GFS2: Use generic list_lru for quota

By using the generic list_lru code, we can now separate the
per sb quota list locking from the lru locking. The lru
lock is made into the inner-most lock.

As a result of this new lock order, we may occasionally see
items on the per-sb quota list which are "dead" so that the
two places where we traverse that list are updated to take
account of that.

As a result of this patch, the gfs2 quota shrinker is now
NUMA zone aware, and we are also laying the foundations for
further improvments in due course.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
Signed-off-by: Abhijith Das <adas@redhat.com>
Tested-by: Abhijith Das <adas@redhat.com>
Cc: Dave Chinner <dchinner@redhat.com>
This commit is contained in:
Steven Whitehouse 2013-11-04 10:15:08 +00:00
parent 7d80823e1d
commit 2147dbfd05
4 changed files with 86 additions and 67 deletions

View File

@ -420,11 +420,10 @@ enum {
struct gfs2_quota_data {
struct list_head qd_list;
struct list_head qd_reclaim;
struct lockref qd_lockref;
struct kqid qd_id;
struct lockref qd_lockref;
struct list_head qd_lru;
unsigned long qd_flags; /* QDF_... */
s64 qd_change;

View File

@ -31,12 +31,6 @@
struct workqueue_struct *gfs2_control_wq;
static struct shrinker qd_shrinker = {
.count_objects = gfs2_qd_shrink_count,
.scan_objects = gfs2_qd_shrink_scan,
.seeks = DEFAULT_SEEKS,
};
static void gfs2_init_inode_once(void *foo)
{
struct gfs2_inode *ip = foo;
@ -87,6 +81,10 @@ static int __init init_gfs2_fs(void)
if (error)
return error;
error = list_lru_init(&gfs2_qd_lru);
if (error)
goto fail_lru;
error = gfs2_glock_init();
if (error)
goto fail;
@ -139,7 +137,7 @@ static int __init init_gfs2_fs(void)
if (!gfs2_rsrv_cachep)
goto fail;
register_shrinker(&qd_shrinker);
register_shrinker(&gfs2_qd_shrinker);
error = register_filesystem(&gfs2_fs_type);
if (error)
@ -179,7 +177,9 @@ fail_wq:
fail_unregister:
unregister_filesystem(&gfs2_fs_type);
fail:
unregister_shrinker(&qd_shrinker);
list_lru_destroy(&gfs2_qd_lru);
fail_lru:
unregister_shrinker(&gfs2_qd_shrinker);
gfs2_glock_exit();
if (gfs2_rsrv_cachep)
@ -214,13 +214,14 @@ fail:
static void __exit exit_gfs2_fs(void)
{
unregister_shrinker(&qd_shrinker);
unregister_shrinker(&gfs2_qd_shrinker);
gfs2_glock_exit();
gfs2_unregister_debugfs();
unregister_filesystem(&gfs2_fs_type);
unregister_filesystem(&gfs2meta_fs_type);
destroy_workqueue(gfs_recovery_wq);
destroy_workqueue(gfs2_control_wq);
list_lru_destroy(&gfs2_qd_lru);
rcu_barrier();

View File

@ -51,6 +51,7 @@
#include <linux/quota.h>
#include <linux/dqblk_xfs.h>
#include <linux/lockref.h>
#include <linux/list_lru.h>
#include "gfs2.h"
#include "incore.h"
@ -72,29 +73,25 @@ struct gfs2_quota_change_host {
struct kqid qc_id;
};
static LIST_HEAD(qd_lru_list);
static atomic_t qd_lru_count = ATOMIC_INIT(0);
/* Lock order: qd_lock -> qd->lockref.lock -> lru lock */
static DEFINE_SPINLOCK(qd_lock);
struct list_lru gfs2_qd_lru;
unsigned long gfs2_qd_shrink_scan(struct shrinker *shrink,
struct shrink_control *sc)
static void gfs2_qd_dispose(struct list_head *list)
{
struct gfs2_quota_data *qd;
struct gfs2_sbd *sdp;
int nr_to_scan = sc->nr_to_scan;
long freed = 0;
if (!(sc->gfp_mask & __GFP_FS))
return SHRINK_STOP;
spin_lock(&qd_lock);
while (nr_to_scan && !list_empty(&qd_lru_list)) {
qd = list_entry(qd_lru_list.next,
struct gfs2_quota_data, qd_reclaim);
while (!list_empty(list)) {
qd = list_entry(list->next, struct gfs2_quota_data, qd_lru);
sdp = qd->qd_gl->gl_sbd;
list_del(&qd->qd_lru);
/* Free from the filesystem-specific list */
spin_lock(&qd_lock);
list_del(&qd->qd_list);
spin_unlock(&qd_lock);
gfs2_assert_warn(sdp, !qd->qd_change);
gfs2_assert_warn(sdp, !qd->qd_slot_count);
@ -104,24 +101,59 @@ unsigned long gfs2_qd_shrink_scan(struct shrinker *shrink,
atomic_dec(&sdp->sd_quota_count);
/* Delete it from the common reclaim list */
list_del_init(&qd->qd_reclaim);
atomic_dec(&qd_lru_count);
spin_unlock(&qd_lock);
kmem_cache_free(gfs2_quotad_cachep, qd);
spin_lock(&qd_lock);
nr_to_scan--;
freed++;
}
spin_unlock(&qd_lock);
}
static enum lru_status gfs2_qd_isolate(struct list_head *item, spinlock_t *lock, void *arg)
{
struct list_head *dispose = arg;
struct gfs2_quota_data *qd = list_entry(item, struct gfs2_quota_data, qd_lru);
if (!spin_trylock(&qd->qd_lockref.lock))
return LRU_SKIP;
if (qd->qd_lockref.count == 0) {
lockref_mark_dead(&qd->qd_lockref);
list_move(&qd->qd_lru, dispose);
}
spin_unlock(&qd->qd_lockref.lock);
return LRU_REMOVED;
}
static unsigned long gfs2_qd_shrink_scan(struct shrinker *shrink,
struct shrink_control *sc)
{
LIST_HEAD(dispose);
unsigned long freed;
if (!(sc->gfp_mask & __GFP_FS))
return SHRINK_STOP;
freed = list_lru_walk_node(&gfs2_qd_lru, sc->nid, gfs2_qd_isolate,
&dispose, &sc->nr_to_scan);
gfs2_qd_dispose(&dispose);
return freed;
}
unsigned long gfs2_qd_shrink_count(struct shrinker *shrink,
struct shrink_control *sc)
static unsigned long gfs2_qd_shrink_count(struct shrinker *shrink,
struct shrink_control *sc)
{
return vfs_pressure_ratio(atomic_read(&qd_lru_count));
return vfs_pressure_ratio(list_lru_count_node(&gfs2_qd_lru, sc->nid));
}
struct shrinker gfs2_qd_shrinker = {
.count_objects = gfs2_qd_shrink_count,
.scan_objects = gfs2_qd_shrink_scan,
.seeks = DEFAULT_SEEKS,
.flags = SHRINKER_NUMA_AWARE,
};
static u64 qd2index(struct gfs2_quota_data *qd)
{
struct kqid qid = qd->qd_id;
@ -153,7 +185,7 @@ static int qd_alloc(struct gfs2_sbd *sdp, struct kqid qid,
spin_lock_init(&qd->qd_lockref.lock);
qd->qd_id = qid;
qd->qd_slot = -1;
INIT_LIST_HEAD(&qd->qd_reclaim);
INIT_LIST_HEAD(&qd->qd_lru);
error = gfs2_glock_get(sdp, qd2index(qd),
&gfs2_quota_glops, CREATE, &qd->qd_gl);
@ -181,13 +213,9 @@ static int qd_get(struct gfs2_sbd *sdp, struct kqid qid,
found = 0;
spin_lock(&qd_lock);
list_for_each_entry(qd, &sdp->sd_quota_list, qd_list) {
if (qid_eq(qd->qd_id, qid)) {
lockref_get(&qd->qd_lockref);
if (!list_empty(&qd->qd_reclaim)) {
/* Remove it from reclaim list */
list_del_init(&qd->qd_reclaim);
atomic_dec(&qd_lru_count);
}
if (qid_eq(qd->qd_id, qid) &&
lockref_get_not_dead(&qd->qd_lockref)) {
list_lru_del(&gfs2_qd_lru, &qd->qd_lru);
found = 1;
break;
}
@ -229,18 +257,13 @@ static void qd_hold(struct gfs2_quota_data *qd)
static void qd_put(struct gfs2_quota_data *qd)
{
spin_lock(&qd_lock);
if (lockref_put_or_lock(&qd->qd_lockref))
return;
if (!lockref_put_or_lock(&qd->qd_lockref)) {
qd->qd_lockref.count = 0;
list_lru_add(&gfs2_qd_lru, &qd->qd_lru);
spin_unlock(&qd->qd_lockref.lock);
/* Add to the reclaim list */
list_add_tail(&qd->qd_reclaim, &qd_lru_list);
atomic_inc(&qd_lru_count);
spin_unlock(&qd->qd_lockref.lock);
}
spin_unlock(&qd_lock);
}
static int slot_get(struct gfs2_quota_data *qd)
@ -398,11 +421,11 @@ static int qd_check_sync(struct gfs2_sbd *sdp, struct gfs2_quota_data *qd,
(sync_gen && (qd->qd_sync_gen >= *sync_gen)))
return 0;
list_move_tail(&qd->qd_list, &sdp->sd_quota_list);
if (!lockref_get_not_dead(&qd->qd_lockref))
return 0;
list_move_tail(&qd->qd_list, &sdp->sd_quota_list);
set_bit(QDF_LOCKED, &qd->qd_flags);
gfs2_assert_warn(sdp, !__lockref_is_dead(&qd->qd_lockref));
lockref_get(&qd->qd_lockref);
qd->qd_change_sync = qd->qd_change;
gfs2_assert_warn(sdp, qd->qd_slot_count);
qd->qd_slot_count++;
@ -1329,10 +1352,7 @@ void gfs2_quota_cleanup(struct gfs2_sbd *sdp)
list_del(&qd->qd_list);
/* Also remove if this qd exists in the reclaim list */
if (!list_empty(&qd->qd_reclaim)) {
list_del_init(&qd->qd_reclaim);
atomic_dec(&qd_lru_count);
}
list_lru_del(&gfs2_qd_lru, &qd->qd_lru);
atomic_dec(&sdp->sd_quota_count);
spin_unlock(&qd_lock);
@ -1487,7 +1507,7 @@ static int gfs2_quota_get_xstate(struct super_block *sb,
}
fqs->qs_uquota.qfs_nextents = 1; /* unsupported */
fqs->qs_gquota = fqs->qs_uquota; /* its the same inode in both cases */
fqs->qs_incoredqs = atomic_read(&qd_lru_count);
fqs->qs_incoredqs = list_lru_count(&gfs2_qd_lru);
return 0;
}

View File

@ -10,9 +10,10 @@
#ifndef __QUOTA_DOT_H__
#define __QUOTA_DOT_H__
#include <linux/list_lru.h>
struct gfs2_inode;
struct gfs2_sbd;
struct shrink_control;
#define NO_UID_QUOTA_CHANGE INVALID_UID
#define NO_GID_QUOTA_CHANGE INVALID_GID
@ -53,10 +54,8 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip)
return ret;
}
extern unsigned long gfs2_qd_shrink_count(struct shrinker *shrink,
struct shrink_control *sc);
extern unsigned long gfs2_qd_shrink_scan(struct shrinker *shrink,
struct shrink_control *sc);
extern const struct quotactl_ops gfs2_quotactl_ops;
extern struct shrinker gfs2_qd_shrinker;
extern struct list_lru gfs2_qd_lru;
#endif /* __QUOTA_DOT_H__ */