Implement large_dnode pool feature

[mirror_zfs.git] / include / sys / dnode.h

diff --git a/include/sys/dnode.h b/include/sys/dnode.h
index c5250d51abf11b0a6172c76995ba21b713dfd79c..cee4ea783810a071ecb0425d9bfae2bc01c21c50 100644 (file)
--- a/include/sys/dnode.h
+++ b/include/sys/dnode.h
@@ -79,11 +79,18 @@ extern "C" {
 /*
  * Derived constants.
  */
-#define        DNODE_SIZE      (1 << DNODE_SHIFT)
-#define        DN_MAX_NBLKPTR  ((DNODE_SIZE - DNODE_CORE_SIZE) >> SPA_BLKPTRSHIFT)
-#define        DN_MAX_BONUSLEN (DNODE_SIZE - DNODE_CORE_SIZE - (1 << SPA_BLKPTRSHIFT))
+#define        DNODE_MIN_SIZE          (1 << DNODE_SHIFT)
+#define        DNODE_MAX_SIZE          (1 << DNODE_BLOCK_SHIFT)
+#define        DNODE_BLOCK_SIZE        (1 << DNODE_BLOCK_SHIFT)
+#define        DNODE_MIN_SLOTS         (DNODE_MIN_SIZE >> DNODE_SHIFT)
+#define        DNODE_MAX_SLOTS         (DNODE_MAX_SIZE >> DNODE_SHIFT)
+#define        DN_BONUS_SIZE(dnsize)   ((dnsize) - DNODE_CORE_SIZE - \
+       (1 << SPA_BLKPTRSHIFT))
+#define        DN_SLOTS_TO_BONUSLEN(slots)     DN_BONUS_SIZE((slots) << DNODE_SHIFT)
+#define        DN_OLD_MAX_BONUSLEN     (DN_BONUS_SIZE(DNODE_MIN_SIZE))
+#define        DN_MAX_NBLKPTR  ((DNODE_MIN_SIZE - DNODE_CORE_SIZE) >> SPA_BLKPTRSHIFT)
 #define        DN_MAX_OBJECT   (1ULL << DN_MAX_OBJECT_SHIFT)
-#define        DN_ZERO_BONUSLEN        (DN_MAX_BONUSLEN + 1)
+#define        DN_ZERO_BONUSLEN        (DN_BONUS_SIZE(DNODE_MAX_SIZE) + 1)
 #define        DN_KILL_SPILLBLK (1)
 
 #define        DNODES_PER_BLOCK_SHIFT  (DNODE_BLOCK_SHIFT - DNODE_SHIFT)
@@ -131,7 +138,8 @@ typedef struct dnode_phys {
        uint8_t dn_flags;               /* DNODE_FLAG_* */
        uint16_t dn_datablkszsec;       /* data block size in 512b sectors */
        uint16_t dn_bonuslen;           /* length of dn_bonus */
-       uint8_t dn_pad2[4];
+       uint8_t dn_extra_slots;         /* # of subsequent slots consumed */
+       uint8_t dn_pad2[3];
 
        /* accounting is protected by dn_dirty_mtx */
        uint64_t dn_maxblkid;           /* largest allocated block ID */
@@ -140,8 +148,11 @@ typedef struct dnode_phys {
        uint64_t dn_pad3[4];
 
        /*
-        * The tail region is 448 bytes, and there are three ways to
-        * look at it.
+        * The tail region is 448 bytes for a 512 byte dnode, and
+        * correspondingly larger for larger dnode sizes. The spill
+        * block pointer, when present, is always at the end of the tail
+        * region. There are three ways this space may be used, using
+        * a 512 byte dnode for this diagram:
         *
         * 0       64      128     192     256     320     384     448 (offset)
         * +---------------+---------------+---------------+-------+
@@ -149,23 +160,27 @@ typedef struct dnode_phys {
         * +---------------+---------------+---------------+-------+
         * | dn_blkptr[0]  | dn_bonus[0..319]                      |
         * +---------------+-----------------------+---------------+
-        * | dn_blkptr[0]  | /                     | dn_spill      |
+        * | dn_blkptr[0]  | dn_bonus[0..191]      | dn_spill      |
         * +---------------+-----------------------+---------------+
         */
        union {
-               blkptr_t dn_blkptr[1+DN_MAX_BONUSLEN/sizeof (blkptr_t)];
+               blkptr_t dn_blkptr[1+DN_OLD_MAX_BONUSLEN/sizeof (blkptr_t)];
                struct {
                        blkptr_t __dn_ignore1;
-                       uint8_t dn_bonus[DN_MAX_BONUSLEN];
+                       uint8_t dn_bonus[DN_OLD_MAX_BONUSLEN];
                };
                struct {
                        blkptr_t __dn_ignore2;
-                       uint8_t __dn_ignore3[DN_MAX_BONUSLEN-sizeof (blkptr_t)];
+                       uint8_t __dn_ignore3[DN_OLD_MAX_BONUSLEN -
+                           sizeof (blkptr_t)];
                        blkptr_t dn_spill;
                };
        };
 } dnode_phys_t;
 
+#define        DN_SPILL_BLKPTR(dnp)    (blkptr_t *)((char *)(dnp) + \
+       (((dnp)->dn_extra_slots + 1) << DNODE_SHIFT) - (1 << SPA_BLKPTRSHIFT))
+
 typedef struct dnode {
        /*
         * Protects the structure of the dnode, including the number of levels
@@ -202,6 +217,7 @@ typedef struct dnode {
        uint32_t dn_datablksz;          /* in bytes */
        uint64_t dn_maxblkid;
        uint8_t dn_next_type[TXG_SIZE];
+       uint8_t dn_num_slots;           /* metadnode slots consumed on disk */
        uint8_t dn_next_nblkptr[TXG_SIZE];
        uint8_t dn_next_nlevels[TXG_SIZE];
        uint8_t dn_next_indblkshift[TXG_SIZE];
@@ -299,7 +315,7 @@ void dnode_rm_spill(dnode_t *dn, dmu_tx_t *tx);
 
 int dnode_hold(struct objset *dd, uint64_t object,
     void *ref, dnode_t **dnp);
-int dnode_hold_impl(struct objset *dd, uint64_t object, int flag,
+int dnode_hold_impl(struct objset *dd, uint64_t object, int flag, int dn_slots,
     void *ref, dnode_t **dnp);
 boolean_t dnode_add_ref(dnode_t *dn, void *ref);
 void dnode_rele(dnode_t *dn, void *ref);
@@ -307,9 +323,9 @@ void dnode_rele_and_unlock(dnode_t *dn, void *tag);
 void dnode_setdirty(dnode_t *dn, dmu_tx_t *tx);
 void dnode_sync(dnode_t *dn, dmu_tx_t *tx);
 void dnode_allocate(dnode_t *dn, dmu_object_type_t ot, int blocksize, int ibs,
-    dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *tx);
+    dmu_object_type_t bonustype, int bonuslen, int dn_slots, dmu_tx_t *tx);
 void dnode_reallocate(dnode_t *dn, dmu_object_type_t ot, int blocksize,
-    dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *tx);
+    dmu_object_type_t bonustype, int bonuslen, int dn_slots, dmu_tx_t *tx);
 void dnode_free(dnode_t *dn, dmu_tx_t *tx);
 void dnode_byteswap(dnode_phys_t *dnp);
 void dnode_buf_byteswap(void *buf, size_t size);