From f1782c9bc547754f4bd3043fe8cfda53db85f13f Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 10 Apr 2018 16:27:44 -0700 Subject: dcache: account external names as indirectly reclaimable memory I received a report about suspicious growth of unreclaimable slabs on some machines. I've found that it happens on machines with low memory pressure, and these unreclaimable slabs are external names attached to dentries. External names are allocated using generic kmalloc() function, so they are accounted as unreclaimable. But they are held by dentries, which are reclaimable, and they will be reclaimed under the memory pressure. In particular, this breaks MemAvailable calculation, as it doesn't take unreclaimable slabs into account. This leads to a silly situation, when a machine is almost idle, has no memory pressure and therefore has a big dentry cache. And the resulting MemAvailable is too low to start a new workload. To address the issue, the NR_INDIRECTLY_RECLAIMABLE_BYTES counter is used to track the amount of memory, consumed by external names. The counter is increased in the dentry allocation path, if an external name structure is allocated; and it's decreased in the dentry freeing path. To reproduce the problem I've used the following Python script: import os for iter in range (0, 10000000): try: name = ("/some_long_name_%d" % iter) + "_" * 220 os.stat(name) except Exception: pass Without this patch: $ cat /proc/meminfo | grep MemAvailable MemAvailable: 7811688 kB $ python indirect.py $ cat /proc/meminfo | grep MemAvailable MemAvailable: 2753052 kB With the patch: $ cat /proc/meminfo | grep MemAvailable MemAvailable: 7809516 kB $ python indirect.py $ cat /proc/meminfo | grep MemAvailable MemAvailable: 7749144 kB [guro@fb.com: fix indirectly reclaimable memory accounting for CONFIG_SLOB] Link: http://lkml.kernel.org/r/20180312194140.19517-1-guro@fb.com [guro@fb.com: fix indirectly reclaimable memory accounting] Link: http://lkml.kernel.org/r/20180313125701.7955-1-guro@fb.com Link: http://lkml.kernel.org/r/20180305133743.12746-5-guro@fb.com Signed-off-by: Roman Gushchin Reviewed-by: Andrew Morton Cc: Alexander Viro Cc: Michal Hocko Cc: Johannes Weiner Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/dcache.c | 39 ++++++++++++++++++++++++++++++--------- 1 file changed, 30 insertions(+), 9 deletions(-) (limited to 'fs') diff --git a/fs/dcache.c b/fs/dcache.c index 593079176123..915816e90049 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -257,11 +257,25 @@ static void __d_free(struct rcu_head *head) kmem_cache_free(dentry_cache, dentry); } +static void __d_free_external_name(struct rcu_head *head) +{ + struct external_name *name = container_of(head, struct external_name, + u.head); + + mod_node_page_state(page_pgdat(virt_to_page(name)), + NR_INDIRECTLY_RECLAIMABLE_BYTES, + -ksize(name)); + + kfree(name); +} + static void __d_free_external(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); - kfree(external_name(dentry)); - kmem_cache_free(dentry_cache, dentry); + + __d_free_external_name(&external_name(dentry)->u.head); + + kmem_cache_free(dentry_cache, dentry); } static inline int dname_external(const struct dentry *dentry) @@ -291,7 +305,7 @@ void release_dentry_name_snapshot(struct name_snapshot *name) struct external_name *p; p = container_of(name->name, struct external_name, name[0]); if (unlikely(atomic_dec_and_test(&p->u.count))) - kfree_rcu(p, u.head); + call_rcu(&p->u.head, __d_free_external_name); } } EXPORT_SYMBOL(release_dentry_name_snapshot); @@ -1617,6 +1631,7 @@ EXPORT_SYMBOL(d_invalidate); struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) { + struct external_name *ext = NULL; struct dentry *dentry; char *dname; int err; @@ -1637,14 +1652,14 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) dname = dentry->d_iname; } else if (name->len > DNAME_INLINE_LEN-1) { size_t size = offsetof(struct external_name, name[1]); - struct external_name *p = kmalloc(size + name->len, - GFP_KERNEL_ACCOUNT); - if (!p) { + + ext = kmalloc(size + name->len, GFP_KERNEL_ACCOUNT); + if (!ext) { kmem_cache_free(dentry_cache, dentry); return NULL; } - atomic_set(&p->u.count, 1); - dname = p->name; + atomic_set(&ext->u.count, 1); + dname = ext->name; } else { dname = dentry->d_iname; } @@ -1683,6 +1698,12 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) } } + if (unlikely(ext)) { + pg_data_t *pgdat = page_pgdat(virt_to_page(ext)); + mod_node_page_state(pgdat, NR_INDIRECTLY_RECLAIMABLE_BYTES, + ksize(ext)); + } + this_cpu_inc(nr_dentry); return dentry; @@ -2770,7 +2791,7 @@ static void copy_name(struct dentry *dentry, struct dentry *target) dentry->d_name.hash_len = target->d_name.hash_len; } if (old_name && likely(atomic_dec_and_test(&old_name->u.count))) - kfree_rcu(old_name, u.head); + call_rcu(&old_name->u.head, __d_free_external_name); } /* -- cgit v1.2.3-70-g09d2