ocfs2: Add inode stealing for ocfs2_reserve_new_inode

Inode allocation is modified to look in other nodes allocators during
extreme out of space situations. We retry our own slot when space is freed
back to the global bitmap, or whenever we've allocated more than 1024 inodes
from another slot.

Signed-off-by: Tao Ma <tao.ma@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>

1 files changed, 78 insertions, 2 deletions

diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 33d55734c514..d2d278fb9819 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -49,6 +49,8 @@
 #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);
@@ -109,7 +111,7 @@ static inline void ocfs2_block_to_cluster_group(struct inode *inode,
                                                 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;
 
@@ -120,9 +122,17 @@ void ocfs2_free_alloc_context(struct ocfs2_alloc_context *ac)
                 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);
 }
 
@@ -522,10 +532,42 @@ bail:
         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)) {
@@ -539,9 +581,43 @@ int ocfs2_reserve_new_inode(struct ocfs2_super *osb,
 
         (*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);