u32 s_feature_incompat;
u32 s_feature_ro_compat;
- /* Protects s_next_generaion, osb_flags. Could protect more on
- * osb as it's very short lived. */
+ /* Protects s_next_generation, osb_flags and s_inode_steal_slot.
+ * Could protect more on osb as it's very short lived.
+ */
spinlock_t osb_lock;
u32 s_next_generation;
unsigned long osb_flags;
+ s16 s_inode_steal_slot;
+ atomic_t s_num_inodes_stolen;
unsigned long s_mount_opt;
unsigned int s_atime_quantum;
return pages_per_cluster;
}
+static inline void ocfs2_init_inode_steal_slot(struct ocfs2_super *osb)
+{
+ spin_lock(&osb->osb_lock);
+ osb->s_inode_steal_slot = OCFS2_INVALID_SLOT;
+ spin_unlock(&osb->osb_lock);
+ atomic_set(&osb->s_num_inodes_stolen, 0);
+}
+
+static inline void ocfs2_set_inode_steal_slot(struct ocfs2_super *osb,
+ s16 slot)
+{
+ spin_lock(&osb->osb_lock);
+ osb->s_inode_steal_slot = slot;
+ spin_unlock(&osb->osb_lock);
+}
+
+static inline s16 ocfs2_get_inode_steal_slot(struct ocfs2_super *osb)
+{
+ s16 slot;
+
+ spin_lock(&osb->osb_lock);
+ slot = osb->s_inode_steal_slot;
+ spin_unlock(&osb->osb_lock);
+
+ return slot;
+}
+
#define ocfs2_set_bit ext2_set_bit
#define ocfs2_clear_bit ext2_clear_bit
#define ocfs2_test_bit ext2_test_bit
#define NOT_ALLOC_NEW_GROUP 0
#define ALLOC_NEW_GROUP 1
+#define OCFS2_MAX_INODES_TO_STEAL 1024
+
static inline void ocfs2_debug_bg(struct ocfs2_group_desc *bg);
static inline void ocfs2_debug_suballoc_inode(struct ocfs2_dinode *fe);
static inline u16 ocfs2_find_victim_chain(struct ocfs2_chain_list *cl);
u64 *bg_blkno,
u16 *bg_bit_off);
-void ocfs2_free_alloc_context(struct ocfs2_alloc_context *ac)
+static void ocfs2_free_ac_resource(struct ocfs2_alloc_context *ac)
{
struct inode *inode = ac->ac_inode;
mutex_unlock(&inode->i_mutex);
iput(inode);
+ ac->ac_inode = NULL;
}
- if (ac->ac_bh)
+ if (ac->ac_bh) {
brelse(ac->ac_bh);
+ ac->ac_bh = NULL;
+ }
+}
+
+void ocfs2_free_alloc_context(struct ocfs2_alloc_context *ac)
+{
+ ocfs2_free_ac_resource(ac);
kfree(ac);
}
return status;
}
+static int ocfs2_steal_inode_from_other_nodes(struct ocfs2_super *osb,
+ struct ocfs2_alloc_context *ac)
+{
+ int i, status = -ENOSPC;
+ s16 slot = ocfs2_get_inode_steal_slot(osb);
+
+ /* Start to steal inodes from the first slot after ours. */
+ if (slot == OCFS2_INVALID_SLOT)
+ slot = osb->slot_num + 1;
+
+ for (i = 0; i < osb->max_slots; i++, slot++) {
+ if (slot == osb->max_slots)
+ slot = 0;
+
+ if (slot == osb->slot_num)
+ continue;
+
+ status = ocfs2_reserve_suballoc_bits(osb, ac,
+ INODE_ALLOC_SYSTEM_INODE,
+ slot, NOT_ALLOC_NEW_GROUP);
+ if (status >= 0) {
+ ocfs2_set_inode_steal_slot(osb, slot);
+ break;
+ }
+
+ ocfs2_free_ac_resource(ac);
+ }
+
+ return status;
+}
+
int ocfs2_reserve_new_inode(struct ocfs2_super *osb,
struct ocfs2_alloc_context **ac)
{
int status;
+ s16 slot = ocfs2_get_inode_steal_slot(osb);
*ac = kzalloc(sizeof(struct ocfs2_alloc_context), GFP_KERNEL);
if (!(*ac)) {
(*ac)->ac_group_search = ocfs2_block_group_search;
+ /*
+ * slot is set when we successfully steal inode from other nodes.
+ * It is reset in 3 places:
+ * 1. when we flush the truncate log
+ * 2. when we complete local alloc recovery.
+ * 3. when we successfully allocate from our own slot.
+ * After it is set, we will go on stealing inodes until we find the
+ * need to check our slots to see whether there is some space for us.
+ */
+ if (slot != OCFS2_INVALID_SLOT &&
+ atomic_read(&osb->s_num_inodes_stolen) < OCFS2_MAX_INODES_TO_STEAL)
+ goto inode_steal;
+
+ atomic_set(&osb->s_num_inodes_stolen, 0);
status = ocfs2_reserve_suballoc_bits(osb, *ac,
INODE_ALLOC_SYSTEM_INODE,
osb->slot_num, ALLOC_NEW_GROUP);
+ if (status >= 0) {
+ status = 0;
+
+ /*
+ * Some inodes must be freed by us, so try to allocate
+ * from our own next time.
+ */
+ if (slot != OCFS2_INVALID_SLOT)
+ ocfs2_init_inode_steal_slot(osb);
+ goto bail;
+ } else if (status < 0 && status != -ENOSPC) {
+ mlog_errno(status);
+ goto bail;
+ }
+
+ ocfs2_free_ac_resource(*ac);
+
+inode_steal:
+ status = ocfs2_steal_inode_from_other_nodes(osb, *ac);
+ atomic_inc(&osb->s_num_inodes_stolen);
if (status < 0) {
if (status != -ENOSPC)
mlog_errno(status);