From 6e580ab50a3d3344be5d410406967edcc691d8a0 Mon Sep 17 00:00:00 2001 From: Frank Zago Date: Mon, 14 Sep 2015 18:41:18 -0400 Subject: [PATCH] staging/lustre/obdclass: reorganize busy object accounting Due to some accounting bug, lsb_busy of a hash bucket can become larger than the total number of objects in said bucket. A busy object can be counted more than once. When that happens, a negative value is returned by the shrinker callback. Instead of trying (and failing) to count the busy objects, count the objects than are not busy, i.e. the objects that are present on the lsb_lru list. The number of busy objects is then the difference between the number of objects in the hash and the objects on the lsb_lru list. Signed-off-by: frank zago Reviewed-on: http://review.whamcloud.com/12468 Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5722 Reviewed-by: Andreas Dilger Reviewed-by: Mike Pershin Signed-off-by: Oleg Drokin Signed-off-by: Greg Kroah-Hartman --- .../staging/lustre/lustre/include/lu_object.h | 4 +-- .../lustre/lustre/obdclass/lu_object.c | 35 ++++++++----------- 2 files changed, 16 insertions(+), 23 deletions(-) diff --git a/drivers/staging/lustre/lustre/include/lu_object.h b/drivers/staging/lustre/lustre/include/lu_object.h index a16c9ea98373..ea13a82ff887 100644 --- a/drivers/staging/lustre/lustre/include/lu_object.h +++ b/drivers/staging/lustre/lustre/include/lu_object.h @@ -554,9 +554,9 @@ struct fld; struct lu_site_bkt_data { /** - * number of busy object on this bucket + * number of object in this bucket on the lsb_lru list. */ - long lsb_busy; + long lsb_lru_len; /** * LRU list, updated on each access to object. Protected by * bucket lock of lu_site::ls_obj_hash. diff --git a/drivers/staging/lustre/lustre/obdclass/lu_object.c b/drivers/staging/lustre/lustre/obdclass/lu_object.c index 3111982f69c2..4f7899f9a15c 100644 --- a/drivers/staging/lustre/lustre/obdclass/lu_object.c +++ b/drivers/staging/lustre/lustre/obdclass/lu_object.c @@ -113,8 +113,6 @@ void lu_object_put(const struct lu_env *env, struct lu_object *o) return; } - LASSERT(bkt->lsb_busy > 0); - bkt->lsb_busy--; /* * When last reference is released, iterate over object * layers, and notify them that object is no longer busy. @@ -127,6 +125,7 @@ void lu_object_put(const struct lu_env *env, struct lu_object *o) if (!lu_object_is_dying(top)) { LASSERT(list_empty(&top->loh_lru)); list_add_tail(&top->loh_lru, &bkt->lsb_lru); + bkt->lsb_lru_len++; cfs_hash_bd_unlock(site->ls_obj_hash, &bd, 1); return; } @@ -179,7 +178,13 @@ void lu_object_unhash(const struct lu_env *env, struct lu_object *o) struct cfs_hash_bd bd; cfs_hash_bd_get_and_lock(obj_hash, &top->loh_fid, &bd, 1); + if (!list_empty(&top->loh_lru)) { + struct lu_site_bkt_data *bkt; + list_del_init(&top->loh_lru); + bkt = cfs_hash_bd_extra_get(obj_hash, &bd); + bkt->lsb_lru_len--; + } cfs_hash_bd_del_locked(obj_hash, &bd, &top->loh_hash); cfs_hash_bd_unlock(obj_hash, &bd, 1); } @@ -349,6 +354,7 @@ int lu_site_purge(const struct lu_env *env, struct lu_site *s, int nr) cfs_hash_bd_del_locked(s->ls_obj_hash, &bd2, &h->loh_hash); list_move(&h->loh_lru, &dispose); + bkt->lsb_lru_len--; if (did_sth == 0) did_sth = 1; @@ -561,7 +567,10 @@ static struct lu_object *htable_lookup(struct lu_site *s, if (likely(!lu_object_is_dying(h))) { cfs_hash_get(s->ls_obj_hash, hnode); lprocfs_counter_incr(s->ls_stats, LU_SS_CACHE_HIT); + if (!list_empty(&h->loh_lru)) { list_del_init(&h->loh_lru); + bkt->lsb_lru_len--; + } return lu_object_top(h); } @@ -599,7 +608,6 @@ static struct lu_object *lu_object_new(const struct lu_env *env, struct lu_object *o; struct cfs_hash *hs; struct cfs_hash_bd bd; - struct lu_site_bkt_data *bkt; o = lu_object_alloc(env, dev, f, conf); if (IS_ERR(o)) @@ -607,9 +615,7 @@ static struct lu_object *lu_object_new(const struct lu_env *env, hs = dev->ld_site->ls_obj_hash; cfs_hash_bd_get_and_lock(hs, (void *)f, &bd, 1); - bkt = cfs_hash_bd_extra_get(hs, &bd); cfs_hash_bd_add_locked(hs, &bd, &o->lo_header->loh_hash); - bkt->lsb_busy++; cfs_hash_bd_unlock(hs, &bd, 1); return o; } @@ -675,11 +681,7 @@ static struct lu_object *lu_object_find_try(const struct lu_env *env, shadow = htable_lookup(s, &bd, f, waiter, &version); if (likely(PTR_ERR(shadow) == -ENOENT)) { - struct lu_site_bkt_data *bkt; - - bkt = cfs_hash_bd_extra_get(hs, &bd); cfs_hash_bd_add_locked(hs, &bd, &o->lo_header->loh_hash); - bkt->lsb_busy++; cfs_hash_bd_unlock(hs, &bd, 1); return o; } @@ -926,14 +928,7 @@ static void lu_obj_hop_get(struct cfs_hash *hs, struct hlist_node *hnode) struct lu_object_header *h; h = hlist_entry(hnode, struct lu_object_header, loh_hash); - if (atomic_add_return(1, &h->loh_ref) == 1) { - struct lu_site_bkt_data *bkt; - struct cfs_hash_bd bd; - - cfs_hash_bd_get(hs, &h->loh_fid, &bd); - bkt = cfs_hash_bd_extra_get(hs, &bd); - bkt->lsb_busy++; - } + atomic_inc(&h->loh_ref); } static void lu_obj_hop_put_locked(struct cfs_hash *hs, struct hlist_node *hnode) @@ -1802,7 +1797,8 @@ static void lu_site_stats_get(struct cfs_hash *hs, struct hlist_head *hhead; cfs_hash_bd_lock(hs, &bd, 1); - stats->lss_busy += bkt->lsb_busy; + stats->lss_busy += + cfs_hash_bd_count_get(&bd) - bkt->lsb_lru_len; stats->lss_total += cfs_hash_bd_count_get(&bd); stats->lss_max_search = max((int)stats->lss_max_search, cfs_hash_bd_depmax_get(&bd)); @@ -2067,7 +2063,6 @@ void lu_object_assign_fid(const struct lu_env *env, struct lu_object *o, { struct lu_site *s = o->lo_dev->ld_site; struct lu_fid *old = &o->lo_header->loh_fid; - struct lu_site_bkt_data *bkt; struct lu_object *shadow; wait_queue_t waiter; struct cfs_hash *hs; @@ -2082,9 +2077,7 @@ void lu_object_assign_fid(const struct lu_env *env, struct lu_object *o, /* supposed to be unique */ LASSERT(IS_ERR(shadow) && PTR_ERR(shadow) == -ENOENT); *old = *fid; - bkt = cfs_hash_bd_extra_get(hs, &bd); cfs_hash_bd_add_locked(hs, &bd, &o->lo_header->loh_hash); - bkt->lsb_busy++; cfs_hash_bd_unlock(hs, &bd, 1); } EXPORT_SYMBOL(lu_object_assign_fid); -- 2.34.1