com> > ..... > > diff --git a/mm/vmscan.c b/mm/vmscan.c > > index fef7d1c0f82b2..a3e38851b34ac 100644 > > --- a/mm/vmscan.c > > +++ b/mm/vmscan.c > > @@ -511,6 +511,34 @@ static void set_task_reclaim_state(struct task_struct *task, > > task->reclaim_state = rs; > > } > > > > +/* > > + * mm_account_reclaimed_pages(): account reclaimed pages outside of LRU-based > > + * reclaim > > + * @pages: number of pages reclaimed > > + * > > + * If the current process is undergoing a reclaim operation, increment the > > + * number of reclaimed pages by @pages. > > + */ > > +void mm_account_reclaimed_pages(unsigned long pages) > > +{ > > + if (current->reclaim_state) > > + current->reclaim_state->reclaimed += pages; > > +} > > +EXPORT_SYMBOL(mm_account_reclaimed_pages); > > Shouldn't this be a static inline in a header file? > > Then you don't need an EXPORT_SYMBOL() - which should really be > EXPORT_SYMBOL_GPL() - and callers don't add the overhead of a > function call for two lines of code.... Yes it should be. Thanks. An earlier draft of this series had more going on in this function, so I moved it to mm/vmscan.c, then I forgot to move it to the header later. Will do that for v4. > > -Dave. > -- > Dave Chinner > david@fromorbit.com
diff --git a/fs/inode.c b/fs/inode.c index 4558dc2f13557..e60fcc41faf17 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -864,8 +864,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item, __count_vm_events(KSWAPD_INODESTEAL, reap); else __count_vm_events(PGINODESTEAL, reap); - if (current->reclaim_state) - current->reclaim_state->reclaimed_slab += reap; + mm_account_reclaimed_pages(reap); } iput(inode); spin_lock(lru_lock); diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 54c774af6e1c6..15d1e5a7c2d34 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -286,8 +286,7 @@ xfs_buf_free_pages( if (bp->b_pages[i]) __free_page(bp->b_pages[i]); } - if (current->reclaim_state) - current->reclaim_state->reclaimed_slab += bp->b_page_count; + mm_account_reclaimed_pages(bp->b_page_count); if (bp->b_pages != bp->b_page_array) kmem_free(bp->b_pages); diff --git a/include/linux/swap.h b/include/linux/swap.h index 209a425739a9f..589ea2731931f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -153,13 +153,16 @@ union swap_header { * memory reclaim */ struct reclaim_state { - unsigned long reclaimed_slab; + /* pages reclaimed outside of LRU-based reclaim */ + unsigned long reclaimed; #ifdef CONFIG_LRU_GEN /* per-thread mm walk data */ struct lru_gen_mm_walk *mm_walk; #endif }; +void mm_account_reclaimed_pages(unsigned long pages); + #ifdef __KERNEL__ struct address_space; diff --git a/mm/slab.c b/mm/slab.c index dabc2a671fc6f..64bf1de817b24 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1392,8 +1392,7 @@ static void kmem_freepages(struct kmem_cache *cachep, struct slab *slab) smp_wmb(); __folio_clear_slab(folio); - if (current->reclaim_state) - current->reclaim_state->reclaimed_slab += 1 << order; + mm_account_reclaimed_pages(1 << order); unaccount_slab(slab, order, cachep); __free_pages(&folio->page, order); } diff --git a/mm/slob.c b/mm/slob.c index fe567fcfa3a39..79cc8680c973c 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -61,7 +61,7 @@ #include <linux/slab.h> #include <linux/mm.h> -#include <linux/swap.h> /* struct reclaim_state */ +#include <linux/swap.h> /* mm_account_reclaimed_pages() */ #include <linux/cache.h> #include <linux/init.h> #include <linux/export.h> @@ -211,9 +211,7 @@ static void slob_free_pages(void *b, int order) { struct page *sp = virt_to_page(b); - if (current->reclaim_state) - current->reclaim_state->reclaimed_slab += 1 << order; - + mm_account_reclaimed_pages(1 << order); mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE_B, -(PAGE_SIZE << order)); __free_pages(sp, order); diff --git a/mm/slub.c b/mm/slub.c index 39327e98fce34..7aa30eef82350 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -11,7 +11,7 @@ */ #include <linux/mm.h> -#include <linux/swap.h> /* struct reclaim_state */ +#include <linux/swap.h> /* mm_account_reclaimed_pages() */ #include <linux/module.h> #include <linux/bit_spinlock.h> #include <linux/interrupt.h> @@ -2063,8 +2063,7 @@ static void __free_slab(struct kmem_cache *s, struct slab *slab) /* Make the mapping reset visible before clearing the flag */ smp_wmb(); __folio_clear_slab(folio); - if (current->reclaim_state) - current->reclaim_state->reclaimed_slab += pages; + mm_account_reclaimed_pages(pages); unaccount_slab(slab, order, s); __free_pages(&folio->page, order); } diff --git a/mm/vmscan.c b/mm/vmscan.c index fef7d1c0f82b2..a3e38851b34ac 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -511,6 +511,34 @@ static void set_task_reclaim_state(struct task_struct *task, task->reclaim_state = rs; } +/* + * mm_account_reclaimed_pages(): account reclaimed pages outside of LRU-based + * reclaim + * @pages: number of pages reclaimed + * + * If the current process is undergoing a reclaim operation, increment the + * number of reclaimed pages by @pages. + */ +void mm_account_reclaimed_pages(unsigned long pages) +{ + if (current->reclaim_state) + current->reclaim_state->reclaimed += pages; +} +EXPORT_SYMBOL(mm_account_reclaimed_pages); + +/* + * flush_reclaim_state(): add pages reclaimed outside of LRU-based reclaim to + * scan_control->nr_reclaimed. + */ +static void flush_reclaim_state(struct scan_control *sc, + struct reclaim_state *rs) +{ + if (rs) { + sc->nr_reclaimed += rs->reclaimed; + rs->reclaimed = 0; + } +} + static long xchg_nr_deferred(struct shrinker *shrinker, struct shrink_control *sc) { @@ -5346,8 +5374,7 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc) vmpressure(sc->gfp_mask, memcg, false, sc->nr_scanned - scanned, sc->nr_reclaimed - reclaimed); - sc->nr_reclaimed += current->reclaim_state->reclaimed_slab; - current->reclaim_state->reclaimed_slab = 0; + flush_reclaim_state(sc, current->reclaim_state); return success ? MEMCG_LRU_YOUNG : 0; } @@ -6472,10 +6499,7 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) shrink_node_memcgs(pgdat, sc); - if (reclaim_state) { - sc->nr_reclaimed += reclaim_state->reclaimed_slab; - reclaim_state->reclaimed_slab = 0; - } + flush_reclaim_state(sc, reclaim_state); /* Record the subtree's reclaim efficiency */ if (!sc->proactive)
During reclaim, we keep track of pages reclaimed from other means than LRU-based reclaim through scan_control->reclaim_state->reclaimed_slab, which we stash a pointer to in current task_struct. However, we keep track of more than just reclaimed slab pages through this. We also use it for clean file pages dropped through pruned inodes, and xfs buffer pages freed. Rename reclaimed_slab to reclaimed, and add a helper function that wraps updating it through current, so that future changes to this logic are contained within mm/vmscan.c. Signed-off-by: Yosry Ahmed <yosryahmed@google.com> --- fs/inode.c | 3 +-- fs/xfs/xfs_buf.c | 3 +-- include/linux/swap.h | 5 ++++- mm/slab.c | 3 +-- mm/slob.c | 6 ++---- mm/slub.c | 5 ++--- mm/vmscan.c | 36 ++++++++++++++++++++++++++++++------ 7 files changed, 41 insertions(+), 20 deletions(-)