From: green@linuxhacker.ru
To: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
devel@driverdev.osuosl.org,
Andreas Dilger <andreas.dilger@intel.com>
Cc: Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Frank Zago <fzago@cray.com>, Oleg Drokin <oleg.drokin@intel.com>
Subject: [PATCH 02/19] staging/lustre/obdclass: reorganize busy object accounting
Date: Mon, 14 Sep 2015 18:41:18 -0400 [thread overview]
Message-ID: <1442270495-1655259-3-git-send-email-green@linuxhacker.ru> (raw)
In-Reply-To: <1442270495-1655259-1-git-send-email-green@linuxhacker.ru>
From: Frank Zago <fzago@cray.com>
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 <fzago@cray.com>
Reviewed-on: http://review.whamcloud.com/12468
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5722
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Mike Pershin <mike.pershin@intel.com>
Signed-off-by: Oleg Drokin <oleg.drokin@intel.com>
---
drivers/staging/lustre/lustre/include/lu_object.h | 4 +--
drivers/staging/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 a16c9ea..ea13a82 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 3111982..4f7899f 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);
--
2.1.0
next prev parent reply other threads:[~2015-09-14 22:46 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-09-14 22:41 [PATCH 00/19] Lustre fixes green
2015-09-14 22:41 ` [PATCH 01/19] staging/lustre/lnet: Reenable lnet router debugfs green
2015-09-14 22:41 ` green [this message]
2015-09-14 22:41 ` [PATCH 03/19] staging/lustre/llite: cleanup open handle for client open failure green
2015-09-14 22:41 ` [PATCH 04/19] staging/lustre/llite: strengthen checks for hsm flags and archive id green
2015-09-14 22:41 ` [PATCH 05/19] staging/lustre/ptlrpc: remove LUSTRE_MSG_MAGIC_V1 support green
2015-09-14 22:41 ` [PATCH 06/19] staging/lustre/lmv: fix potential null pointer dereference green
2015-09-15 13:26 ` Trevor Woerner
2015-09-15 13:57 ` Oleg Drokin
2015-09-14 22:41 ` [PATCH 07/19] staging/lustre/llite: deny non-root user for changelog operations green
2015-09-14 22:41 ` [PATCH 08/19] staging/lustre/o2iblnd: connection refcount fix for kiblnd_post_rx green
2015-09-14 22:41 ` [PATCH 09/19] staging/lustre/osc: LBUG in osc_lru_reclaim green
2015-09-14 22:41 ` [PATCH 10/19] staging/lustre/libcfs: minor fix in cfs_hash_for_each_relax() green
2015-09-14 22:41 ` [PATCH 11/19] staging/lustre/lnet: fix deadloop in ksocknal_push green
2015-09-14 22:41 ` [PATCH 12/19] staging/lustre/o2iblnd: wrong uses of kib_tx_t::tx_nfrags green
2015-09-14 22:41 ` [PATCH 13/19] staging/lustre/llite: ASSERTION( atomic_read(&d->ld_ref) == 0 ) failed green
2015-09-14 22:41 ` [PATCH 14/19] staging/lustre/obdclass: Eliminate hash bucket scans in lu_cache_shrink green
2015-09-14 22:41 ` [PATCH 15/19] staging/lustre: Remove unused MAY_ constants green
2015-09-14 22:41 ` [PATCH 16/19] staging/lustre/osc: use global osc_rq_pool to reduce memory usage green
2015-09-14 22:41 ` [PATCH 17/19] staging/lustre/o2iblnd: leak cmid in kiblnd_dev_need_failover green
2015-09-14 22:41 ` [PATCH 18/19] staging/lustre/libcfs: remove unused cfs_timer_done green
2015-09-14 22:41 ` [PATCH 19/19] staging/lustre/ptlrpc: make ptlrpcd threads cpt-aware green
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1442270495-1655259-3-git-send-email-green@linuxhacker.ru \
--to=green@linuxhacker.ru \
--cc=andreas.dilger@intel.com \
--cc=devel@driverdev.osuosl.org \
--cc=fzago@cray.com \
--cc=gregkh@linuxfoundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=oleg.drokin@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox